My Final Project

Cell classification via image processing has recently gained interest from the point of view of building computer assisted diagnostic tools for blood disorders such as leukemia. In order to arrive at conclusive decision on disease diagnosis and degree of progression, it is very important to identify malignant cells with high accuracy. Computer assisted tools can be very helpful in automating the process of cell segmentation and identification. Identification of maIignant cells vis-à-vis normal cells from the microscopic images is difficult because morphologically both cells types appear similar.

As a consequence, leukemia (blood cancer) is detected in advanced cancer stages via microscopic image analysis, not because of the ability to identify these under the microscope, but because of the medical domain knowledge, i.e., the cancer cells start growing in an unrestricted fashion and hence, they are present in much more larger numbers as compared to their numbers in a normal person. So, in this project, I was supposed to train a model which can diagnose the cancer cells in a very effective manner. I tried training various models on the basis of their architecture as our model must learn the most minor details from the data. Before training them, I tried a lot of hyper parameter tuning in order to get the best results. After using various network architectures like CNN, ResNet50, Capsnet, SeResNext, DenseNet, ResNext50, VGG19 while also using stacking. I found that SeResNext network architecture was doing really great in comparison to other architectures. The comparison between all these architectures can be found in the link provided. It got an accuracy of about 90% in predicting if a Blood Cell in cancerous or not.

After the model building, I created an Flask API of the same and then created a Docker image of it.

Link to Code

saarques / AI-Without-Borders---Projects

This repository contains my work towards the problems assigned to me by the AI Without Borders organisation.

Blood Cancer Diagnosis

Aim

Creating a state-of-the-art model for classification of leukemic B-lymphoblast cells from normal B-lymphoid precursors from blood smear microscopic images.

View on GitHub