Semi-Supervised Medical Image Segmentation Guided by Bi-Directional Constrained Dual-Task Consistency

Abstract

Background: Medical image processing tasks represented by multi-object segmentation are of great significance for surgical planning, robot-assisted surgery, and surgical safety. However, the exceptionally low contrast among tissues and limited available annotated data makes developing an automatic segmentation algorithm for pelvic CT challenging. Methods: A bi-direction constrained dual-task consistency model named PICT is proposed to improve segmentation quality by leveraging free unlabeled data. First, to learn more unmarked data features, it encourages the model prediction of the interpolated image to be consistent with the interpolation of the model prediction at the pixel, model, and data levels. Moreover, to constrain the error prediction of interpolation interference, PICT designs an auxiliary pseudo-supervision task that focuses on the underlying information of non-interpolation data. Finally, an effective loss algorithm for both consistency tasks is designed to ensure the complementary manner and produce more reliable predictions. Results: Quantitative experiments show that the proposed PICT achieves 87.18%, 96.42%, and 79.41% mean DSC score on ACDC, CTPelvic1k, and the individual Multi-tissue Pelvis dataset with gains of around 0.8%, 0.5%, and 1% compared to the state-of-the-art semi-supervised method. Compared to the baseline supervised method, the PICT brings over 3–9% improvements. Conclusions: The developed PICT model can effectively leverage unlabeled data to improve segmentation quality of low contrast medical images. The segmentation result could improve the precision of surgical path planning and provide input for robot-assisted surgery.

Method for detecting defects in direct metal deposition using a neural network

“…In this case three architectures of neural networks are used. In the researches information about using U-Net, ResUNet and VGG-Net [23][24][25] for image classification and detection was found. YOLO-based neural networks are also widely used in image classification [26] but in this research it is not used due to the idea of building the architecture from scratch.…”