Computer Science Ph.D. students Abdullah-Al-Zubaer Imran and Ali Hatamizadeh won the Nvidia Best Paper Award at the Deep Learning in Medical Image Analysis (DLMIA) workshop of the Medical Image Computing and Computer Assisted Intervention (MICCAI) conference held on Sep 16-20 in Granada, Spain. The paper titled “Automatic Segmentation of Pulmonary Lobes Using a Progressive Dense V-Network,” was authored by Abdullah-Al-Zubaer Imran (UCLA), Ali Hatamizadeh (UCLA), Shilpa Ananth (VoxelCloud Inc.), Xiaowei Ding (UCLA and VoxelCloud Inc.), Demetri Terzopoulos (UCLA and VoxelCloud Inc.), and Nima Tajbakhsh (VoxelCloud Inc.).
In the paper, they demonstrated a fast, automatic, and reliable lung lobe segmentation method based on a 3D convolutional neural network, which overcomes all the major limitations – non-automatic, slow runtime, reliance on prior segmentation, non-robustness, etc. – of previous methods reported in the literature. This efficient and automatic lobe segmentation technique promises to have significant impact in healthcare by assisting radiologists to perform efficient diagnosis, assessment, and quantification of pulmonary diseases.
Imran is a second year CS Ph.D. student under the supervision of Distinguished Professor and Chancellor’s Professor Demetri Terzopoulos who directs the UCLA Computer Graphics & Vision Lab. Before joining UCLA, Imran worked with Professor David Pokrajac (DSU) and Professor Predrag Bakic (UPenn) on improving realism in anthropomorphic software breast phantoms, and was subsequently engaged in teaching undergraduate computer science courses at three universities in Bangladesh.
Hatamizadeh, the recipient of the 2018 UCLA Henry Samueli School of Engineering and Applied Science (HSSEAS) Edward K. Rice Outstanding Masters Student Award, is also a second year CS Ph.D. student under the supervision of Professor Terzopoulos. Hatamizadeh’s research interests span computer vision, deep learning, and artificial intelligence. One of the main highlights of his work is medical image analysis in which his goal is to establish the next generation of intelligent clinical platforms by incorporating a mixture of model-based and data-driven AI approaches.
Dr. Xiaowei Ding, a former UCLA Ph.D. student of Professor Terzopoulos and currently a postdoctoral researcher in his lab, is cofounder and CEO of VoxelCloud, Inc., a multinational startup company that innovates in the application of AI and cloud computing technologies to healthcare. Professor Terzopoulos is cofounder and Chief Scientist of VoxelCloud.
MICCAI is one of the largest medical imaging conferences in the world, where leading biomedical scientists, engineers, and clinicians from a wide range of disciplines associated with medical imaging and computer assisted intervention participate.