Literature DB >> 33407814

Computer vision applied to dual-energy computed tomography images for precise calcinosis cutis quantification in patients with systemic sclerosis.

Anita C Chandrasekaran1, Zhicheng Fu2,3, Reid Kraniski4, F Perry Wilson5, Shannon Teaw1, Michelle Cheng1, Annie Wang4, Shangping Ren2,6, Imran M Omar7, Monique E Hinchcliff8,9,10.   

Abstract

BACKGROUND: Although treatments have been proposed for calcinosis cutis (CC) in patients with systemic sclerosis (SSc), a standardized and validated method for CC burden quantification is necessary to enable valid clinical trials. We tested the hypothesis that computer vision applied to dual-energy computed tomography (DECT) finger images is a useful approach for precise and accurate CC quantification in SSc patients.
METHODS: De-identified 2-dimensional (2D) DECT images from SSc patients with clinically evident lesser finger CC lesions were obtained. An expert musculoskeletal radiologist confirmed accurate manual segmentation (subtraction) of the phalanges for each image as a gold standard, and a U-Net Convolutional Neural Network (CNN) computer vision model for segmentation of healthy phalanges was developed and tested. A validation study was performed in an independent dataset whereby two independent radiologists manually measured the longest length and perpendicular short axis of each lesion and then calculated an estimated area by assuming the lesion was elliptical using the formula long axis/2 × short axis/2 × π, and a computer scientist used a region growing technique to calculate the area of CC lesions. Spearman's correlation coefficient, Lin's concordance correlation coefficient with 95% confidence intervals (CI), and a Bland-Altman plot (Stata V 15.1, College Station, TX) were used to test for equivalence between the radiologists' and the CNN algorithm-generated area estimates.
RESULTS: Forty de-identified 2D DECT images from SSc patients with clinically evident finger CC lesions were obtained and divided into training (N = 30 with image rotation × 3 to expand the set to N = 120) and test sets (N = 10). In the training set, five hundred epochs (iterations) were required to train the CNN algorithm to segment phalanges from adjacent CC, and accurate segmentation was evaluated using the ten held-out images. To test model performance, CC lesional area estimates calculated by two independent radiologists and a computer scientist were compared (radiologist 1 vs. radiologist 2 and radiologist 1 vs. computer vision approach) using an independent test dataset comprised of 31 images (8 index finger and 23 other fingers). For the two radiologists', and the radiologist vs. computer vision measurements, Spearman's rho was 0.91 and 0.94, respectively, both p < 0.0001; Lin's concordance correlation coefficient was 0.91 (95% CI 0.85-0.98, p < 0.001) and 0.95 (95% CI 0.91-0.99, p < 0.001); and Bland-Altman plots demonstrated a mean difference between radiologist vs. radiologist, and radiologist vs. computer vision area estimates of - 0.5 mm2 (95% limits of agreement - 10.0-9.0 mm2) and 1.7 mm2 (95% limits of agreement - 6.0-9.5 mm2, respectively.
CONCLUSIONS: We demonstrate that CNN quantification has a high degree of correlation with expert radiologist measurement of finger CC area measurements. Future work will include segmentation of 3-dimensional (3D) images for volumetric and density quantification, as well as validation in larger, independent cohorts.

Entities:  

Keywords:  Artificial intelligence; Calcinosis cutis; Computer vision; Convolutional neural networks (CNN); Dystrophic calcifications; Medical image analysis; Scleroderma; Systemic sclerosis; U-Net

Year:  2021        PMID: 33407814      PMCID: PMC7788847          DOI: 10.1186/s13075-020-02392-9

Source DB:  PubMed          Journal:  Arthritis Res Ther        ISSN: 1478-6354            Impact factor:   5.156


  28 in total

1.  Validation of a novel radiographic scoring system for calcinosis affecting the hands of patients with systemic sclerosis.

