image-150-64c8cd514b55a.webp

image-151-64c8cd518a917.webp

group-1000002623-64c8cd4f8d576.webp

image-146-64c8cd50567b2.webp

image-147-64c8cd501e463.webp

image-148-64c8cd50b2c5c.webp

image-149-64c8cd50d627e.webp

BBC-Logo.webp

The-Independent-Logo.webp

Featured in

AI biomarkers, built for real-world impact and clinical trials. Meet us at ASCO 2026 | Booth #IH12.

Qure.ai Recognized Among TIME’s 100 Most Influential Companies of 2025

Qure.ai partners with Microsoft to increase access to its lung cancer detection and management suite in the U.S.

qTrack

Clinical history plays a vital role in a physician's or radiologist's diagnosis. However, when training AI models, clinical history or presence of an abnormality which correlates to the target abnormality were not generally considered. In this study, we use scalp hematoma as an additional clinical context in training the models and study the accuracy (AUC and average precision) of a fracture detection AI model before and after adding this clinical context.&nbsp;

Using 141,105 studies, we trained a convolutional neural network (CNN) to detect cranial fractures on non-contrast head CT scans. Scalp hematoma is considered a good indicator by physicians for diagnosing fractures. We confirmed this by automated natural language processing (NLP) analysis of large number of reports. Therefore, scalp hematoma is a good candidate for improving AI algorithms for detecting fractures. A logistic regression model was trained to detect a cranial fracture, using the presence of a scalp hematoma and the output probability of the CNN as inputs. The original CNN by itself (Model 1) and the combined CNN-logistic regression algorithm (Model 2) were tested using an independent set containing 18200 scans. We used area under the ROC curve (AUC) and average precision (AP), a probability based metric that is inversely proportional to false positive rate, as evaluation metrics.&nbsp;

Analysis of 141,105 reports confirmed that scalp hematoma was present in 49.8% of scans with fractures and conversely fractures were present in 29.8% of scans with scalp hematoma. The CNN with images as sole inputs reached an AUC and AP of 0.9599 and 0.7952 respectively. Adding scalp hematoma as a feature increased AUC to 0.9666. AP however, increased significantly to 0.8190.&nbsp;

Using a simple probabilistic algorithm to add clinical context to a CNN resulted in a significant improvement in AP. As AUC is saturated, there is no significant difference in AUC. Results show significant decrease in false positive rate without impacting sensitivity.&nbsp;

Like radiologists, deep learning models can be more accurate when they incorporate clinical context in addition to image analysis.&nbsp;

large_Clinical Context Improves the Performance of AI Models for Cranial Fracture Detection.webp

medium_Clinical Context Improves the Performance of AI Models for Cranial Fracture Detection.webp

small_Clinical Context Improves the Performance of AI Models for Cranial Fracture Detection.webp

thumbnail_Clinical Context Improves the Performance of AI Models for Cranial Fracture Detection.webp

Clinical Context Improves the Performance of AI Models for Cranial Fracture Detection.webp

Clinical Context Improves the Performance of AI Models for Cranial Fracture Detection

Area under receiver operating curve (AUC) is commonly used to evaluate and select artificial intelligence (AI) models for radiology. Artificially balanced/enriched datasets are also usually used to estimate AUC to maximize confidence interval to sample size ratio. In this work, we show that such evaluation of model performance has reached saturation and propose alternate performance evaluation schemes.

Receiver operating curve (ROC) is a curve where false positive rate (1 – specificity) and sensitivity of model at different thresholds are plotted on x and y-axes respectively. Similarly, precision recall curve (PRC) is plotted with recall (sensitivity) and precision (positive predictive value) on x and y-axes respectively. AUC is defined as area under ROC while average precision (AP) is defined as area under PRC. To illustrate the proposed evaluation scheme, two different high-performance models to detect fractures from head CT scans were created. In addition, two datasets were created by uniformly sampling scans and artificially enriching scans with fractures respectively. AUCs and APs were computed for the model-dataset pairs. We propose that AP computed on uniformly sampled dataset is more useful for model selection than other options.&nbsp;

AUCs for all four (model, dataset) pairs were &gt;92%. For both the datasets, difference in AUCs between the models was less than 3%. APs on enriched dataset were high for both models (95% &amp; 92% respectively). However, APs on uniformly sampled dataset were lower than expected (80% &amp; 69% respectively). The difference in models' performance was the highest (difference of 11%) when performance was measured using AP on uniformly sampled dataset.&nbsp;

AUC, although a commonly used performance metric for models, saturates early. Therefore, it is not suitable for model selection among high performance models (i.e. AUC &gt; 0.9). Similarly, model selection using artificially enriched datasets is not a good practice as both AUC and AP saturate early. Average precision measured on a uniformly sampled dataset shows the deficiencies in models' performance well and therefore, is a better metric for model selection.&nbsp;

