Pulmonary vasculature development in congenital diaphragmatic hernia: a novel automated quantitative imaging analysis.

PURPOSE: Impaired fetal lung vasculature determines the degree of pulmonary hypertension in the congenital diaphragmatic hernia (CDH). This study aims to demonstrate the morphometric measurements that differ in pulmonary vessels of fetuses with CDH. METHODS: Nitrofen-induced CDH Sprague-Dawley rat fetuses were scanned with microcomputed tomography. The analysis of the pulmonary vascular tree was performed with artificial intelligence. RESULTS: The number of segments in CDH was significantly lower than that in the control group on the left (U = 2.5, p = 0.004) and right (U = 0, p = 0.001) sides for order 1(O1), whereas there was a significant difference only on the right side for O2 and O3. The pooled element numbers in the control group obeyed Horton's law (R2 = 0.996 left and R2 = 0.811 right lungs), while the CDH group broke it. Connectivity matrices showed that the average number of elements of O1 springing from elements of O1 on the left side and the number of elements of O1 springing from elements of O3 on the right side were significantly lower in CDH samples. CONCLUSION: According to these findings, CDH not only reduced the amount of small order elements, but also destroyed the fractal structure of the pulmonary arterial trees.

UC-NfNet: Deep learning-enabled assessment of ulcerative colitis from colonoscopy images.

Ulcerative colitis (UC) belongs to the inflammatory bowel disease (IBD) family, which is mainly caused by inflammation of the tissue in the colon and rectum. The severity of this infection can radically affect the patient's overall well-being. Although there is no definitive treatment for this disease, diagnosis of the severity of the disease through colonoscopy imaging and the use of personalized treatment can prevent progression to more malignant stages. Inter- and intra-observer variability combined with the complex nature of UC infection makes medical assessment cumbersome. Diagnosis and treatment of UC can be made more accurate and robust if disease severity can be determined in a standardized and automated manner. Therefore, the development of a computerized tool that can be integrated into the clinical decision-making process of UC classification is of great importance. In this work, we present an automated UC classification method, UC-NfNet, complemented by a synthetic data generation pipeline aimed at classifying colonoscopy UC images. We show that our model quantitatively outperforms state-of-the-art classification models such as ConViT, Inception-v4, NFNets, ResNets and Swin Transformer. In an independent reader study of five gastroenterologists, the average agreement between the UC-NfNet and individual gastroenterologists was higher than the agreement between individual gastroenterologists. This robust evaluation of the proposed AI system paves the way for clinical trials of AI-assisted UC classification. The code and dataset are publicly available at https://github.com/DeepMIALab/UC-NfNet.