Objectives Some ovarian tumors may originate in epithelial cells of the fallopian tubes. Computerized morphometry was able to find significant alterations in the fallopian tube epithelium of healthy BRCA carriers. The purpose of this study was to identify a subgroup of BRCA carriers that may be at risk to develop ovarian cancer by evaluation of the epithelium of fallopian tubes using artificial intelligence.

Methods Four groups of patients were analyzed. Healthy patients and ovarian cancer patients, BRCA carriers and non -carriers. All fallopian tubes were normal by H&E examination. Using ImageProPlus software and Neural Network analysis the nuclear symmetry of 65 fimbriae epithelium cells was analyzed. Further evaluation using artificial intelligence was applied in order to detect a subpopulation among fimbriae of healthy BRCA carriers, at risk for ovarian cancer.

Results Significant differences were found between healthy patients and ovarian cancer patients and between BRCA carriers and non-carriers. The artificial intelligence algorithm was able to accurately predict BRCA carriers with associated ovarian cancer based on fallopian tubes nuclear morphometry.

Conclusions These results reinforce the hypothesis that fimbriae epithelium cells of BRCA carriers’ may undergo early-stage changes that may predict progression toward malignancy. Artificial intelligence may identify patients at high risk for malignancy initiated in the fallopian tubes.