KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks
This work addresses a domain-specific problem in medical imaging for osteoarthritis diagnosis, with incremental improvements in accuracy and generalization.
The paper tackles anatomical landmark localization in knee X-ray images across osteoarthritis stages by proposing an efficient deep neural network framework with an hourglass architecture and soft-argmax layer, achieving better generalization performance than state-of-the-art methods on independent datasets.
This paper addresses the challenge of localization of anatomical landmarks in knee X-ray images at different stages of osteoarthritis (OA). Landmark localization can be viewed as regression problem, where the landmark position is directly predicted by using the region of interest or even full-size images leading to large memory footprint, especially in case of high resolution medical images. In this work, we propose an efficient deep neural networks framework with an hourglass architecture utilizing a soft-argmax layer to directly predict normalized coordinates of the landmark points. We provide an extensive evaluation of different regularization techniques and various loss functions to understand their influence on the localization performance. Furthermore, we introduce the concept of transfer learning from low-budget annotations, and experimentally demonstrate that such approach is improving the accuracy of landmark localization. Compared to the prior methods, we validate our model on two datasets that are independent from the train data and assess the performance of the method for different stages of OA severity. The proposed approach demonstrates better generalization performance compared to the current state-of-the-art.