This paper presents a new approach for contrast enhancement of spinal cord medical images based on multirate scheme incorporated into multiscale retinex algorithm. The proposed work here uses HSV color space, since HSV color space separates color details from intensity. The enhancement of medical image is achieved by down sampling the original image into five versions, namely, tiny, small, medium, fine, and normal scale. This is due to the fact that the each versions of the image when independently enhanced and reconstructed results in enormous improvement in the visual quality. Further, the contrast stretching and MultiScale Retinex (MSR) techniques are exploited in order to enhance each of the scaled version of the image. Finally, the enhanced image is obtained by combining each of these scales in an efficient way to obtain the composite enhanced image. The efficiency of the proposed algorithm is validated by using a wavelet energy metric in the wavelet domain. Reconstructed image using proposed method highlights the details (edges and tissues), reduces image noise (Gaussian and Speckle) and improves the overall contrast. The proposed algorithm also enhances sharp edges of the tissue surrounding the spinal cord regions which is useful for diagnosis of spinal cord lesions. Elaborated experiments are conducted on several medical images and results presented show that the enhanced medical pictures are of good quality and is found to be better compared with other researcher methods.
University College London（伦敦大学学院）；University Hospital Zurich（苏黎世大学医院）；University of Zurich（苏黎世大学）
In this paper we will focus on the potential and on the challenges associated with the development of an integrated brain and spinal cord modelling framework for processing MR neuroimaging data. The aim of the work is to explore how a hierarchical generative model of imaging data, which captures simultaneously the distribution of signal intensities and the variability of anatomical shapes across a large population of subjects, can serve to quantitatively investigate, in vivo, the morphology of the central nervous system (CNS). In fact, the generality of the proposed Bayesian approach, which ex…
Polytechnique Montreal（蒙特利尔高等理工学院）；Duke University Medical Center（杜克大学医学中心）；University of California San Francisco（加州大学旧金山分校）；Université de Montréal（蒙特利尔大学）
Gray matter (GM) tissue changes have been associated with a wide range of neurological disorders and was also recently found relevant as a biomarker for disability in amyotrophic lateral sclerosis. The ability to automatically segment the GM is, therefore, an important task for modern studies of the spinal cord. In this work, we devise a modern, simple and end-to-end fully automated human spinal cord gray matter segmentation method using Deep Learning, that works both on in vivo and ex vivo MRI acquisitions. We evaluate our method against six independently developed methods on a GM segmentatio…
Polytechnique Montreal（蒙特利尔理工学院）；Mila, Quebec AI Institute（米拉魁北克人工智能研究所）；Beijing Tiantan Hospital, Capital Medical University（首都医科大学附属北京天坛医院）；Université de Montréal（蒙特利尔大学）
Spinal cord tumors lead to neurological morbidity and mortality. Being able to obtain morphometric quantification (size, location, growth rate) of the tumor, edema, and cavity can result in improved monitoring and treatment planning. Such quantification requires the segmentation of these structures into three separate classes. However, manual segmentation of 3-dimensional structures is time-consuming and tedious, motivating the development of automated methods. Here, we tailor a model adapted to the spinal cord tumor segmentation task. Data were obtained from 343 patients using gadolinium-enha…
University of Oxford（牛津大学）；Plexalis Ltd（Plexalis有限公司）
This paper proposes a novel transformer-based model architecture for medical imaging problems involving analysis of vertebrae. It considers two applications of such models in MR images: (a) detection of spinal metastases and the related conditions of vertebral fractures and metastatic cord compression, (b) radiological grading of common degenerative changes in intervertebral discs. Our contributions are as follows: (i) We propose a Spinal Context Transformer (SCT), a deep-learning architecture suited for the analysis of repeated anatomical structures in medical imaging such as vertebral bodies…