Average precision and uniformly sampled datasets should be used to evaluate artificial intelligence models in radiology instead of AUC and enriched datasets.&nbsp;

large_AUC and Enriched Datasets are Not Good Enough Anymore Presenting an Alternative Metric to Evaluate Radiology AI Models.webp

medium_AUC and Enriched Datasets are Not Good Enough Anymore Presenting an Alternative Metric to Evaluate Radiology AI Models.webp

small_AUC and Enriched Datasets are Not Good Enough Anymore Presenting an Alternative Metric to Evaluate Radiology AI Models.webp

thumbnail_AUC and Enriched Datasets are Not Good Enough Anymore Presenting an Alternative Metric to Evaluate Radiology AI Models.webp

AUC and Enriched Datasets are Not Good Enough Anymore Presenting an Alternative Metric to Evaluate Radiology AI Models.webp

AUC and Enriched Datasets are Not Good Enough Anymore: Presenting an Alternative Metric to Evaluate Radiology AI Models

Deep learning (DL) neural networks have only recently been employed to interpret chest radiography (CXR) to screen and triage people for pulmonary tuberculosis (TB). No published studies have compared multiple DL systems and populations. We conducted a retrospective evaluation of three DL systems (CAD4TB, Lunit INSIGHT, and qXR) for detecting TB-associated abnormalities in chest radiographs from outpatients in Nepal and Cameroon. All 1196 individuals received a Xpert MTB/RIF assay and a CXR read by two groups of radiologists and the DL systems. Xpert was used as the reference standard. The area under the curve of the three systems was similar: Lunit (0.94, 95% CI: 0.93–0.96), qXR (0.94, 95% CI: 0.92–0.97) and CAD4TB (0.92, 95% CI: 0.90–0.95). When matching the sensitivity of the radiologists, the specificities of the DL systems were significantly higher except for one. Using DL systems to read CXRs could reduce the number of Xpert MTB/RIF tests needed by 66% while maintaining sensitivity at 95% or better. Using a universal cutoff score resulted different performance in each site, highlighting the need to select scores based on the population screened. These DL systems should be considered by TB programs where human resources are constrained, and automated technology is available.

large_Using artificial intelligence to read chest radiographs for tuberculosis detection – A multi-site evaluation of the diagnostic accuracy of three deep learning systems.webp

medium_Using artificial intelligence to read chest radiographs for tuberculosis detection – A multi-site evaluation of the diagnostic accuracy of three deep learning systems.webp

small_Using artificial intelligence to read chest radiographs for tuberculosis detection – A multi-site evaluation of the diagnostic accuracy of three deep learning systems.webp

thumbnail_Using artificial intelligence to read chest radiographs for tuberculosis detection – A multi-site evaluation of the diagnostic accuracy of three deep learning systems.webp

Using artificial intelligence to read chest radiographs for tuberculosis detection – A multi-site evaluation of the diagnostic accuracy of three deep learning systems.webp

Using artificial intelligence to read chest radiographs for tuberculosis detection – A multi-site evaluation of the diagnostic accuracy of three deep learning systems

Majority of chest X-rays (CXRs) performed globally are normal radiologists spend significant time ruling out these scans. We present a Deep Learning (DL) model trained for the specific use of classifying CXRs into normal and abnormal, potentially reducing time and cost associated with reporting normal studies.

A DL algorithm trained on 1,150,084 CXRs and their corresponding reports was developed. A retrospectively acquired independent test set of 430 CXRs (285 abnormal, 145 normal) was analyzed by the algorithm classifying each X-Ray as normal or abnormal. Ground truth for the independent test set was established by a sub-specialist chest radiologist with 8 years’ experience by reviewing every Chest X-Ray image with reference to the existing report. Algorithm output was compared against ground truth and summary statistics were calculated.

The algorithm correctly classified 376 (87.44%) CXRs with sensitivity of 97.19% (95% CI – 94.54% to 98.78%) and specificity of 68.28% (95% CI – 60.04% to 75.75%). There were 46 (10.70%) false positives and 8 (1.86%) false negatives (FNs). Out of 8 FNs, 3 were designated as clinically insignificant (mild, inactive fibrosis) and 5 as significant (rib fractures, pneumothorax).

High-sensitivity DL algorithms can potentially be deployed for primary read of CXRs enabling radiologists to spend appropriate time on abnormal cases, saving time and thereby cost of reporting CXRs, especially on non-emergency situations, More in-depth prospective trials are required to ascertain the overall impact of such algorithms.

large_Automated classification of X-rays as normalAbnormal using a high sensitivity deep learning algorithm.webp

medium_Automated classification of X-rays as normalAbnormal using a high sensitivity deep learning algorithm.webp

small_Automated classification of X-rays as normalAbnormal using a high sensitivity deep learning algorithm.webp

thumbnail_Automated classification of X-rays as normalAbnormal using a high sensitivity deep learning algorithm.webp

Automated classification of X-rays as normalAbnormal using a high sensitivity deep learning algorithm.webp

Automated classification of X-rays as normal/Abnormal using a high sensitivity deep learning algorithm

Pneumocephalus, accumulation of air in intracranial space, can lead to midline shift and compression of brain. In this work, we detail the development of deep learning algorithms for automated detection and localization of pneumocephalus in head CT scans.

