Medical College of Wisconsin
CTSICores SearchResearch InformaticsREDCap

General and custom deep learning autosegmentation models for organs in head and neck, abdomen, and male pelvis. Med Phys 2022 Mar;49(3):1686-1700

Date

01/31/2022

Pubmed ID

35094390

Pubmed Central ID

PMC8917093

DOI

10.1002/mp.15507

Scopus ID

2-s2.0-85124464974   5 Citations

Abstract

PURPOSE: To reduce workload and inconsistencies in organ segmentation for radiation treatment planning, we developed and evaluated general and custom autosegmentation models on computed tomography (CT) for three major tumor sites using a well-established deep convolutional neural network (DCNN).

METHODS: Five CT-based autosegmentation models for 42 organs at risk (OARs) in head and neck (HN), abdomen (ABD), and male pelvis (MP) were developed using a full three-dimensional (3D) DCNN architecture. Two types of deep learning (DL) models were separately trained using either general diversified multi-institutional datasets or custom well-controlled single-institution datasets. To improve segmentation accuracy, an adaptive spatial resolution approach for small and/or narrow OARs and a pseudo scan extension approach, when CT scan length is too short to cover entire organs, were implemented. The performance of the obtained models was evaluated based on accuracy and clinical applicability of the autosegmented contours using qualitative visual inspection and quantitative calculation of dice similarity coefficient (DSC), mean distance to agreement (MDA), and time efficiency.

RESULTS: The five DL autosegmentation models developed for the three anatomical sites were found to have high accuracy (DSC ranging from 0.8 to 0.98) for 74% OARs and marginally acceptable for 26% OARs. The custom models performed slightly better than the general models, even with smaller custom datasets used for the custom model training. The organ-based approaches improved autosegmentation accuracy for small or complex organs (e.g., eye lens, optic nerves, inner ears, and bowels). Compared with traditional manual contouring times, the autosegmentation times, including subsequent manual editing, if necessary, were substantially reduced by 88% for MP, 80% for HN, and 65% for ABD models.

CONCLUSIONS: The obtained autosegmentation models, incorporating organ-based approaches, were found to be effective and accurate for most OARs in the male pelvis, head and neck, and abdomen. We have demonstrated that our multianatomical DL autosegmentation models are clinically useful for radiation treatment planning.

Author List

Amjad A, Xu J, Thill D, Lawton C, Hall W, Awan MJ, Shukla M, Erickson BA, Li XA

Authors

Musaddiq J. Awan MD Assistant Professor in the Radiation Oncology department at Medical College of Wisconsin
Beth A. Erickson MD Professor in the Radiation Oncology department at Medical College of Wisconsin
William Adrian Hall MD Associate Professor in the Radiation Oncology department at Medical College of Wisconsin
Xiaochuan Allen Li PhD Professor in the Radiation Oncology department at Medical College of Wisconsin
Monica E. Shukla MD Associate Professor in the Radiation Oncology department at Medical College of Wisconsin




MESH terms used to index this publication - Major topics in bold

Abdomen
Head and Neck Neoplasms
Humans
Image Processing, Computer-Assisted
Male
Organs at Risk
Pelvis
Radiotherapy Planning, Computer-Assisted