Contour interpolation by deep learning approach.
Date
2022-11
Authors
Journal Title
Journal ISSN
Volume Title
Repository Usage Stats
views
downloads
Citation Stats
Abstract
Purpose
Contour interpolation is an important tool for expediting manual segmentation of anatomical structures. The process allows users to manually contour on discontinuous slices and then automatically fill in the gaps, therefore saving time and efforts. The most used conventional shape-based interpolation (SBI) algorithm, which operates on shape information, often performs suboptimally near the superior and inferior borders of organs and for the gastrointestinal structures. In this study, we present a generic deep learning solution to improve the robustness and accuracy for contour interpolation, especially for these historically difficult cases.Approach
A generic deep contour interpolation model was developed and trained using 16,796 publicly available cases from 5 different data libraries, covering 15 organs. The network inputs were a 128×128×5 image patch and the two-dimensional contour masks for the top and bottom slices of the patch. The outputs were the organ masks for the three middle slices. The performance was evaluated on both dice scores and distance-to-agreement (DTA) values.Results
The deep contour interpolation model achieved a dice score of 0.95±0.05 and a mean DTA value of 1.09±2.30 mm , averaged on 3167 testing cases of all 15 organs. In a comparison, the results by the conventional SBI method were 0.94±0.08 and 1.50±3.63 mm , respectively. For the difficult cases, the dice score and DTA value were 0.91±0.09 and 1.68±2.28 mm by the deep interpolator, compared with 0.86±0.13 and 3.43±5.89 mm by SBI. The t-test results confirmed that the performance improvements were statistically significant ( p<0.05 ) for all cases in dice scores and for small organs and difficult cases in DTA values. Ablation studies were also performed.Conclusions
A deep learning method was developed to enhance the process of contour interpolation. It could be useful for expediting the tasks of manual segmentation of organs and structures in the medical images.Type
Department
Description
Provenance
Citation
Permalink
Published Version (Please cite this version)
Publication Info
Zhao, Chenxi, Ye Duan and Deshan Yang (2022). Contour interpolation by deep learning approach. Journal of medical imaging (Bellingham, Wash.), 9(6). p. 064003. 10.1117/1.jmi.9.6.064003 Retrieved from https://hdl.handle.net/10161/26986.
This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.
Collections
Scholars@Duke
Deshan Yang
Deshan Yang is the professor of Medical Physics in the Department of Radiation Oncology, Duke University. He received his bachelor's degree in electronics engineering from Tsinghua University in 1992, a master’s degree in computer science from the Illinois Institute of Technologies in 2002, and his master’s and Ph.D. degrees in Biomedical Engineering from the University of Wisconsin-Madison in 2005. He spent two years as a postdoctoral researcher before joining Washington University in St. Louis as a faculty member. He worked as an instructor to a professor at Washington University in St. Louis between 2006 and 2021 before joining Duke University in 2021. His main research areas are medical image processing and analysis for radiation oncology applications, adaptive radiotherapy, cardiac radiosurgery, health information technologies for radiation oncology and medical physics.
Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.