Machine Learning for Medical Image Analysis
Multi-instance deep learning of ultrasound imaging data for pattern classification of congenital abnormalities of the kidney and urinary tract in children
This package contains deep learning tools for instance-level classification of congenital abnormalities of the kidney and urinary tract (CAKUT), as described in the following papers:
- Shi Yin, Qinmu Peng, Hongming Li, Zhengqiang Zhang, Xinge You, Katherine Fischer, Susan L Furth, Yong Fan, Gregory E Tasian. Multi-instance Deep Learning of Ultrasound Imaging Data for Pattern Classification of Congenital Abnormalities of the Kidney and Urinary Tract in Children. Urology. 2020 Aug;142:183-189. doi: 10.1016/j.urology.2020.05.019. Epub 2020 May 20. PMID: 32445770; PMCID: PMC7387180.
- Shi Yin, Qinmu Peng, Hongming Li, Zhengqiang Zhang, Xinge You, Katherine Fischer, Susan L Furth, Gregory E Tasian, Yong Fan. Computer-Aided Diagnosis of Congenital Abnormalities of the Kidney and Urinary Tract in Children Using a Multi-Instance Deep Learning Method Based on Ultrasound Imaging Data. Proc IEEE Int Symp Biomed Imaging. 2020 Apr;2020:1347-1350. doi: 10.1109/isbi45749.2020.9098506. Epub 2020 May 22. PMID: 33850604; PMCID: PMC8040672.
Classification Of Morphological Patterns using Adaptive Regional Elements (COMPARE)
COMPARE is a method for classification of structural brain magnetic resonance (MR) images, which is a combination of deformation-based morphometry and machine learning methods. Before running classification, a morphological representation of the anatomy of interest is obtained from structural MR brain images using a high-dimensional mass-preserving template warping method [1, 2]. Regions that display strong correlations between tissue volumes and classification (clinical) variables learned from training samples are extracted using a watershed segmentation algorithm. To achieve robustness to outliers, the regional smoothness of the correlation map is estimated by a cross-validation strategy. A volume increment algorithm is then applied to these regions to extract regional volumetric features. To improve efficiency and generalization ability of the classification, a feature selection technique using Support Vector Machine-based criteria is used to select the most discriminative features, according to their effect on the upper bound of the leave-one-out generalization error. Finally, SVM-based classification is applied using the best set of features, and it is tested using a leave-one-out cross-validation strategy. Although the algorithm is designed for structural brain image classification, it is readily applicable for functional brain image classification with proper feature images.
- COMPARE: Classification Of Morphological Patterns using Adaptive Regional Elements Yong Fan, Dinggang Shen, Ruben C. Gur, Raquel E. Gur, Christos Davatzikos IEEE Transactions on Medical Imaging, 93-105, Vol. 26, No. 1, 2007