Charisma: An integrated approach to automatic H&amp;E-stained skeletal muscle cell segmentation using supervised learning and novel robust clump splitting

Janssens, Thomas; Antanas, Laura; Derde, Sarah; Vanhorebeek, Ilse; Berghe, Greet Van den; Güiza, Fabián

doi:10.1016/j.media.2013.07.007

Cited by 33 publications

(20 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To control for potential illness‐ or resuscitation‐related changes in fluid content, dry weight of isolated tissues was obtained by a freeze‐drying process. Myofibre cross‐sectional area (CSA) was quantified on digital microscopy images of haematoxylin and eosin stained paraffin sections with in‐house designed algorithms, as described earlier . In addition, the presence of myofibre degeneration, necrosis, and inflammation was histologically evaluated as described earlier .…”

Section: Methodsmentioning

confidence: 99%

Premorbid obesity, but not nutrition, prevents critical illness‐induced muscle wasting and weakness

Goossens

Marques

Derde

et al. 2016

J cachexia sarcopenia muscle

Self Cite

View full text Add to dashboard Cite

BackgroundThe ‘obesity paradox’ of critical illness refers to better survival with a higher body mass index. We hypothesized that fat mobilized from excess adipose tissue during critical illness provides energy more efficiently than exogenous macronutrients and could prevent lean tissue wasting.MethodsIn lean and premorbidly obese mice, the effect of 5 days of sepsis‐induced critical illness on body weight and composition, muscle wasting, and weakness was assessed, each with fasting and parenteral feeding. Also, in lean and overweight/obese prolonged critically ill patients, markers of muscle wasting and weakness were compared.ResultsIn mice, sepsis reduced body weight similarly in the lean and obese, but in the obese with more fat loss and less loss of muscle mass, better preservation of myofibre size and muscle force, and less loss of ectopic lipids, irrespective of administered feeding. These differences between lean and obese septic mice coincided with signs of more effective hepatic fatty acid and glycerol metabolism, and ketogenesis in the obese. Also in humans, better preservation of myofibre size and muscle strength was observed in overweight/obese compared with lean prolonged critically ill patients.ConclusionsDuring critical illness premorbid obesity, but not nutrition, optimized utilization of stored lipids and attenuated muscle wasting and weakness.

show abstract

Section: Methodsmentioning

confidence: 99%

Premorbid obesity, but not nutrition, prevents critical illness‐induced muscle wasting and weakness

Goossens

Marques

Derde

et al. 2016

J cachexia sarcopenia muscle

Self Cite

View full text Add to dashboard Cite

show abstract

“…Janssens et al [272] have applied a multi-class SVM classifier to cell segmentation on H&E stained skeletal muscle images. It consists of three steps: 1) generate initial segments by thresholding the saturation and the brightness of the image; 2) classify these segments into three categories with a set of features consisting of geometry, texture, bottle measurement, and luminosity: individual cells, cell clumps, and remnant connective tissues; 3) split the cell clumps based on concave point detection [306].…”

Section: Nucleus and Cell Segmentation Methodsmentioning

confidence: 99%

Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review

Xing

Yang

2016

IEEE Rev. Biomed. Eng.

443

220

View full text Add to dashboard Cite

Digital pathology and microscopy image analysis is widely used for comprehensive studies of cell morphology or tissue structure. Manual assessment is labor intensive and prone to inter-observer variations. Computer-aided methods, which can significantly improve the objectivity and reproducibility, have attracted a great deal of interest in recent literatures. Among the pipeline of building a computer-aided diagnosis system, nucleus or cell detection and segmentation play a very important role to describe the molecular morphological information. In the past few decades, many efforts have been devoted to automated nucleus/cell detection and segmentation. In this review, we provide a comprehensive summary of the recent state-of-the-art nucleus/cell segmentation approaches on different types of microscopy images including bright-field, phase-contrast, differential interference contrast (DIC), fluorescence, and electron microscopies. In addition, we discuss the challenges for the current methods and the potential future work of nucleus/cell detection and segmentation.

show abstract

“…Liu et al proposed the adoption of a learning-based seed detection scheme to find the centers of the muscle fibers and then apply a deformable model to find the boundaries of the muscle fibers [10]. Janssens et al designed a top-down multiclass support vector machine (SVM) scheme to segment muscle fibers in the steps of thresholding an image and classifying the segmentation into categories of individual muscle cells, clumps of muscle cells, and remnant connective tissues and then splitting the clumps of muscle cells into individual cells according to [11]. Smith and Barton proposed the use of a smooth filter to first suppress local minimums, followed by watershed transform to segment the boundaries of muscle fibers [6].…”

Section: Introductionmentioning

confidence: 99%

A neural network approach to analyze cross-sections of muscle fibers in pathological images

Wang

et al. 2019

Computers in Biology and Medicine

View full text Add to dashboard Cite

Morphological characteristics of muscle fibers, such as their cross-sections, are important indicators of the health and function of the musculoskeletal system. However, manual analysis of muscle fiber morphology is a labor-intensive and time-consuming process that is prone to errors. Overall, the procedure involves high inter- and intra-observer variability. Therefore, it is desirable for biologists to have a tool that can produce objective and reproducible analysis for muscle fiber images. In this work, we propose a deep convolutional neural network (DCNN) followed by post-processing for detecting and measuring the cross-sections of muscle fibers. We evaluate three segmentation networks for muscle boundary segmentation: (1) U-net, (2) FusionNet, and (3) a customized FusionNet. The customized FusionNet, which had the highest Dice coefficient on the test set, was used for subsequent morphological analysis of the muscle fibers. The proposed method was tested on microscopic images of the tibialis anterior muscles of a pre-clinical model of muscular dystrophy. The dataset contained four mosaic images, each having more than 3500 fibers. Because of the severity of muscle injury in this pre-clinical model, its muscle fiber images present a challenge for quantitative analysis for several reasons. First, the muscle fibers had inhomogeneous spatial distribution and very different sizes. Second, the membranes of the muscle fibers had uneven signal intensity due to the loss of a membrane protein. Third, the shapes of intact muscle fibers were very different. All these factors contributed to the difficulty of acquiring good training data in the first place. Despite these difficulties, we achieved an average muscle fiber overlay precision of 0.65 and an average recall of 0.49. In this context, overlaid fibers are defined as fibers that have one or more pixels overlaying in the manual and DCNN cross-section segmentation. For the overlaid fibers, the proposed method achieved excellent segmentation accuracy of 94%±10.26%, as measured by the Dice-Sorensen coefficient.

show abstract

Charisma: An integrated approach to automatic H&E-stained skeletal muscle cell segmentation using supervised learning and novel robust clump splitting

Cited by 33 publications

References 39 publications

Premorbid obesity, but not nutrition, prevents critical illness‐induced muscle wasting and weakness

Premorbid obesity, but not nutrition, prevents critical illness‐induced muscle wasting and weakness

Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review

A neural network approach to analyze cross-sections of muscle fibers in pathological images

Contact Info

Product

Resources

About