Supervised Machine Learning Segmentation and Quantification of Gastric Pacemaker Cells

Mah, Sue Ann; Avci, Recep; Du, Peng; Vanderwinden, Jean‐Marie; Cheng, Leo K.

doi:10.1109/embc44109.2020.9176445

Cited by 7 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Structural metrics were then applied to assess structural variations of ICC populations around the circumference, i.e., from greater to lesser curvature, and along the length of the gastric antrum. The analysis extended on a previous preliminary study reported in a conference proceeding that applied a number of classifiers in a small image field, 21 to accurately segment three different ICC networks in larger imaging fields with additional metrics for validation and quantification of spatial variations. The study provides an efficient and accurate framework for the analysis of ICC of the gut, with specific applications in addressing the complex relationship between variations of ICC structures and distinct functions of different portions of the stomach.…”

Section: Introductionmentioning

confidence: 90%

“…A previously described machine learning approach was used to segment ICC from each image stack. 21 A ''gold standard'' (GS) training dataset was created by manually segmenting ICC from non-ICC regions from 17 sub-images of 59.3 9 59.3 lm 2 (100 9 100 pixels). Three investigators performed the manual segmentation independently and the median of the three binary ICC masks was defined as the overall GS training dataset.…”

Section: Image Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Regional Variations of the Interstitial Cells of Cajal in the Murine Distal Stomach Informed by Confocal Imaging and Machine Learning Methods

Mah

Avci

et al. 2022

Cel. Mol. Bioeng.

Self Cite

View full text Add to dashboard Cite

Introduction-The network of Interstitial Cells of Cajal (ICC) plays a plethora of key roles in maintaining, coordinating, and regulating the contractions of the gastrointestinal (GI) smooth muscles. Several GI functional motility disorders have been associated with ICC degradation. This study extended a previously reported 2D morphological analysis and applied it to 3D spatial quantification of three different types of ICC networks in the distal stomach guided by confocal imaging and machine learning methods. The characterization of the complex changes in spatial structure of the ICC network architecture contributes to our understanding of the roles that different types of ICC may play in postprandial physiology, pathogenesis, and/or amelioration of GI dsymotility-bridging structure and function. Methods-A validated classification method using Trainable Weka Segmentation was applied to segment the ICC from a confocal dataset of the gastric antrum of a transgenic mouse, followed by structural analysis of the segmented images. Results-The machine learning model performance was compared to manually segmented subfields, achieving an area under the receiver-operating characteristic (AUROC) of 0.973 and 0.995 for myenteric ICC (ICC-MP; n = 6) and intramuscular ICC (ICC-IM; n = 17). The myenteric layer in the distal antrum increased in thickness (from 14.5 to 34 lm) towards the lesser curvature, whereas the thickness decreased towards the lesser curvature in the proximal antrum (17.7 to 9 lm). There was an increase in ICC-MP volume from proximal to distal antrum (406,960 ± 140,040 vs. 559,990 ± 281,000 lm 3 ; p = 0.000145). The % of ICC volume was similar for ICC-LM and for ICC-CM between proximal (3.6 ± 2.3% vs. 3.1 ± 1.2%; p = 0.185) and distal antrum (3.2 ± 3.9% vs. 2.5 ± 2.8%; p = 0.309). The aver-age % volume of ICC-MP was significantly higher than ICC-IM at all points throughout sample (p < 0.0001). Conclusions-The segmentation and analysis methods provide a high-throughput framework of investigating the structural changes in extended ICC networks and their associated physiological functions in animal models.

show abstract

Section: Introductionmentioning

confidence: 90%

Section: Image Segmentationmentioning

confidence: 99%

Analysis of Regional Variations of the Interstitial Cells of Cajal in the Murine Distal Stomach Informed by Confocal Imaging and Machine Learning Methods

Mah

Avci

et al. 2022

Cel. Mol. Bioeng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…These types of data are relatively straightforward to work with since the images are of high contrast with relatively smooth contours. However, analysing 3D ICC confocal images is more challenging due to the variation in ICC processes shape, size, and orientation; and differing signal-to-noise ratios of different confocal data 36 . The ideal graph construction algorithm should possess several key properties, including the ability to handle noise, object boundary irregularities, and spatial variations in branch shape and thickness 16 .…”

