This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.

/pdf/deep-learning-in-medical-image-analysis-4jwausnkq2.pdf

Deep Learning in Medical Image Analysis

Deep convolutional neural networks for multi-modality isointense infant brain image segmentation.

https://hal.archives-ouvertes.fr/hal-02433855/document

The early development of brain white matter: A review of imaging studies in fetuses, newborns and infants

Automatic segmentation in MR brain images is important for quantitative analysis in large-scale studies with images acquired at all ages. This paper presents a method for the automatic segmentation of MR brain images into a number of tissue classes using a convolutional neural network. To ensure that the method obtains accurate segmentation details as well as spatial consistency, the network uses multiple patch sizes and multiple convolution kernel sizes to acquire multi-scale information about each voxel. The method is not dependent on explicit features, but learns to recognise the information that is important for the classification based on training data. The method requires a single anatomical MR image only. The segmentation method is applied to five different data sets: coronal $ {\rm T}_{2}$ -weighted images of preterm infants acquired at 30 weeks postmenstrual age (PMA) and 40 weeks PMA, axial $ {\rm T}_{2}$ -weighted images of preterm infants acquired at 40 weeks PMA, axial $ {\rm T}_{1}$ -weighted images of ageing adults acquired at an average age of 70 years, and $ {\rm T}_{1}$ -weighted images of young adults acquired at an average age of 23 years. The method obtained the following average Dice coefficients over all segmented tissue classes for each data set, respectively: 0.87, 0.82, 0.84, 0.86, and 0.91. The results demonstrate that the method obtains accurate segmentations in all five sets, and hence demonstrates its robustness to differences in age and acquisition protocol.

Automatic Segmentation of MR Brain Images With a Convolutional Neural Network

Background— Adverse neurodevelopmental outcome is an important source of morbidity in children with congenital heart disease (CHD). A significant proportion of newborns with complex CHD have abnormalities of brain size, structure, or function, which suggests that antenatal factors may contribute to childhood neurodevelopmental morbidity. Methods and Results— Brain volume and metabolism were compared prospectively between 55 fetuses with CHD and 50 normal fetuses with the use of 3-dimensinal volumetric magnetic resonance imaging and proton magnetic resonance spectroscopy. Fetal intracranial cavity volume, cerebrospinal fluid volume, and total brain volume were measured by manual segmentation. Proton magnetic resonance spectroscopy was used to measure the cerebral N-acetyl aspartate: choline ratio (NAA:choline) and identify cerebral lactate. Complete fetal echocardiograms were performed. Gestational age at magnetic resonance imaging ranged from 25\batchmode \documentclass[fleqn,10pt,legalpaper]{article} \us...

Brain Volume and Metabolism in Fetuses With Congenital Heart Disease Evaluation With Quantitative Magnetic Resonance Imaging and Spectroscopy

Automatic segmentation and reconstruction of the cortex from neonatal MRI.

Motion degrades magnetic resonance (MR) images and prevents acquisition of self-consistent and high-quality volume images. A novel methodology, Snapshot magnetic resonance imaging (MRI) with volume reconstruction (SVR) has been developed for imaging moving subjects at high resolution and high signal-to-noise ratio (SNR). The method combines registered 2D slices from sequential dynamic single-shot scans. The SVR approach requires that the anatomy in question is not changing shape or size and is moving at a rate that allows snapshot images to be acquired. After imaging the target volume repeatedly to guarantee sufficient sampling every where, a robust slice-to-volume registration method has been implemented that achieves alignment of each slice within 0.3 mm in the examples tested. Multilevel scattered interpolation has been used to obtain high-fidelity reconstruction with root-mean-square (rms) error that is less than the noise level in the images. The SVR method has been performed successfully for brain studies on subjects that cannot stay still, and in some cases were moving substantially during scanning. For example, awake neonates, deliberately moved adults and, especially, on fetuses, for which no conventional high-resolution 3D method is currently available. Fine structure of the in-utero fetal brain is clearly revealed for the first time and substantial SNR improvement is realized by having many individually acquired slices contribute to each voxel in the reconstructed image.

MRI of Moving Subjects Using Multislice Snapshot Images With Volume Reconstruction (SVR): Application to Fetal, Neonatal, and Adult Brain Studies

We present a methodology to achieve 3D high-resolution diffusion tensor image reconstruction of the brain in moving subjects. The source data is diffusion-sensitized single-shot echo-planar images. After continuous scanning to acquire a repeated series of parallel slices with 15 diffusion directions, image registration is used to realign the images to correct for subject motion. Once aligned, the diffusion images are treated as irregularly-sampled data where each voxel is associated with an appropriately rotated diffusion direction. This data is used to estimate the diffusion tensor on a regular grid. The method has been tested on data acquired at 1.5T from adults who deliberately moved and from eight fetuses imaged in utero. Maps of apparent diffusion coefficient (ADC) were reliably produced in all cases and promising performance was achieved for fractional anisotropy maps. Results from normal fetal brains were found to be consistent with published data from premature infants of similar gestational age.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/mrm.22032

Diffusion tensor imaging (DTI) of the brain in moving subjects: application to in-utero fetal and ex-utero studies.

Fetal magnetic resonance imaging provides an ideal tool for investigating growth and development of the brain in vivo. Current imaging methods have been hampered by fetal motion but recent advances in image acquisition can produce high signal to noise, high resolution 3-dimensional datasets suitable for objective quantification by state of the art post acquisition computer programs. Continuing development of imaging techniques will allow a unique insight into the developing brain, more specifically process of cell migration, axonal pathway formation, and cortical maturation. Accurate quantification of these developmental processes in the normal fetus will allow us to identify subtle deviations from normal during the second and third trimester of pregnancy either in the compromised fetus or in infants born prematurely.

MR Imaging Methods for Assessing Fetal Brain Development

We present a methodology to achieve 3D high resolution in-utero fetal brain DTI that shows excellent ADC as well as promising FA maps. After continuous DTI scanning to acquire a repeated series of parallel slices with 15 diffusion directions, image registration is used to realign the images to correct for fetal motion. Once aligned, the diffusion images are treated as irregularly sampled data where each voxel is associated with an appropriately rotated diffusion direction, and used to estimate the diffusion tensor on a regular grid. The method has been tested successful on eight fetuses and has been validated on adults imaged at 1.5T.

/pdf/in-utero-three-dimension-high-resolution-fetal-brain-9evpuqzo3s.pdf

Shuzhou Jiang

Papers

Automatic segmentation and reconstruction of the cortex from neonatal MRI.

MRI of Moving Subjects Using Multislice Snapshot Images With Volume Reconstruction (SVR): Application to Fetal, Neonatal, and Adult Brain Studies

Diffusion tensor imaging (DTI) of the brain in moving subjects: application to in-utero fetal and ex-utero studies.

MR Imaging Methods for Assessing Fetal Brain Development

In-utero three dimension high resolution fetal brain diffusion tensor imaging