Firstly, to localize the intracranial space from a given head CT scan, a skullÂ­-stripping algorithm was developed using a randomly sampled anonymized dataset of 78 head CT scans (1608 slices). We sampled another anonymized dataset containing 83 head CT scans (3546 slices) having pneumocephalus and 310 normal head CT scans which were randomly sampled to represent natural distribution. These 3546 slices (932 slices had pneumocephalus) were annotated for pneumocephalus regions. Then UÂ­Net based deep neural network algorithm was trained on these scans to accurately predict the pneumocephalus region . The predicted pneumocephalus region is refined by removing the regions outside the intracranial space identified by the skull stripping algorithm. The refined pneumocephalus region is then used to extract features. Using these features, a random forest was trained to classify the presence of pneumocephalus in a scan. Areas under receiver operating characteristics curves (AUC) were used to evaluate the algorithms.

An independent dataset of 1891 head CT scans (40 scans had pneumocephalus) was used for testing above algorithms. AUC for the scan level predictions was 0.89. Sensitivity and Specificity of 0.80 and 0.83 respectively were observed.

In this work, we showed the efficacy of deep learning algorithms in localizing and classifying the pneumocephalus accurately in a head CT scan.

large_Automated Detection and Localization of Pneumocephalus in Head CT scan.webp

medium_Automated Detection and Localization of Pneumocephalus in Head CT scan.webp

small_Automated Detection and Localization of Pneumocephalus in Head CT scan.webp

thumbnail_Automated Detection and Localization of Pneumocephalus in Head CT scan.webp

Automated Detection and Localization of Pneumocephalus in Head CT scan.webp

Automated Detection and Localization of Pneumocephalus in Head CT scan

Mass effect and Midline shift are most critical and time­ sensitive abnormalities that can be readily detected on head-CT scan. We describe development and validation of deep learning algorithms to automatically detect the mentioned abnormalities.

We labeled slices from 699 anonymized nonÂ­contrast head-CT scans for the presence or absence of mass effect and midline shift in that slice. Number of scans(slices) with mass effect were 320(3143) and midline shift were 249(2074). We used these labels to train a modified ResNet18, a popular convolutional neural network to predict softmax based confidences for the presence of mass effect and midline shift in a slice. We modified the network by using two parallel fully connected(FC) layers in place of a single FC layer. The confidences at the slice­-level were combined using random forest to predict the scan-level confidence for the presence of mass effect and midline shift. A separate dataset(CQ500 dataset) was collected for the validation of the algorithm. Three senior radiologists independently read each scan in this dataset. Consensus of the readers’ opinion was used as the gold standard. We used areas under receiver operating characteristics curves(AUC) to evaluate the algorithm.

CQ500 dataset contained 491 scans of which number of scans with mass effect and midline shift were 99 and 47 respectively. AUC for detecting mass effect was 0.92(95%CI 0.89-0.95) and for detecting midline shift was 0.97(95%CI 0.94-0.99).

We show that a deep learning algorithm can be trained to accurately detect mass effect and midline shift from head CT scans.

large_Automated Detection of Midline Shift and Mass Effect from Head CT Scans using Deep Learning.webp

medium_Automated Detection of Midline Shift and Mass Effect from Head CT Scans using Deep Learning.webp

small_Automated Detection of Midline Shift and Mass Effect from Head CT Scans using Deep Learning.webp

thumbnail_Automated Detection of Midline Shift and Mass Effect from Head CT Scans using Deep Learning.webp

Automated Detection of Midline Shift and Mass Effect from Head CT Scans using Deep Learning.webp

Automated Detection of Midline Shift and Mass Effect from Head CT Scans using Deep Learning

Non-contrast Head-CT scans are primary imaging modality for evaluating patients with trauma or stroke. While results of deep learning algorithms to identify head-CT scans containing critical abnormalities has been published in retrospective studies, effects of deployment of such an algorithm in a real-world setting, with mobile notifications to clinician remain unstudied. In this prospective study, we evaluated performance of such an automated triage system in an urban 24-hour imaging facility.

We developed an accurate deep neural network algorithm that identifies and localizes intracranial bleeds, cranial fractures, mass effect and midline shift on non-contrast head-CT scans. The algorithm is deployed in clinical imaging facility in conjunction with an on-premise module that automatically selects eligible scans from PACS and uploads them to cloud-based algorithm for processing. Once processed, cloud algorithm returns an additional series, viewable as an overlay over the original, and a text notification to radiologist with preview images. Mobile notifications facilitated confirmation of the detected abnormalities. We studied the performance of the automated system over 60 days.

748 CT scans were taken over 60 days, of which 194 were non-contrast head-CT scans and these are evaluated by senior radiologist. Sensitivity, specificity, AUC and average time to notification of head-CT scans with critical abnormalities were Â&nbsp;0.90 (95% CI 0.74-0.98), 0.86 (0.80-0.91), 0.97 (0.92-1.00) and 3.2 minutes respectively.

