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

Qure.ai is deploying deep learning for radiology across the globe. This blog is the first in the series where we will talk about our learnings from deploying deep learning solutions at radiology centers. We will cover the technical aspects of the challenges and solutions in here. The operational hurdles will be covered in the next part of this series.

The dawn of an AI revolution is upon us. Deep learning or deep neural networks have crawled into our daily lives transforming how we type, write emails, search for photos etc. It is revolutionizing major fields like healthcare, banking, driving etc. At Qure.ai, we have been working for the past couple of years on&nbsp;<a href="https://blog.qure.ai/notes/on-qure-ai" target="_blank">our mission</a>&nbsp;of making healthcare more affordable and accessible through the power of deep learning.

Since our journey began more than two years ago, we have seen excellent progress in development and visualization of deep learning models. With Nvidia leading the advancements in GPUs and the release of Pytorch, Tensorflow, MXNet etc leading the war on deep learning frameworks, training deep learning models has become faster and easier than ever.

However, deploying these deep learning models at scale has become a different beast altogether. Let’s discuss some of the major problems that Qure.ai has tackled/is tackling in deploying deep learning for hospitals and radiologists across the globe.

Let us start with understanding how the challenges in deploying deep learning models are different from training them. During training, the focus is mainly on the accuracy of predictions, while deployment focuses on speed and reliability of predictions. Models can be trained on local servers, but in deployment, they need to be capable of scaling up or down depending upon the volume of API requests. Companies like&nbsp;<a href="https://algorithmia.com/" target="_blank">Algorithmia</a>&nbsp;and&nbsp;<a href="https://www.envoyai.com/" target="_blank">EnvoyAI</a>&nbsp;are trying to solve this problem by providing a layer over AI to serve the end users. We are already working with EnvoyAI to explore this route of deploying deep learning.

Selecting the right deep learning framework

Caffe was the first framework built to focus on production. Initially, our research team was using both Torch (flexible, imperative) as well as Lasagne/Keras (python!) for training. The release of Pytorch in late 2016 settled the debate on frameworks within our team.

Thankfully, this happened before we started looking into deployment. Once we finalized Pytorch for training and tweaking our models, we started looking into best practices for deploying the same. Meanwhile, Facebook released&nbsp;<a href="https://research.fb.com/downloads/caffe2/" target="_blank">Caffe2</a>&nbsp;for easier deployment, especially into mobile devices.

The AI community including Facebook, Microsoft and Amazon came together to release&nbsp;<a href="https://onnx.ai/" target="_blank">Open Neural Network Exchange (ONNX)</a>&nbsp;making it easier to switch between tools as per need. For example, it enables you to train your model in Pytorch and then export it into Caffe2/ MXNet/ CNTK (Cognitive Toolkit) for deployment. This approach is worth looking into when the load on our servers increase. But for our present needs, deploying models in Pytorch has sufficed.

We use following components to build our Linux servers keeping our pythonic deep learning framework in mind.

Most of these tools can be replaced as per requirements. The following diagram represents our present stack.

We use Amazon EC2 P2 instances as our cloud GPU servers primarily due to our team’s familiarity with AWS. Although, Microsoft’s Azure and Google Cloud can also be excellent options.

Our servers are built using small components performing specific services and it was important to have them on the same host for easy configuration. Moreover, we handle large dicom images (each having a size between 10 and 50 Mb) and they get transferred between the components. It made sense to have all the components on the same host or else, the network bandwidth might get choked due to these transfers. The following diagram illustrates various software components comprising a typical qure deployment.

We started with launching&nbsp;<a href="https://blog.qure.ai/notes/visualizing_deep_learning" target="_blank">qXR</a>&nbsp;(Chest X-ray product) on a P2 instance but as the load on our servers rose, managing GPU memory became an overhead. We were also planning to launch&nbsp;<a href="http://headctstudy.qure.ai/" target="_blank">qER</a>&nbsp;(HeadCT product) which had even higher GPU memory requirements.

Initially, we started with buying new P2 instances. Optimizing their usage and making sure that few instances are not bogged down by the incoming load while other instances remain comparatively free became a challenge. It became clear that we needed auto-scaling for our containers.

That was when we started looking into solutions for managing our containerized applications. We decided to go ahead with&nbsp;<a href="https://kubernetes.io/" target="_blank">Kubernetes</a>&nbsp;(Amazon ECS is also an excellent alternative) majorly because it runs independently of specific provider (ECS has to be deployed on Amazon cloud). Since many hospitals and radiology centers prefer on-premise deployment, Kubernetes is clearly more suited for such needs. It makes life easier by automatic bin-packing of containers based on resource requirements, simpler horizontal scaling, and load balancing.

Initially, when qXR was deployed, it dealt with fewer abnormalities. So for an incoming request, loading models into memory, processing images through it and then releasing the memory worked fine. But as the number of abnormalities (thereby models) increased, loading all models sequentially for each upcoming request became an overhead.

