Imitating Radiological Scrolling: A Glocal-Lobal Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification

Théo Di Piazza, Carole Lazarus, Olivier Nempont, Loic Boussel
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:1313-1325, 2026.

Abstract

The rapid increase in the number of Computed Tomography (CT) scan examinations has created an urgent need for automated tools, such as organ segmentation, anomaly classification, and report generation, to assist radiologists with their growing workload. Multi-label classification of Three-Dimensional (3D) CT scans is a challenging task due to the volumetric nature of the data and the variety of anomalies to be detected. Existing deep learning methods based on Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies effectively, while Vision Transformers require extensive pre-training, posing challenges for practical use. Additionally, these existing methods do not explicitly model the radiologistś navigational behavior while scrolling through CT scan slices, which requires both global context understanding and local detail awareness. In this study, we present CT-Scroll, a novel global-local attention model specifically designed to emulate the scrolling behavior of radiologists during the analysis of 3D CT scans. Our approach is evaluated on two public datasets, demonstrating its efficacy through comprehensive experiments and an ablation study that highlights the contribution of each model component.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-di-piazza26a, title = {Imitating Radiological Scrolling: A Glocal-Lobal Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification}, author = {Di Piazza, Th\'eo and Lazarus, Carole and Nempont, Olivier and Boussel, Loic}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {1313--1325}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/di-piazza26a/di-piazza26a.pdf}, url = {https://proceedings.mlr.press/v301/di-piazza26a.html}, abstract = {The rapid increase in the number of Computed Tomography (CT) scan examinations has created an urgent need for automated tools, such as organ segmentation, anomaly classification, and report generation, to assist radiologists with their growing workload. Multi-label classification of Three-Dimensional (3D) CT scans is a challenging task due to the volumetric nature of the data and the variety of anomalies to be detected. Existing deep learning methods based on Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies effectively, while Vision Transformers require extensive pre-training, posing challenges for practical use. Additionally, these existing methods do not explicitly model the radiologistś navigational behavior while scrolling through CT scan slices, which requires both global context understanding and local detail awareness. In this study, we present CT-Scroll, a novel global-local attention model specifically designed to emulate the scrolling behavior of radiologists during the analysis of 3D CT scans. Our approach is evaluated on two public datasets, demonstrating its efficacy through comprehensive experiments and an ablation study that highlights the contribution of each model component.} }
Endnote
%0 Conference Paper %T Imitating Radiological Scrolling: A Glocal-Lobal Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification %A Théo Di Piazza %A Carole Lazarus %A Olivier Nempont %A Loic Boussel %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-di-piazza26a %I PMLR %P 1313--1325 %U https://proceedings.mlr.press/v301/di-piazza26a.html %V 301 %X The rapid increase in the number of Computed Tomography (CT) scan examinations has created an urgent need for automated tools, such as organ segmentation, anomaly classification, and report generation, to assist radiologists with their growing workload. Multi-label classification of Three-Dimensional (3D) CT scans is a challenging task due to the volumetric nature of the data and the variety of anomalies to be detected. Existing deep learning methods based on Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies effectively, while Vision Transformers require extensive pre-training, posing challenges for practical use. Additionally, these existing methods do not explicitly model the radiologistś navigational behavior while scrolling through CT scan slices, which requires both global context understanding and local detail awareness. In this study, we present CT-Scroll, a novel global-local attention model specifically designed to emulate the scrolling behavior of radiologists during the analysis of 3D CT scans. Our approach is evaluated on two public datasets, demonstrating its efficacy through comprehensive experiments and an ablation study that highlights the contribution of each model component.
APA
Di Piazza, T., Lazarus, C., Nempont, O. & Boussel, L.. (2026). Imitating Radiological Scrolling: A Glocal-Lobal Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:1313-1325 Available from https://proceedings.mlr.press/v301/di-piazza26a.html.

Related Material