FODA-PG for Enhanced Medical Imaging Narrative Generation: Adaptive Differentiation of Normal and Abnormal Attributes
This work addresses the problem of reducing radiologists' workload by improving automatic report generation, but it is incremental as it builds on existing transformer-based methods with domain-specific adaptations.
The paper tackled the problem of generating accurate medical imaging narratives by addressing the challenge of distinguishing normal and abnormal findings, and the result was that FODA-PG outperformed state-of-the-art methods on benchmarks like IU-Xray and MIMIC-CXR.
Automatic Medical Imaging Narrative generation aims to alleviate the workload of radiologists by producing accurate clinical descriptions directly from radiological images. However, the subtle visual nuances and domain-specific terminology in medical images pose significant challenges compared to generic image captioning tasks. Existing approaches often neglect the vital distinction between normal and abnormal findings, leading to suboptimal performance. In this work, we propose FODA-PG, a novel Fine-grained Organ-Disease Adaptive Partitioning Graph framework that addresses these limitations through domain-adaptive learning. FODA-PG constructs a granular graphical representation of radiological findings by separating disease-related attributes into distinct "disease-specific" and "disease-free" categories based on their clinical significance and location. This adaptive partitioning enables our model to capture the nuanced differences between normal and pathological states, mitigating the impact of data biases. By integrating this fine-grained semantic knowledge into a powerful transformer-based architecture and providing rigorous mathematical justifications for its effectiveness, FODA-PG generates precise and clinically coherent reports with enhanced generalization capabilities. Extensive experiments on the IU-Xray and MIMIC-CXR benchmarks demonstrate the superiority of our approach over state-of-the-art methods, highlighting the importance of domain adaptation in medical report generation.