Exploration of machine learning models for surgical incision healing assessment based on thermal imaging: A feasibility study

Abstract

In this study, we explored the use of thermal imaging technology combined with computer vision techniques for assessing surgical incision healing. We processed 1189 thermal images, annotated by experts to define incision boundaries and healing statuses. Using these images, we developed a machine learning model based on YOLOV8, which automates the recognition of incision areas, lesion segmentation and healing classification. The dataset was divided into training, testing and validation sets in a 7:2:1 ratio. Our results show high accuracy rates in incision location recognition, lesion segmentation and healing classification, indicating the model's effectiveness as a precise and automated diagnostic tool for surgical incision healing assessment. Conclusively, our thermal image-based machine learning model demonstrates excellent performance in wound assessment, paving the way for its clinical application in intelligent and standardized wound management.

Efficacy of mesenchymal stromal cells in the treatment of unexplained recurrent spontaneous abortion in mice: An analytical and systematic review of meta-analyses

by Xiaoxuan Zhao, Yijie Hu, Wenjun Xiao, Yiming Ma, Dan Shen, Yuepeng Jiang, Yi Shen, Suxia Wang, Jing Ma

Unexplained recurrent spontaneous abortion (URSA) remains an intractable reproductive dilemma due to the lack of understanding of the pathogenesis. This study aimed to evaluate the preclinical evidence for the mesenchymal stromal cell (MSC) treatment for URSA.

A meticulous literature search was independently performed by two authors across the Cochrane Library, EMBASE, and PubMed databases from inception to April 9, 2023. Each study incorporated was assessed using the Systematic Review Centre for Laboratory Animal Experimentation (SYRCLE) risk of bias tool. The amalgamated standardized mean difference (SMD) accompanied by 95% confidence interval (CI) were deduced through a fixed-effects or random-effects model analysis.

A total of ten studies incorporating 140 mice were subjected to data analysis. The MSC treatment yielded a significant reduction in the abortion rate within the URSA model (OR = 0.23, 95%CI [0.17, 0.3], PP = 0.01), IL10 (SMD 1.60, 95% CI [0.58, 2.61], P = 0.002), IFN-γ (SMD -1.66, 95%CI [-2.79, -0.52], P = 0.004), and TNF-α (SMD -1.98, 95% CI [-2.93, -1.04], PPP>0.05).

The findings underscore the considerable potential of MSCs in URSA therapy. Nonetheless, the demand for enhanced transparency in research design and direct comparisons between various MSC sources and administration routes in URSA is paramount to engendering robust evidence that could pave the way for successful clinical translation.