We thought of accumulating incoming requests and processing images in batches on a periodic basis. This could have been a decent solution except that time was critical when dealing with medical images, more so in emergency situations. It was especially critical for qER where in cases of strokes, one has less than an hour to make a diagnostic decision. This ruled out the batch processing approach.

Beware of GPUs !! (warning at Qure's Mumbai office)

Moreover, our models for qER were even larger and required approximately 10x GPU memory of what qXR models required. Another thought was to keep the models loaded in memory and process images through them as the requests arrive. This is a good solution where you need to run your models every second or even millisecond (think of AI models running on millions of images being uploaded to Facebook or Google Photos). However, this is not a typical scenario within the medical domain. Radiology centers do not encounter patients at that scale. Even if the servers send back the results within a couple of minutes, that’s like a 30x improvement in the amount of time that a radiologist would take to report the scan. And that’s when you assume that a radiologist is immediately available. Otherwise, an average turnaround period of a chest x-ray scan varies from 1 to 2 days (700-1400x of what we take currently).

As of now, auto-scaling with Kubernetes solves our problems but we would definitely look into it in future. The solution lies somewhere between the two approaches (think of a caching mechanism for deep learning models).

Training deep learning models, especially in healthcare, is only one part of building a successful AI product. Bringing it to healthcare practitioners is a formidable and interesting challenge in itself. There are other operational hurdles like convincing doctors to embrace AI, offline working style at some hospitals (using radiographic films), lack of modern infrastructure at radiology centers (operating systems, bandwidth, RAM, disk space, GPU), varying procedures for scan acquisition etc. We will talk about them in detail in the next part of this series.

large_blog 29.webp

medium_blog 29.webp

small_blog 29.webp

thumbnail_blog 29.webp

blog 29.webp

What We Learned Deploying Deep Learning at Scale for Radiology Images

In the&nbsp;previous post&nbsp;we looked at methods to visualize and interpret the decisions made by deep learning models using perturbation based techniques.To summarize the previous post, perturbation based methods do a good job of explaining decisions but they suffer fromexpensive computations and instability to surprise artifacts. In this post, we’ll give a brief overview and drawbacks of the various gradient-based algorithms for deep learning based classification models.

We would be discussing the following types of algorithms in this post:

In gradient-based algorithms, the gradient of the output with respect to the input is used for constructing the saliency maps. The algorithms in this class differ in the way the gradients are modified during backpropagation. Relevance score based algorithms try to attribute the relevance of each input pixel by backpropagating the probability score instead of the gradient. However, all of these methods involve a single forward and backward pass through the net to generate heatmaps as opposed to multiple forward passes for the perturbation based methods. Evidently, all of these methods are computationally cheaper as well as free of artifacts originating from perturbation techniques.

To illustrate each algorithm, we would be considering a Chest X-Ray (image below) of a patient diagnosed with pulmonary consolidation. Pulmonary consolidation is simply a “solidification” of the lung tissue due to the accumulation of solid and liquid material in the air spaces that would have normally been filled by gas. The dense material deposition in the airways could have been affected by infection or pneumonia (deposition of pus) or lung cancer (deposition of malignant cells) or pulmonary hemorrhage (airways filled with blood) etc. An easy way to diagnose consolidation is to look out for dense abnormal regions with ill-defined borders in the X-ray image.

We would be considering this X-ray and one of our models trained for detecting consolidation for demonstration purposes. For this patient, our consolidation model predicts a possible consolidation with 98.2% confidence.

Explanation:Measure the relative importance of input features by calculating the gradient of the output decision with respect to those input features.

There were 2 very similar papers that pioneered the idea in 2013. In these papers — Saliency features by Simonyan et al. and DeconvNet by Zeiler et al. — authors used directly the gradient of the majority class prediction with respect to input to observe saliency features. The main difference between the above papers was how the authors handle the backpropagation of gradients through non-linear layers like ReLU. In Saliency features paper, the gradients of neurons with negative input were suppressed while propagating through ReLU layers. In the DeconvNet paper, the gradients of neurons with incoming negative gradients were suppressed.

Algorithm:Given an image&nbsp;I0, a class&nbsp;c, and a classification ConvNet with the class score function&nbsp;Sc(I). The heatmap is calculated as absolute of the gradient of&nbsp;Sc&nbsp;with respect to&nbsp;I&nbsp;at&nbsp;I0[frac{partial S_c}{partial I} |_{I_0} ]

It is to be noted here, that DeepLIFT paper (which we’ll discuss later) explores the idea of gradient * input also as an alternate indicator as it leverages the strength and signal of input[frac{partial S_c}{partial I} |_{I_0} * I_0 ]

Shortcomings:The problem with such a simple algorithm arises from non-linear activation functions like ReLU, ELU etc. Such non-linear functions being inherently non-differentiable at certain locations have discontinuous gradients. Now as the methods measured partial derivatives with respect to each pixel, the gradient heatmap is inherently discontinuous over the entire image and produces artifacts if viewed as it is. Some of it can be overcome by convolving with a Gaussian kernel. Also, the gradient flow suffers in case of renormalization layers like BatchNorm or max pooling.

