Yoshinobu Hamada

Comparison of the risk of ovarian malignancy algorithm and Copenhagen Index for the preoperative assessment of Japanese women with ovarian tumors

AbstractObjectiveTo compare the risk of ovarian malignancy algorithm (ROMA) and Copenhagen Index (CPH‐I) in their ability to distinguish epithelial ovarian cancer (EOC) and malignant ovarian tumors (MLOT) from benign ovarian tumors (BeOT) in Japanese women.MethodsPatients with pathologically diagnosed ovarian tumors were included in this study. The study validated the diagnostic performance of ROMA and CPH‐I.ResultsAmong the 463 Japanese women included in this study, 312 had BeOT, 99 had EOC, and 52 had other MLOT. The receiver‐operator characteristic (ROC) area under the curve (AUCs) of ROMA (0.89) and CPH‐I (0.89) for distinguishing EOC from BeOT were significantly higher than that of CA125 (0.82) (CA 125 vs. ROMA; p = 0.002, vs. CPH‐I; p < 0.001). The ROC‐AUCs of ROMA (0.82) and CPH‐I (0.81) for distinguishing MLOT from BeOT were significantly higher than that of CA125 (0.75) (CA 125 vs. ROMA: p = 0.003, vs. CPH‐I: p < 0.001). The sensitivity (SN)/specificity (SP) of ROMA and CPH‐I for distinguishing EOC from BeOT at standard cut‐off points were 69%/90%, and 69%/90%, respectively, those for distinguishing MLOT from BeOT were 54%/90%, and 55%/90%, respectively.ConclusionROMA and CPH‐I performed comparably well and better than CA125 in distinguishing EOC from BeOT in Japanese women. ROMA and CHP‐I should be used with caution in practical situations, where all histological possibilities for must be considered, because the SNs of ROMA and CPH‐I were only 54% and 55%.

Establishment of a Model to Predict the Prognosis of Endometrial Carcinoma Using Tumor‐Infiltrating Lymphocytes Evaluated With Artificial Intelligence: A Retrospective Analysis

ABSTRACT Background The objective of this study was to establish a new model for predicting the prognosis of endometrial carcinoma (EC) using tumor‐infiltrating lymphocytes (TILs) based on artificial intelligence (AI). Methods Patients with EC who were treated between 1989 and 2022 were included in this study. For each patient, one hematoxylin and eosin‐stained slide containing the most invasive frontline of the tumor was selected and digitized. The area within a 500 μm width span, extending 250 μm toward the stroma and tumor from the manually annotated invasive frontline, was automatically annotated. The average number of lymphocytes per area (μm 2 ) in the annotated area was calculated using AI. Patients were classified into the High‐TIL and Low‐TIL groups, and survival analysis was conducted. Four mismatch repair (MMR)‐related proteins were evaluated using immunohistochemical staining. Results A total of 659 patients were included: 346 (52.5%) in the High‐TIL group and 313 (47.5%) in the Low‐TIL group. MMR deficiency was observed more frequently in the High‐TIL group than in the Low‐TIL group ( p  < 0.01). Progression‐free survival (PFS) and overall survival (OS) were better in the High‐TIL group than in the Low‐TIL group (both p  < 0.01). Multivariate analysis revealed that TIL status was a prognostic factor for PFS (hazard ratio [HR] (95% confidence interval [CI]) 0.61 (0.43–0.87); p  < 0.01) and OS (HR (95% CI) 0.54 (0.33–0.86); p  = 0.01). Conclusion TILs evaluated using AI could accurately and significantly predict the prognosis of EC. Further studies are needed to establish new methods for evaluating TILs in ECs.