LiFE-Net: Longitudinal information Fusion for Enhanced lesion detection in unsupervised learning contexts

Walid Yassine, Martin Charachon, Celine Hudelot, Roberto Ardon
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:1755-1770, 2026.

Abstract

Accurate detection of liver lesions in longitudinal follow-up is critical for assessing disease progression. Unlike clinical practices that compare multiple time points, most deep-learning approaches treat these time points independently. Existing longitudinal imaging methods, particularly in brain imaging, use strategies like channel-wise concatenation, recurrent architectures, or temporal difference computation. However, these methods might fall short in liver imaging due to challenges like non-rigid motions, anatomical variability, and changes in imaging conditions.To address these challenges, we introduce LiFE-Net, the first framework to integrate longitudinal information from baseline liver CT scans through feature fusion. Our method employs intermediate feature fusion via self-attention mechanisms, leveraging baseline images to incorporate longitudinal information for more accurate predictions. We adopt an unsupervised training approach using synthetic lesions to address the lack of supervised datasets for longitudinal liver tumors.Our results show improvements in detection performance on follow-up images when baseline information is incorporated, with gains in both detection mAP and ROC AUC per exam metrics. An exhaustive ablation study further highlights the impact of baseline image integration, registration quality, and architectural components in achieving these improvements. Our code for LiFE-Net is made publicly available at: https://github.com/walid-yassine/LiFE-Net

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-yassine26a, title = {LiFE-Net: Longitudinal information Fusion for Enhanced lesion detection in unsupervised learning contexts}, author = {Yassine, Walid and Charachon, Martin and Hudelot, Celine and Ardon, Roberto}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {1755--1770}, 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/yassine26a/yassine26a.pdf}, url = {https://proceedings.mlr.press/v301/yassine26a.html}, abstract = {Accurate detection of liver lesions in longitudinal follow-up is critical for assessing disease progression. Unlike clinical practices that compare multiple time points, most deep-learning approaches treat these time points independently. Existing longitudinal imaging methods, particularly in brain imaging, use strategies like channel-wise concatenation, recurrent architectures, or temporal difference computation. However, these methods might fall short in liver imaging due to challenges like non-rigid motions, anatomical variability, and changes in imaging conditions.To address these challenges, we introduce LiFE-Net, the first framework to integrate longitudinal information from baseline liver CT scans through feature fusion. Our method employs intermediate feature fusion via self-attention mechanisms, leveraging baseline images to incorporate longitudinal information for more accurate predictions. We adopt an unsupervised training approach using synthetic lesions to address the lack of supervised datasets for longitudinal liver tumors.Our results show improvements in detection performance on follow-up images when baseline information is incorporated, with gains in both detection mAP and ROC AUC per exam metrics. An exhaustive ablation study further highlights the impact of baseline image integration, registration quality, and architectural components in achieving these improvements. Our code for LiFE-Net is made publicly available at: https://github.com/walid-yassine/LiFE-Net} }
Endnote
%0 Conference Paper %T LiFE-Net: Longitudinal information Fusion for Enhanced lesion detection in unsupervised learning contexts %A Walid Yassine %A Martin Charachon %A Celine Hudelot %A Roberto Ardon %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-yassine26a %I PMLR %P 1755--1770 %U https://proceedings.mlr.press/v301/yassine26a.html %V 301 %X Accurate detection of liver lesions in longitudinal follow-up is critical for assessing disease progression. Unlike clinical practices that compare multiple time points, most deep-learning approaches treat these time points independently. Existing longitudinal imaging methods, particularly in brain imaging, use strategies like channel-wise concatenation, recurrent architectures, or temporal difference computation. However, these methods might fall short in liver imaging due to challenges like non-rigid motions, anatomical variability, and changes in imaging conditions.To address these challenges, we introduce LiFE-Net, the first framework to integrate longitudinal information from baseline liver CT scans through feature fusion. Our method employs intermediate feature fusion via self-attention mechanisms, leveraging baseline images to incorporate longitudinal information for more accurate predictions. We adopt an unsupervised training approach using synthetic lesions to address the lack of supervised datasets for longitudinal liver tumors.Our results show improvements in detection performance on follow-up images when baseline information is incorporated, with gains in both detection mAP and ROC AUC per exam metrics. An exhaustive ablation study further highlights the impact of baseline image integration, registration quality, and architectural components in achieving these improvements. Our code for LiFE-Net is made publicly available at: https://github.com/walid-yassine/LiFE-Net
APA
Yassine, W., Charachon, M., Hudelot, C. & Ardon, R.. (2026). LiFE-Net: Longitudinal information Fusion for Enhanced lesion detection in unsupervised learning contexts. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:1755-1770 Available from https://proceedings.mlr.press/v301/yassine26a.html.

Related Material