Authors:  Lorinda Chung; Antonia Valenzuela; David Fiorentino; Kathryn Stevens; Shufeng Li; Jonathan Harris; Charles Hutchinson; Shervin Assassi; Lorenzo Beretta; Santhanam Lakshminarayanan; Tatiana S Rodriguez-Reyna; Christopher P Denton; Rebecca G Taillefer; Ariane L Herrick; Murray Baron
Journal:  Arthritis Care Res (Hoboken)       Date:  2015-03       Impact factor: 4.794

2.  Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network.

Authors:  Anabik Pal; Utpal Garain; Aditi Chandra; Raghunath Chatterjee; Swapan Senapati
Journal:  Comput Methods Programs Biomed       Date:  2018-02-06       Impact factor: 5.428

3.  Ultrasonographic hand features in systemic sclerosis and correlates with clinical, biologic, and radiographic findings.

Authors:  Muriel Elhai; Henri Guerini; Ramin Bazeli; Jerôme Avouac; Véronique Freire; Jean-Luc Drapé; André Kahan; Yannick Allanore
Journal:  Arthritis Care Res (Hoboken)       Date:  2012-08       Impact factor: 4.794

4.  Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network.

Authors:  Adhish Prasoon; Kersten Petersen; Christian Igel; François Lauze; Erik Dam; Mads Nielsen
Journal:  Med Image Comput Comput Assist Interv       Date:  2013

5.  Hand and wrist involvement in systemic sclerosis: US features.

Authors:  Véronique Freire; Ramin Bazeli; Muriel Elhai; Raphaël Campagna; Éric Pessis; Jérôme Avouac; Yannick Allanore; Jean-Luc Drapé; Henri Guérini
Journal:  Radiology       Date:  2013-10-28       Impact factor: 11.105

Review 6.  Clinical value of prostate segmentation and volume determination on MRI in benign prostatic hyperplasia.

Authors:  Brian Garvey; Barış Türkbey; Hong Truong; Marcelino Bernardo; Senthil Periaswamy; Peter L Choyke
Journal:  Diagn Interv Radiol       Date:  2014 May-Jun       Impact factor: 2.630

Review 7.  Calcinosis in scleroderma.

Authors:  Antonia Valenzuela; Paula Song; Lorinda Chung
Journal:  Curr Opin Rheumatol       Date:  2018-11       Impact factor: 5.006

8.  Dermatologist-level classification of skin cancer with deep neural networks.

Authors:  Andre Esteva; Brett Kuprel; Roberto A Novoa; Justin Ko; Susan M Swetter; Helen M Blau; Sebastian Thrun
Journal:  Nature       Date:  2017-01-25       Impact factor: 49.962

9.  Diagnostic Performance of Deep Learning Algorithms Applied to Three Common Diagnoses in Dermatopathology.

Authors:  Thomas George Olsen; B Hunter Jackson; Theresa Ann Feeser; Michael N Kent; John C Moad; Smita Krishnamurthy; Denise D Lunsford; Rajath E Soans
Journal:  J Pathol Inform       Date:  2018-09-27

10.  High-throughput quantitative histology in systemic sclerosis skin disease using computer vision.

Authors:  Chase Correia; Seamus Mawe; Shane Lofgren; Roberta G Marangoni; Jungwha Lee; Rana Saber; Kathleen Aren; Michelle Cheng; Shannon Teaw; Aileen Hoffmann; Isaac Goldberg; Shawn E Cowper; Purvesh Khatri; Monique Hinchcliff; J Matthew Mahoney
Journal:  Arthritis Res Ther       Date:  2020-03-14       Impact factor: 5.156

View more
  2 in total

Review 1.  Calcinosis in systemic sclerosis.

Authors:  Srijana Davuluri; Christian Lood; Lorinda Chung
Journal:  Curr Opin Rheumatol       Date:  2022-08-19       Impact factor: 4.941

Review 2.  Systemic Scleroderma-Definition, Clinical Picture and Laboratory Diagnostics.

Authors:  Anna Kowalska-Kępczyńska
Journal:  J Clin Med       Date:  2022-04-20       Impact factor: 4.964

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.