Application of Masked RCNN for segmentation of brain haemorrhage from Computed Tomography Images

Automated analysis of CT scan images using AI solutions to diagnose abnormalities will help in overcoming the costly, time consuming and prone to error from manual analysis. Deep Learning has proved to be quite efficient to mimic human cognitive abilities (and even exceed that in many cases), especially with unstructured data.

DL algorithms can detect, localize and quantify a growing list of brain pathologies including intra-cerebral bleeds and their subtypes, infarcts, mass effect, midline shift, and cranial fractures. So, with advanced DL algorithms, analysis of radiographic data can be easily achieved and this can accelerate early detection of certain critical medical conditions, powered by AI.

As mentioned, Deep Learning algorithms for computer vision use cases has been extremely successful for classification and localization related problems. With the availability of annotated dataset, object of interest or region of interest segmentation using Deep Learning has been plausible.

Algorithms like Regional Convolutional Neural Network (RCNN) and it’s evolved forms, Faster RCNN and Masked RCNN is being widely used in the field of advanced radiology to auto detect medical conditions through radio-graphic images.

For this session, I am particularly going to talk about application of Masked RCNN for detection of regions of brain haemorrhage from CT scan images of the brain.

 
 

Outline/Structure of the Demonstration

Topics to be discussed

  • Need of an automated AI based solution in CT Scan Image Analysis (2 mins)
  • Importance of Deep Learning based solutions for localizing object of interests within CT Scan images (2 mins)
  • Efficient usage of Masked RCNN for segmentation of brain hemorrhage from CT Scan Images (8 mins)
  • Working demo and explanation of how Masked RCNN functions in segmenting brain hemorrhage (8 mins)

Learning Outcome

1. Basic intuition of Deep Learning to solve instance segmentation in computer vision domain

2. Wide range of applications for Mask RCNN for real time instance segmentation from images.

Target Audience

AI Researchers, ML Engineers, DL Engineers, Data Scientists

Prerequisites for Attendees

1. Working knowledge on Machine Learning

2. Working knowledge on Deep Learning

3. Basics of maths and statistics

schedule Submitted 3 months ago

Public Feedback

comment Suggest improvements to the Speaker
  • Deepti Tomar
    By Deepti Tomar  ~  3 months ago
    reply Reply

    Hello Aditya,

    Thanks for your time and efforts on the proposal! Could you answer the following questions to help the program committee understand your proposal better?

    • Are you going to share demo(s) /use case(s) from your project work (industry-specific use cases)? Speaker's experience on the project helps people understand the concept better.
    • Did you use these techniques to help solve a particular problem? 
    • If yes, would you be sharing the Challenges faced in the implementation of the technique in your application and the workarounds?

    Thanks,

    Deepti

    • Aditya Bhattacharya
      By Aditya Bhattacharya  ~  3 months ago
      reply Reply

      Hello Deepti,

      Thank you for taking your time and reviewing my proposal! To answer your questions:
      1.  Yes, I am planning to show a demo. I will be using my notebook to briefly explain how Mask RCNN works for this use-case: https://github.com/adib0073/Application_Of_Mask_RCNN_For_CT_Image_Analysis/blob/master/samples/bhd/inspect_BHD_model.ipynb

      You can also take a look at my medium post about the same topic: https://medium.com/@adib0073/brain-haemorrhage-segmentation-from-ct-scan-images-using-mask-rcnn-e4f478ee10b2

      Any suggestions or ideas if you have to make this proposal better, please feel free to let me know.

      2. I did use Mask RCNN before. But not exactly for this use case, but a computer vision project in manufacturing for quality inspection for certain material, and it proved quite successful in localizing and segmenting the region of interest.

      3. Mostly the challenges was related to the creation of initial annotated data. But I can mention about some tools, I had used that did make the job somewhat easy. So, I can mention about these challenges and talk about workarounds that I had used.

      I would be happy to discuss more if you have any further queries.

      Regards,

      Aditya

      • Deepti Tomar
        By Deepti Tomar  ~  3 months ago
        reply Reply

        Thanks for your response, Aditya! We will let you know in case if we have more questions.

        • Ashay Tamhane
          By Ashay Tamhane  ~  2 months ago
          reply Reply

          Hi Aditya, thanks for the proposal. The blog mentions a Kaggle problem. Could you clarify if this talk is about solving a Kaggle problem, or if this is deployed by you on an actual industry use case?

          • Aditya Bhattacharya
            By Aditya Bhattacharya  ~  2 months ago
            reply Reply

            Hey Ashay,

            Thanks for reviewing my proposal. To answer your question, it is an actual industry use case, but since MRI or CT image data is mostly proprietary, I had referred the Kaggle site for using CT image data provided over there as an example of the use case. The technique, approach  and the algorithm remains same with any other MRI/CT/Radiographic image data.

            I would be happy to discuss more if you have any further queries.

            Regards,

            Aditya


  • Liked Anupam Ranjan
    keyboard_arrow_down

    Anupam Ranjan / Yash Raj - SQUAD application through Knowledge Graph for COVID-19 Literature

    20 Mins
    Demonstration
    Advanced

    There are numerous documents and research papers being published for COVID-19 and doctors are not able to absorb the content of all the literature. It has become a real challenge to extract relevant information in a short span of time.

    Knowledge Graph along with SQUAD application can help process multiple documents and extract precise information from a set of documents quickly. This will be a very handy application for healthcare professional to extract relevant information without going in detail with each application.