Explanation:The next paper, by Springenberg et. al, released in 2014 introduces GuidedBackprop, suppressed the flow of gradients through neurons wherein either of input or incoming gradients were negative. Springenberg et al. showed the difference amongst their methods through a beautiful illustration given below. As we discussed, this paper combined the gradient handling of both the Simonyan et al. and Zeiler et al.

Shortcomings:The problem of gradient flow through ReLU layers still remained a problem at large. Tackling renormalization layers were still an unresolved problem as most of the above papers (including this paper) proposed mostly fully convolutional architectures (without max pool layers) and batch normalization was yet to ‘alchemised’ in 2014. Another such fully-convolutional architecture paper was CAM.

Explanation:An effective way to circumnavigate the backpropagation problems were explored in the GradCAM by Selvaraju et al. This paper was a generalization of CAM algorithm given by Zhou et al., that tried to describe attribution scores using fully connected layers. The idea is, instead of trying to propagate back the gradients, can the activation maps of the final convolutional layer be directly used to infer downsampled relevance map of the input pixels. The downsampled heatmap is upsampled to obtain a coarse relevance heatmap.

Let the feature maps in the final convolutional layers be&nbsp;F1,&nbsp;F2&nbsp;… ,Fn. Like before assume image&nbsp;I0, a class&nbsp;c, and a classification ConvNet with the class score function&nbsp;Sc(I).

Steps 1-4 makes up the GradCAM method. Including step 5 constitutes the Guided Grad CAM method. Here’s how a heat map generated from Grad CAM method looks like. The best contribution from the paper was the generalization of the CAM paper in the presence of fully-connected layers.

Shortcomings:The algorithm managed to steer clear of backpropagating the gradients all the way up to inputs – it only propagates the gradients only till the final convolutional layer. The major problem with GradCAM was its limitation to specific architectures which use the AveragePooling layer to connect convolutional layers to fully connected layers. The other major drawback of GradCAM was the upsampling to coarse heatmap results in artifacts and loss in signal.

There are a couple of major problems with the gradient-based methods which can be summarised as follows:

Explanation:To counter these issues, relevance score based attribution technique was discussed for the first time by Bach et al. in 2015 in this paper. The authors suggested a simple yet strong technique of propagating relevance scores and redistributing as per the proportion of the activation of previous layers. The redistribution based on activation scores means we steer clear of the difficulties that arise with non-linear activation layers.

This implementation is according to epsilon-LRP&nbsp;where small epsilon is added in denominator to propagate relevance with numerical stability. Like before assume image&nbsp;I0, a class&nbsp;c, and a classification ConvNet with the class score function&nbsp;Sc(I).

Explanation: The last paper&nbsp;we cover in this series, is based on layer-wise relevance. However, herein instead of directly explaining the output prediction in previous models, the authors explain the difference in the output prediction and prediction on a baseline reference image. The concept is similar to Integrated Gradients which we discussed in the previous post. The authors bring out a valid concern with the gradient-based methods described above – gradients don’t use a reference which limits the inference. This is because gradient-based methods only describe the local behavior of the output at the specific input value, without considering how the output behaves over a range of inputs.

Algorithm:The reference image (IR) is chosen as the neutral image, suitable for the problem at hand. For class&nbsp;c, and a classification ConvNet with the class score function&nbsp;Sc(I),&nbsp;SRc&nbsp;be the probability for image&nbsp;IR. The relevance score to be propagated is not&nbsp;Sc&nbsp;but&nbsp;Sc&nbsp;– SRc.

We have so far understood both perturbation based algorithms as well as gradient-based methods. Computationally and practically, perturbation based methods are not much of a win although their performance is relatively uniform and consistent with an underlying concept of interpretability. The gradient-based methods are computationally cheaper and measure the contribution of the pixels in the neighborhood of the original image. But these papers are plagued by the difficulties in propagating gradients back through non-linear and renormalization layers. The layer relevance techniques go a step ahead and directly redistribute relevance in the proportion of activations, thereby steering clear of the problems in propagating through non-linear layers. In order to understand the relative importance of pixels, not only in the local neighborhood of pixel intensities, DeepLIFT redistributes difference of activation of an image and a baseline image.

