Ultrasound radiomics-based artificial intelligence model to assist in the differential diagnosis of ovarian endometrioma and ovarian dermoid cyst

Abstract

Background: Accurately differentiating between ovarian endometrioma and ovarian dermoid cyst is of clinical significance. However, the ultrasound appearance of these two diseases is variable, occasionally causing confusion and overlap with each other. This study aimed to develop a diagnostic classification model based on ultrasound radiomics to intelligently distinguish and diagnose the two diseases.

Methods: We collected ovarian ultrasound images from participants diagnosed as patients with ovarian endometrioma or ovarian dermoid cyst. Feature extraction and selection were performed using the Mann-Whitney U-test, Spearman correlation analysis, and the least absolute shrinkage and selection operator (LASSO) regression. We then input the final features into the machine learning classifiers for model construction. A nomogram was established by combining the radiomic signature and clinical signature.

Results: A total of 407 participants with 407 lesions were included and categorized into the ovarian endometriomas group (n = 200) and the dermoid cyst group (n = 207). In the test cohort, Logistic Regression (LR) achieved the highest area under curve (AUC) value (0.981, 95% CI: 0.963-1.000), the highest accuracy (94.8%), and the highest sensitivity (95.5%), while LightGBM achieved the highest specificity (97.1%). A nomogram incorporating both clinical features and radiomic features achieved the highest level of performance (AUC: 0.987, 95% CI: 0.967-1.000, accuracy: 95.1%, sensitivity: 88.0%, specificity: 100.0%, PPV: 100.0%, NPV: 88.0%, precision: 93.6%). No statistical difference in diagnostic performance was observed between the radiomic model and the nomogram (P > 0.05). The diagnostic indexes of radiomic model were comparable to that of senior radiologists and superior to that of junior radiologist. The diagnostic performance of junior radiologists significantly improved with the assistance of the model.

Conclusion: This ultrasound radiomics-based model demonstrated superior diagnostic performance compared to those of junior radiologists and comparable diagnostic performance to those of senior radiologists, and it has the potential to enhance the diagnostic performance of junior radiologists.

Keywords: artificial intelligence; machine learning; ovarian dermoid cyst; ovarian endometrioma; ultrasound radiomics.

FIGURE 1

Flowchart of the study subjects screening based on inclusion and exclusion criteria.

FIGURE 2

Workflow of ultrasound-based radiomic analysis.

FIGURE 3

Number and ratio of handcrafted features.

FIGURE 4

Statistics of radiomic features.

FIGURE 5

Spearman correlation coefficients between each feature.

FIGURE 6

Coefficients of 10-fold cross-validation based on LASSO algorithm.

FIGURE 7

MSE of 10-fold cross-validation based on LASSO algorithm.

FIGURE 8

Histogram depicting the values of coefficients in the final selected non-zero features.

FIGURE 9

The ROC curves and AUC of different models in the training cohort.

FIGURE 10

The ROC curves and AUC of different models in the test cohort.

FIGURE 11

The nomogram with a total score reflecting the probability of ovarian dermoid cyst.

FIGURE 12

The ROC curves and AUC of the clinical, radiomic, and nomogram models in the training cohort.

FIGURE 13

The ROC curves and AUC of the clinical, radiomic, and nomogram models in the test cohort.

FIGURE 14

The DCA curves for clinical, radiomic, and nomogram models in training cohort.

FIGURE 15

The DCA curves for clinical, radiomic, and nomogram models in test cohort.