11 Papers
5 Citations
Lin Ma is an academic researcher from University of Texas Southwestern Medical Center. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 3, co-authored 8 publications. Previous affiliations of Lin Ma include Peking University.
Chat about Author
Papers
Deep learning based medical image segmentation with limited labels.
TL;DR: Experimental results demonstrated the proposed method outperformed traditional multi-atlas DIR methods and fully-supervised limited data training and is promising for DL-based medical image segmentation application with limited annotated data.
37
Evaluation Exploration of Atlas-Based and Deep Learning-Based Automatic Contouring for Nasopharyngeal Carcinoma
Jinyuan Wang,Zhaocai Chen,Cungeng Yang,Bao-Lin Qu,Lin Ma,Wenjun Fan,Qichao Zhou,Qingzeng Zheng,Shouping Xu +8 more
TL;DR: The trained DL-based segmentation performs significantly better than atlas- based segmentation for nasopharyngeal carcinoma, especially for the OARs with small volumes.
•Posted Content
Registration-Guided Deep Learning Image Segmentation for Cone Beam CT-based Online Adaptive Radiotherapy
Leong Chean Ring,Lin Ma,Philip J. Burton,Weicheng Chi,Howard E. Morgan,Mu-Han Lin,Mingli Chen,David J. Sher,Dominic Moon,Dat T. Vo,Vladimir Avkshtol,Weiguo Lu,Xuejun Gu +12 more
TL;DR: Wang et al. as discussed by the authors proposed a registration-guided DL (RgDL) segmentation framework that integrates image registration algorithms and DL segmentation models to obtain accurate final segmentations.
8
Mixed secondary chromatin structure revealed by modeling radiation-induced DNA fragment length distribution.
Wenzong Ma,Chenyang Gu,Chenyang Gu,Lin Ma,Lin Ma,Caoqi Fan,Chao Zhang,Yujie Sun,Cheng Li,Gen Yang +9 more
TL;DR: A novel “30-C” model combining 30 nm chromatin structure models with Hi-C data was developed, which measured the spatial contact frequency between different loci in the genome and predicted that the most probable chromatin fiber structure for human interphase fibroblasts in vivo was 45% zig-zag 30 nm fibers and 55% 10 nm fibers.
5
•Posted Content
Generalizability of deep learning based fluence map prediction as an inverse planning approach
TL;DR: In this article, the authors designed four experiments to validate the generalizability of DL-FMP to other types of plans apart from the training data, which contained only clinical head and neck (HN) full-arc VMAT plans.
2