ORIGINAL RESEARCH article
Front. Bioeng. Biotechnol.
Sec. Biosensors and Biomolecular Electronics
Volume 13 - 2025 | doi: 10.3389/fbioe.2025.1593534
Utilizing Detectron2 for Accurate and Efficient Colon Cancer Detection in Histopathological Images
Provisionally accepted
- 1Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang Province, China
- 2China Telecom Corporation Limited Zhejiang Branch，China Hangzhou，310000, Hangzhou, China
- 3Hangzhou Dianzi University, Hangzhou, Zhejiang Province, 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
Colon cancer is among the most prevalent and deadly cancers worldwide, making its early and accurate detection a critical priority in healthcare. This study introduces a new method for identifying colon tissue images as normal or cancerous, using the powerful Detectron2 deep learning framework. Renowned for its robust object detection and segmentation capabilities, Detectron2 was adapted and optimized to tackle the challenges of medical image analysis. Using the publicly available LC25000 dataset, which has 10,000 detailed images of tissue samples (5,000 normal and 5,000 cancerous), the model reached an amazing accuracy of 99.8%. This outstanding result highlights the effectiveness of Detectron2 in analyzing complex medical datasets, surpassing traditional methods in both accuracy and computational efficiency. The proposed approach demonstrates its potential as a reliable and scalable tool for computer-aided diagnostics, offering significant support to pathologists in the early detection of colon cancer. Furthermore, this study underscores the transformative role of cutting-edge machine learning techniques in enhancing the accuracy and efficiency of cancer detection systems, paving the way for improved patient outcomes and reduced mortality rates.
Keywords: Detectron2, Colon Cancer Detection, normal and cancerous tissue classification, Histopathological Images, deep learning, medical diagnostics
Received: 14 Mar 2025; Accepted: 19 Jul 2025.
Copyright: © 2025 Chen, Shen, Li, Li, Gao, Chen, Pan and Jin. 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: Xiaotian Pan, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang Province, 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.