Curriculum Learning for Language-Guided, Multi-Modal Detection of Various Pathologies

Abstract

Pathology detection in medical imaging is crucial for radiologists, yet current approaches that train specialized models for each region of interest often lack efficiency and robustness. Furthermore, the scarcity of annotated medical data, particularly for diverse phenotypes, poses significant challenges in achieving generalizability. To address these challenges, we present a novel language-guided object detection pipeline that leverages curriculum learning strategies, chosen for their ability to progressively train models on increasingly complex samples, thereby improving generalization across pathologies, phenotypes, and modalities. We developed a unified pipeline to convert segmentation datasets into bounding box annotations, and applied two curriculum learning approaches - teacher curriculum and bounding box size curriculum - to train a Grounding DINO model. Our method was evaluated on different tumor types in MRI and CT scans and showed significant improvements in detection accuracy. The teacher and bounding box size curriculum learning approaches yielded a 4.9\% AP and 5.2\% AP increase over baseline, respectively. The results highlight the potential of curriculum learning to optimize medical image analysis and clinical workflow. The code is available at https://github.com/CCI-Bonn/CL4OD.