U2AD: Uncertainty-based Unsupervised Anomaly Detection Framework for Detecting T2 Hyperintensity in MRI Spinal Cord
School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）；Renji Hospital, School of Medicine, Shanghai Jiao Tong University（上海交通大学医学院附属仁济医院）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属瑞金医院）；National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy (NERC-AMRT)（先进磁共振诊疗技术国家工程研究中心）；Med-X Research Institute, Shanghai Jiao Tong University（上海交通大学Med-X研究院）
Polytechnique Montreal（蒙特利尔理工学院）；University of Montreal（蒙特利尔大学）；Zuckerberg San Francisco General Hospital（扎克伯格旧金山综合医院）；University of California（加利福尼亚大学）；Montreal Neurological Institute（蒙特利尔神经学研究所）；Capital Medical University（首都医科大学）；Xuanwu Hospital（宣武医院）；Beijing Tiantan Hospital（北京天坛医院）；Karolinska Institutet（卡罗林斯卡学院）；Massachusetts General Hospital（麻省总医院）；CHU Rennes（雷恩大学医学中心）；Univ Rennes（雷恩大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Inserm（法国国家健康与医学研究院）；IRISA（法国计算机与随机系统研究所）；University Hospital of Montpellier（蒙彼利埃大学医院）
The spinal cord is frequently affected by atrophy and/or lesions in multiple sclerosis (MS) patients. Segmentation of the spinal cord and lesions from MRI data provides measures of damage, which are key criteria for the diagnosis, prognosis, and longitudinal monitoring in MS. Automating this operation eliminates inter-rater variability and increases the efficiency of large-throughput analysis pipelines. Robust and reliable segmentation across multi-site spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts. The goal of this study…
Monitoring morphometric drift in lifelong learning segmentation of the spinal cord
Polytechnique Montreal（蒙特利尔理工学院）；Mila - Quebec AI Institute（魁北克人工智能研究所）；Palacký University Olomouc（帕拉茨基大学奥洛穆茨）；Physikalisch-Technische Bundesanstalt（德国联邦物理技术研究院）；Max Planck Institute for Human Development（马克斯·普朗克人类发展研究所）；Rennes University Hospital（雷恩大学医院）；University Hospital Brno（布尔诺大学医院）；Masaryk University（马萨里克大学）；Aix-Marseille Univ（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）；APHM（马赛公共医院援助）；University College London（伦敦大学学院）；Vanderbilt University Medical Center（范德堡大学医学中心）；Balgrist University Hospital（巴尔格里斯特大学医院）；University of Zurich（苏黎世大学）；Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）
University of Basel（巴塞尔大学）；University Hospital Basel（巴塞尔大学医院）
The small butterfly shaped structure of spinal cord (SC) gray matter (GM) is challenging to image and to delinate from its surrounding white matter (WM). Segmenting GM is up to a point a trade-off between accuracy and precision. We propose a new pipeline for GM-WM magnetic resonance (MR) image acquisition and segmentation. We report superior results as compared to the ones recently reported in the SC GM segmentation challenge and show even better results using the averaged magnetization inversion recovery acquisitions (AMIRA) sequence. Scan-rescan experiments with the AMIRA sequence show high …
Longitudinal tracking of multiple sclerosis lesions in the spinal cord: A validation study
Polytechnique Montreal（蒙特利尔理工学院）；TUM University Hospital（慕尼黑工业大学附属医院）；University of British Columbia（不列颠哥伦比亚大学）；University of Calgary（卡尔加里大学）；University of Toronto（多伦多大学）；Université de Montréal（蒙特利尔大学）；University of Alberta（阿尔伯塔大学）
Rootlets-based registration to the spinal cord PAM50 template
Polytechnique Montreal（蒙特利尔理工学院）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Palacký University Olomouc（帕拉茨基大学奥洛穆茨分校）；Stanford School of Medicine（斯坦福医学院）；Italian National Institute of Health（意大利国家卫生研究院）；Université de Montréal（蒙特利尔大学）；Centre de Recherche du CHU Sainte-Justine（圣贾斯汀大学医学中心研究中心）
Automatic Segmentation of the Spinal Cord Nerve Rootlets
Polytechnique Montreal（蒙特利尔高等理工学院）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Palacký University Olomouc（奥洛穆茨帕拉茨基大学）；CNRS – Aix Marseille Université（法国国家科学研究中心-艾克斯-马赛大学）；King’s College London（伦敦国王学院）；University College London（伦敦大学学院）；Université de Montréal（蒙特利尔大学）；Centre de Recherche du CHU Sainte-Justine, Université de Montréal（圣贾斯汀大学医院研究中心，蒙特利尔大学）
Towards contrast-agnostic soft segmentation of the spinal cord
NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montréal（神经Poly实验室，生物医学工程学院，蒙特利尔理工学院）；Mila - Québec Artificial Intelligence Institute（魁北克人工智能研究所）；Translational Imaging in Neurology (ThINK) Basel（神经学转化成像（ThINK）巴塞尔）；Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel（生物医学工程系，医学学院，巴塞尔大学医院和巴塞尔大学）；Department of Neurology, University Hospital Basel（神经病学系，巴塞尔大学医院）；Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel（临床神经免疫学和神经科学巴塞尔研究中心（RC2NB），巴塞尔大学医院和巴塞尔大学）；Neuroradiology Department, Neurocenter of Southern Switzerland, Ospedale Regionale di Lugano（神经放射科，瑞士南部神经中心，卢加诺地区医院）；Department of Physical Medicine and Rehabilitation Physical Therapy Program, University of Colorado School of Medicine（康复医学系，科罗拉多大学医学院物理治疗项目）；Division of Pain Medicine, Department of Anesthesiology, Perioperative, and Pain Medicine, Stanford University School of Medicine（疼痛医学科，麻醉学、围手术期和疼痛医学部，斯坦福大学医学院）；Functional Neuroimaging Unit, CRIUGM, University of Montreal（功能神经影像单元，CRIUGM，蒙特利尔大学）
SCIsegV2: A Universal Tool for Segmentation of Intramedullary Lesions in Spinal Cord Injury
Polytechnique Montreal（蒙特利尔大学）；Mila - Quebec AI Institute（魁北克人工智能研究所）；Palacký University Olomouc（奥洛穆茨帕拉茨基大学）；University of Zürich（苏黎世大学）；Stanford University School of Medicine（斯坦福大学医学院）；University of Colorado School of Medicine（科罗拉多大学医学院）；Max Planck Institute for Human Cognitive and Brain Sciences（人类认知与脑科学(Max Planck)研究所）；CHU Sainte-Justine, Université de Montréal（蒙特利尔大学圣-让医院）；Functional Neuroimaging Unit, CRIUGM, Université de Montréal（蒙特利尔大学功能神经影像单元）
Aix Marseille Univ（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）；CRMBM（生物医学与医学影像学研究中心）；APHM（Assistance Publique - Hôpitaux de Marseille（马赛公立医院系统））；CHU Timone（蒂莫讷大学医院）；CEMEREM（马赛医学研究中心）；NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montréal（蒙特利尔理工大学生物医学工程系NeuroPoly实验室）；MILA - Québec AI Institute（魁北克人工智能研究所（MILA））
The spinal cord (SC), which conveys information between the brain and the peripheral nervous system, plays a key role in various neurological disorders such as multiple sclerosis (MS) and amyotrophic lateral sclerosis (ALS), in which both gray matter (GM) and white matter (WM) may be impaired. While automated methods for WM/GM segmentation are now largely available, these techniques, developed for conventional systems (3T or lower) do not necessarily perform well on 7T MRI data, which feature finer details, contrasts, but also different artifacts or signal dropout. The primary goal of this stu…
A Personalized Video-Based Hand Taxonomy: Application for Individuals with Spinal Cord Injury
Institute of Biomedical Engineering, University of Toronto（多伦多大学生物医学工程研究所）；Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto（多伦多大学爱德华·S·罗杰斯 Sr. 电气与计算机工程系）；Vector Institute（向量研究所）；Department of Computer Science, University of Toronto（多伦多大学计算机科学系）
SpineReport: Automated 3D Quantification and Reporting of Lumbar Spine Degeneration on MRI
NeuroPoly, Institute of Biomedical Engineering, Polytechnique Montreal（NeuroPoly，生物医学工程研究所，蒙特利尔大学）；Mila, Quebec AI Institute, Montreal（Mila，魁北克人工智能研究所，蒙特利尔）；Department of Radiology, Balgrist University Hospital, Zurich（放射科，巴尔格里斯大学医院，苏黎世）；Faculty of Medicine, University of Zurich（医学学院，苏黎世大学）；Department of Neurosurgery, Brain & Spine, University of South Florida（神经外科，脑与脊柱，佛罗里达大学）；Center for Neuromusculoskeletal Research, University of South Florida（神经肌肉研究中心，佛罗里达大学）；Department of Medical Engineering, University of South Florida（医学工程系，佛罗里达大学）；Stanford School of Medicine, Stanford（斯坦福医学院，斯坦福）；Functional Neuroimaging Unit, CRIUGM, Université de Montréal（功能神经影像单元，CRIUGM，蒙特利尔大学）；Centre de recherche du CHU Sainte-Justine, Université de Montréal（圣若泽中心研究，蒙特利尔大学）
Polytechnique Montreal（蒙特利尔综合理工学院）；Ecole Centrale de Lille（里尔中央理工学院）；Ecole Centrale de Nantes（南特中央理工学院）；Université de Montréal（蒙特利尔大学）
Segmentation of axon and myelin from microscopy images of the nervous system provides useful quantitative information about the tissue microstructure, such as axon density and myelin thickness. This could be used for instance to document cell morphometry across species, or to validate novel non-invasive quantitative magnetic resonance imaging techniques. Most currently-available segmentation algorithms are based on standard image processing and usually require multiple processing steps and/or parameter tuning by the user to adapt to different modalities. Moreover, only few methods are publicly…
NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal（蒙特利尔理工学院生物医学工程研究所NeuroPoly实验室）；Mila - Quebec AI Institute（Mila-魁北克人工智能研究所）；Functional Neuroimaging Unit, CRIUGM, Université de Montréal（蒙特利尔大学CRIUGM功能神经影像单元）