Section: Discussionmentioning

confidence: 99%

“…The validated Weka Fast Random Forest (FRF) machine learning model deduced previously was adapted to the present dataset without further training for segmenting all networks of ICC 36,37 . Following segmentation, each transmural image stack (serosa to mucosa) was visually inspected to categorise image slices belonging to the LM, MP and the CM regions 35 based on the segmented networks of ICC-LM, ICC-MP and ICC-CM that could be observed.…”

Section: Tissue Preparation Confocal Imaging Icc Segmentation and Ide...mentioning

confidence: 99%

See 1 more Smart Citation

Unravelling the Three-Dimensional Structure-Function Relationships of Interstitial Cells of Cajal Networks: A Graph Theoretical Approach to Neurogastroenterology

Mah,

Avci,

Vanderwinden

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Specific structural traits such as deficient or altered networks of interstitical cells of Cajal (ICC) are often observed in gastroparesis, constipation, chronic intestinal pseudo-obstruction, and Hirschsprung disease based on qualitative histopathological findings, serve as key factors in inferring the health of gastrointestinal (GI) motility function. However, the assessment of ICC at present is limited by the lack of readily available 3D quantitative metrics. Although confocal microscopy can image and quantify the spatial distribution of ICC networks, current techniques to evaluate ICC in histological studies are limited to nuclei counts, or simply by objective visual grading. Although a suite of numerical metrics for the quantitative assessment of the structural features of ICC networks has previously been developed. However, the analysis has been limited to the analysis of ICC structure in 2D images. A 3D framework for quantifying and visualising these ICC networks could provide a valuable tool to elucidate the pathophysiology of GI motility disorders. In our analysis, 3D visualization techniques namely, 3D structure tensor analysis, 3D Fourier analysis, 3D Graph Network, capable of providing whole-mount gastric antrum tissue imaging representations of proximal and distal regional descriptors based on fluorescence data acquisition have been developed. Using the murine stomach as a model, the methods outlined in this paper allowed us to analyse and interrogate the gastrointestinal ICC networks structural variations and orientation distribution and better infer and delineate the underlying structural network in unprecedented detail.

show abstract

Current applications of mathematical models of the interstitial cells of Cajal in the gastrointestinal tract

Mah

Avci

Cheng

et al. 2020

WIREs Mechanisms of Disease

Self Cite

View full text Add to dashboard Cite

The interstitial cells of Cajal (ICC) form interconnected networks throughout the gastrointestinal (GI) tract. ICC act as the pacemaker cells that initiate the rhythmic bioelectrical slow waves and intermediary between the GI musculature and nerves, both of which are critical to GI motility. Disruptions to the number of ICC and the integrity of ICC networks have been identified as a key pathophysiological mechanism in a number of clinically challenging GI disorders. The current analyses of ICC generally rely on either functional recordings taken directly from excised tissue or morphological analysis based on images of labeled ICC, where the structural‐functional relationship is investigated in an associative manner rather than mechanistically. On the other hand, computational physiology has played a significant role in facilitating our understanding of a number of physiological systems in both health and disease, and investigations in the GI field are beginning to incorporate several mathematical models of the ICC. The main aim of this review is to present the major modeling advances in GI electrophysiology, in order to introduce a multi‐scale framework for mathematically quantifying the functional consequences of ICC degradation at both cellular and tissue scales. The outcomes will inform future investigators utilizing modeling techniques in their studies. This article is categorized under: Metabolic Diseases > Computational Models

show abstract

Supervised Machine Learning Segmentation and Quantification of Gastric Pacemaker Cells

Cited by 7 publications

References 18 publications

Analysis of Regional Variations of the Interstitial Cells of Cajal in the Murine Distal Stomach Informed by Confocal Imaging and Machine Learning Methods

Analysis of Regional Variations of the Interstitial Cells of Cajal in the Murine Distal Stomach Informed by Confocal Imaging and Machine Learning Methods

Unravelling the Three-Dimensional Structure-Function Relationships of Interstitial Cells of Cajal Networks: A Graph Theoretical Approach to Neurogastroenterology

Current applications of mathematical models of the interstitial cells of Cajal in the gastrointestinal tract

Contact Info

Product

Resources

About