An automated triage system in a radiology facility results in rapid notification of critical scans, with a low false positive rate and this may be used to expedite treatment initiation.

large_Prospective evaluation of a deep learning algorithm deployed in an urban imaging centre to notify clinicians of head CT scans with critical abnormalities.webp

medium_Prospective evaluation of a deep learning algorithm deployed in an urban imaging centre to notify clinicians of head CT scans with critical abnormalities.webp

small_Prospective evaluation of a deep learning algorithm deployed in an urban imaging centre to notify clinicians of head CT scans with critical abnormalities.webp

thumbnail_Prospective evaluation of a deep learning algorithm deployed in an urban imaging centre to notify clinicians of head CT scans with critical abnormalities.webp

Prospective evaluation of a deep learning algorithm deployed in an urban imaging centre to notify clinicians of head CT scans with critical abnormalities.webp

Prospective evaluation of a deep learning algorithm deployed in an urban imaging centre to notify clinicians of head CT scans with critical abnormalities

To validate set of deep learning algorithms for automated detection of key findings from nonÂ­contrast head-CT scans: intracranial hemorrhage and its subtypes, calvarial fractures, midline shift and mass effect.

We retrospectively collected a dataset containing 313,318 head-CT scans of which random subset(Qure25k dataset) was used to validate and rest to develop algorithms. Additional dataset(CQ500 dataset) was collected from different centers to validate algorithms. Patients with postÂ­operative defect or age&lt;7 were excluded from all datasets. Three independent radiologists read each scan in CQ500 dataset. Original clinical radiology report and consensus of readers were considered as gold standards for Qure25k and CQ500 datasets respectively. Areas under receiver operating characteristics curves(AUCs) were used to evaluate algorithms.

After exclusion, Qure25k dataset contained 21,095 scans(mean-age 43;43% female) while CQ500 dataset consisted of 491(mean-age 48;36% female) scans. On Qure25k dataset, algorithms achieved an AUC of 0.92 for detecting intracranial hemorrhage(0.90-intraparenchymal, 0.96-intraventricular, 0.92-subdural, 0.93-extradural, and 0.90-subarachnoid hemorrhages). On CQ500 dataset, AUC was 0.94 for intracranial haemorrhage(0.95, 0.93, 0.95, 0.97, and 0.96 respectively). AUCs on Qure25k dataset were 0.92 for calvarial fractures, 0.93 for midline shift, and 0.86 for mass effect, while AUCs on CQ500 dataset were 0.96, 0.97 and 0.92 respectively.

This study demonstrates that deep learning algorithms can identify head-CT scan abnormalities requiring urgent attention with high AUCs.

large_Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

medium_Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

small_Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

thumbnail_Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans

The purpose of this study was to use a deep learning algorithm to detect and localize subacute and chronic ischemic infarcts on head CT scans for use in automated volumetric progression tracking.

We sampled 308 head CT scans (11840 slices) which were reported with chronic or subacute infarct. The infarcted regions in 11840 infarct-positive slices were marked. We trained segmentation algorithm to predict a heatmap of infarct lesion. The heatmap was used to derive scan level features representative of lesion density and volume to train a random forest to predict scan-level probabilities of chronic infarct. Area under receiver operating characteristics curves (AUC) were used to evaluate scan level predictions.

The algorithm was validated on an independent dataset of 1610 head CT scans containing 78 chronic &amp; 9 subacute infarct, 45 chronic ICH, 6 glioblastomas. The distribution of infarct affected territories was – 52.9% MCA, 33.3 % PCA, 9.3% ACA and 4.7% vertebrobasilar territories. The algorithm yielded AUC of 0.8474 (95% CI 0.7964 – 0.8984) for scan level predictions. It identified 8 of 9 subacute infarcts (88.89% recall) and 70 out of 78 chronic infarcts (89.74% recall). The eight missed chronic infarcts constituted of 3 lacunar and 2 hemorrhagic. The volumes of predicted infarct lesions ranged from 1 mL – 526 mL with mean prediction volume as 55.60mL.

The study demonstrates the capability of deep learning algorithms to accurately differentiate infarcts from infarct mimics.

large_Deep Learning for Infarct Detection and Localization from Head CT Scans.webp

medium_Deep Learning for Infarct Detection and Localization from Head CT Scans.webp

small_Deep Learning for Infarct Detection and Localization from Head CT Scans.webp

thumbnail_Deep Learning for Infarct Detection and Localization from Head CT Scans.webp

Deep Learning for Infarct Detection and Localization from Head CT Scans.webp

Deep Learning for Infarct Detection and Localization from Head CT Scans

Non-contrast head CT scan is the current standard for initial imaging of patients with head trauma or stroke symptoms. We aimed to develop and validate a set of deep learning algorithms for automated detection of the following key findings from these scans: intracranial haemorrhage and its types (ie, intraparenchymal, intraventricular, subdural, extradural, and subarachnoid); calvarial fractures; midline shift; and mass effect.

We retrospectively collected a dataset containing 313 318 head CT scans together with their clinical reports from around 20 centres in India between Jan 1, 2011, and June 1, 2017. A randomly selected part of this dataset (Qure25k dataset) was used for validation and the rest was used to develop algorithms. An additional validation dataset (CQ500 dataset) was collected in two batches from centres that were di erent from those used for the development and Qure25k datasets. We excluded postoperative scans and scans of patients younger than 7 years. The original clinical radiology report and consensus of three independent radiologists were considered as gold standard for the Qure25k and CQ500 datasets, respectively. Areas under the receiver operating characteristic curves (AUCs) were primarily used to assess the algorithms.

