Literature DB >> 35855715

Development of a Machine learning image segmentation-based algorithm for the determination of the adequacy of Gram-stained sputum smear images.

Manraj Sirohi1, Mahima Lall2, Swapna Yenishetti3, Lakshmi Panat3, Ajai Kumar3.   

Abstract

Background: Machine learning (ML) prepares and trains a model through supervised or unsupervised learning methods. Sputum, a respiratory tract secretion, is a common laboratory specimen that aids in diagnosing respiratory diseases, including pulmonary tuberculosis (TB). Gram stain is an easy, cost-effective stain, which may be applied to sputum smears to screen out an unsatisfactory sample. ML model may help in screening sputum smears.
Methods: This collaborative project was carried out from June 2020-July 2021. In this study, a color-based segmentation ML algorithm using K-Means clustering was developed. A library of stained sputum smears was built. The Bartletts criteria (based on neutrophil and squamous cell count) for screening and selecting satisfactory sputum smears were used. A smartphone camera was used to take several photographs of satisfactory, as well as unsatisfactory, smears. The image segmentation algorithm was applied to medical image analysis, color-segmentation of sputum images was done. The hue saturation value (HSV) color ranges were defined on a prototype image. Then, all connected pixels were identified as a single object, and morphological operations were applied.
Results: Usage of AI-driven model on the slide-image revealed the slide adequacy as the cell count was acceptable based on Bartlett's criteria. Both the manual cell counts (Range: 126-203 neutrophils, 14-47 squamous cells) and the model counts (Range: 117-242 neutrophils, 14-37 squamous cells) are within acceptable limits.
Conclusion: The use of a model to screen a large number of sputum slides may be a boon in resource-limited settings where trained microscopists may not be easily available.
© 2021 Director General, Armed Forces Medical Services. Published by Elsevier, a division of RELX India Pvt. Ltd.

Entities:  

Keywords:  Color-based segmentation; Gram stain; Machine learning; Sputum smears

Year:  2021        PMID: 35855715      PMCID: PMC9287657          DOI: 10.1016/j.mjafi.2021.09.012

Source DB:  PubMed          Journal:  Med J Armed Forces India        ISSN: 0377-1237


  12 in total

1.  Multicenter Assessment of Gram Stain Error Rates.

Authors:  Linoj P Samuel; Joan-Miquel Balada-Llasat; Amanda Harrington; Robert Cavagnolo
Journal:  J Clin Microbiol       Date:  2016-02-17       Impact factor: 5.948

2.  Guided sputum sample collection and culture contamination rates in the diagnosis of pulmonary TB.

Authors:  Ethel Leonor Noia Maciel; Thiago Nascimento do Prado; Renata Lyrio Peres; Moises Palaci; John L Johnson; Reynaldo Dietze
Journal:  J Bras Pneumol       Date:  2009-05       Impact factor: 2.624

3.  Quality assurance of gram-stained direct smears.

Authors:  R C Bartlett; J Tetreault; J Evers; J Officer; J Derench
Journal:  Am J Clin Pathol       Date:  1979-12       Impact factor: 2.493

4.  Automated Interpretation of Blood Culture Gram Stains by Use of a Deep Convolutional Neural Network.

Authors:  Kenneth P Smith; Anthony D Kang; James E Kirby
Journal:  J Clin Microbiol       Date:  2018-02-22       Impact factor: 5.948

Review 5.  Image analysis and artificial intelligence in infectious disease diagnostics.

Authors:  K P Smith; J E Kirby
Journal:  Clin Microbiol Infect       Date:  2020-03-22       Impact factor: 8.067

6.  Validation of sputum Gram stain for treatment of community-acquired pneumonia and healthcare-associated pneumonia: a prospective observational study.

Authors:  Hajime Fukuyama; Shin Yamashiro; Kiyoshi Kinjo; Hitoshi Tamaki; Tomoo Kishaba
Journal:  BMC Infect Dis       Date:  2014-10-18       Impact factor: 3.090

7.  The Quality of Sputum Specimens as a Predictor of Isolated Bacteria From Patients With Lower Respiratory Tract Infections at a Tertiary Referral Hospital, Denpasar, Bali-Indonesia.

Authors:  Nyoman Sri Budayanti; Kadek Suryawan; Ida Sri Iswari; Dewa Made Sukrama
Journal:  Front Med (Lausanne)       Date:  2019-04-05

8.  Using Machine Learning Techniques to Aid Empirical Antibiotic Therapy Decisions in the Intensive Care Unit of a General Hospital in Greece.

Authors:  Georgios Feretzakis; Evangelos Loupelis; Aikaterini Sakagianni; Dimitris Kalles; Maria Martsoukou; Malvina Lada; Nikoletta Skarmoutsou; Constantinos Christopoulos; Konstantinos Valakis; Aikaterini Velentza; Stavroula Petropoulou; Sophia Michelidou; Konstantinos Alexiou
Journal:  Antibiotics (Basel)       Date:  2020-01-31

Review 9.  Application of Machine Learning in Microbiology.

Authors:  Kaiyang Qu; Fei Guo; Xiangrong Liu; Yuan Lin; Quan Zou
Journal:  Front Microbiol       Date:  2019-04-18       Impact factor: 5.640

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.