Integrating Feature and Image Pyramid: A Lung Nodule Detector Learned in Curriculum Fashion
This work addresses the challenge of efficient and accurate lung nodule detection in medical imaging, which is crucial for early diagnosis, but it is incremental as it builds on existing pyramid and training methods.
The paper tackled the problem of detecting lung nodules in CT images, which vary in size and appearance, by integrating 3D image and feature pyramids to improve recall, and introduced a curriculum training strategy with dynamic sampling that halved training time on the LUNA16 dataset.
Lung nodules suffer large variation in size and appearance in CT images. Nodules less than 10mm can easily lose information after down-sampling in convolutional neural networks, which results in low sensitivity. In this paper, a combination of 3D image and feature pyramid is exploited to integrate lower-level texture features with high-level semantic features, thus leading to a higher recall. However, 3D operations are time and memory consuming, which aggravates the situation with the explosive growth of medical images. To tackle this problem, we propose a general curriculum training strategy to speed up training. An dynamic sampling method is designed to pick up partial samples which give the best contribution to network training, thus leading to much less time consuming. In experiments, we demonstrate that the proposed network outperforms previous state-of-the-art methods. Meanwhile, our sampling strategy halves the training time of the proposal network on LUNA16.