We’ll be following up with a final post on the performance of all the methods discussed in the current and previous post and detailed analysis of their performance.

large_blog30.webp

medium_blog30.webp

small_blog30.webp

thumbnail_blog30.webp

blog30.webp

Visualizing Deep Learning Networks - Part II

With close to 30 years of radiology experience, Dr Biviji is an eminent radiologist based in Nagpur. He is an authority on developing deep learning solutions to radiology problems and works closely with early-stage healthcare technology innovators.

Q&amp;A with Dr Mustafa Biviji on artificial intelligence in radiology.

How do you see Artificial Intelligence in radiology evolving in the future?

In the future, radiologists and radiographers could be replaced by intelligent machines. CT and MRI machines of the future would be embedded with AI programs capable of modifying scanning protocols on the fly, depending on the disease process initially identified. Highly accurate automated reports would be produced almost instantly. Machines would prognosticate, identify as yet unknown imaging patterns associated with diseases and may also uncover new diseases.

There will be objectivity to the radiology reports with personal bias of the radiologist no longer a factor. Remote and isolated areas of the world will have an equal access to the best diagnostic information. Coupled with this would be better machine navigation during surgeries or probably even complete robotic surgery based on the imaging patterns identified with AI. Through it all, I believe that radiologists will continue to reinvent themselves.

How far away is the industry from realizing these goals, and how does Qure compare to similar solutions that you may have seen/ implemented?

These are initial days and the role of AI in Radiology is currently restricted to assistance. While most solutions talk about simplifying workflows, Qure to the best of my knowledge is the only one talking about automated reports with a remarkable degree of accuracy, thereby opening up exciting new prospects for the future. While the perfect radiology AI may be far in the future, at least a promising beginning has been made.

How does Qure.ai help in your radiology practice?

Qure.ai solutions in radiology now include automated head CT reports particularly for trauma and strokes. Reporting for these conditions would earlier have either necessitated a sleepless night or a delay in reporting. Automated reports can now be used to assist residents and help can be sought in case of a doubt or discrepancy. Delayed radiology reports will soon be a thing of the past.

How do you think the Qure’s Chest X-ray solution can help or is helping radiologists in their practice?

Qure’s chest X-ray solution presently is best targeted to a general practitioner in a remote or rural location interpreting his own chest radiographs. Qure CXR could help provide radiologist-level accuracy, previously only available at the larger centers in the bigger cities. Better radiology would lead to better treatment outcomes and obviate the need for patients to travel long distances to seek a diagnosis.

How do you think young radiologists should prepare for AI?

AI in the future will radically modify the role of a radiologist. I predict a significant blurring of the roles of a diagnostic radiologist, surgeon or a physician. The radiologist of the future will have to stop behaving like an unseen backroom doctor and reinvent to participate actively in patient management. Image assisted robotic surgeries and integrated patient care are not too far off in the future.

large_blog 31.jpeg

medium_blog 31.jpeg

small_blog 31.jpeg

thumbnail_blog 31.jpeg

blog 31.jpeg

Interview with Dr Mustafa Biviji - Artificial Intelligence and the Future of Radiology

Dr. Bharat Aggarwal is the Director of Radiology Services at Max Healthcare. A distinguished third generation Radiologist, he was previously the promoter and lead Radiologist at Diwan Chand Aggarwal Imaging Research Centre, New Delhi. Dr. Aggarwal is an alumnus of Tata Memorial Hospital, Mumbai, and UCMS, Delhi.

Q&amp;A with Dr. Bharat Aggarwal on artificial intelligence in radiology.

There is going to be a significant role of AI in the field of imaging, and it will form a critical part of service delivery. There are many gaps in the existing model of service offerings. Some examples where AI will be commonly used include triaging and highlighting critical cases (reporting is done sequentially and a diagnosis requiring urgent intervention could be “at the bottom of the pile”); early diagnosis (pixel resolution of AI vs the human eye); pre-reading to take care of resource crunch, automation in comparisons, objectivization of disease &amp; response to treatment; quality assurance etc.

Dr. Bharat Aggarwal is the Director of Radiology Services at Max Healthcare. A distinguished third generation Radiologist, he was previously the promoter and lead Radiologist at Diwan Chand Aggarwal Imaging Research Centre, New Delhi. Dr. Aggarwal is an alumnus of Tata Memorial Hospital, Mumbai, and UCMS, Delhi.

How do you think the Qure.ai Chest X-ray solution can help radiologists in their practice?

Triaging normal from abnormal; building efficiency; quality assurance.

What is your advice to young radiologists who are just getting started on their career? How should they think about adopting AI in their practice and should they be doing anything differently to succeed as a radiologist 10-20 years from now?

