Weakly-Supervised Gated Attention Multiple Instance Learning for Multi-Center Cervical Cytology Slide Triage
- 1Muhimbili University of Health and Allied Sciences
Abstract
Automated triage of whole-slide cervical cytology images remains constrained by the heavy dependence on single-cell bounding boxes or pixel-level annotations, which introduce significant bottlenecks, high expert overhead, and observer variability. To address these challenges, we present a weakly-supervised, detection-free Multiple Instance Learning (MIL) framework powered by a Gated Attention pooling engine that operates exclusively on slide-level predictions. By treating whole-slide images as bags of local instance patches, the dual-branch gated network dynamically assigns non-linear attention weights to highlight isolated dysplastic cells while suppressing benign background and debris, successfully resolving the "needle-in-a-haystack" problem inherent to high-grade lesions. Evaluated across multi-center cohorts including internal datasets (SIPaKMeD, Herlev, and CRIC) and the unannotated, out-of-distribution Mendeley LBC validation cohort processed via an unsupervised marker-controlled watershed pipeline our approach demonstrates robust generalization without requiring dense instance labels. Furthermore, our architectural comparison reveals a key trade-off: lightweight backbones like MobileNetV2 optimize in-distribution multi-center accuracy (90.96% Accuracy, 0.9800 ROC-AUC), whereas higher-capacity models like Xception ensure superior out-of-distribution robustness (80.43% Balanced Accuracy) under domain shifts. Ultimately, this detection-less pipeline provides a scalable and clinically viable solution to automate slide triage and alleviate cytopathologist shortages in resource-constrained environments.
Author summaryAutomated screening of cervical cytology slides is traditionally hindered by the need for labor-intensive, pixel-level cell annotations. To overcome this limitation, this study introduces a weakly-supervised, detection-free Multiple Instance Learning framework that performs slide triage using only slide-level diagnostic labels. By employing a Gated Attention mechanism, the model dynamically focuses on informative cellular regions while ignoring background debris, successfully addressing the challenge of identifying rare dysplastic cells across gigapixel images. Evaluations across multi-center datasets demonstrate that lightweight models like MobileNetV2 achieve high accuracy on in-distribution data, whereas deeper architectures like Xception provide superior robustness against out-of-distribution variations. Ultimately, this approach offers a scalable, annotation-free triage tool designed to assist cytopathologists and improve screening workflows in resource-constrained environments.
Related
- Weakly-Supervised Detection of Facial Motor Tics in Video Data Using Score-Driven Top-k Multiple Instance Learning
- Weakly Supervised Multiple-Instance Learning for Seizure Onset Zone Identification
- Multimodal Multiple Instance Learning for Fibroepithelial Tumor Diagnosis in Breast Ultrasound
- FragMIL: A Fragment-Token Multiple-Instance Learning Framework for Cancer Detection from Cell-Free DNA Fragmentomics
- Multiple instance learning for differentiating neoplastic and non-neoplastic brain lesions using MR spectroscopy.
BibTeX
@misc{mayala2026weaklysupervised,
title = {{Weakly-Supervised Gated Attention Multiple Instance Learning for Multi-Center Cervical Cytology Slide Triage}},
author = {S. Mayala and S. Sang'udi and D. Mzurikwao and E. Suluba},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.29.26364279},
url = {https://www.medrxiv.org/content/10.64898/2026.09.29.26364279v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Weakly-Supervised Gated Attention Multiple Instance Learning for Multi-Center Cervical Cytology Slide Triage
AU - S. Mayala
AU - S. Sang'udi
AU - D. Mzurikwao
AU - E. Suluba
PY - 2026
DA - 2026/09/29
PB - medRxiv
DO - 10.64898/2026.09.29.26364279
UR - https://www.medrxiv.org/content/10.64898/2026.09.29.26364279v1
AB - Automated triage of whole-slide cervical cytology images remains constrained by the heavy dependence on single-cell bounding boxes or pixel-level annotations, which introduce significant bottlenecks, high expert overhead, and observer variability. To address these challenges, we present a weakly-supervised, detection-free Multiple Instance Learning (MIL) framework powered by a Gated Attention pooling engine that operates exclusively on slide-level predictions. By treating whole-slide images as bags of local instance patches, the dual-branch gated network dynamically assigns non-linear attention weights to highlight isolated dysplastic cells while suppressing benign background and debris, successfully resolving the "needle-in-a-haystack" problem inherent to high-grade lesions. Evaluated across multi-center cohorts including internal datasets (SIPaKMeD, Herlev, and CRIC) and the unannotated, out-of-distribution Mendeley LBC validation cohort processed via an unsupervised marker-controlled watershed pipeline our approach demonstrates robust generalization without requiring dense instance labels. Furthermore, our architectural comparison reveals a key trade-off: lightweight backbones like MobileNetV2 optimize in-distribution multi-center accuracy (90.96% Accuracy, 0.9800 ROC-AUC), whereas higher-capacity models like Xception ensure superior out-of-distribution robustness (80.43% Balanced Accuracy) under domain shifts. Ultimately, this detection-less pipeline provides a scalable and clinically viable solution to automate slide triage and alleviate cytopathologist shortages in resource-constrained environments. Author summaryAutomated screening of cervical cytology slides is traditionally hindered by the need for labor-intensive, pixel-level cell annotations. To overcome this limitation, this study introduces a weakly-supervised, detection-free Multiple Instance Learning framework that performs slide triage using only slide-level diagnostic labels. By employing a Gated Attention mechanism, the model dynamically focuses on informative cellular regions while ignoring background debris, successfully addressing the challenge of identifying rare dysplastic cells across gigapixel images. Evaluations across multi-center datasets demonstrate that lightweight models like MobileNetV2 achieve high accuracy on in-distribution data, whereas deeper architectures like Xception provide superior robustness against out-of-distribution variations. Ultimately, this approach offers a scalable, annotation-free triage tool designed to assist cytopathologists and improve screening workflows in resource-constrained environments.
ER -