José E. Romero

Nonlocal intracranial cavity extraction

Automatic and accurate methods to estimate normalized regional brain volumes from MRI data are valuable tools which may help to obtain an objective diagnosis and followup of many neurological diseases. To estimate such regional brain volumes, the intracranial cavity volume (ICV) is often used for normalization. However, the high variability of brain shape and size due to normal intersubject variability, normal changes occurring over the lifespan, and abnormal changes due to disease makes the ICV estimation problem challenging. In this paper, we present a new approach to perform ICV extraction based on the use of a library of prelabeled brain images to capture the large variability of brain shapes. To this end, an improved nonlocal label fusion scheme based on BEaST technique is proposed to increase the accuracy of the ICV estimation. The proposed method is compared with recent state-of-the-art methods and the results demonstrate an improved performance both in terms of accuracy and reproducibility while maintaining a reduced computational burden.

CERES: A new cerebellum lobule segmentation method

ABSTRACT The human cerebellum is involved in language, motor tasks and cognitive processes such as attention or emotional processing. Therefore, an automatic and accurate segmentation method is highly desirable to measure and understand the cerebellum role in normal and pathological brain development. In this work, we propose a patch‐based multi‐atlas segmentation tool called CERES (CEREbellum Segmentation) that is able to automatically parcellate the cerebellum lobules. The proposed method works with standard resolution magnetic resonance T1‐weighted images and uses the Optimized PatchMatch algorithm to speed up the patch matching process. The proposed method was compared with related recent state‐of‐the‐art methods showing competitive results in both accuracy (average DICE of 0.7729) and execution time (around 5 minutes). HIGHLIGHTSWe present a novel method for cerebellum lobule segmentation on MRI.The method consists of a fast multi‐atlas non‐local patch‐based label fusion.Our proposed method was shown to improve the state‐of‐the‐art methods with a reduced temporal cost (5 minutes).The pipeline presented in this work will be made available to scientific community through our web ‐based platform volBrain.

NABS: non-local automatic brain hemisphere segmentation

In this paper, we propose an automatic method to segment the five main brain sub-regions (i.e. left/right hemispheres, left/right cerebellum and brainstem) from magnetic resonance images. The proposed method uses a library of pre-labeled brain images in a stereotactic space in combination with a non-local label fusion scheme for segmentation. The main novelty of the proposed method is the use of a multi-label block-wise label fusion strategy specifically designed to deal with the classification of main brain sub-volumes that process only specific parts of the brain images significantly reducing the computational burden. The proposed method has been quantitatively evaluated against manual segmentations. The evaluation showed that the proposed method was faster while producing more accurate segmentations than a current state-of-the-art method. We also present evidences suggesting that the proposed method was more robust against brain pathologies than the compared method. Finally, we demonstrate the clinical value of our method compared to the state-of-the-art approach in terms of the asymmetry quantification in Alzheimers disease.

Regional hippocampal vulnerability in early multiple sclerosis: Dynamic pathological spreading from dentate gyrus to CA1

Whether hippocampal subfields are differentially vulnerable at the earliest stages of multiple sclerosis (MS) and how this impacts memory performance is a current topic of debate.

HIPS: A new hippocampus subfield segmentation method

&NA; The importance of the hippocampus in the study of several neurodegenerative diseases such as Alzheimers disease makes it a structure of great interest in neuroimaging. However, few segmentation methods have been proposed to measure its subfields due to its complex structure and the lack of high resolution magnetic resonance (MR) data. In this work, we present a new pipeline for automatic hippocampus subfield segmentation using two available hippocampus subfield delineation protocols that can work with both high and standard resolution data. The proposed method is based on multi‐atlas label fusion technology that benefits from a novel multi‐contrast patch match search process (using high resolution T1‐weighted and T2‐weighted images). The proposed method also includes as post‐processing a new neural network‐based error correction step to minimize systematic segmentation errors. The method has been evaluated on both high and standard resolution images and compared to other state‐of‐the‐art methods showing better results in terms of accuracy and execution time. Graphical abstract Figure. No caption available. HighlightsWe present a novel method for hippocampus subfield segmentation on MRI.The method consists of a fast multi‐atlas non‐local patch‐based label fusion.Our proposed method was shown to improve the state‐of‐the‐art methods with a reduced temporal cost (20 mins).The pipeline presented in this work will be made available to scientific community through our web ‐based platform volBrain.

High Resolution Hippocampus Subfield Segmentation Using Multispectral Multiatlas Patch-Based Label Fusion

The hippocampus is a brain structure that is involved in several cognitive functions such as memory and learning. It is a structure of great interest due to its relationship to neurodegenerative processes such as the Alzheimer’s disease. In this work, we propose a novel multispectral multiatlas patch-based method to automatically segment hippocampus subfields using high resolution T1-weighted and T2-weighted magnetic resonance images (MRI). The proposed method works well also on standard resolution images after superresolution and consistently performs better than monospectral version. Finally, the proposed method was compared with similar state-of-the-art methods showing better results in terms of both accuracy and efficiency.

Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images

&NA; The human cerebellum plays an essential role in motor control, is involved in cognitive function (i.e., attention, working memory, and language), and helps to regulate emotional responses. Quantitative in‐vivo assessment of the cerebellum is important in the study of several neurological diseases including cerebellar ataxia, autism, and schizophrenia. Different structural subdivisions of the cerebellum have been shown to correlate with differing pathologies. To further understand these pathologies, it is helpful to automatically parcellate the cerebellum at the highest fidelity possible. In this paper, we coordinated with colleagues around the world to evaluate automated cerebellum parcellation algorithms on two clinical cohorts showing that the cerebellum can be parcellated to a high accuracy by newer methods. We characterize these various methods at four hierarchical levels: coarse (i.e., whole cerebellum and gross structures), lobe, subdivisions of the vermis, and the lobules. Due to the number of labels, the hierarchy of labels, the number of algorithms, and the two cohorts, we have restricted our analyses to the Dice measure of overlap. Under these conditions, machine learning based methods provide a collection of strategies that are efficient and deliver parcellations of a high standard across both cohorts, surpassing previous work in the area. In conjunction with the rank‐sum computation, we identified an overall winning method.

LesionBrain: An Online Tool for White Matter Lesion Segmentation

In this paper, we present a new tool for white matter lesion segmentation called lesionBrain. Our method is based on a 3-stage strategy including multimodal patch-based segmentation, patch-based regularization of probability map and patch-based error correction using an ensemble of shallow neural networks. Its robustness and accuracy have been evaluated on the MSSEG challenge 2016 datasets. During our validation, the performance obtained by lesionBrain was competitive compared to recent deep learning methods. Moreover, lesionBrain proposes automatic lesion categorization according to location. Finally, complementary information on gray matter atrophy is included in the generated report. LesionBrain follows a software as a service model in full open access.

Non-local MRI Library-Based Super-Resolution: Application to Hippocampus Subfield Segmentation

Magnetic Resonance Imaging (MRI) has become one of the most used techniques in research and clinical settings. One of the limiting factors of the MRI is the relatively low resolution for some applications. Although new high resolution MR sequences have been proposed recently, usually these acquisitions require long scanning times which is not always possible neither desirable. Recently, super-resolution techniques have been proposed to alleviate this problem by inferring the underlying high resolution images from low resolution acquisitions. We present a new super-resolution technique that takes benefit from the self-similarity properties of the images and the use of a high resolution image library. The proposed method is compared with related state-of-the-art methods showing a significant reconstruction improvement. Finally, we show the advantage of the proposed framework compared to classic interpolation when used for segmentation of hippocampus subfields.