This paper presents a fully automated algorithm for segmentation of multiple sclerosis (MS) lesions from multispectral magnetic resonance (MR) images. The method performs intensity-based tissue classification using a stochastic model for normal brain images and simultaneously detects MS lesions as outliers that are not well explained by the model. It corrects for MR field inhomogeneities, estimates tissue-specific intensity models from the data itself, and incorporates contextual information in the classification using a Markov random field. The results of the automated method are compared with lesion delineations by human experts, showing a high total lesion load correlation. When the degree of spatial correspondence between segmentations is taken into account, considerable disagreement is found, both between expert segmentations, and between expert and automatic measurements.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/42.938237 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Interventricular septal dissection secondary to acute inferior myocardial infarction: case series and literature review.
J Cardiothorac Surg
January 2025
Echocardiography and Vascular Ultrasound Center, The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qingchun Road, Hangzhou, 310003, China.
Background: Interventricular septal dissection is a critical disease characterized by the separation of the intraventricular septum into two layers, forming an intermediate layer with a cystic cavity that communicates with the root of the aorta or ventricle. It has low morbidity and high mortality rates.
Case Presentation: Case 1: A 58-year-old male with a history of hypertension and smoking presented to a local hospital due to chest tightness and pain for 4 days.
Genome-wide identification of the Sec14 gene family and the response to salt and drought stress in soybean (Glycine max).
BMC Genomics
January 2025
Henan Collaborative Innovation Center of Modern Biological Breeding, College of Agronomy, Henan Institute of Science and Technology, Xinxiang, 453003, China.
Background: The Sec14 domain is an ancient lipid-binding domain that evolved from yeast Sec14p and performs complex lipid-mediated regulatory functions in subcellular organelles and intracellular traffic. The Sec14 family is characterized by a highly conserved Sec14 domain, and is ubiquitously expressed in all eukaryotic cells and has diverse functions. However, the number and characteristics of Sec14 homologous genes in soybean, as well as their potential roles, remain understudied.
View Article and Find Full Text PDFDeep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach.
Sci Rep
January 2025
Department of Electrical Electronical Engineering, Yaşar University, Bornova, İzmir, Turkey.
We aimed to build a robust classifier for the MGMT methylation status of glioblastoma in multiparametric MRI. We focused on multi-habitat deep image descriptors as our basic focus. A subset of the BRATS 2021 MGMT methylation dataset containing both MGMT class labels and segmentation masks was used.
View Article and Find Full Text PDFAssessment of corneal vessels activity through the 'Barcode sign' of corneal OCT.
Eye (Lond)
January 2025
Division of Clinical Neuroscience, Department of Ophthalmology, University of Nottingham, Nottingham, UK.
Background/objectives: Anterior segment optical Coherence Tomography (AS-OCT) is used extensively in imaging the cornea in health and disease. Our objective was to analyse and monitor corneal vascularisation (CVas) through the corresponding back-shadows visible on AS-OCT.
Subjects/methods: AS-OCT scans were obtained from 26 consecutive patients (eyes) with CVas of different aetiologies.
Automatic segmentation of cortical bone microstructure: Application and analysis of three proximal femur sites.
Bone
January 2025
ARTORG Centre for Biomedical Engineering Research, University of Bern, Bern, Switzerland.
Osteoporosis is the most common bone metabolic unbalance, leading to fragility fractures, which are known to be associated with structural changes in the bone. Cortical bone accounts for 80 % of the skeleton mass and undergoes remodeling throughout life, leading to changes in its thickness and microstructure. Although many studies quantified the different cortical bone structures using CT techniques (3D), they are often realised on a small number of samples.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!