The Qure25k dataset contained 21 095 scans (mean age 43 years; 9030 [43%] female patients), and the CQ500 dataset consisted of 214 scans in the rst batch (mean age 43 years; 94 [44%] female patients) and 277 scans in the second batch (mean age 52 years; 84 [30%] female patients). On the Qure25k dataset, the algorithms achieved an AUC of 0·92 (95% CI 0·91–0·93) for detecting intracranial haemorrhage (0·90 [0·89–0·91] for intraparenchymal, 0·96 [0·94–0·97] for intraventricular, 0·92 [0·90–0·93] for subdural, 0·93 [0·91–0·95] for extradural, and 0·90 [0·89–0·92] for subarachnoid). On the CQ500 dataset, AUC was 0·94 (0·92–0·97) for intracranial haemorrhage (0·95 [0·93–0·98], 0·93 [0·87–1·00], 0·95 [0·91–0·99], 0·97 [0·91–1·00], and 0·96 [0·92–0·99], respectively). AUCs on the Qure25k dataset were 0·92 (0·91–0·94) for calvarial fractures, 0·93 (0·91–0·94) for midline shift, and 0·86 (0·85–0·87) for mass e ect, while AUCs on the CQ500 dataset were 0·96 (0·92–1·00), 0·97 (0·94–1·00), and 0·92 (0·89–0·95), respectively.

Our results show that deep learning algorithms can accurately identify head CT scan abnormalities requiring urgent attention, opening up the possibility to use these algorithms to automate the triage process.

large_Deep learning algorithms for detection of critical findings in head CT scans – A retrospective study.webp

medium_Deep learning algorithms for detection of critical findings in head CT scans – A retrospective study.webp

small_Deep learning algorithms for detection of critical findings in head CT scans – A retrospective study.webp

thumbnail_Deep learning algorithms for detection of critical findings in head CT scans – A retrospective study.webp

Deep learning algorithms for detection of critical findings in head CT scans – A retrospective study.webp

Deep learning algorithms for detection of critical findings in head CT scans – A retrospective study

Deep learning (DL) based solutions have been proposed for interpretation of several imaging modalities including radiography, CT, and MR. For chest radiographs, DL algorithms have found success in the evaluation of abnormalities such as lung nodules, pulmonary tuberculosis, cystic fibrosis, pneumoconiosis, and location of peripherally inserted central catheters. Chest radiography represents the most commonly performed radiological test for a multitude of non-emergent and emergent clinical indications. This study aims to assess accuracy of deep learning (DL) algorithm for detection of abnormalities on routine frontal chest radiographs (CXR), and assessment of stability or change in findings over serial radiographs.

We processed 874 de-identified frontal CXR from 724 adult patients (&gt; 18 years) with DL (Qure AI). Scores and prediction statistics from DL were generated and recorded for the presence of pulmonary opacities, pleural effusions, hilar prominence, and enlarged cardiac silhouette. To establish a standard of reference (SOR), two thoracic radiologists assessed all CXR for these abnormalities. Four other radiologists (test radiologists), unaware of SOR and DL findings, independently assessed the presence of radiographic abnormalities. A total 724 radiographs were assessed for detection of findings. A subset of 150 radiographs with follow up examinations was used to asses change over time. Data were analyzed with receiver operating characteristics analyses and post-hoc power analysis.

About 42% (305/ 724) CXR had no findings according to SOR; single and multiple abnormalities were seen in 23% (168/724) and 35% (251/724) of CXR. There was no statistical difference between DL and SOR for all abnormalities (p = 0.2–0.8). The area under the curve (AUC) for DL and test radiologists ranged between 0.837–0.929 and 0.693–0.923, respectively. DL had lowest AUC (0.758) for assessing changes in pulmonary opacities over follow up CXR. Presence of chest wall implanted devices negatively affected the accuracy of DL algorithm for evaluation of pulmonary and hilar abnormalities.

DL algorithm can aid in interpretation of CXR findings and their stability over follow up CXR. However, in its present version, it is unlikely to replace radiologists due to its limited specificity for categorizing specific findings.

large_Deep learning in chest radiography Detection of findings and presence of change.webp

medium_Deep learning in chest radiography Detection of findings and presence of change.webp

small_Deep learning in chest radiography Detection of findings and presence of change.webp

thumbnail_Deep learning in chest radiography Detection of findings and presence of change.webp

Deep learning in chest radiography Detection of findings and presence of change.webp

Deep learning in chest radiography: Detection of findings and presence of change

Chest x-rays are the most commonly performed, cost-effective diagnostic imaging tests ordered by physicians. A clinically validated, automated artificial intelligence system that can reliably separate normal from abnormal would be invaluable in addressing the problem of reporting backlogs and the lack of radiologists in low-resource settings. The aim of this study was to develop and validate a deep learning system to detect chest x-ray abnormalities.