Yes, adopting AI is a must. Radiologists will not be irrelevant in the world of machines. The role of the radiologists will be to direct research towards clinical gaps, validate AI diagnosis and focus on new problems that will emerge in the AI world. They need to treat AI with healthy competitiveness and build their careers with AI on their team. The opposition is the disease. The goal is health for all.

large_blog 32.jpeg

medium_blog 32.jpeg

small_blog 32.jpeg

thumbnail_blog 32.jpeg

blog 32.jpeg

Interview with Dr Bharat Aggarwal - Artificial Intelligence and the Radiology Workflow

Dr Shalini Govil is the Lead Abdominal Radiologist, Senior Advisor and Quality Controller at the Columbia Asia Radiology Group. Through her years as Associate Professor at CMC Vellore, Dr Shalini Govil has taught and mentored countless radiologists and medical students and continues to do so. Nowadays, she is busy training a new student – an Artificial Intelligence system that is learning to read Chest X-rays. Dr Govil is an accomplished researcher having published 30+ papers, and has won numerous awards for her contributions to Radiology.

Q&amp;A with Dr Shalini Govil on artificial intelligence in radiology.

Given the accuracy levels being reported across the world for deep learning algorithm diagnosis on imaging, I am sure AI has the potential to emerge as a strong diagnostic tool in the clinical armamentarium.

The only factor that could stand in the way of this progress is the very human fear of being “replaced”, “overtaken” or “made redundant”.

I feel that any crossroad like this in the practice of Medicine is best approached from the point of view of the patient and not from the viewpoint of commerce or market forces.Medicine is not a “job”…Medicine is “healing”…Medicine…is a patient trusting you at a vulnerable moment in his/her life.

From that standpoint, it is very simple – if AI is as accurate as a Senior Radiology Resident or even more accurate, let the patient have the benefit of a timely and accurate DRAFT report that can be validated by a physician or radiologist. This would certainly be better than the current practice in many parts of the world where the x-ray is not formally reported by a trained Radiologist or even a Trainee Radiologist.

Even as researchers are racing to study AI performance in increasingly complex pathology, widespread and parallel clinical testing is the need of the hour, to build confidence in Radiology AI and to obtain to a critical mass that will allow the threshold of human fear to be crossed.

Qure.ai has come up with a way to “see through the computer’s eyes”. I think this will be a game changer on the road to building confidence in AI. Whenever I have discussed the work I am doing on the use of AI in chest x-ray diagnosis with doctors, they tend to get a glassy look that says, “This is impractical…it’s never going to come into clinical use…”

But the minute they see a chest x-ray with the Qure.ai heatmap shading the abnormality that the AI actually “picked up”…the glassy look turns into one of wonder…because it is exactly what the doctor sees himself! I find this happens with lay people as well, even high school kids!

How do you think the Qure CXR solution can help or is helping radiologists in their practice?

Once the algorithm has been trained on a large number of chest x-rays and robust clinical testing has demonstrated a low false negative rate, I think the best use of the Qure.ai CXR solution would be to run all chest x-rays in our practice through the algorithm and obtain a DRAFT report to ease validation by a Radiologist.

What is your advice to young radiologists who are just getting started on their career? How should they think about adopting AI in their practice and what should they learn to succeed as a radiologist 10-20 years from now?

I would tell young Radiologists that help is on the way…that the days of struggling without a mentor when viewing a difficult case are over…that very soon, an “App” will help them derive a keyword tag to the image that has confounded them and that this keyword will then enable them to research and read and provide an articulate and lucid differential diagnosis.

What should they learn?They should learn Radiology of course…as in-depth and in-breadth as has ever been done…and they possibly can….But they should also learn the basics of neural networks, deep learning algorithms and keep abreast of evolving AI.Oh! and another thing – it might be a good idea to brush up on their 12th grade calculus!

large_blog 33.webp

medium_blog 33.webp

small_blog 33.webp

thumbnail_blog 33.webp

blog 33.webp

Interview with Dr Shalini Govil - Training Artificial Intelligence to Read Chest X-Rays

Dr Bhavin Jankharia is one of India’s leading radiologists, former president of the IRIA as well as a renowned educator, speaker and writer. Dr Jankharia’s radiology and imaging practice, “Picture This by Jankharia”, is known for being an early adopter of innovation and for pioneering new technologies in radiology.

Q&amp;A with Dr Jankharia on artificial intelligence in radiology.

AI is here to stay and will be a major factor to shape radiology over the next 10 years. It will be incorporated in some form or the other in protocols and workflows across the spectrum of radiology work and across the globe.

You have been an early adopter of AI in your practice. What would your advice be to other institutions globally who are considering incorporating AI into their workflow?

It is about questions that need to be answered. At present, AI is good at solving specific questions or given numerical data from CT scans of the abdomen and pelvis with respect to bone density and aortic size, etc. Wherever there is a need for such issues to be addresses, AI should be incorporated into those specific workflows. We still haven’t gotten to the stage where AI can report every detail in every scan and that may actually never happen.

It may never happen that AI can do what a radiologist does, but looking at the near team (say next 3-5 years), what do you think AI can achieve? (For example, what tasks can it automate? Can it improve reporting accuracy? ) Where will the biggest value addition be?

