Abstract :

Colorectal Cancer (CRC) Remains One Of The Leading Causes Of Cancer-related Mortality Worldwide, Underscoring The Critical Need For Early And Accurate Diagnosis. While Histopathological Examination Of Colorectal Tissue Is The Clinical Gold Standard, It Is Labor-intensive And Prone To Human Error. To Overcome These Challenges, This Study Proposes An Attention-driven, Lightweight Deep Learning Model Based On MobileNetV2 For The Automated Classification Of CRC Histopathology Images. The Architecture Is Designed To Capture Both Global And Local Discriminative Features Efficiently, Leveraging Attention Refinement Modules To Focus On Diagnostically Relevant Regions. In Addition To The Proposed Model, A Comparative Analysis Is Performed With A Baseline Xception Architecture, Known For Its High Performance In Image Classification Tasks. Experimental Results Demonstrate That The MobileNetV2-based Attention Model Achieves Comparable Or Superior Accuracy While Significantly Reducing Computational Complexity, Making It Suitable For Real-time Clinical Applications. This Approach Shows Promise In Assisting Pathologists, Reducing Diagnostic Workload, And Enhancing The Overall Reliability Of Colorectal Cancer Detection.

Published:

14-8-2026

Issue:

Vol. 26 No. 8 (2026)

Page Nos:

891-896

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite