Artificial intelligence (AI) in the detection of rectosigmoid deep endometriosis.

OBJECTIVES: The aim of this study was to compare the accuracy of seven classical Machine Learning (ML) models trained with ultrasound (US) soft markers to raise suspicion of endometriotic bowel involvement. MATERIALS AND METHODS: Input data to the models was retrieved from a database of a previously published study on bowel endometriosis performed on 333 patients. The following models have been tested: k-nearest neighbors algorithm (k-NN), Naive Bayes, Neural Networks (NNET-neuralnet), Support Vector Machine (SVM), Decision Tree, Random Forest, and Logistic Regression. The data driven strategy has been to split randomly the complete dataset in two different datasets. The training dataset and the test dataset with a 67 % and 33 % of the original cases respectively. All models were trained on the training dataset and the predictions have been evaluated using the test dataset. The best model was chosen based on the accuracy demonstrated on the test dataset. The information used in all the models were: age; presence of US signs of uterine adenomyosis; presence of an endometrioma; adhesions of the ovary to the uterus; presence of "kissing ovaries"; absence of sliding sign. All models have been trained using CARET package in R with ten repeated 10-fold cross-validation. Accuracy, Sensitivity, Specificity, positive (PPV) and negative (NPV) predictive value were calculated using a 50 % threshold. Presence of intestinal involvement was defined in all cases in the test dataset with an estimated probability greater than 0.5. RESULTS: In our previous study from where the inputs were retrieved, 106 women had a final expert US diagnosis of rectosigmoid endometriosis. In term of diagnostic accuracy the best model was the Neural Net (Accuracy, 0.73; sensitivity, 0.72; specificity 0.73; PPV 0.52; and NPV 0.86) but without significant difference with the others. CONCLUSIONS: The accuracy of ultrasound soft markers in raising suspicion of rectosigmoid endometriosis using Artificial Intelligence (AI) models showed similar results to the logistic model.

Ultrasonography and Atypical Sites of Endometriosis.

In the present pictorial we show the ultrasonographic appearances of endometriosis in atypical sites. Scar endometriosis may present as a hypoechoic solid nodule with hyperechoic spots while umbilical endometriosis may appear as solid or partially cystic areas with ill-defined margins. In the case of endometriosis of the rectus muscle, ultrasonography usually demonstrates a heterogeneous hypoechogenic formation with indistinct edges. Inguinal endometriosis is quite variable in its ultrasonographic presentation showing a completely solid mass or a mixed solid and cystic mass. The typical ultrasonographic finding associated with perineal endometriosis is the presence of a solid lesion near to the episiotomy scar. Under ultrasonography, appendiceal endometriosis is characterized by a solid lesion in the wall of the small bowel, usually well defined. Superficial hepatic endometriosis is characterized by a small hypoechoic lesion interrupting the hepatic capsula, usually hyperechoic. Ultrasound endometriosis of the pancreas is characterized by a small hypoechoic lesion while endometriosis of the kidney is characterized by a hyperechoic small nodule. Diaphragmatic endometriosis showed typically small hypoechoic lesions. Only peripheral nerves can be investigated using ultrasound, with a typical solid appearance. In conclusion, ultrasonography seems to have a fundamental role in the majority of endometriosis cases in "atypical" sites, in all the cases where "typical" clinical findings are present.