Medical-based Deep Curriculum Learning for Improved Fracture Classification
This work addresses a domain-specific problem in medical imaging by improving fracture classification for clinical applications, though it is incremental as it builds on existing curriculum learning methods.
The paper tackles the challenge of classifying proximal femur fractures from X-ray images by proposing medical knowledge-based curriculum learning strategies, which improve accuracy by up to 15% compared to baseline methods, achieving performance comparable to experienced trauma surgeons on a dataset of about 1000 images.
Current deep-learning based methods do not easily integrate to clinical protocols, neither take full advantage of medical knowledge. In this work, we propose and compare several strategies relying on curriculum learning, to support the classification of proximal femur fracture from X-ray images, a challenging problem as reflected by existing intra- and inter-expert disagreement. Our strategies are derived from knowledge such as medical decision trees and inconsistencies in the annotations of multiple experts, which allows us to assign a degree of difficulty to each training sample. We demonstrate that if we start learning "easy" examples and move towards "hard", the model can reach a better performance, even with fewer data. The evaluation is performed on the classification of a clinical dataset of about 1000 X-ray images. Our results show that, compared to class-uniform and random strategies, the proposed medical knowledge-based curriculum, performs up to 15% better in terms of accuracy, achieving the performance of experienced trauma surgeons.