HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis
2026-04-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed HyperCT, a new method to analyze chest CT scans that can look for multiple lung and heart issues at once. Their approach uses a special type of neural network that adapts itself for different medical tasks efficiently, avoiding the need to retrain everything from scratch. They tested their method on a large dataset and found it works better than other common methods while using fewer resources. This helps doctors get a more complete understanding of a patient from one scan.
Non-contrast chest CTMulti-Task LearningVision TransformerHypernetworkLow-Rank Adaptation (LoRA)Pulmonary screeningExtra-pulmonary screeningParameter efficiencyRadiological tasksCardiological tasks
Authors
Fengbei Liu, Sunwoo Kwak, Hao Phung, Nusrat Binta Nizam, Ilan Richter, Nir Uriel, Hadar Averbuch-Elor, Daborah Estrin, Mert R. Sabuncu
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, \method{} outperforms various strong baselines, offering a unified, parameter-efficient solution for holistic patient assessment. Our code is available at https://github.com/lfb-1/HyperCT.