Assay type detection using advanced machine learning algorithms

Marzia Hoque Tania; Khin T. Lwin; Antesar M. Shabut; Kamal J. Abu-Hassan; M. Shamim Kaiser; M. A. Hossain

doi:10.1109/SKIMA47702.2019.8982449

Assay type detection using advanced machine learning algorithms

Marzia Hoque Tania, Khin T. Lwin, Antesar M. Shabut, Kamal J. Abu-Hassan, M. Shamim Kaiser, M. A. Hossain

Department of Physics

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

17 Citations (SciVal)

Abstract

The colourimetric analysis has been used in diversified fields for years. This paper provides a unique overview of colourimetric tests from the perspective of computer vision by describing different aspects of a colourimetric test in the context of image processing, followed by an investigation into the development of a colorimetric assay type detection system using advanced machine learning algorithms. To the best of our knowledge, this is the first attempt to define colourimetric assay types from the eyes of a machine and perform any colorimetric test using deep learning. This investigation utilizes the state-of-the-art pre-trained models of Convolutional Neural Network (CNN) to perform the assay type detection of an enzyme-linked immunosorbent assay (ELISA) and lateral flow assay (LFA). The ELISA dataset contains images of both positive and negative samples, prepared for the plasmonic ELISA based TB-antigen specific antibody detection. The LFA dataset contains images of the universal pH indicator paper of eight pH levels. It is noted that the pre-trained models offered 100% accurate visual recognition for the assay type detection. Such detection can assist novice users to initiate a colorimetric test using his/her personal digital devices. The assay type detection can also aid in calibrating an image-based colorimetric classification.

Original language	English
Title of host publication	2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019
Publisher	IEEE
ISBN (Electronic)	9781728127415
DOIs	https://doi.org/10.1109/SKIMA47702.2019.8982449
Publication status	Published - Aug 2019
Event	13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019 - Island of Ulkulhas, Maldives Duration: 26 Aug 2019 → 28 Aug 2019

Publication series

Name	2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019

Conference

Conference	13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019
Country/Territory	Maldives
City	Island of Ulkulhas
Period	26/08/19 → 28/08/19

Funding

ACKNOWLEDGMENT The research work has been funded by Erasmus Mundus Partnerships Action 2 “FUSION” (Featured eUrope and South asIa mObility Network). Grant reference number: 2013-3254 1/001001. The authors’ thank Prof Nor Azah Yusof and her team, Universiti Putra Malaysia for their support to collect the ELISA dataset. The original ELISA dataset was generated as part of the project named ‘TB-Test -A smart mobile enabled scheme for tuberculosis testing’, supported by British Council Newton Institutional Links and Newton-Ungku Omar Fund (Grant ID: 216385726), The authors also thank Dr Mohammad Najlah and Mr Paul Cotton, Anglia Ruskin University for their support to conduct the laboratory experiments on LFA.

Keywords

Colorimetric test
Computer vision
Deep learning
Diagnosis
Point-of-care system
Transfer learning

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Software
Information Systems and Management

Access to Document

10.1109/SKIMA47702.2019.8982449

Cite this

Tania, M. H., Lwin, K. T., Shabut, A. M., Abu-Hassan, K. J., Kaiser, M. S., & Hossain, M. A. (2019). Assay type detection using advanced machine learning algorithms. In 2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019 Article 8982449 (2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019). IEEE. https://doi.org/10.1109/SKIMA47702.2019.8982449

Assay type detection using advanced machine learning algorithms. / Tania, Marzia Hoque; Lwin, Khin T.; Shabut, Antesar M. et al.
2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019. IEEE, 2019. 8982449 (2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Tania, MH, Lwin, KT, Shabut, AM, Abu-Hassan, KJ, Kaiser, MS & Hossain, MA 2019, Assay type detection using advanced machine learning algorithms. in 2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019., 8982449, 2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019, IEEE, 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019, Island of Ulkulhas, Maldives, 26/08/19. https://doi.org/10.1109/SKIMA47702.2019.8982449

Tania MH, Lwin KT, Shabut AM, Abu-Hassan KJ, Kaiser MS, Hossain MA. Assay type detection using advanced machine learning algorithms. In 2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019. IEEE. 2019. 8982449. (2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019). doi: 10.1109/SKIMA47702.2019.8982449