Its basic value addition will be to take away drudge work. Automated measurements, automated checking of densities, enhancement patterns, perhaps even automated follow-ups for measurements of abnormal areas already marked out on the first scans and the like.

Now that you have experienced AI in practice, how would you differentiate this technology from traditional CAD solutions that have been around for a while?

AI learns much faster and the basic approach is different. To the end user though, it matters not, does it, how we get the answer we want…

You have seen several AI companies in Radiology. What should they be doing differently to reach this goal?

At present, all of AI is problem-solving based. And since each company deals with different problems based on the doctors they work with, this approach is fine. The company that figures out a way to handle a non-problem based approach to basic interpretation of scans, the way radiologists do, will have a head-start.

How do you think the Qure.ai solutions can help or are helping radiologists in their practice?

They are slowly saving time and helping radiologists work smarter and better.

I don’t think radiologists per se have to do anything about AI, unless they want to change track and work in the field of AI from a technical perspective. AI incorporation into workflow will happen anyway and like all changes to radiology workflow over the decades, it will become routine and a way of life. They don’t really need to do anything different, except be willing to accept change.

large_blog 34.webp

medium_blog 34.webp

small_blog 34.webp

thumbnail_blog 34.webp

blog 34.webp

Interview with Dr Bhavin Jankharia - Radiologist Perspective on AI

As Associate Director at Mahajan Imaging, Dr Vidur Mahajan oversees scientific and clinical research, and pioneers the application of new techniques in radiology. Having collaborated with multiple healthcare tech companies, he is a thought leader in the AI-radiology space. Both doctor and entrepreneur, Dr Vidur Mahajan is passionate about improving access and affordability of high-end medical care across the developing world.

Q&amp;A with Dr Vidur Mahajan on artificial intelligence in radiology.

AI will keep playing a more important role in radiology as time progresses. The benefits, the way I see them, would be around 2 dimensions: quality and efficiency.

How far away is the industry from realizing this future, and how does Qure compare to similar solutions that you may have seen/ implemented?

We work with several AI companies today and are covered by a plethora of non-disclosure agreements, so wont be able to comment on how Qure compares to other solutions. That said, Qure’s pragmatic and user-oriented approach to developing algorithms is a definite plus. Given that Qure is backed by one of India’s best analytics companies, I would be surprised if they don’t end up taking the radiology AI world by storm! On the industry, I strongly feel that it will not be “sudden” transition. The industry will enter into this “AI future” in a step-by-step incremental way – we may not even notice and suddenly we’re surrounded by AI!

How do you think the Qure’s products can help or is helping radiologists in their practice? Would you be able to indicate specific benefits such as increased precision or time saved?

Qure’s chest X-Ray algorithm has the potential to change the entire paradigm of diagnostics in the developing world. The Chest X-Ray is the most commonly prescribed radiology investigation and everyday, thousands of X-Rays go un-reported in the developing world. Qure has the potential to give these patients a proper report and hence impact their treatment outcomes in a very positive way.

How well does the Qure solution integrate with your workflow? How can this be made better?

I think Qure has this nailed down completely. The strategy of integrating with Osirix (the world’s most widely used dicom viewer) through an extremely user-friendly and straightforward plugin enables instant reach to radiologists all over the world. Additionally, Qure’s ability to automatically email the AI system’s report to its users should also increase its usability across the world.

What are your expectations from AI in radiology software and how well has Qure met these?

While I think I have answered this in Q-1, the primary, and most important expectation from AI in radiology is a product that works. Simple. I would be very guarded about promoting a product with less that 90% accuracy since I would not want potential users to form a negative opinion about Qure’s product based on their initial experience. The stakes in healthcare are too high and reliability of an algorithm is paramount. Qure is definitely a leader in the AI space globally and I am very proud of the fact that an Indian company is taking the lead in this.

large_blog 35.webp

medium_blog 35.webp

small_blog 35.webp

thumbnail_blog 35.webp

blog 35.webp

Interview with Dr Vidur Mahajan - Artificial Intelligence and Radiology

At Qure, we regularly work on segmentation and object detection problems and we were therefore interested in reviewing the current state of the art.

In this post, I review the literature on semantic segmentation. Most research on semantic segmentation use natural/real world image datasets.Although the results are not directly applicable to medical images, I review these papers because research on the natural images is much more mature than that of medical images.

Post is organized as follows: I first&nbsp;explain the semantic segmentation&nbsp;problem, give an&nbsp;overview of the approaches&nbsp;and&nbsp;summarize a few interesting papers.

In a later post, I’ll explain why medical images are different from natural images and examine how the approaches from this review fare on a dataset representative of medical images.

Semantic segmentation is understanding an image at pixel level i.e., we want to assign each pixel in the image an object class.&nbsp;

Apart from recognizing the bike and the person riding it, we also have to delineate the boundaries of each object. Therefore, unlike classification, we need dense pixel-wise predictions from our models.

