Computer Vision in Medical Image Analysis
Publication in Ph.D
Supervisor: Dr. Jianming Liang
Foundation X: Integrating Classification, Localization, and Segmentation through Lock-Release Pretraining Strategy for Chest X-ray Analysis
Developing deep-learning models for medical imaging requires large, annotated datasets, but the heterogeneity of annotations across tasks presents significant challenges.
Foundation X is an end-to-end framework designed to train a multi-task foundation model by leveraging diverse expert-level annotations from multiple public datasets.
It introduces a Cyclic & Lock-Release pretraining strategy alongside a student-teacher learning paradigm to enhance knowledge retention while mitigating overfitting.
Trained on 11 chest X-ray datasets, Foundation X seamlessly integrates classification, localization, and segmentation tasks.
Experimental results demonstrate its ability to maximize annotation utility, improve cross-dataset and cross-task learning, and
achieve superior performance in disease classification, localization, and segmentation.
Seeking an Optimal Approach for Computer-aided Diagnosis of Pulmonary Embolism
Pulmonary embolism (PE) represents a blood clot that travels to the blood vessels in the lung, causing vascular obstruction, and in some patients, death.
CT pulmonary angiography (CTPA), is the most common type of medical imaging to evaluate patients with suspected PE.
These CT scans consist of hundreds of images that require detailed review to identify clots within the pulmonary arteries.
Recent research in deep learning across academia and industry produced numerous architectures, various model initializations, and distinct learning paradigms.
It has resulted in many competing approaches to Computer-aided Diagnosis (CAD) implementation in medical imaging and produced great confusion in the CAD community.
We have conducted extensive experiments with various deep learning architectures, model initializations, learning paradigms, and
data pre-processing techniques applicable for PE diagnosis at both the slice and exam levels.
Publication Link: Workshop Paper in MICCAI
Publication Link: Medical Image Analysis Journal
GitHub Link: CAD_PE
Computer Vision
M.Sc. Thesis
Supervisor: Dr. Qi Tian
Worked on Face Detection, Gender Classification and Age Estimation classification algorithm enhancement using Discrete Cosine Transformation, Histogram of Oriented Features as Feature Extraction and Convolutional Neural Network and Support Vector Machine as Machine Learning techniques.
Image processing
B.Sc. Thesis
Supervisor: Rubel Biswas
Co-Supervisor: Zahangir Alom
Worked on Automated parking lot management system for Bengali Language, by using Connected Component labeling, Bounding Box, Canny Edge Detection & Hough Transformation for license plate localization and used OCR for pattern recognition following by database to store as well as manipulating the system.
