AI Analysis of Liver Fat in Mice with Metabolic Dysfunction
Author Information
Author(s): Wang Xiao-Xiao, Song Yu-Yun, Jin Rui, Wang Zi-Long, Li Xiao-He, Yang Qiang, Teng Xiao, Liu Fang-Fang, Wu Nan, Xie Yan-Di, Rao Hui-Ying, Liu Feng
Primary Institution: Peking University People’s Hospital
Hypothesis
Can artificial intelligence improve the assessment of hepatic steatosis in mouse models of metabolic dysfunction-associated steatotic liver disease?
Conclusion
AI technology provides a more accurate and objective method for diagnosing steatosis in mouse models of metabolic dysfunction-associated steatotic liver disease.
Supporting Evidence
- AI analysis showed significant increases in the percentage of intrahepatic fatty vacuole area and the number of fatty vacuoles over time.
- The NASH CRN score did not show significant differences between 8 and 16 weeks, highlighting the limitations of traditional scoring methods.
- AI methods provided a more objective assessment compared to semi-quantitative histological grading.
Takeaway
Scientists used a computer program to look at liver fat in mice to see how it changes over time, and they found that the program is better at measuring fat than traditional methods.
Methodology
The study used AI analysis of SHG/TPEF images to evaluate hepatic steatosis in six different mouse models of MASLD.
Potential Biases
Potential bias due to the use of only one gender of mice and lack of comprehensive physiological assessments.
Limitations
The study only used male mice, and did not assess water balance or intra-abdominal fat.
Participant Demographics
Male C57BL/6 mice.
Statistical Information
P-Value
p<0.001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website