Deep similarity learning for multimodal medical images. Issue 3 (4th May 2018)

• Record Type: Journal Article
• Authors: Cheng, Xi; Zhang, Li; Zheng, Yefeng
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 6:Issue 3(2018)
• Page Start: 248
• Page End: 252
• Publication Date: 2018-05-04
• Subjects: Multi-modal medical images -- deep neural network -- multi-modal denoising autoencoder -- similarity metric learning; Imaging systems in biology -- Periodicals; Imaging systems in medicine -- Periodicals; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; 616.0757
• DOI: 10.1080/21681163.2015.1135299
• Languages: English
• ISSNs: 2168-1163

Abstract

Abstract : An effective similarity measure for multi-modal images is crucial for medical image fusion in many clinical applications. The underlining correlation across modalities is usually too complex to be modelled by intensity-based statistical metrics. Therefore, approaches of learning a similarity metric are proposed in recent years. In this work, we propose a novel deep similarity learning method that trains a binary classifier to learn the correspondence of two image patches. The classification output is transformed to a continuous probability value, then used as the similarity score. Moreover, we propose to utilise multi-modal stacked denoising autoencoder to effectively pre-train the deep neural network. We train and test the proposed metric using sampled corresponding/non-corresponding computed tomography and magnetic resonance head image patches from a same subject. Comparison is made with two commonly used metrics: normalised mutual information and local cross correlation. The contributions of the multi-modal stacked denoising autoencoder and the deep structure of the neural network are also evaluated. Both the quantitative and qualitative results from the similarity ranking experiments show the advantage of the proposed metric for a highly accurate and robust similarity measure.