A deep learning system was trained on 1.2 million x-rays and their corresponding radiology reports to identify abnormal x-rays and the following specific abnormalities: blunted costophrenic angle, calcification, cardiomegaly, cavity, consolidation, fibrosis, hilar enlargement, opacity and pleural effusion. The system was tested versus a 3-radiologist majority on an independent, retrospectively collected de-identified set of 2000 x-rays. The primary accuracy measure was area under the ROC curve (AUC), estimated separately for each abnormality as well as for normal versus abnormal reports.

The deep learning system demonstrated an AUC of 0.93(CI 0.92-0.94) for detection of abnormal scans, and AUC(CI) of 0.94(0.92-0.97),0.88(0.85-0.91), 0.97(0.95-0.99), 0.92(0.82-1), 0.94(0.91-0.97), 0.92(0.88-0.95), 0.89(0.84-0.94), 0.93(0.92-0.95), 0.98(0.97-1), 0.93(0.0.87-0.99) for the detection of blunted CP angle, calcification, cardiomegaly, cavity, consolidation, fibrosis,hilar enlargement, opacity and pleural effusion respectively.

Our study shows that a deep learning algorithm trained on a large quantity of labelled data can accurately detect abnormalities on chest x-rays. As these systems further increase in accuracy, the feasibility of using artificial intelligence to extend the reach of chest x-ray interpretation and improve reporting efficiency will increase in tandem.

large_Can Artificial Intelligence Reliably Report Chest X-Rays Radiologist Validation of an Algorithm trained on 1.2 Million X-Rays.webp

medium_Can Artificial Intelligence Reliably Report Chest X-Rays Radiologist Validation of an Algorithm trained on 1.2 Million X-Rays.webp

small_Can Artificial Intelligence Reliably Report Chest X-Rays Radiologist Validation of an Algorithm trained on 1.2 Million X-Rays.webp

thumbnail_Can Artificial Intelligence Reliably Report Chest X-Rays Radiologist Validation of an Algorithm trained on 1.2 Million X-Rays.webp

Can Artificial Intelligence Reliably Report Chest X-Rays Radiologist Validation of an Algorithm trained on 1.2 Million X-Rays.webp

Can Artificial Intelligence Reliably Report Chest X-Rays? Radiologist Validation of an Algorithm trained on 1.2 Million X-Rays

Whereas heart failure (HF) is a complex clinical syndrome, conventional approaches to its management have treated it as a singular disease, leading to inadequate patient care and inefficient clinical trials. We hypothesized that applying advanced analytics to a large cohort of HF patients would improve prognostication of outcomes, identify distinct patient phenotypes, and detect heterogeneity in treatment response.

The Swedish Heart Failure Registry is a nationwide registry collecting detailed demographic, clinical, laboratory, and medication data and linked to databases with outcome information. We applied random forest modeling to identify predictors of 1‐year survival. Cluster analysis was performed and validated using serial bootstrapping. Association between clusters and survival was assessed with Cox proportional hazards modeling and interaction testing was performed to assess for heterogeneity in response to HF pharmacotherapy across propensity‐matched clusters. Our study included 44 886 HF patients enrolled in the Swedish Heart Failure Registry between 2000 and 2012. Random forest modeling demonstrated excellent calibration and discrimination for survival (C‐statistic=0.83) whereas left ventricular ejection fraction did not (C‐statistic=0.52): there were no meaningful differences per strata of left ventricular ejection fraction (1‐year survival: 80%, 81%, 83%, and 84%). Cluster analysis using the 8 highest predictive variables identified 4 clinically relevant subgroups of HF with marked differences in 1‐year survival. There were significant interactions between propensity‐matched clusters (across age, sex, and left ventricular ejection fraction and the following medications: diuretics, angiotensin‐converting enzyme inhibitors, β‐blockers, and nitrates, P &lt; 0.001, all).

Machine learning algorithms accurately predicted outcomes in a large data set of HF patients. Cluster analysis identified 4 distinct phenotypes that differed significantly in outcomes and in response to therapeutics. Use of these novel analytic approaches has the potential to enhance effectiveness of current therapies and transform future HF clinical trials.

large_Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients.webp

medium_Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients.webp

small_Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients.webp

thumbnail_Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients.webp

Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients.webp

Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients

Non-contrast head CT scan is the current standard for initial imaging of patients with head trauma or stroke symptoms.

To develop and validate a set of deep learning algorithms for automated detection of following key findings from non-contrast head CT scans: intracranial hemorrhage (ICH) and its types, intraparenchymal (IPH), intraventricular (IVH), subdural (SDH), ex- tradural (EDH) and subarachnoid (SAH) hemorrhages, calvarial fractures, midline shift and mass effect.

We retrospectively collected a dataset containing 313,318 head CT scans along with their clinical reports from various centers. A part of this dataset (Qure25k dataset) was used to validate and the rest to develop algorithms. Additionally, a dataset (CQ500 dataset) was collected from different centers in two batches B1 &amp; B2 to clinically validate the algorithms.

Original clinical radiology report and consensus of three independent radiologists were considered as gold standard for Qure25k and CQ500 datasets respectively. Area under receiver operating characteristics curve (AUC) for each finding was primarily used to evaluate the algorithms.

