Wyniki wyszukiwania - BazTech

1

Endoscopy, video capsule endoscopy, and biopsy for automated celiac disease detection: A review

Jahmunah V., En Wei Koh Joel, Sudarshan Vidya K., Raghavendra U., Gudigar Anjan, Lih Oh Shu, Wen Loh Hui, Faust Oliver, Datta Barua Prabal, Ciaccio Edward J., Rajendra Acharya U.

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 1

82--108

EN

Celiac Disease (CD) is a common ailment that affects approximately 1% of the world population. Automated CD detection can help experts during the diagnosis of this condition at an early stage and bring significant benefits to both patients and healthcare providers. For this purpose, scientists have created automatic and semi-automatic CD diagnostic support systems. In this study, we performed information extraction methods that were found useful for efforts to differentiate CD versus non-CD. To focus the review process, only methods for endoscopy, video capsule endoscopy (VCE) and biopsy image analyses were considered. As described herein, we have learned that statistical and non-linear methods are most important for information extraction. These information extraction tools might benefit clinical workflows by reducing intra- and inter-observer variability. However, bias, introduced by resolving design choices during the creation of diagnostic support systems, may limit the general validity of the performance results, impacting the transferability of study outcomes. Therefore, having am overview of information extraction tools. Together with their general and specific limitations, might be assistive in improving the information extraction process. We hope our review results will provide a foundation for the design of next-generation statistical and nonlinear methods that can be used in CD detection systems. We have also compared various review articles and discussed recommendations to improve CD diagnosis. From this review, it is evident that CD diagnosis is slowly moving away from conventional techniques towards advanced deep learning techniques.

2

Transfer learning techniques for medical image analysis: A review

Kora Padmavathi, Ooi Chui Ping, Faust Oliver, Raghavendra U., Gudigar Anjan, Chan Wai Yee, Meenakshi K., Swaraja K., Plawiak Pawel, Acharya U. Rajendra

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 1

79--107

EN

Medical imaging is a useful tool for disease detection and diagnostic imaging technology has enabled early diagnosis of medical conditions. Manual image analysis methods are labor-intense and they are susceptible to intra as well as inter-observer variability. Automated medical image analysis techniques can overcome these limitations. In this review, we investigated Transfer Learning (TL) architectures for automated medical image analysis. We discovered that TL has been applied to a wide range of medical imaging tasks, such as segmentation, object identification, disease categorization, severity grading, to name a few. We could establish that TL provides high quality decision support and requires less training data when compared to traditional deep learning methods. These advantageous properties arise from the fact that TL models have already been trained on large generic datasets and a task specific dataset is only used to customize the model. This eliminates the need to train the models from scratch. Our review shows that AlexNet, ResNet, VGGNet, and GoogleNet are the most widely used TL models for medical image analysis. We found that these models can understand medical images, and the customization refines the ability, making these TL models useful tools for medical image analysis.

3

Assessment of CT for the categorization of hemorrhagic stroke (HS) and cerebral amyloid angiopathy hemorrhage (CAAH): A review

Sudarshan Vidya K., Raghavendra U., Gudigar Anjan, Ciaccio Edward J., Vijayananthan Anushya, Sahathevan Ramesh, Acharya U. Rajendra

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

888--901

EN

The management of intracerebral hemorrhage (ICH) requires prompt diagnostic assessment and recognition. Accurate localization and categorization of ICH-type is crucial. There are two main categories of ICH: 1) hemorrhagic stroke (HS), which occurs in the deeper or subcortical regions of the brain, where the arterial network tapers to fine end-arteries, and, 2) cerebral amyloid angiopathy hemorrhage (CAAH), which occurs at the superficial or cortical-subcortical region of the grey and white matter junction. Computed tomography (CT) and magnetic resonance imaging (MRI) are the most used imaging tools in diagnosing ICH. However, availability, time, and cost often prevent emergent MRI use. Therefore, CT remains the primary tool in the diagnosis of ICH. The assessment of imaging studies is time-dependent, and a radiologist should do a detailed diagnostic evaluation. Human error can occur in a pressured clinical setting, even for highly trained medical professionals. Assisted or automated computer-aided analysis of CT/MRI may help to reduce the assessment time, improve the diagnostic accuracy, better differentiate between types of ICH, and reduce the risk of human errors. This review evaluates CT and MRI’s role in distinguishing between the two varieties of ICH-HS and CAAH. It focuses on how CT could be utilized as the preferred diagnostic tool. In addition, we discuss the role of automation using machine learning (ML) and the role or advantages of ML in the automated assessment of CT for the detection and classification of HS and CAAH. We have included our observations for future research and the requirements for further evaluation.

4

Novel expert system for glaucoma identification using non-parametric spatial envelope energy spectrum with fundus images

Raghavendra U., Bhandary S. V., Gudigar A., Acharya U. R.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 1

170--180

EN

Glaucoma is the prime cause of blindness and early detection of it may prevent patients from vision loss. An expert system plays a vital role in glaucoma screening, which assist the ophthalmologists to make accurate decision. This paper proposes a novel technique for glaucoma detection using optic disk localization and non-parametric GIST descriptor. The method proposes a novel area based optic disk segmentation followed by the Radon transformation (RT). The change in the illumination levels of Radon transformed image are compensated using modified census transformation (MCT). The MCT images are then subjected to GIST descriptor to extract the spatial envelope energy spectrum. The obtained dimension of the GIST descriptor is reduced using locality sensitive discriminant analysis (LSDA) followed by various feature selection and ranking schemes. The ranked features are used to build an efficient classifier to detect glaucoma. Our system yielded a maximum accuracy (97.00%), sensitivity (97.80%) and specificity (95.80%) using support vector machine (SVM) classifier with nineteen features. Developed expert system also achieved maximum accuracy (93.62%), sensitivity (87.50%) and specificity (98.43%) for public dataset using twenty six features. The proposed method is efficient and computationally less expensive as it require only nineteen features to model a classifier for the huge dataset. Therefore the proposed method can be effectively utilized in hospitals for glaucoma screening.