PULSE: A Unified Multi-Task Architecture for Cardiac Segmentation, Diagnosis, and Few-Shot Cross-Modality Clinical Adaptation

TL;DR

PULSE is a versatile multi-task framework that unifies cardiac segmentation, diagnosis, and clinical report generation, demonstrating robust cross-modality generalization and minimal supervision adaptation.

Contribution

It introduces a unified architecture leveraging self-supervised learning and multi-task training to perform diverse cardiac analysis tasks within a single model.

Findings

Achieves accurate cardiac segmentation and diagnosis across multiple datasets.

Supports clinical report generation grounded in visual and structural understanding.

Generalizes effectively to new imaging modalities with minimal supervision.

Abstract

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.