Multiple organ segmentation framework for brain metastasis radiotherapy

• Published in: Computers in biology and medicine 2024-07, Vol.177, p.108637, Article 108637
• Main Authors: Yu, Hui, Yang, Ziyuan, Zhang, Zhongzhou, Wang, Tao, Ran, Maoson, Wang, Zhiwen, Liu, Lunxin, Liu, Yan, Zhang, Yi
• Format: Article
• Language: English
• Subjects: Brain; Brain - diagnostic imaging; Brain - pathology; Brain cancer; Brain metastases; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - radiotherapy; Brain Neoplasms - secondary; Delineation; Humans; Image Processing, Computer-Assisted - methods; Image segmentation; Metastases; Organ-at-risk delineation; Organs at Risk; Point-cloud alignment; Prior knowledge; Radiation damage; Radiation effects; Radiation therapy; Radiotherapy Planning, Computer-Assisted - methods; Radiotherapy treatment; Segmentation; Toxicity
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108637

Radiotherapy is a preferred treatment for brain metastases, which kills cancer cells via high doses of radiation meanwhile hardly avoiding damage to surrounding healthy cells. Therefore, the delineation of organs-at-risk (OARs) is vital in treatment planning to minimize radiation-induced toxicity. However, the following aspects make OAR delineation a challenging task: extremely imbalanced organ sizes, ambiguous boundaries, and complex anatomical structures. To alleviate these challenges, we imitate how specialized clinicians delineate OARs and present a novel cascaded multi-OAR segmentation framework, called OAR-SegNet. OAR-SegNet comprises two distinct levels of segmentation networks: an Anatomical-Prior-Guided network (APG-Net) and a Point-Cloud-Guided network (PCG-Net). Specifically, APG-Net handles segmentation for all organs, where multi-view segmentation modules and a deep prior loss are designed under the guidance of prior knowledge. After APG-Net, PCG-Net refines small organs through the mini-segmentation and the point-cloud alignment heads. The mini-segmentation head is further equipped with the deep prior feature. Extensive experiments were conducted to demonstrate the superior performance of the proposed method compared to other state-of-the-art medical segmentation methods. [Display omitted] •Our OAR-SegNet innovatively combines prior knowledge and point-cloud alignment.•Prior knowledge is applied in RoI extraction, loss function design and feature learning.•Point-cloud alignment serves as an extra shape constraint to refine small organs.