Qure25k dataset contained 21,095 scans (mean age 43.31; 42.87% female) while batches B1 and B2 of CQ500 dataset consisted of 214 (mean age 43.40; 43.92% female) and 277 (mean age 51.70; 30.31% female) scans respectively. On Qure25k dataset, the algorithms achieved AUCs of 0.9194, 0.8977, 0.9559, 0.9161, 0.9288 and 0.9044 for detecting ICH, IPH, IVH, SDH, EDH and SAH respectively. AUCs for the same on CQ500 dataset were 0.9419, 0.9544, 0.9310, 0.9521, 0.9731 and 0.9574 respectively. For detecting calvarial fractures, midline shift and mass effect, AUCs on Qure25k dataset were 0.9244, 0.9276 and 0.8583 respectively, while AUCs on CQ500 dataset were 0.9624, 0.9697 and 0.9216 respectively.

This study demonstrates that deep learning algorithms can accurately identify head CT scan abnormalities requiring urgent attention. This opens up the possibility to use these algorithms to automate the triage process. They may also provide a lower bound for quality and consistency of radiological interpretation.

large_Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

medium_Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

small_Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

thumbnail_Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans.webp

Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans

To develop and validate a deep neural network-based algorithm for automated, rapid and accurate detection from head CT for the following haemorrhages: intracerebral (ICH), subdural (SDH), extradural (EDH) and subarachnoid (SAH).

An anonymised database of head CTs was searched for non-contrast scans which were reported with any of ICH, SDH, EDH, SAH and those which were reported with neither of these. Each slice of these scans is manually tagged with the haemorrhages that are visible in that slice. In all, 3040 scans (116227 slices) were annotated, of which number of scans(slices) with ICH, SDH, EDH, SAH and neither of these are 781(6957), 493(6593), 742(6880), 561(5609) and 944(92999), respectively. Our deep learning model is a modified ResNet18 with 4 parallel final fully connected layers for each of the haemorrhages. This model is trained on the slices from the annotated dataset to make slice-level decisions. Random forests are trained with ResNet’s softmax outputs for all the slices in a scan as features to make scan-level decisions.

A different set of 2993 scans, uniformly sampled from the database without any exclusion criterion, is used for testing the scan-level decisions. Number of scans with ICH, SDH, EDH and SAH in this set are 123, 58, 41 and 62, respectively. Area under the receiver operating curve (AUC) for scan-level decisions for ICH, SDH, EDH and SAH are 0.91, 0.90, 0.90 and 0.90, respectively. Algorithm takes less than 1s to produce the decision for a scan.

Deep learning can accurately detect intra- and extra-axial haemorrhages from head CTs.

large_Automated detection of intra- and extra-axial haemorrhages on CT brain images using deep neural networks.webp

medium_Automated detection of intra- and extra-axial haemorrhages on CT brain images using deep neural networks.webp

small_Automated detection of intra- and extra-axial haemorrhages on CT brain images using deep neural networks.webp

thumbnail_Automated detection of intra- and extra-axial haemorrhages on CT brain images using deep neural networks.webp

Automated detection of intra- and extra-axial haemorrhages on CT brain images using deep neural networks.webp

Automated detection of intra- and extra-axial haemorrhages on CT brain images using deep neural networks

Chest X-rays(CXR), being highly sensitive, serve as a Screening tool in TB diagnosis. Though there are no classical features diagnostic of TB on CXR, there are a few patterns that can be used as supportive evidence. In Resource limited settings, developing Deep Learning algorithms for CXR based TB screening, could reduce diagnostic delay. Our algorithm screens for 8 abnormal patterns(TB tags)- Pleural effusion, blunted CP, Atelectasis, Fibrosis, Opacity, Nodules, Calcification and Cavity. It reports ‘No Abnormality Detected’ if none of these patterns are present on CXR.

An anonymized dataset of 423,218 CXRs with matched radiologist reports across (22 models, 9 manufacturers, 166 centres in India) was used to generate training data for the deep learning models. Natural Language Processing techniques were used to extract TB tags from these reports. Deep learning systems were trained to predict the probability of the presence/absence of each TB tag along with heat-maps that highlight abnormal regions in the CXR for each positive result.

We validated the screening algorithm on 3 datasets external to our training set- two public datasets maintained by NIH(from Montgomery and Shenzen) and a third from NIRT, India. The Area under the Receiver Operating Curve (AUC-ROC) for TB prediction was 0.91, 0.87 and 0.83 respectively.

Training on a diversified dataset enabled good performance on samples from completely different demographics. After further validation of it’s robustness against variation, the system can be deployed at scale to improve the current systems for TB screening significantly

large_Efficacy of deep learning for screening pulmonary tuberculosis.webp

medium_Efficacy of deep learning for screening pulmonary tuberculosis.webp

small_Efficacy of deep learning for screening pulmonary tuberculosis.webp

thumbnail_Efficacy of deep learning for screening pulmonary tuberculosis.webp

Efficacy of deep learning for screening pulmonary tuberculosis.webp

Efficacy of deep learning for screening pulmonary tuberculosis

Chest x-rays are widely used to identify pulmonary consolidation because they are highly accessible, cheap and sensitive. Automating the diagnosis in chest x-rays can reduce diagnostic delay, especially in resource-limited settings.

