CancerSeg-XA: Medical Histopathology Segmentation System Based on Xception Backbone and Attention Mechanisms

Authors

DOI:

https://doi.org/10.19139/soic-2310-5070-3023

Keywords:

Deep learning, cancer segmentation, Histopathological images, DeepLabV3, Xception backbone, Attention mechanism, BCSS, PanNuke, PUMA

Abstract

Accurate segmentation of histopathological images is essential to support early diagnosis and effective treatment planning in cancer care. This study presents CancerSeg-XA, a deep learning-based histopathology segmentation system designed to deliver robust performance across diverse tissue types and imaging sources. Built upon the DeepLabV3+ framework, CancerSeg-XA incorporates architectural enhancements to strengthen feature representation and improve model stability. The system was evaluated on three widely recognized datasets—BCSS, PanNuke, and PUMA—each presenting distinct structural and clinical challenges. Across all datasets, CancerSeg-XA consistently outperformed the baseline DeepLabV3+ in terms of segmentation accuracy, recall, and F1-score. Specifically, it achieved accuracy improvements of 4.78%, 4.31%, and 3.22% on BCSS, PanNuke, and PUMA, respectively, along with substantial gains in FwIoU. These results highlight the model’s ability to generalize effectively across varied histopathological contexts, positioning CancerSeg-XA as a promising solution for clinical integration and future research in digital pathology.

Author Biographies

Alaa Youssef, aculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt

Alaa Mohamed Youssef is currently pursuing a Ph.D. degree in Computer Science at Helwan University. She holds both a B.S. degree and an M.S. degree in Computer Science. Her research journey has been marked by an exciting focus on object detection in images, a field where she has made significant contributions. As she progresses in her academic career, she is now keen to deepen her expertise in machine learning and explore emerging fields of medical image analysis.

Aliaa Youssif, Arab Academy for Science, Technology and Maritime Transport (AASTMT), Cairo, Egypt

Aliaa Abdel-Haleim Abdel-Razik Youssif: She is currently a professor at the College of Computing and Information Technology, Arab Academy for Science Technology and Maritime Transport (AAST), Cairo, Egypt. She received her BSc and MSc degrees in telecommunications and electronics engineering from the Helwan University. She also completed her Ph.D. at Helwan University. She had a postdoctoral degree at George Washington University, USA in 2005. In addition, she was a visiting professor at many universities, such as Cardiff University in the United Kingdom (2008), International Telematic University in Italy (2012), Masaryk University, Czech Republic (2016), Oviedo University, Spain (2017), Vilnius Gediminas Technical University, Lithuania (2018), and Cardiff Metropolitan University, UK (2020).

Wessam El Behaidy, aculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt; Faculty of Informatics and Computer Science, British University in Egypt (BUE), El-Sherouk, Egypt

Wessam Hassan El Behadidy: She earned her honors bachelor

Downloads

Published

2025-12-03

How to Cite

Youssef, A., Youssif, A., & El Behaidy, W. (2025). CancerSeg-XA: Medical Histopathology Segmentation System Based on Xception Backbone and Attention Mechanisms. Statistics, Optimization & Information Computing, 15(3), 2026–2046. https://doi.org/10.19139/soic-2310-5070-3023

Issue

Vol. 15 No. 3 (2026)

Section

Research Articles

License

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).