Medical Imaging

The study included 50 epilepsy patients undergoing long-term video-EEG monitoring at the Epilepsy Center of Guangdong 999 Brain Hospital. The inclusion criteria for patients were as follows: (1) VEEG reports confirming definite epileptic seizures, (2) complete video data containing both seizure and non-seizure periods, (3) no intentional interference during patient seizures, and no occlusion of the patient, such as patients were covered by quilts.

CT RECIST response, as measured by the change of tumor diameter, can accurately reflect objective response rate for advanced NSCLC patients. However, there exists obvious discordant between CT RECIST response and prognostic indicators. Thus, our study aimed to identify a new CT RECIST response indicator at the early treatment stage to reflect the prognosis more accurately.We studied 916 tumor lesions obtained through deep learning and found that the shape of the lesions was irregular.

Prostate cancer is a major global health challenge. In this study, we present an approach for the detection and grading of prostate cancer through the semantic segmentation of adenocarcinoma tissues, specifically focusing on distinguishing between Gleason patterns 3 and 4. Our method leverages deep learning techniques to improve diagnostic accuracy and enhance patient treatment strategies. We developed a new dataset comprising 100 digitized whole-slide images of prostate needle core biopsy specimens, which are publicly available for research purposes.

UTERUS: The uterus dataset (Huang et al. 2021) collected from the treatment device HIFU Pro2008 of Shenzhen ProHuiren Company. The dataset comprises 495 HIFU treatment ultrasound monitoring images of uterus, with 330 images randomly selected for training, 50 images for validating and 115 images for testing. The target region for treatment is the tumor region in the ultrasound image, as marked by professional doctors, and the image size is 448×544 pixels.