Improving automatic endoscopic stone recognition using a multi-view fusion approach enhanced with two-step transfer learning
This work addresses the challenge of accurate kidney stone classification in medical imaging, which is incremental as it builds on existing deep-learning techniques with specific enhancements.
The paper tackled the problem of identifying kidney stone types from endoscopic images by developing a deep-learning method that fuses multi-view image information and uses two-step transfer learning, achieving over 6% accuracy improvement compared to single-view models.
This contribution presents a deep-learning method for extracting and fusing image information acquired from different viewpoints, with the aim to produce more discriminant object features for the identification of the type of kidney stones seen in endoscopic images. The model was further improved with a two-step transfer learning approach and by attention blocks to refine the learned feature maps. Deep feature fusion strategies improved the results of single view extraction backbone models by more than 6% in terms of accuracy of the kidney stones classification.