Artificial intelligence in multiparametric magnetic resonance imaging: A review

Abstract

Multiparametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availabilities of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting.However,the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI.

A modality‐collaborative convolution and transformer hybrid network for unpaired multi‐modal medical image segmentation with limited annotations

“…For example, by effectively learning modality-invariant and modalityspecific representations, our method allows employing more modalities (e.g., multiple MR modalities, MR and pathology, MR and PET) to segment various organs (e.g., prostate, brain, breast) and lesion areas (e.g., cancers) from large-scale clinical datasets. 56,57 On the other…”

“…Although our experiments are conducted on the cardiac substructure and abdominal multi‐organ datasets with CT and MR modalities, our proposed approach can be easily extended to other multi‐modal analysis tasks or datasets in clinical practice. For example, by effectively learning modality‐invariant and modality‐specific representations, our method allows employing more modalities (e.g., multiple MR modalities, MR and pathology, MR and PET) to segment various organs (e.g., prostate, brain, breast) and lesion areas (e.g., cancers) from large‐scale clinical datasets 56,57 . On the other hand, by simply adjusting the network architecture and normalization parameters of our method, our method can also be applied in the classification, segmentation, and reconstruction tasks of multi‐site CT or MR datasets 58–60 .…”

Machine learning for automatic Alzheimer’s disease detection: addressing domain shift issues for building robust models

“…Computer-aided diagnosis systems are highly desired to help physicians achieve fast and accurate neuroimaging data analysis. ML techniques have had great success in different fields in recent decades, including medical and neuroimaging fields [25][26][27], and the ability and accuracy of largescale complicated data analyses have been significantly improved due to recent developments in DL techniques [21,[28][29][30][31]. Essential obstacles, however, still prevent the direct and efficient application of DL algorithms in the clinical setting because there are few labeled medical datasets because annotating medical datasets is a labor-intensive, costly, and time-consuming procedure that requires neurologists, neuroradiologists, and other experts [5].…”

Single image denoising based on adaptive fusion dual‐domain network

“…DL-based image denoising models are realized by learning the latent features between noisy and clean images. Meanwhile, the key point of DL-based algorithms [13][14][15] is their independence from explicit imaging models and backup by big data. The two main issues of the DL-based denoising methods are presented as follows.…”