Cross-Modal Guidance Assisted Hierarchical Learning Based Siamese Network for MR Image Denoising

Abstract

Cross-modal medical imaging techniques are predominantly being used in the clinical suite. The ensemble learning methods using cross-modal medical imaging adds reliability to several medical image analysis tasks. Motivated by the performance of deep learning in several medical imaging tasks, a deep learning-based denoising method Cross-Modality Guided Denoising Network CMGDNet for removing Rician noise in T1-weighted (T1-w) Magnetic Resonance Images (MRI) is proposed in this paper. CMGDNet uses a guidance image, which is a cross-modal (T2-w) image of better perceptual quality to guide the model in denoising its noisy T1-w counterpart. This cross-modal combination allows the network to exploit complementary information existing in both images and therefore improve the learning capability of the model. The proposed framework consists of two components: Paired Hierarchical Learning (PHL) module and Cross-Modal Assisted Reconstruction (CMAR) module. PHL module uses Siamese network to extract hierarchical features from dual images, which are then combined in a densely connected manner in the CMAR module to finally reconstruct the image. The impact of using registered guidance data is investigated in removing noise as well as retaining structural similarity with the original image. Several experiments were conducted on two publicly available brain imaging datasets available on the IXI database. The quantitative assessment using Peak Signal to noise ratio (PSNR), Structural Similarity Index (SSIM), and Feature Similarity Index (FSIM) demonstrates that the proposed method exhibits 4.7% and 2.3% gain (average), respectively, in SSIM and FSIM values compared to other state-of-the-art denoising methods that do not integrate cross-modal image information in removing various levels of noise.

Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging—State-of-the-Art and Challenges

“…Apart from these, a ten-layer CNN [102], multi-channel residual learning CNN [103], CNN-DMRI [104], HydraNet [105], NNDnet [106], CMGDNet [107], 3D-Parallel-RicianNet [108], and a patch-based CNN [109] have been developed for accurate MRI denoising. Several other recent works incorporated CNN-based solutions for brain MRI denoising [110][111][112][113][114][115].…”

Machine Learning Technologies for Big Data Analytics

“…In this paper [1], a deep learning-based denoising approach Cross-Modality Guided Denoising Network (CMGDNet) for reducing Rician noise in T1-weighted (T1-w) magnetic resonance images (MRI) is suggested, motivated by deep learning performance in numerous medical imaging applications.…”

Contrast enhancement: Cross-modal learning approach for medical images

“…It not only endorses the initial diagnosis, moreover, it also provides complementary information that can play an influential role in several stages of diagnosis and treatment. The multi-modal image information has been utilized to solve various problems in medical imaging such as segmentation, detection and denoising [29,7,19]. The complementary information equips the image analysis tasks with additional capability enabling these methods to outperform those that rely on single images for these tasks [8,22].…”