An extended machine learning technique for polycystic ovary syndrome detection using ovary ultrasound image

Abstract

Polycystic ovary syndrome (PCOS) is the most prevalent endocrinological abnormality and one of the primary causes of anovulatory infertility in women globally. The detection of multiple cysts using ovary ultrasonograpgy (USG) scans is one of the most reliable approach for making an accurate diagnosis of PCOS and creating an appropriate treatment plan to heal the patients with this syndrome. Instead of depending on error-prone manual identification, an intelligent computer-aided cyst detection system can be a viable approach. Therefore, in this research, an extended machine learning classification technique for PCOS prediction has been proposed, trained and tested over 594 ovary USG images; where the Convolutional Neural Network (CNN) incorporating different state-of-the-art techniques and transfer learning has been employed for feature extraction from the images; and then stacking ensemble machine learning technique using conventional models as base learners and bagging or boosting ensemble model as meta-learner have been used on that reduced feature set to classify between PCOS and non-PCOS ovaries. The proposed technique significantly enhances the accuracy while also reducing training execution time comparing with the other existing ML based techniques. Again, following the proposed extended technique, the best performing results are obtained by incorporating the "VGGNet16" pre-trained model with CNN architecture as feature extractor and then stacking ensemble model with the meta-learner being "XGBoost" model as image classifier with an accuracy of 99.89% for classification.

Figure 1

Framework of research methodology.

Figure 2

Architecture of deep learning technique and proposed technique.

Figure 3

USG scans with image processing steps.

Figure 4

Accuracy and Loss per epoch for DNN models (technique 3) (a) CNN without transfer learning (b) CNN with VGGNet16 for transfer learning (c) with InceptionV3 for transfer learning (d) with MobileNet for transfer learning (e) with Xception for transfer learning.

Figure 5

Comparative analysis of (a) accuracy and (b) execution time for ML models using different techniques.

Figure 6

AUC-ROC curve for ML models (a) without image pre-processing (technique 1) (b) with image pre-processing (technique 1) (c) with deep learning (technique 3) (d) with proposed technique (technique 4).