<a href="http://host.robots.ox.ac.uk/pascal/VOC/voc2012/">VOC2012</a>&nbsp;and&nbsp;MSCOCO&nbsp;are the most important datasets for semantic segmentation.

Before deep learning took over computer vision, people used approaches like&nbsp;<a href="http://mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2008-CVPR-semantic-texton-forests.pdf">TextonForest</a>&nbsp;and&nbsp;<a href="http://www.cse.chalmers.se/edu/year/2011/course/TDA361/Advanced%20Computer%20Graphics/BodyPartRecognition.pdf">Random Forest based classifiers</a>&nbsp;for semantic segmentation. As with image classification, convolutional neural networks (CNN) have had enormous success on segmentation problems.

One of the popular initial deep learning approaches was&nbsp;<a href="http://people.idsia.ch/~juergen/nips2012.pdf">patch classification</a>&nbsp;where each pixel was separately classified into classes using a patch of image around it. Main reason to use patches was that classification networks usually have full connected layers and therefore required fixed size images.

In 2014,&nbsp;Fully Convolutional Networks (FCN)&nbsp;by Long et al. from Berkeley, popularized CNN architectures for dense predictions without any fully connected layers. This allowed segmentation maps to be generated for image of any size and was also much faster compared to the patch classification approach. Almost all the subsequent state of the art approaches on semantic segmentation adopted this paradigm.

Apart from fully connected layers, one of the main problems with using CNNs for segmentation is&nbsp;pooling layers. Pooling layers increase the field of view and are able to aggregate the context while discarding the ‘where’ information. However, semantic segmentation requires the exact alignment of class maps and thus, needs the ‘where’ information to be preserved. Two different classes of architectures evolved in the literature to tackle this issue.

First one is encoder-decoder architecture. Encoder gradually reduces the spatial dimension with pooling layers and decoder gradually recovers the object details and spatial dimension. There are usually shortcut connections from encoder to decoder to help decoder recover the object details better.&nbsp;<a href="https://arxiv.org/abs/1505.04597">U-Net</a>&nbsp;is a popular architecture from this class.

<a href="https://arxiv.org/abs/1210.5644">Conditional Random Field (CRF) postprocessing</a>&nbsp;are usually used to improve the segmentation. CRFs are graphical models which ‘smooth’ segmentation based on the underlying image intensities. They work based on the observation that similar intensity pixels tend to be labeled as the same class. CRFs can boost scores by 1-2%.

In the next section, I’ll summarize a few papers that represent the evolution of segmentation architectures starting from FCN. All these architectures are benchmarked on&nbsp;<a href="http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php">VOC2012 evaluation server</a>.

Following papers are summarized (in chronological order):

For each of these papers, I list down their key contributions and explain them. I also show their benchmark scores (mean IOU) on VOC2012 test dataset.

Key observation is that fully connected layers in classification networks can be viewed as convolutions with kernels that cover their entire input regions.This is equivalent to evaluating the original classification network on overlapping input patches but is much more efficient because computation is shared over the overlapping regions of patches. Although this observation is not unique to this paper (see&nbsp;<a href="https://arxiv.org/abs/1312.6229">overfeat</a>,&nbsp;<a href="https://plus.google.com/+PierreSermanet/posts/VngsFR3tug9">this post</a>), it improved the state of the art on VOC2012 significantly.

After convolutionalizing fully connected layers in a imagenet pretrained network like VGG, feature maps still need to be upsampled because of pooling operations in CNNs. Instead of using simple bilinear interpolation,&nbsp;deconvolutional layers&nbsp;can learn the interpolation. This layer is also known as upconvolution, full convolution, transposed convolution or fractionally-strided convolution.

However, upsampling (even with deconvolutional layers) produces coarse segmentation maps because of loss of information during pooling. Therefore, shortcut/skip connections are introduced from higher resolution feature maps.

ScoreCommentSource62.2–<a href="http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php?cls=mean&amp;challengeid=11&amp;compid=6&amp;submid=6103#KEY_FCN-8s">leaderboard</a>&nbsp;67.2More momentum. Not described in paper&nbsp;<a href="http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php?cls=mean&amp;challengeid=11&amp;compid=6&amp;submid=6103#KEY_FCN-8s-heavy">leaderboard</a>

FCN, despite upconvolutional layers and a few shortcut connections produces coarse segmentation maps. Therefore, more shortcut connections are introduced. However, instead of copying the encoder features as in FCN, indices from maxpooling are copied. This makes SegNet more memory efficient than FCN.