Anonymised dataset of 423,218 chest x-rays with corresponding reports (collected from 166 centres across India spanning 22 x-ray machine variants from 9 manufacturers) is used for training and validation. x-rays with consolidation are identified from their reports using natural language processing techniques. Images are preprocessed to a standard size and normalised to remove source dependency. These images are trained using deep residual neural networks. Multiple models are trained on various selective subsets of the dataset along with one model trained on entire data set. Scores yielded by each of these models is passed through a 2-layer neural network to generate final probabilities for presence of consolidation in an x-ray.

The model is validated and tested on a test dataset that is uniformly sampled from the parent dataset without any exclusion criteria. Sensitivity and specificity for the tag has been observed as 0.81 and 0.80, respectively. Area under the Receiver Operating Curve (AUC-ROC) was observed as 0.88.

Deep learning can be used to diagnose pulmonary consolidation in chest x-rays with models trained on a generalised dataset with samples from multiple demographics. This model performs better than a model trained on controlled dataset and is suited for a real world setting where x-ray quality may not be consistent.

large_Identifying pulmonary consolidation in Chest X Rays using deep learning.webp

medium_Identifying pulmonary consolidation in Chest X Rays using deep learning.webp

small_Identifying pulmonary consolidation in Chest X Rays using deep learning.webp

thumbnail_Identifying pulmonary consolidation in Chest X Rays using deep learning.webp

Identifying pulmonary consolidation in Chest X Rays using deep learning.webp

Identifying pulmonary consolidation in Chest X Rays using deep learning

To develop and validate deep learning-based algorithm pipeline for fast detection and localisation of skull fractures from non-contrast CT scans. All kinds of skull fractures: undisplaced, depressed, comminuted, etc. were included as part of study.

Anonymized and annotated dataset of 350 scans (11750 slices) with skull fractures were used for generating candidate proposals for fractures. Stacked network pipeline was used for candidate generation – a fully convolutional network for ROI generation and another deep convolutional network for ROI classification. Final ROI classification model (ResNet18) yielded fracture probabilities for candidates generated through the fully convolutional (UNet) network. Separate deep learning model was trained to detect haemorrhages on scan level which was used as proxy for clinical information. Fracture candidate features like size, probabilities, depth for top 5 most probable fracture candidates along with haemorrhage model confidence (phaemorrhage) were combined to train random forest classifier to detect fracture on scan level. In case of predicted fracture, most probable candidate(s) were used for localization.

Separate set of 2971 scans, uniformly sampled from database with no exclusion criterion, was used for testing scan-level decisions with 108 scans reported as skull fracture cases. To evaluate scan-level decisions for fractures, area under receiver operating curve (AUC-ROC) was calculated as 0.83 with phaemorrhage as feature and 0.72 without. Free receiver operating curve yielded 0.9 sensitivity at 2.85 false-positives-per-scan. Predictions on each patient takes &lt; 30s.

Deep learning-based pipeline can accurately detect and localize skull fractures. Pipeline can be used for triaging patients for presence of skull fractures.

large_Automated detection and localisation of skull fractures from CT scans using deep learning.webp

medium_Automated detection and localisation of skull fractures from CT scans using deep learning.webp

small_Automated detection and localisation of skull fractures from CT scans using deep learning.webp

thumbnail_Automated detection and localisation of skull fractures from CT scans using deep learning.webp

Automated detection and localisation of skull fractures from CT scans using deep learning.webp

Automated detection and localisation of skull fractures from CT scans using deep learning

Radiologists are currently ill equipped to precisely estimate disease burden and track the progression of idiopathic pulmonary fibrosis (IPF). Development of an automated method for IPF segmentation is challenging, due to the complexity of the fibrosis pattern and degree of variation between patients. Deep neural networks are machine learning algorithms that overcome these challenges. We describe the development and validation of a novel deep learning method to quantify the IPF pattern.

We used high-resolution chest CT scans from 23 patients with IPF as training data. The fibrosis pattern was marked out on 60 slices per scan. Annotated scans, with 6 additional normal scans were used to train a convolutional neural network to outline the IPF disease pattern. Segmentation accuracy was measured using Dice score. For each patient, percentage of lungs affected by IPF was calculated. An independent set of 50 scans was used for clinical validation. Disease volume was independently estimated by 2 thoracic radiologists blinded to the algorithm estimate. Algorithm-derived estimates were correlated with radiologist estimates of disease volume.

A 3-dimensional neural network architecture coupled with 2-dimensional post-processing of each slice produced the most accurate segmentation, with a Dice score of 0.77. The correlation between algorithm-derived disease volume estimate and average radiologist estimates was 0.92. Inter-radiologist correlation was 0.89. Radiologist estimates of disease volume varied by 5.5% (range 0-15%).

We demonstrate that a deep neural network, trained using expert-annotated images, can accurately quantify the percentage of lung volume affected by IPF.

Evidence (Publications & White Papers)