BACKGROUND/AIMS: We aimed to determine the association between the co-expression patterns of Notch1, Snail, and p53 proteins (NSP) and the postoperative prognosis of hepatocellular carcinoma (HCC). METHODS: The immunoblot data for molecular expression (147 HCC/corresponding non-HCC tissues and 15 dysplastic nodules) and the sequencing data for p53 mutations (110 HCCs) were obtained from our previous study. Data analyses were restricted to cases with HCC differentiation grade III (n=47), due to its high p53 mutation rate. RESULTS: Nineteen of the 47 patients (40.4%) -comprising 12 in the liver and 7 in distant organs-had relapsed at 1-2 years after surgery. There was no relationship between p53 mutation and postoperative recurrence in the grade III HCCs. Seven (87.5%) of the eight relapsed cases with Notch1, Snail, and p53 (wild) co-expression experienced recurrence only within the liver, and all tumors were smaller than 5 cm in diameter. Extrahepatic relapse occurred mostly in HCC patients with tumors larger than 5 cm in diameter, without any deviation in the NSP pattern. CONCLUSIONS: The results of this preliminary study suggest that the co-expression of Notch1, Snail, and p53 (wild) is not inferior to the patterns with p53 mutation as an indicator of postoperative recurrence of grade III HCC.
Adult ; Aged ; Carcinoma, Hepatocellular/*metabolism/pathology/surgery ; Female ; Humans ; Liver Neoplasms/*metabolism/pathology/surgery ; Male ; Middle Aged ; Mutation ; Neoplasm Staging ; Postoperative Period ; Prognosis ; Receptor, Notch1/*metabolism ; Recurrence ; Transcription Factors/*metabolism ; Tumor Suppressor Protein p53/genetics/*metabolism

Objectives:To examine the feasibility of using foundation model in computer vision for echocardiographic left ventricular ejection fraction measurement. Methods:Based on the most extensive publicly accessible repository of echocardiographic loops,EchoNet-Dynamic,featuring 10024 recordings from individual patients,a foundation model in computer vision,VideoMAE V2,was fine-tuned,validated,tested using 7460,1288,and 1276 echocardiographic loops,respectively. Results:The mean absolute error between left ventricular ejection fraction measurements of VideoMAE V2 and expert's measurements was 3.94％ (95％CI:3.79％-4.11％).The Pearson's correlation coefficient was 0.91 (95％CI:0.89-0.92).Additionally,VideoMAE V2 demonstrated exceptional accuracy in identifying patients with a left ventricular ejection fraction below 50％,achieving an AUC of 0.96 (95％CI:0.95-0.97). Conclusions:This study validates the feasibility of using foundation model in computer vision for measuring left ventricular ejection fraction in echocardiographic loops and lays the foundation for the development of a generalized multimodal automated interpretation system for echocardiography.