activity
20192024
collaborators

7 papers

cs.CV2024

Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation

Vince Zhu, Zhanghexuan Ji, Dazhou Guo +6

Deep segmentation networks achieve high performance when trained on specific datasets. However, in clinical practice, it is often desirable that pretrained segmentation models can…

cs.CV2022

A Bayesian Detect to Track System for Robust Visual Object Tracking and Semi-Supervised Model Learning

Yan Shen, Zhanghexuan Ji, Chunwei Ma +1

Object tracking is one of the fundamental problems in visual recognition tasks and has achieved significant improvements in recent years. The achievements often come with the price…

cs.LG2021

Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment

Zhanghexuan Ji, Mohammad Abuzar Shaikh, Dana Moukheiber +3

Self-supervised learning provides an opportunity to explore unlabeled chest X-rays and their associated free-text reports accumulated in clinical routine without manual supervision…

cs.CV2021

An End-to-End learnable Flow Regularized Model for Brain Tumor Segmentation

Yan Shen, Zhanghexuan Ji, Mingchen Gao

Many segmentation tasks for biomedical images can be modeled as the minimization of an energy function and solved by a class of max-flow and min-cut optimization algorithms. Howeve…

cs.CV2020

User-Guided Domain Adaptation for Rapid Annotation from User Interactions: A Study on Pathological Liver Segmentation

Ashwin Raju, Zhanghexuan Ji, Chi Tung Cheng +6

Mask-based annotation of medical images, especially for 3D data, is a bottleneck in developing reliable machine learning models. Using minimal-labor user interactions (UIs) to guid…

eess.IV2019

Scribble-based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentation

Zhanghexuan Ji, Yan Shen, Chunwei Ma +1

The recent state-of-the-art deep learning methods have significantly improved brain tumor segmentation. However, fully supervised training requires a large amount of manually label…