Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on Ultrasound imaging data

TL;DR

This paper introduces a transfer learning approach using a pre-trained deep neural network to extract features from ultrasound images, significantly enhancing the diagnosis of congenital kidney abnormalities in children.

Contribution

It presents a novel transfer learning-based feature extraction method combined with conventional features, improving classification accuracy for CAKUT diagnosis from ultrasound images.

Findings

Transfer learning features improve classification accuracy.

Combining transfer learning and conventional features yields best results.

The method outperforms traditional feature-based approaches.

Abstract

Classification of ultrasound (US) kidney images for diagnosis of congenital abnormalities of the kidney and urinary tract (CAKUT) in children is a challenging task. It is desirable to improve existing pattern classification models that are built upon conventional image features. In this study, we propose a transfer learning-based method to extract imaging features from US kidney images in order to improve the CAKUT diagnosis in children. Particularly, a pre-trained deep learning model (imagenet-caffe-alex) is adopted for transfer learning-based feature extraction from 3-channel feature maps computed from US images, including original images, gradient features, and distanced transform features. Support vector machine classifiers are then built upon different sets of features, including the transfer learning features, conventional imaging features, and their combination. Experimental results have demonstrated that the combination of transfer learning features and conventional imaging features yielded the best classification performance for distinguishing CAKUT patients from normal controls based on their US kidney images.