RECIST-Net: Lesion detection via grouping keypoints on RECIST-based annotation
This addresses lesion detection in medical imaging for clinical applications, offering an incremental improvement over existing bounding-box-based approaches.
The authors tackled universal lesion detection in CT images by proposing RECIST-Net, which detects lesions via keypoints based on RECIST diameters, achieving a sensitivity of 92.49% at four false positives per image and outperforming other methods.
Universal lesion detection in computed tomography (CT) images is an important yet challenging task due to the large variations in lesion type, size, shape, and appearance. Considering that data in clinical routine (such as the DeepLesion dataset) are usually annotated with a long and a short diameter according to the standard of Response Evaluation Criteria in Solid Tumors (RECIST) diameters, we propose RECIST-Net, a new approach to lesion detection in which the four extreme points and center point of the RECIST diameters are detected. By detecting a lesion as keypoints, we provide a more conceptually straightforward formulation for detection, and overcome several drawbacks (e.g., requiring extensive effort in designing data-appropriate anchors and losing shape information) of existing bounding-box-based methods while exploring a single-task, one-stage approach compared to other RECIST-based approaches. Experiments show that RECIST-Net achieves a sensitivity of 92.49% at four false positives per image, outperforming other recent methods including those using multi-task learning.