ScoreCommentSource59.9–<a href="http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php?challengeid=11&amp;compid=6#KEY_SegNet">leaderboard</a>

Pooling helps in classification networks because receptive field increases. But this is not the best thing to do for segmentation because pooling decreases the resolution. Therefore, authors use&nbsp;dilated convolution&nbsp;layer which works like this:

large_blog 37.webp

medium_blog 37.webp

small_blog 37.webp

thumbnail_blog 37.webp

blog 37.webp

A 2017 Guide to Semantic Segmentation with Deep Learning

Knowing the state of the cells and amount of blood flow in brain, can reveal huge amount of information about it. Tumor cells have high consumption of blood metabolites (like glucose) than normal. This information can contribute significantly towards diagnosis of the brain. Perfusion Imaging allows us to measure all of these quantities. Combine this with Machine Learning, and we can build a system that takes perfusion images and gives out a complete report about the brain. This is the future.

Brain tumors are the leading cause of cancer-related deaths in children (males and females) age 1-19. It is estimated that as many as 5.1 million Americans may have Alzheimer’s disease. And there are many such degenerative diseases such as Parkinson’s, Autism, Schizophrenia that affect thousands and millions of people amongst us. Neuroimaging or brain imaging is the use of various techniques to either directly or indirectly image the structure, function/pharmacology of the nervous system. One of the techniques of neuroimaging is Perfusion Imaging.

Perfusion imaging captures the qualitative and quantitative information of the blood flow and various kinetics related to blood flow in your brain. Technically, Perfusion is defined as the passage of fluid through the lymphatic system or blood vessels to an organ or a tissue. If you know the blood flow of affected and the normal brain, it can be helpful in finding the abnormalities. Perfusion imaging helps in measurement of various parameters such as

For Brain Tumors, the World Health Organization (WHO), has developed a histological classification system that focuses on the tumor’s biological behavior. The system classifies tumors into grades I to IV. Grade IV are the most malignant primary brain tumors. Histopathological analysis or analysing a biopsy of brain serves as a final test to decide the grade. This is an invasive procedure and requires the availability of an expert for the analysis.

Glioblastoma, a form of Brain Tumor, exhibits increased rCBV values. Source :<a href="https://www.intechopen.com/books/neurooncology-newer-developments/advanced-mr-imaging-techniques-in-the-diagnosis-of-intraaxial-brain-tumors">Neurooncology – Newer Developments</a>

Recent papers&nbsp;have found strong correlation between perfusion parameters such as relative cerebral blood volume (abbr. rCBV), volume transfer coefficient (abbr. kTrans) and grade of the tumor. Higher perfusion values in marked RoIs (regions of interest) suggested higher grades. Taking a step further another paper&nbsp;also suggested use of perfusion to measure prognosis and thus it can be a great indicator to quickly measure the effects of treatment or medication the subject is undergoing.

Alzheimer’s is the cause of 60%-70% cases of dementia&nbsp;and it has no cure. Globally, dementia affects 47.5 million people. About 3% of people between the ages of 65–74 have dementia, 19% between 75 and 84 and nearly half of those over 85 years of age.

The normal brain (on the left) shows normal blood perfusion, denoted by an abundance of yellow color. The scan on the right, of a person suffering from Alzheimer’s, shows pervasive low perfusion all around, denoted by blues and greens. Source :The Physiological and Neurological basis of Cerebra TurboBrain

A 2001 paper&nbsp;in American Journal of Neuroradiology showed that perfusion or rCBV values in particular can be used to replace nuclear medical imaging techniques for the evaluation of patients with Alzheimer’s disease. Another paper&nbsp;published in 2014 suggests closely linked mechanisms of neurodegeneration mediating the evolution of dementia in both Alzheimers and Parkinsons. Many other papers&nbsp;suggest strong linkage between early Alzheimer’s and cerebral blood flow and thus can help in detection at earlier stage.

A lot of work in last decade has also been done to try to develop autonomous/semi-autonomous process of decision making in solving various problems mentioned above. Some papers&nbsp;have shown promise in developing semi-autonomous systems using Support Vector Machines (SVM) and other ML techniques for brain tumor grade classification with accuracies as high as 80%. In the domain of neurodegenerative diseases, accuracies as high as 85% have been achieved in classification of MRIs&nbsp;using perfusion and ML, and a recent article&nbsp;suggested that Alzheimer’s early detection might be possible using AI which could predict onset of Alzheimer’s with accuracy of 85% to 90%.

Even though the perfusion imaging looks promising, but there are some major hurdles due to which it has not yet spread into the hospitals as go-to method for analysis. Standardisation is the biggest problem that needs to be tackled in the first place. This paper&nbsp;highlights various methods used in brain perfusion imaging. There aren’t one or two different methods, but seven that are highlighted in the paper. Another paper&nbsp;published in Journal of Magnetic Resonance Imaging (JMRI) gives a deeper insight into two successful approaches being used. Measurements from different methods have different accuracies, and asks for different expertise from the doctors performing.

Blogs