An intelligent mobile-enabled expert system for tuberculosis disease diagnosis in real time

Shabut, Antesar M.; Tania, Marzia Hoque; Lwin, Khin T.; Evans, Benjamin A.; Yusof, Nor Azah; Abuhassan, Kamal; Hossain, M. A.

doi:10.1016/j.eswa.2018.07.014

Cited by 60 publications

(47 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both of these assays are well utilized in the reported articles [13]- [18]. The state of matter is an important consideration because, based on the critical review conducted in this paper, the physical state of the sample can dictate the overall system regarding image processing algorithm and feature-set [10], [17], [19]. In Fig.…”

Section: A State Of Mattermentioning

confidence: 99%

“…A wide range of smartphone camera specifications along with intrinsic and extrinsic parameters has been explored in the literature such as the International Organization for Standardization (ISO), flash and focus. Such explorations are exemplified in TABLE I. ISO Varying from 50 [13] to 800 [30], [31] Auto [17], [30] Other parameters…”

Section: (A) and (B) Vary In Viscositymentioning

confidence: 99%

“…Parallel [13], [17] Tilted [30] Our research assumes, due to the advancement of hardware as well as software components of the phone camera, these parameters can be set to the automatic mode. For field operation, the systems would be exposed to the ambient illumination condition to capture images.…”

Section: Distancementioning

confidence: 99%

“…Therefore, a computer-aided colourimetric test should aim for the requirement of minimum fine-tuning in case of such variations including the variations due to the change of platform. The variation of the illumination condition and inconsistencies due to the device to device variation is a more severe concern for traditional machine learning based colorimetric tests [17]. The advanced machine learning techniques such as CNN based deep learning techniques are capable of handling such variations.…”

Section: Distancementioning

confidence: 99%

“…Such an interactive overlay could ease the necessity to use computational intelligence to separate the region of interest. Alternatively, one could use computer vision and machine learning techniques such as [17], [41].…”

Section: ) Multi-test Per Image and Single Object Per Testmentioning

confidence: 99%

See 4 more Smart Citations

Assay Type Detection Using Advanced Machine Learning Algorithms

Tania

Lwin

Shabut

et al. 2019

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

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: A State Of Mattermentioning

confidence: 99%

Section: (A) and (B) Vary In Viscositymentioning

confidence: 99%

Section: Distancementioning

confidence: 99%

Section: Distancementioning

confidence: 99%

Section: ) Multi-test Per Image and Single Object Per Testmentioning

confidence: 99%

See 3 more Smart Citations

Assay Type Detection Using Advanced Machine Learning Algorithms

Tania

Lwin

Shabut

et al. 2019

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

Self Cite

View full text Add to dashboard Cite

show abstract

Severity detection and infection level identification of tuberculosis using deep learning

Chithra

Jagatheeswari

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Tuberculosis (TB) is a highly infectious disease and is one of the major health problems all over the world. The accurate detection of TB is a major challenge faced by most of the existing methods. This work addresses these issues and developed an effective mechanism for detecting TB using deep learning. Here, the color space transformation is applied for transforming the red green and blue image to LUV space, where L stands for luminance, U and V represent chromaticity values of color images. Then, adaptive thresholding is carried out for image segmentation and various features, like coverage, density, color histogram, area, length, and texture features, are extracted to enable effective classification. After the feature extraction, the size of the features is reduced using principal component analysis. The extracted features are subjected to fractional crow search‐based deep convolutional neural network (FC‐SVNN) for the classification. Then, the image level features, like bacilli count, bacilli area, scattering coefficients and skeleton features are considered to perform severity detection using proposed adaptive fractional crow (AFC)‐deep CNN. Finally, the inflection level is determined using entropy, density and detection percentage. The proposed AFC‐Deep CNN algorithm is designed by modifying FC algorithm using self‐adaptive concept. The proposed AFC‐Deep CNN shows better performance with maximum accuracy value as 0.935.

show abstract

A Comparative Performance Analysis of Different Denoising Techniques in Sputum Smear Images

Nagoor

Jinny

2020

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

An intelligent mobile-enabled expert system for tuberculosis disease diagnosis in real time

Cited by 60 publications

References 18 publications

Assay Type Detection Using Advanced Machine Learning Algorithms

Assay Type Detection Using Advanced Machine Learning Algorithms

Severity detection and infection level identification of tuberculosis using deep learning

A Comparative Performance Analysis of Different Denoising Techniques in Sputum Smear Images

Contact Info

Product

Resources

About