論文

This study aims to develop a deep learning model that takes whole slide images (WSI) as input to predict cancer progression. By incorporating cancer segmentation, the proposed model improved diagnostic accuracy compared to using WSI alone. Although high accuracy was achieved for specific datasets, further model improvements are needed for consistent performance across all datasets.

Dermal grafts are used for patients with severe burn injuries whose natural healing abilities are limited or exhausted. This paper proposes a method to segment burnt and grafted areas from images with meshed grafts. First, RGB colour input images are converted to images in the L*a*b* colour space. The transformed images are then segmented with the simple linear iterative clustering superpixel algorithm. Subsequently, the burnt and grafted areas are classified with a support vector machine, and the output area size is modified for all burnt areas. The segmentation results are compared with the areas identified by two dermatologists based on the concordance rate (CR), positive predictive value (PPV), sensitivity, and F-measure values. The proposed segmentation method yielded CRs equal to 84.3 % and 85.9 %, PPVs equal to 87.2 % and 87.9 %, sensitivities equal to 84.7 % and 86.4 %, and F-measure values equal to 85.8 % and 87.0 %. This study developed a segmentation method for classifying burnt and grafted areas from images with meshed grafts. The segmented areas obtained were significantly consistent with those identified by the two dermatologists.

This paper deals with a method of segmenting skin and skin grafts using GrowCut. The previous lacks system usability because the evaluating physician needed approximately 100–200 mouse clicks for each image to acquire training data. Therefore, we propose a method to automate the acquisition of training data while maintaining the accuracy of domain segmentation from the previous study. Based on the proposed method, the ratio of the two areas-of-interest was calculated as the burn ratio and used to evaluate treatment quantitatively. The results show that the segmentation of skin and skin grafts is as accurate as by mouse clicks. We think that automating the acquisition of training data as preprocessing will improve the usability of the system.