While multiple studies have explored the relation between inter-rater variability and deep learning model uncertainty in medical segmentation tasks, little is known about the impact of individual rater style. This study quantifies rater style in the form of bias and consistency and explores their impacts when used to train deep learning models. Two multi-rater public datasets were used, consisting of brain multiple sclerosis lesion and spinal cord grey matter segmentation. On both datasets, results show a correlation ($R^2 = 0.60$ and $0.93$) between rater bias and deep learning uncertainty. T…
Measuring hand use in the home after cervical spinal cord injury using egocentric video
KITE Research Institute, University Health Network（KITE研究所（大学健康网络））；The BioRobotics Institute, Scuola Superiore Sant’Anna（圣安娜高等学校生物机器人研究所）；Institute of Biomedical Engineering, University of Toronto（多伦多大学生物医学工程研究所）；Sunnybrook Research Institute, Sunnybrook Health Sciences Centre（桑尼布鲁克健康科学中心桑尼布鲁克研究所）；Temerty Faculty of Medicine, University of Toronto（多伦多大学特默蒂医学院）；Brain and Spinal Cord Rehabilitation Program, Toronto Rehabilitation Institute – University Health Network（大学健康网络多伦多康复研究所脑与脊髓康复项目）；Department of Physical Therapy, University of Toronto（多伦多大学物理治疗系）；Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto（多伦多大学爱德华·S·罗杰斯 Sr. 电气与计算机工程系）
SPINEPS -- Automatic Whole Spine Segmentation of T2-weighted MR images using a Two-Phase Approach to Multi-class Semantic and Instance Segmentation
Technical University of Munich（慕尼黑工业大学）；Klinikum rechts der Isar（伊萨尔河右岸医院）；University of Zurich（苏黎世大学）；Imperial College London（帝国理工学院）；Helmholtz Munich（亥姆霍兹慕尼黑中心）；University Medical Center Rostock（罗斯托克大学医学中心）；University of Freiburg（弗赖堡大学）；University Hospital Augsburg（奥格斯堡大学医院）；Augsburg University（奥格斯堡大学）
National University of Singapore（新加坡国立大学）；National University Hospital（国立大学医院）；Zhejiang University（浙江大学）
In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can adaptively leverage the cluster assumption and consistency regularization of the unlabeled data according to the current learning status. This strategy can adaptively generate one-hot "hard" labels converted from task model predictions for better task model training. (2) For the unselected unlabeled images with low confidence, we introduce an Active learning (AL) …
Georgia Institute of Technology（佐治亚理工学院）；Emory University（埃默里大学）；Georgia Tech Research Institute（佐治亚理工研究院）
This paper presents a method of navigating a surgical robot beyond the resolution of magnetic resonance imaging (MRI) by using a resolution enhancement technique enabled by high-precision piezoelectric actuation. The surgical robot was specifically designed for injecting stem cells into the spinal cord. This particular therapy can be performed in a shorter time by using a MRI-compatible robotic platform than by using a manual needle positioning platform. Imaging resolution of fiducial markers attached to the needle guide tubing was enhanced by reconstructing a high-resolution image from multip…
Korea Institute of Science and Technology（韩国科学技术研究院）；Korea University of Science and Technology（韩国科学技术大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
There has been a significant increase from 2010 to 2016 in the number of people suffering from spine problems. The automatic image segmentation of the spine obtained from a computed tomography (CT) image is important for diagnosing spine conditions and for performing surgery with computer-assisted surgery systems. The spine has a complex anatomy that consists of 33 vertebrae, 23 intervertebral disks, the spinal cord, and connecting ribs. As a result, the spinal surgeon is faced with the challenge of needing a robust algorithm to segment and create a model of the spine. In this study, we develo…
Polytechnique Montreal（蒙特利尔理工学院）；Mila, Quebec AI Institute（魁北克人工智能研究所米拉）；Beijing Tiantan Hospital, Capital Medical University（首都医科大学附属北京天坛医院）；Stanford University Center for Artificial Intelligence in Medicine & Imaging（斯坦福大学医学与影像人工智能中心）；University of Montreal（蒙特利尔大学）
Medical images are often accompanied by metadata describing the image (vendor, acquisition parameters) and the patient (disease type or severity, demographics, genomics). This metadata is usually disregarded by image segmentation methods. In this work, we adapt a linear conditioning method called FiLM (Feature-wise Linear Modulation) for image segmentation tasks. This FiLM adaptation enables integrating metadata into segmentation models for better performance. We observed an average Dice score increase of 5.1% on spinal cord tumor segmentation when incorporating the tumor type with FiLM. The m…
