A polar transformation augmentation approach for enhancing mammary gland segmentation in ultrasound images

Abstract

Environmental factors can detrimentally affect mammary gland development, leading to negative impacts on milk secretion in mammals. Ultrasonography serves as a non-invasive and non-destructive method for assessing mammary gland characteristics and development. Deep learning approaches enable automated monitoring of mammary gland development, though they typically require large, labeled datasets that may be limited by data collection constraints. This study aimed to develop and evaluate a polar transformation-based augmentation strategy to enhance the performance of deep learning algorithms for mammary gland segmentation in small datasets. We collected 405 ultrasound images of mammary glands (front and rear quarters) from 29 crossbred F1 Holstein x Gyr calves aged 5 to 11 weeks. The parenchyma tissue in these images was manually annotated using the VGG Image Annotator. A leave-one-animal-out cross-validation approach was employed to train the semantic segmentation algorithm. In this approach, all images from one calf were used as a testing set, and images from the remaining 28 calves were used for training in each of the 29 iterations. Our proposed method involved utilizing a polar transform technique for data augmentation in ultrasound images and the PSPNet deep learning algorithm for image segmentation. The average F1-score on the testing set was 54% in week 1, 70% in week 2, and 75% in week 3. Our findings revealed that the algorithm’s performance was suboptimal for images with very small parenchyma (week 1). However, as the mammary gland developed, the identification and segmentation of parenchymal tissue significantly improved. The performance of deep learning algorithms in segmenting small tissues could potentially be enhanced by using larger datasets and higher resolution images. In conclusion, our study demonstrates that polar transformation is an effective strategy for augmenting mammary gland ultrasound images, which in turn improves the performance of deep neural networks in segmenting parenchymal tissue.