HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis

Fengbei Liu, Sunwoo Kwak, Hao Phung, Nusrat Binta Nizam, Ilan Richter, Nir Uriel, Hadar Averbuch-Elor, Deborah Estrin, Mert R. Sabuncu
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:1768-1801, 2026.

Abstract

Non-contrast chest CTs offer a rich opportunity for both conventional pulmonary and opportunistic extra-pulmonary screening. While Multi-Task Learning (MTL) can unify these diverse tasks, standard hard-parameter sharing approaches are often suboptimal for modeling distinct pathologies. We propose HyperCT, a framework that dynamically adapts a Vision Transformer backbone via a Hypernetwork. To ensure computational efficiency, we integrate Low-Rank Adaptation (LoRA), allowing the model to regress task-specific low-rank weight updates rather than full parameters. Validated on a large-scale dataset of radiological and cardiological tasks, HyperCT outperforms various strong baselines, offering a unified, parameter-efficient solution for holistic patient assessment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-liu26c, title = {HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis}, author = {Liu, Fengbei and Kwak, Sunwoo and Phung, Hao and Nizam, Nusrat Binta and Richter, Ilan and Uriel, Nir and Averbuch-Elor, Hadar and Estrin, Deborah and Sabuncu, Mert R.}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {1768--1801}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/liu26c/liu26c.pdf}, url = {https://proceedings.mlr.press/v315/liu26c.html}, abstract = {Non-contrast chest CTs offer a rich opportunity for both conventional pulmonary and opportunistic extra-pulmonary screening. While Multi-Task Learning (MTL) can unify these diverse tasks, standard hard-parameter sharing approaches are often suboptimal for modeling distinct pathologies. We propose HyperCT, a framework that dynamically adapts a Vision Transformer backbone via a Hypernetwork. To ensure computational efficiency, we integrate Low-Rank Adaptation (LoRA), allowing the model to regress task-specific low-rank weight updates rather than full parameters. Validated on a large-scale dataset of radiological and cardiological tasks, HyperCT outperforms various strong baselines, offering a unified, parameter-efficient solution for holistic patient assessment.} }
Endnote
%0 Conference Paper %T HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis %A Fengbei Liu %A Sunwoo Kwak %A Hao Phung %A Nusrat Binta Nizam %A Ilan Richter %A Nir Uriel %A Hadar Averbuch-Elor %A Deborah Estrin %A Mert R. Sabuncu %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-liu26c %I PMLR %P 1768--1801 %U https://proceedings.mlr.press/v315/liu26c.html %V 315 %X Non-contrast chest CTs offer a rich opportunity for both conventional pulmonary and opportunistic extra-pulmonary screening. While Multi-Task Learning (MTL) can unify these diverse tasks, standard hard-parameter sharing approaches are often suboptimal for modeling distinct pathologies. We propose HyperCT, a framework that dynamically adapts a Vision Transformer backbone via a Hypernetwork. To ensure computational efficiency, we integrate Low-Rank Adaptation (LoRA), allowing the model to regress task-specific low-rank weight updates rather than full parameters. Validated on a large-scale dataset of radiological and cardiological tasks, HyperCT outperforms various strong baselines, offering a unified, parameter-efficient solution for holistic patient assessment.
APA
Liu, F., Kwak, S., Phung, H., Nizam, N.B., Richter, I., Uriel, N., Averbuch-Elor, H., Estrin, D. & Sabuncu, M.R.. (2026). HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:1768-1801 Available from https://proceedings.mlr.press/v315/liu26c.html.

Related Material