@inproceedings{435dce214c4342cf8a108dc6cecca221,

title = "Assay type detection using advanced machine learning algorithms",

abstract = "The colourimetric analysis has been used in diversified fields for years. This paper provides a unique overview of colourimetric tests from the perspective of computer vision by describing different aspects of a colourimetric test in the context of image processing, followed by an investigation into the development of a colorimetric assay type detection system using advanced machine learning algorithms. To the best of our knowledge, this is the first attempt to define colourimetric assay types from the eyes of a machine and perform any colorimetric test using deep learning. This investigation utilizes the state-of-the-art pre-trained models of Convolutional Neural Network (CNN) to perform the assay type detection of an enzyme-linked immunosorbent assay (ELISA) and lateral flow assay (LFA). The ELISA dataset contains images of both positive and negative samples, prepared for the plasmonic ELISA based TB-antigen specific antibody detection. The LFA dataset contains images of the universal pH indicator paper of eight pH levels. It is noted that the pre-trained models offered 100% accurate visual recognition for the assay type detection. Such detection can assist novice users to initiate a colorimetric test using his/her personal digital devices. The assay type detection can also aid in calibrating an image-based colorimetric classification.",

keywords = "Colorimetric test, Computer vision, Deep learning, Diagnosis, Point-of-care system, Transfer learning",

author = "Tania, {Marzia Hoque} and Lwin, {Khin T.} and Shabut, {Antesar M.} and Abu-Hassan, {Kamal J.} and Kaiser, {M. Shamim} and Hossain, {M. A.}",

year = "2019",

month = aug,

doi = "10.1109/SKIMA47702.2019.8982449",

language = "English",

series = "2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019",

publisher = "IEEE",

booktitle = "2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019",

address = "USA United States",

note = "13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019 ; Conference date: 26-08-2019 Through 28-08-2019",

}

TY - GEN

T1 - Assay type detection using advanced machine learning algorithms

AU - Tania, Marzia Hoque

AU - Lwin, Khin T.

AU - Shabut, Antesar M.

AU - Abu-Hassan, Kamal J.

AU - Kaiser, M. Shamim

AU - Hossain, M. A.

PY - 2019/8

Y1 - 2019/8

N2 - The colourimetric analysis has been used in diversified fields for years. This paper provides a unique overview of colourimetric tests from the perspective of computer vision by describing different aspects of a colourimetric test in the context of image processing, followed by an investigation into the development of a colorimetric assay type detection system using advanced machine learning algorithms. To the best of our knowledge, this is the first attempt to define colourimetric assay types from the eyes of a machine and perform any colorimetric test using deep learning. This investigation utilizes the state-of-the-art pre-trained models of Convolutional Neural Network (CNN) to perform the assay type detection of an enzyme-linked immunosorbent assay (ELISA) and lateral flow assay (LFA). The ELISA dataset contains images of both positive and negative samples, prepared for the plasmonic ELISA based TB-antigen specific antibody detection. The LFA dataset contains images of the universal pH indicator paper of eight pH levels. It is noted that the pre-trained models offered 100% accurate visual recognition for the assay type detection. Such detection can assist novice users to initiate a colorimetric test using his/her personal digital devices. The assay type detection can also aid in calibrating an image-based colorimetric classification.

AB - The colourimetric analysis has been used in diversified fields for years. This paper provides a unique overview of colourimetric tests from the perspective of computer vision by describing different aspects of a colourimetric test in the context of image processing, followed by an investigation into the development of a colorimetric assay type detection system using advanced machine learning algorithms. To the best of our knowledge, this is the first attempt to define colourimetric assay types from the eyes of a machine and perform any colorimetric test using deep learning. This investigation utilizes the state-of-the-art pre-trained models of Convolutional Neural Network (CNN) to perform the assay type detection of an enzyme-linked immunosorbent assay (ELISA) and lateral flow assay (LFA). The ELISA dataset contains images of both positive and negative samples, prepared for the plasmonic ELISA based TB-antigen specific antibody detection. The LFA dataset contains images of the universal pH indicator paper of eight pH levels. It is noted that the pre-trained models offered 100% accurate visual recognition for the assay type detection. Such detection can assist novice users to initiate a colorimetric test using his/her personal digital devices. The assay type detection can also aid in calibrating an image-based colorimetric classification.

KW - Colorimetric test

KW - Computer vision

KW - Deep learning

KW - Diagnosis

KW - Point-of-care system

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85081048532&partnerID=8YFLogxK

U2 - 10.1109/SKIMA47702.2019.8982449

DO - 10.1109/SKIMA47702.2019.8982449

M3 - Chapter in a published conference proceeding

AN - SCOPUS:85081048532

T3 - 2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019

BT - 2019 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019

PB - IEEE

T2 - 13th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2019

Y2 - 26 August 2019 through 28 August 2019

ER -

Assay type detection using advanced machine learning algorithms

Abstract

Publication series

Conference

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this