Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Mar 8;12(1):4071.
doi: 10.1038/s41598-022-07199-z.

Automated detection of celiac disease using Machine Learning Algorithms

Cristian-Andrei Stoleru  1 , Eva H Dulf  2 , Lidia Ciobanu  3
Affiliations

Automated detection of celiac disease using Machine Learning Algorithms

Cristian-Andrei Stoleru et al. Sci Rep. .

Abstract

Celiac disease is a disorder of the immune system that mainly affects the small intestine but can also affect the skeletal system. The diagnosis relies on histological assessment of duodenal biopsies acquired by upper digestive endoscopy. Immunological tests involve collecting a blood sample to detect if the antibodies have been produced in the body. Endoscopy is invasive and histology is time-consuming. In recent years there have been various algorithms that use artificial intelligence (AI) and neural convolutions (CNN, Convolutional Neural Network) to process images from capsule endoscopy, a non-invasive endoscopy approach, that provides magnified, high qualitative images of the small bowel mucosa, to quickly establish a diagnosis. The proposed innovative approach do not use complex learning algorithms, instead it find some artefacts in the endoscopies using kernels and use classified machine learning algorithms. Each used artefacts have a psychical meaning: atrophies of the mucosa with a visible submucosal vascular pattern; the presence of cracks (depressions) that have an appearance similar to that of dry land; reduction or complete loss of folds in the duodenum; the presence of a submerged appearance at the Kerckring folds and a low number of villi. The results obtained for video capsule endoscopy images processing reveal an accuracy of 94.1% and F1 score of 94%, which is competitive with other complex algorithms. The main goal of the present research was to demonstrate that computer-aided diagnosis of celiac disease is possible even without the use of very complex algorithms, which require expensive hardware and a lot of processing time. The use of the proposed automated images processing acquired noninvasively by capsule endoscopy would be assistive in detecting the subtle presence of villous atrophy not evident by visual inspection. It may also be useful to assess the degree of improvement of celiac. Patients on a gluten-free diet, the main treatment method for stopping the autoimmune process and improving the state of the small intestinal villi. The novelty of the work is that the algorithm uses two modified filters to properly analyse the intestine wall texture. It is proved that using the right filters, the proper diagnostic can be obtained by image processing, without the use of a complicated machine learning algorithm.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Experiment workflow.
Figure 2
Figure 2
Unwanted information.
Figure 3
Figure 3
Steps required to remove the unwanted information. (1) Black and White image, (2) binary image, (3) centre of the regions, (4) final result.
Figure 4
Figure 4
Before and after the cropping.
Figure 5
Figure 5
Before and after Sobel filter.
Figure 6
Figure 6
Modification to the Sobel filter. (1) Black and white Image, (2) contrast adjustments, (3) simple Sobel filter, (4) final result.
Figure 7
Figure 7
Before and after binarization.
Figure 8
Figure 8
Entropy analysis. (1) Black and White image. (2) Histogram of the image.
Figure 9
Figure 9
KNN example.
Figure 10
Figure 10
Weighted KNN example.
Figure 11
Figure 11
2D and 3D hyperplanes.
Figure 12
Figure 12
Average variation in light intensity. Red = Healthy and Blue = Celiac.
Figure 13
Figure 13
The standard deviation of the light intensity value. Red = Healthy and Blue = Celiac.
Figure 14
Figure 14
Red spectrum variation. Red = Healthy and Blue = Celiac.
Figure 15
Figure 15
Green spectrum variation. Red = Healthy and Blue = Celiac.
Figure 16
Figure 16
Blue spectrum variation. Red = Healthy and Blue = Celiac.
Figure 17
Figure 17
The values obtained after applying the Sobel filter. Red = Healthy and Blue = Celiac.
Figure 18
Figure 18
The values obtained after applying the generated filter. Red = Healthy and Blue = Celiac.
Figure 19
Figure 19
The value of entropy. Red = Healthy and Blue = Celiac.
Figure 20
Figure 20
Variation in the number of large regions. Red = Healthy and Blue = Celiac.
Figure 21
Figure 21
Variation in the number of small regions. Red = Healthy and Blue = Celiac.
Figure 22
Figure 22
Correctly analysed data.
Figure 23
Figure 23
Wrong analysed data.
Figure 24
Figure 24
Confusion matrixes: (1) fine KNN; (2) weighted KNN; (3) linear SVM.
Figure 25
Figure 25
Correctly analysed data.
Figure 26
Figure 26
Wrong analysed data.
Figure 27
Figure 27
Correctly analysed data.
Figure 28
Figure 28
Wrong analysed data.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Popp A, Balaba VD, Mäki M. Celiac disease. In: Gershman G, Thomson M, editors. Practical Pediatric Gastrointestinal Endoscopy. Wiley; 2021. pp. 207–211.
    1. Caio G, et al. Celiac disease: A comprehensive current review. BMC Med. 2019;17(1):1–20. doi: 10.1186/s12916-019-1380-z. - DOI - PMC - PubMed
    1. Lewis NR, Scott BB. Systematic review: The use of serology to exclude or diagnose coeliac disease (a comparison of the endomysial and tissue transglutaminase antibody tests) Aliment. Pharmacol. Ther. 2006;24(1):47–54. doi: 10.1111/j.1365-2036.2006.02967.x. - DOI - PubMed
    1. Cichewicz AB, et al. Diagnosis and treatment patterns in celiac disease. Dig. Dis. Sci. 2019;64(8):2095–2106. doi: 10.1007/s10620-019-05528-3. - DOI - PubMed
    1. Wei JW, et al. Automated detection of celiac disease on duodenal biopsy slides: A deep learning approach. J. Pathol. Inform. 2019;10:7. doi: 10.4103/jpi.jpi_87_18. - DOI - PMC - PubMed

Publication types