Detecting small polyps using a Dynamic SSD-GAN
This addresses a critical bottleneck in medical imaging for cancer screening, though it is an incremental improvement over existing methods.
The paper tackled the problem of poor detection of visually-small polyps in colonoscopy images by combining a single-shot detector with an adversarial generator for upsampling, resulting in a 12% increase in sensitivity compared to a baseline.
Endoscopic examinations are used to inspect the throat, stomach and bowel for polyps which could develop into cancer. Machine learning systems can be trained to process colonoscopy images and detect polyps. However, these systems tend to perform poorly on objects which appear visually small in the images. It is shown here that combining the single-shot detector as a region proposal network with an adversarially-trained generator to upsample small region proposals can significantly improve the detection of visually-small polyps. The Dynamic SSD-GAN pipeline introduced in this paper achieved a 12% increase in sensitivity on visually-small polyps compared to a conventional FCN baseline.