ORIGINAL RESEARCH article

Front. Oncol.

Sec. Radiation Oncology

Volume 15 - 2025 | doi: 10.3389/fonc.2025.1534740

This article is part of the Research TopicRecent Advances in Radiation Oncology for the Management of Thoracic MalignanciesView all 5 articles

Artificial Intelligence in Automatic Image Segmentation System for Exploring Recurrence Patterns in Small Cell Carcinoma of the Lung

Provisionally accepted
Jie ShenJie Shen1,2,3*Jing ShenJing Shen1,2,3Shaobin WangShaobin Wang4Hui GuanHui Guan1,2,3Mingyi DiMingyi Di5Zhikai LiuZhikai Liu1,2,5Qi ChenQi Chen6Mei LiMei Li1,3Ke HuKe Hu1,2Fuquan ZHANGFuquan ZHANG1,3
  • 1Chinese Academy of Medical Sciences and Peking Union Medical College, Dongcheng, China
  • 2Peking Union Medical College Hospital (CAMS), Beijing, Beijing Municipality, China
  • 3Department of Radiation Oncology, Peking Union Medical College Hospital, Department of Medical Oncology, Peking Union Medical College Hospital (CAMS), Beijing, Beijing, China
  • 4Department of Biomedical Engineering,School of Medicine, School of Medicine, Tsinghua University, Beijing, Beijing Municipality, China
  • 5Peking university first hospital, Beijing, China
  • 6MedMind Technology Co., Ltd. Beijing, China, Beijing, China

The final, formatted version of the article will be published soon.

Select one of your emails

You have multiple emails registered with Frontiers:

Notify me on publication

Please enter your email address:

If you already have an account, please login

You don't have a Frontiers account ? You can register here

The integration of artificial intelligence (AI) in automatic image segmentation systems enhances clinical target volume (CTV) evaluation for small cell lung cancer (SCLC). This study analyzed data from 180 SCLC patients (2010–2021) treated with curative radiotherapy, utilizing AI-driven segmentation and recursive feature elimination to model recurrence. Tumor size (≥5cm) independently impacted local control (HR=1.635, p=0.028), with 3-year recurrence rates of 61.1% vs. 86.7% (p=0.004). Recurrence predominantly occurred in regions 10R, 10L, 4R, and 7 (67.65% of cases). A random forest model incorporating 110 clinical variables achieved 77% accuracy in predicting recurrence. AI-based CTV delineation identified initial tumor regions (GTV/GTVnd) as critical recurrence zones, offering a clinically viable tool for optimizing radiotherapy targeting and patient outcomes.

Keywords: Small Cell Lung Cancer, Clinical target volume (CTV), artificial intelligence, Local recurrence, Prediction model

Received: 26 Nov 2024; Accepted: 04 Apr 2025.

Copyright: © 2025 Shen, Shen, Wang, Guan, Di, Liu, Chen, Li, Hu and ZHANG. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Jie Shen, Chinese Academy of Medical Sciences and Peking Union Medical College, Dongcheng, China

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Supplementary Material