ORIGINAL RESEARCH article
Oncol. Rev.
Sec. Oncology Reviews: Original Research
Volume 19 - 2025 | doi: 10.3389/or.2025.1592408
This article is part of the Research TopicApplication of Deep Learning in Biomedical Image ProcessingView all 10 articles
Research on the Application of a Multi-model Cascaded Deep Learning Framework in the Pathological Diagnosis of Osteosarcoma
Provisionally accepted- 1Department of Pathology, Chongqing General Hospital, Chongqing University, Chongqing 401121, China, Chongqing, China
- 2Chongqing Medical University, Chongqing, 400016, Chongqing, China
- 3Zhaotong First People's Hospital, zhaotong, China
- 4Hangzhou Medipath Intelligent Technology Co., Ltd, Hangzhou, Zhejiang, China, hangzhou, China
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
Osteosarcoma is the most common malignant tumor of bone tissue in adolescents, and precise pathological diagnosis is the primary foundation for establishing the most effective treatment. The pathological evaluation of tumor necrosis after chemotherapy is crucial for assessing its efficacy in osteosarcoma patients. Pathologists often encounter several challenges in the diagnosis and evaluation of osteosarcoma. In order to address the above needs, we designed and developed a multi-model cascaded deep learning framework using an advanced Vision Mamba (ViM) model as the core network architecture. We used one of the most comprehensive datasets of osteosarcoma cases, obtained from two key sources: (1) real-world data from 68 osteosarcoma patients collected at the Chongqing General Hospital, and (2) publicly available osteosarcoma assessment data from the University of Texas (UT) Southwestern/UT Dallas. We used the Palgo pathology image artificial intelligence self-training platform to annotate these pathological images according to the requirements of the algorithms used. We implemented a triple verification mechanism of annotation, review, and archiving, and used the integrated interactive algorithm correction mechanism of Palgo to continuously refine the data annotation process. The final results demonstrated that this model achieved Dice coefficient values of 0.83 or higher in tumor segmentation, osteosarcoma osteoid matrix segmentation, necrotic area segmentation, lung metastatic tumor segmentation, and lung metastatic osteoid matrix segmentation. The area under the receiver operating characteristics (ROC) curve (AUC), sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) for necrosis classification, overall osteosarcoma subtypes, and localized osteosarcoma subtypes were all above 90%. This model had excellent performance, indicating a high potential for future application in osteosarcoma patients.
Keywords: Osteosarcoma, multi-model cascaded deep learning framework, Pathological diagnosis, Vision Mamba model, Adolescent
Received: 12 Mar 2025; Accepted: 20 Oct 2025.
Copyright: © 2025 Yao, Yang, Jiang, Jia, Sun, Li, Wang and Tang. 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: Xuefeng Tang, txfaty@163.com
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.