PULSE: A Unified Multi-Task Architecture for Cardiac Segmentation, Diagnosis, and Few-Shot Cross-Modality Clinical Adaptation
This addresses the problem of fragmented cardiac analysis pipelines for medical imaging researchers and clinicians, representing a significant step toward a scalable foundation-style framework rather than an incremental improvement.
The paper tackles the fragmentation in cardiac image analysis by introducing PULSE, a unified multi-task architecture that handles anatomical segmentation, disease classification, and clinical report generation within a single framework, achieving robust generalization across datasets and modalities with minimal supervision.
Cardiac image analysis remains fragmented across tasks: anatomical segmentation, disease classification, and grounded clinical report generation are typically handled by separate networks trained under different data regimes. No existing framework unifies these objectives within a single architecture while retaining generalization across imaging modalities and datasets. We introduce PULSE, a multi-task vision-language framework built on self-supervised representations and optimized through a composite supervision strategy that balances region overlap learning, pixel wise classification fidelity, and boundary aware IoU refinement. A multi-scale token reconstruction decoder enables anatomical segmentation, while shared global representations support disease classification and clinically grounded text output allowing the model to transition from pixels to structures and finally clinical reasoning within one architecture. Unlike prior task-specific pipelines, PULSE learns task-invariant cardiac priors, generalizes robustly across datasets, and can be adapted to new imaging modalities with minimal supervision. This moves the field closer to a scalable, foundation style cardiac analysis framework.