Weakly supervised anomaly segmentation in retinal OCT images using an adversarial learning approach

Abstract

Lesion detection is a critical component of disease diagnosis, but the manual segmentation of lesions in medical images is time-consuming and experience-demanding. These issues have recently been addressed through deep learning models. However, most of the existing algorithms were developed using supervised training, which requires time-intensive manual labeling and prevents the model from detecting unaware lesions. As such, this study proposes a weakly supervised learning network based on CycleGAN for lesions segmentation in full-width optical coherence tomography (OCT) images. The model was trained to reconstruct underlying normal anatomic structures from abnormal input images, then the lesions can be detected by calculating the difference between the input and output images. A customized network architecture and a multi-scale similarity perceptual reconstruction loss were used to extend the CycleGAN model to transfer between objects exhibiting shape deformations. The proposed technique was validated using an open-source retinal OCT image dataset. Image-level anomaly detection and pixel-level lesion detection results were assessed using area-under-curve (AUC) and the Dice similarity coefficient, producing results of 96.94% and 0.8239, respectively, higher than all comparative methods. The average test time required to generate a single full-width image was 0.039 s, which is shorter than that reported in recent studies. These results indicate that our model can accurately detect and segment retinopathy lesions in real-time, without the need for supervised labeling. And we hope this method will be helpful to accelerate the clinical diagnosis process and reduce the misdiagnosis rate.

Cardiac Adipose Tissue Segmentation via Image-Level Annotations

“…Comparison with existing weakly supervised learning framework. We compared our method with two existing weakly supervised learning frameworks: reliable region mining (RRM) [57] and CycleGAN [52]. As shown in Table V, our methods generally produce a higher true positive rate and a lower false positive rate than RRM and cycleGAN, independent of segmentation models (i.e., U-Net, FCN, and DeepLab).…”

“…Existing work mainly relies upon fully supervised learning techniques. In contrast to fully supervised methods, weakly supervised approaches use higher level labels including scribbles [26], [35], bounding boxes [28], [53], and image-level labels [52] to guide the pixel-level segmentation training process. [52] successfully segmented lesions by calculating the differences between the input abnormal images and normal-like retinal OCT images from a CycleGAN model.…”

“…In contrast to fully supervised methods, weakly supervised approaches use higher level labels including scribbles [26], [35], bounding boxes [28], [53], and image-level labels [52] to guide the pixel-level segmentation training process. [52] successfully segmented lesions by calculating the differences between the input abnormal images and normal-like retinal OCT images from a CycleGAN model. [56] employed a few shot learning technique for retinal disease classification and applied a GAN to enrich normal OCT images with OCT images of rare diseases.…”

“…Thus, automatic analysis with weakly supervised learning models is of great interest. Although recent studies have conducted retinal OCT analysis [52], [56], transferring OCT retinal segmentation to cardiac solution for weakly supervised cardiac OCT segmentation is still elusive for three reasons. First, cardiac adipose and fibrosis tissues can appear in multiple sub-regions with irregular shapes and infiltrating patterns.…”

A deep learning network for parallel self-denoising and segmentation in visible light optical coherence tomography of human retina

“…Therefore, annotation-efficient approaches are necessary. Such approaches include the semi-supervised method [19] and the weakly-supervised method [20].…”