ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentation

Abstract

Curating a large scale fully-annotated dataset can be both labour-intensive and expertise-demanding, especially for medical images.To alleviate this problem, we propose to utilize solely scribble annotations for weakly supervised segmentation. Existing solutions mainly leverage selective losses computed solely on annotated areas and generate pseudo gold standard segmentation by propagating labels to adjacent areas. However, these methods could suffer from the inaccurate and sometimes unrealistic pseudo segmentation due to the insufficient supervision and incomplete shape features. Different from previous efforts, we first investigate the principle of "good scribble annotations", which leads to efficient scribble forms via supervision maximization and randomness simulation. Furthermore, we introduce regularization terms to encode the spatial relationship and shape prior, where a new formulation is developed to estimate the mixture ratios of label classes. These ratios are critical in identifying the unlabeled pixels for each class and correcting erroneous predictions, thus the accurate estimation lays the foundation for the incorporation of spatial prior. Finally, we integrate the efficient scribble supervision with the prior into a unified framework, denoted as ZScribbleSeg, and apply the method to multiple scenarios. Leveraging only scribble annotations, ZScribbleSeg set new state-of-thearts on four segmentation tasks using ACDC, MSCMRseg, MyoPS and PPSS datasets.

Leveraging Bounding Box Annotations for Fish Segmentation in Underwater Images

“…In the general computer vision literature several recent articles propose the use of these types of annotations, specially in the field of medical image segmentation. Scribble annotations are used in [48]- [51], points in [52]- [54] and bounding boxes in [55]- [58]. In Marine Science applications the literature on weakly supervised methods is scarce.…”

A Study of Latent Tuberculosis Infection And its Influencing Factors in Diabetic Patients in Nanshan District, Shenzhen, China

“…Following [29], we utilize a Gaussian kernel function to design the low-level weight function 𝜔 low , which is defined by the distinction between two pixels in terms of image intensity value 𝑣 and spatial location 𝑙…”