Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{192221,
        author = {Anandakumar K and Chandrasekar C},
        title = {A QUANTUM-INSPIRED ATTENTION FRAMEWORK FOR WEAKLY SUPERVISED TUMOR SEGMENTATION AND LOCALIZATION IN OVARIAN CANCER HISTOPATHOLOGY IMAGES},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {702-709},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192221},
        abstract = {Pixel-level annotation is expensive, making it difficult to achieve accurate tumor segmentation in ovarian cancer histopathological images. This paper proposes a Quantum-Inspired Attention-based Weakly Supervised Tumor Segmentation framework (QIAB-WATS) for tumor segmentation and localization in ovarian cancer histopathological images, taking into account the subtypes Endometrioid Carcinoma (EC), High-Grade Serous Carcinoma (HGSC), and Low-Grade Serous Carcinoma (LGSC). The proposed framework uses self-supervised reconstruction learning to overcome the requirement for manually annotated segmentation masks. A quantum-inspired attention module is incorporated into a WATS-Net backbone to improve discriminative tumor feature learning, with the help of reconstruction error analysis for effective tumor localization. Experimental results show that QIAB-WATS has an accuracy of 89.0%, Dice of 88.2%, and IoU of 86.2%, which outperforms existing fully supervised and weakly supervised approaches. These results validate that QIAB-WATS is a reliable, annotation-efficient, and scalable approach for ovarian cancer histopathological image segmentation.},
        keywords = {Ovarian cancer histopathology; Weakly supervised learning; Tumor segmentation; Tumor localization; Quantum-inspired attention; Self-supervised reconstruction; WATS-Net.},
        month = {February},
        }