    The session will demonstrate the following:

    a) Text Processing of COVID-19 literature

    b) Named Entity Extraction from the documents using BERT/Spacy

    c) Building a Knowledge Graph of the documents

    d) Building question-answer application

  • Liked Aditya Bhattacharya
    keyboard_arrow_down

    Aditya Bhattacharya - Using Deep Learning to identify medical conditions related to Thorax Region from Radiographic X-Ray Images

    20 Mins
    Talk
    Intermediate

    Automated analysis of Chest X-ray images to diagnose various pathologies will help in overcoming the costly, time consuming and prone to error from manual analysis of them, especially using deep learning based approaches. One of such recent efforts in this direction is Classification of Common Thorax which combines the advantages of CNN based feature extraction and problem transformation methods in multi-label classification task.

    So this is one of the key areas where deep learning based solution has already made an impact and has the potential to come up with even a better and well improved performance.

    For this session, I am going to discuss about the problem at hand, the data-set, several approaches that has been explored and that worked quite well so far in this research. Also I am going to mention about the potential use case and the real world impact of such a real world healthcare application that can save millions of lives by early and effective detection.

    Also I am going to mention about some of the key challenges faced during this research and how it can be scaled to build an end to end software solution!

  • Liked Dr Purnendu Sekhar Das
    keyboard_arrow_down

    Dr Purnendu Sekhar Das - Screening for COVID-19 Patients using Deep Convolutional Neural Networks on Chest X-Ray Images

    20 Mins
    Talk
    Intermediate

    As the COVID-19 pandemic rages on across the world as one of the most catastrophic healthcare crises in recent memory, the medical world is grappling with several challenges at once to cope with this crisis in the best possible manner. Following problem areas need urgent attention:

    • Timely screening and identification of infected Covid-19 patients to help in triaging of scarce healthcare resources
    • Monitoring the response to clinical interventions to decide best treatment possible.
    • Rapid scale-up of capacities in both testing of new patients and monitoring treatment response

    The current gold standard for confirmatory diagnosis of SARS-CoV2 infection is the RT-PCR lab test which is an expensive and time-consuming test relying on identification of viral genetic material – it is not possible to quickly scale up testing capacity using this technique in countries like India due to lack of the required equipment. In this scenario, we need to come up with an accurate and rapidly scalable method as an alternative testing strategy.

    The Chest X-Ray is a basic test that is widely available in healthcare facilities across India and the developing world and can be done and analyzed within a short time frame.

    Deep Convolutional Neural Networks offer great promise in automating the classification of Chest X-ray images to accurately identify COVID-19 patients from patients with normal lungs and those with other lung pathology related conditions like viral and bacterial pneumonias. This technique can be used as a reliable screening methodology to identify COVID-19 patients and recommend the appropriate therapy before it is too late.

    Various CNN architectures have been explored recently to perform efficient image classification and segmentation on lung radiology images originating from X-Ray and CT Scans. These Deep Learning based techniques leverage the power of CNNs to extract hidden features from radiology images that can further be exploited for accurate identification of the disease process affecting the patient.

    This technique promises to be a game changer in COVID-19 screening that can both be scaled up rapidly and can also be used as a Clinical Decision Support Tool by radiologists inside hospitals, critical care units and isolation wards. It also has the potential to reduce the time required by experienced radiologists to screen through huge volumes of Chest X-Ray images, while maintaining optimal levels of accuracy in diagnosis.

  • Liked Bhavesh Laddagiri
    keyboard_arrow_down

    Bhavesh Laddagiri - Getting closer to Artificial General Intelligence with Neuro-Symbolic AI

    Bhavesh Laddagiri
    Bhavesh Laddagiri
    AI Researcher
    CellStrat AI Lab
    schedule 3 months ago
    Sold Out!
    20 Mins
    Demonstration
    Advanced

    The recent advances in AI over the last decade has been heavily powered by Deep Learning with a new SOTA algorithm being released every other week by developers and researchers all across the globe. The concept of neural networks came into existence in the 1960s but made a come-back when fueled by the massive datasets and GPU farms. But the field of AI is much richer than just this one type of algorithm. Symbolic reasoning based algorithms also pioneered in the 1960s and were more practical for the time as they were less computationally intensive.

    Deep Learning is great at understanding and finding patterns in massive streams of data but fails when it comes to using logic and reasoning to understand a concept with minimal data. Symbolic AI, on the other hand, is good at reasoning and creating abstractions from pre-defined concepts but fails to scale to real-world problems. However, there is something interesting here, the weaknesses of neural nets are actually the strengths of symbolic AI (and vice-versa), for the most part. So why not, Hybridize AI with Neural Nets and Symbolic AI to pave out a path for human-level AGI?

    In this session, we are going to learn how this radical approach to AI can help solve real-world problems by demonstrating my proof-of-concept which can navigate a simple environment using natural language commands in a few shots of training. This demo will also allow the attendees to understand the usage of pretrained models for generalizing to new tasks using a multi-modal approach. Finally, we will look at the industry use cases of Neuro-Symbolic AI and the potential advantages of this approach over vanilla deep learning in that domain.

  • Liked Aditya Bhattacharya
    keyboard_arrow_down

    Aditya Bhattacharya - Enterprise DL - Accelerating Deep Learning Solutions to Production

    20 Mins
    Talk
    Intermediate

    Advanced deep learning approaches have been quite successful to solve real world problems related to unstructured data like images, audio-signals and texts. But how often are we able to make best use of these solutions by exercising their benefits at scale? Even when the deep neural network based solutions have made a significant impact in the world of AI and data science, but the key challenge which most organizations face, is bringing their solutions to production. As a matter of fact, until and unless these remarkable but yet complex algorithms are operated at scale, considering production and if these doesn’t have the capability to be integrated with various software applications, these solutions will never be really impactful.

    So, for this talk, I will be discussing about various approaches to accelerate deep learning solutions from notebooks or research environment to production environment and how these solutions can be transformed as an enterprise level end to end Deep Learning Solution, which can be consumed as a service by any software application, with a practical use-case example.