Automated segmentation of muscle fiber images using active contour models

Klemencic, A.; Kovačič, Stanislav; Pernuš, Franjo

doi:10.1002/(sici)1097-0320(19980801)32:4<317::aid-cyto9>3.0.co;2-e

Cited by 48 publications

(38 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, this is the largest and most comprehensive dataset of images analyzed in a neuromuscular study. Previous reports have been published of attempts to facilitate the automated extraction of geometric characteristics from muscle biopsies [11][12][13][14][15][16]. These studies rely on the development of segmentation methods using a very small number of samples to only extract morphometric information.…”

Section: Discussionmentioning

confidence: 99%

“…A large panel of different histochemical and histoenzymatic techniques are necessary to identify pathologic changes in the routine diagnostic process [9,10] (Additional file 1: Figure S1). Previous attempts to automate the extraction of geometrical characteristics from normal muscle biopsies have been published [11][12][13][14][15][16], but those methods fail to provide an automated analysis or adequate scrutiny of the information derived from the analysis. Our analysis begins at this point, taking into account a large number of samples to study both geometrical and network data to include morphometric and organizational information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quantifiable diagnosis of neuromuscular diseases through network analysis

Rivas¹,

Sáez²,

Montero-Sánchez³

et al. 2015

Neuromuscular Disorders

View full text Add to dashboard Cite

Background: The diagnosis of neuromuscular diseases is strongly based on the histological characterization of muscle biopsies. However, this morphological analysis is mostly a subjective process and difficult to quantify. We have tested if network science can provide a novel framework to extract useful information from muscle biopsies, developing a novel method that analyzes muscle samples in an objective, automated, fast and precise manner.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Quantifiable diagnosis of neuromuscular diseases through network analysis

Rivas¹,

Sáez²,

Montero-Sánchez³

et al. 2015

Neuromuscular Disorders

View full text Add to dashboard Cite

show abstract

“…2 In this sense, in the recent literature works related to grading of prostate cancer, 3 detection of cervical cancer, 4 classification of hepatocellular carcicoma, 5 detection of cervical cell nuclei, 6 or simple detection of different types of cells [7][8][9] can be found. Focusing on the studies of muscular fibers, we can find some works that address the segmentation of fibers in muscular biopsies, [10][11][12] the classification of muscle-fiber type, [13][14][15][16] and the extraction of morphometric features. 17 However, studies of the characterization of neuromuscular disease based on image processing have not been found in the current literature.…”

Section: Introductionmentioning

confidence: 99%

Neuromuscular disease classification system

et al. 2013

View full text Add to dashboard Cite

Abstract. Diagnosis of neuromuscular diseases is based on subjective visual assessment of biopsies from patients by the pathologist specialist. A system for objective analysis and classification of muscular dystrophies and neurogenic atrophies through muscle biopsy images of fluorescence microscopy is presented. The procedure starts with an accurate segmentation of the muscle fibers using mathematical morphology and a watershed transform. A feature extraction step is carried out in two parts: 24 features that pathologists take into account to diagnose the diseases and 58 structural features that the human eye cannot see, based on the assumption that the biopsy is considered as a graph, where the nodes are represented by each fiber, and two nodes are connected if two fibers are adjacent. A feature selection using sequential forward selection and sequential backward selection methods, a classification using a Fuzzy ARTMAP neural network, and a study of grading the severity are performed on these two sets of features. A database consisting of 91 images was used: 71 images for the training step and 20 as the test. A classification error of 0% was obtained. It is concluded that the addition of features undetectable by the human visual inspection improves the categorization of atrophic patterns.

show abstract

“…The usability and performance of these semi-automated methods are still limited by inaccurate delineation of fibers as well as the need of special histochemical stains and user interaction (4,6,7). In contrast to these pixel intensity-and pixel gradient-based applications, Klemenčič et al (8) suggested a semi-automated approach based on active contour models. The practicability of this method is restricted by the need of pointing the approximate centroid of each fiber manually by the investigator.…”

mentioning

confidence: 99%

“…Whereas edge based active contours require an accurate contour initialization, which is usually provided by manual interaction, as in Ref. 8, region based active contours depend less on the initialization and can therefore ensure a reliable separation process without manual interaction. This leads to an accurate, fully automated methodology that allows for time-saving batch processing of the entire biopsy samples.…”

mentioning

confidence: 99%

Fully automated segmentation and morphometrical analysis of muscle fiber images

et al. 2007

View full text Add to dashboard Cite

Background: Measurement of muscle fiber size and determination of size distribution is important in the assessment of neuromuscular disease. Fiber size estimation by simple inspection is inaccurate and subjective. Manual segmentation and measurement are time-consuming and tedious. We therefore propose an automated image analysis method for objective, reproducible, and time-saving measurement of muscle fibers in routinely hematoxylineosin stained cryostat sections. Methods: The proposed segmentation technique makes use of recent advances in level set based segmentation, where classical edge based active contours are extended by region based cues, such as color and texture. Segmentation and measurement are performed fully automatically. Multiple morphometric parameters, i.e., cross sectional area, lesser diameter, and perimeter are assessed in a single pass.

show abstract

Automated segmentation of muscle fiber images using active contour models

Cited by 48 publications

References 24 publications

Quantifiable diagnosis of neuromuscular diseases through network analysis

Quantifiable diagnosis of neuromuscular diseases through network analysis

Neuromuscular disease classification system

Fully automated segmentation and morphometrical analysis of muscle fiber images

Contact Info

Product

Resources

About