Mohammed Yusuf Ansari

Mohammed Yusuf Ansari

PhD Candidate in Computer Engineering

Talks and presentations

Conference Proceeding talk: Neural Network-Based Fast Liver Ultrasound Image Segmentation

June 20, 2023

Conference proceedings talk, International Joint Conference on Neural Networks (IJCNN), Queensland, Australia

This talk explored the development of a novel neural network designed specifically for real-time liver ultrasound (US) image segmentation. Emphasizing the challenges posed by noisy and low-contrast ultrasound images, the presentation highlighted how the new network leverages advanced architecture, including Pyramid Scene Parsing, to deliver accurate and efficient segmentation in real-time. By addressing the clinical need for rapid and precise liver segmentation, this talk demonstrated the potential of the network to enhance diagnostic workflows and improve decision-making in liver disease management.

Lightweight Deep Neural Network Framework for Liver CT Segmentation

October 18, 2022

Talk, Hamad Bin Khalifa University, Doha, Qatar

This presentation explored the significant advancements in AI-driven medical imaging technologies, emphasizing the development of lightweight deep learning frameworks for liver CT segmentation. Highlighting the growing need for computationally efficient solutions in cancer diagnostics and treatment planning, this talk delved into how lightweight neural networks are revolutionizing the segmentation process. These networks not only reduce computational overhead but also ensure robust segmentation performance, paving the way for improved diagnosis, treatment, and follow-up care for liver-related cancers.

Conference Proceeding talk: Towards Developing a Lightweight Neural Network for Liver CT Segmentation

January 15, 2022

Conference proceedings talk, International Conference on Medical Imaging and Computer-Aided Diagnosis, Online

This talk focused on the development of Res-PAC-UNet, a cutting-edge neural network tailored for liver CT image segmentation, specifically targeting challenges in the diagnosis and treatment planning of liver diseases like hepatocellular carcinoma (HCC). The network employed Pyramid Atrous Convolutions and a fixed-width residual UNet backbone to achieve high segmentation accuracy with a remarkably low parameter count. This efficient and lightweight architecture demonstrated the potential to enhance clinical workflows by providing precise and scalable solutions for liver CT segmentation, paving the way for improved patient outcomes in liver disease management.

Real-Time Image Segmentation for Enabling Fusion Imaging in Hepatocellular Carcinoma Ablation

November 15, 2021

Talk, Hamad Bin Khalifa University, Doha, Qatar

This talk discussed the transformative role of recent advancements in Artificial Intelligence and Deep Learning in medical imaging, specifically for cancer treatment. With a focus on real-time image segmentation, the presentation highlighted how lightweight neural networks enable the fusion of imaging modalities to improve the precision and efficacy of hepatocellular carcinoma ablation procedures. By integrating real-time segmentation into clinical workflows, this talk showcased how deep learning models are being leveraged to identify liver boundaries more accurately, ensure better ablation targeting, and ultimately enhance patient outcomes.