<abstract xmlns="http://www.w3.org/1999/xhtml">
<italic>Introduction: </italic>The brain is harmed by a medical condition known as a stroke when the blood vessels in the brain burst. Symptoms may appear when the brain’s flow of blood and other nutrients is disrupted. The World Health Organization (WHO) claims that stroke is the leading cause of disability and death worldwide. A stroke can be made less severe by detecting its different warning symptoms early. A brain stroke can be quickly diagnosed using computed tomography (CT) images. Time is passing quickly, although experts are studying every brain CT scan. This situation can cause therapy to be delayed and mistakes to be made. As a result, we focused on using an effective transfer learning approach for stroke detection.
<italic>Material and methods: </italic>To improve the detection accuracy, the stroke-affected region of the brain is segmented using the Red Fox optimization algorithm (RFOA). The processed area is then further processed using the Advanced Dragonfly Algorithm. The segmented image extracts include morphological, wavelet features, and grey-level co-occurrence matrix (GLCM). Modified ResNet152V2 is then used to classify the images of Normal and Stroke. We use the Brain Stroke CT Image Dataset to conduct tests using Python for implementation.
<italic>Results</italic>: Per the performance analysis, the proposed approach outperformed the other deep learning algorithms, achieving the best accuracy of 99.25%, sensitivity of 99.65%, F1-score of 99.06%, precision of 99.63%, and specificity of 99.56%.
<italic>Conclusions: </italic>The proposed deep learning-based classification system returns the best possible solution among all input predictive models considering performance criteria and improves the system’s efficacy; hence, it can assist doctors and radiologists in a better way to diagnose Brain Stroke patients.
</abstract>

Introduction: The brain is harmed by a medical condition known as a stroke when the blood vessels in the brain burst. Symptoms may appear when the brain’s flow of blood and other nutrients is disrupted. The World Health Organization (WHO) claims that stroke is the leading cause of disability and death worldwide. A stroke can be made less severe by detecting its different warning symptoms early. A brain stroke can be quickly diagnosed using computed tomography (CT) images. Time is passing quickly, although experts are studying every brain CT scan. This situation can cause therapy to be delayed and mistakes to be made. As a result, we focused on using an effective transfer learning approach for stroke detection.
Material and methods: To improve the detection accuracy, the stroke-affected region of the brain is segmented using the Red Fox optimization algorithm (RFOA). The processed area is then further processed using the Advanced Dragonfly Algorithm. The segmented image extracts include morphological, wavelet features, and grey-level co-occurrence matrix (GLCM). Modified ResNet152V2 is then used to classify the images of Normal and Stroke. We use the Brain Stroke CT Image Dataset to conduct tests using Python for implementation.
Results: Per the performance analysis, the proposed approach outperformed the other deep learning algorithms, achieving the best accuracy of 99.25%, sensitivity of 99.65%, F1-score of 99.06%, precision of 99.63%, and specificity of 99.56%.
Conclusions: The proposed deep learning-based classification system returns the best possible solution among all input predictive models considering performance criteria and improves the system’s efficacy; hence, it can assist doctors and radiologists in a better way to diagnose Brain Stroke patients.

Modified ResNet152v2: Binary Classification and Hybrid Segmentation of Brain Stroke Using Transfer Learning-Based Approach

School of Computer Science and Engineering, VIT-AP University

Polish Journal of Medical Physics and Engineering

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Introduction: The brain is harmed by a medical condition known as a stroke when the blood vessels in the brain burst. Symptoms may appear when the brain’s flow...

Modified ResNet152v2: Binary Classification and Hybrid Segmentation of Brain Stroke Using Transfer Learning-Based Approach

Data publikacji: 26 mar 2024

Zakres stron: 24 - 35

Otrzymano: 15 lip 2023

Przyjęty: 03 lut 2024

DOI: https://doi.org/10.2478/pjmpe-2024-0004

Słowa kluczowe
stroke, transfer learning approach, Red Fox optimization algorithm (RFOA), Advanced Dragonfly algorithm, morphological features, ResNet152v2

© 2024 Nallamotu Parimala et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Modified ResNet152v2: Binary Classification and Hybrid Segmentation of Brain Stroke Using Transfer Learning-Based Approach

Data publikacji: 26 mar 2024

Zakres stron: 24 - 35

Otrzymano: 15 lip 2023

Przyjęty: 03 lut 2024

DOI: https://doi.org/10.2478/pjmpe-2024-0004

Słowa kluczowestroke, transfer learning approach, Red Fox optimization algorithm (RFOA), Advanced Dragonfly algorithm, morphological features, ResNet152v2

© 2024 Nallamotu Parimala et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Słowa kluczowe
stroke, transfer learning approach, Red Fox optimization algorithm (RFOA), Advanced Dragonfly algorithm, morphological features, ResNet152v2