Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification
Inherently ultrasound images are susceptible to noise which leads to several image quality issues. Hence, rating of an image’s quality is crucial since diagnosing diseases requires accurate and high-quality ultrasound images. This research presents an intelligent architecture to rate the...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Journal of Translational Engineering in Health and Medicine |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9853521/ |
_version_ | 1811266230485516288 |
---|---|
author | Muhammad Minoar Hossain Md. Mahmodul Hasan Md. Abdur Rahim Mohammad Motiur Rahman Mohammad Abu Yousuf Samer Al-Ashhab Hanan F. Akhdar Salem A. Alyami Akm Azad Mohammad Ali Moni |
author_facet | Muhammad Minoar Hossain Md. Mahmodul Hasan Md. Abdur Rahim Mohammad Motiur Rahman Mohammad Abu Yousuf Samer Al-Ashhab Hanan F. Akhdar Salem A. Alyami Akm Azad Mohammad Ali Moni |
author_sort | Muhammad Minoar Hossain |
collection | DOAJ |
description | Inherently ultrasound images are susceptible to noise which leads to several image quality issues. Hence, rating of an image’s quality is crucial since diagnosing diseases requires accurate and high-quality ultrasound images. This research presents an intelligent architecture to rate the quality of ultrasound images. The formulated image quality recognition approach fuses feature from a Fuzzy convolutional neural network (fuzzy CNN) and a handcrafted feature extraction method. We implement the fuzzy layer in between the last max pooling and the fully connected layer of the multiple state-of-the-art CNN models to handle the uncertainty of information. Moreover, the fuzzy CNN uses Particle swarm optimization (PSO) as an optimizer. In addition, a novel Quantitative feature extraction machine (QFEM) extracts hand-crafted features from ultrasound images. Next, the proposed method uses different classifiers to predict the image quality. The classifiers categories ultrasound images into four types (normal, noisy, blurry, and distorted) instead of binary classification into good or poor-quality images. The results of the proposed method exhibit a significant performance in accuracy (99.62%), precision (99.62%), recall (99.61%), and f1-score (99.61%). This method will assist a physician in automatically rating informative ultrasound images with steadfast operation in real-time medical diagnosis. |
first_indexed | 2024-04-12T20:39:32Z |
format | Article |
id | doaj.art-88d42a091152439f93d3ef363ecfb18f |
institution | Directory Open Access Journal |
issn | 2168-2372 |
language | English |
last_indexed | 2024-04-12T20:39:32Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Translational Engineering in Health and Medicine |
spelling | doaj.art-88d42a091152439f93d3ef363ecfb18f2022-12-22T03:17:28ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722022-01-011011210.1109/JTEHM.2022.31979239853521Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality IdentificationMuhammad Minoar Hossain0https://orcid.org/0000-0002-3936-5539Md. Mahmodul Hasan1Md. Abdur Rahim2https://orcid.org/0000-0003-1717-5109Mohammad Motiur Rahman3Mohammad Abu Yousuf4https://orcid.org/0000-0001-8065-7173Samer Al-Ashhab5Hanan F. Akhdar6https://orcid.org/0000-0001-5144-7169Salem A. Alyami7https://orcid.org/0000-0002-5507-9399Akm Azad8Mohammad Ali Moni9https://orcid.org/0000-0003-0756-1006Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Tangail, BangladeshDepartment of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Tangail, BangladeshDepartment of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Tangail, BangladeshDepartment of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Tangail, BangladeshInstitute of Information Technology, Jahangirnagar University, Savar, Dhaka, BangladeshDepartment of Mathematics and Statistics, Faculty of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi ArabiaDepartment of Physics, Faculty of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi ArabiaDepartment of Mathematics and Statistics, Faculty of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi ArabiaFaculty of Science, Engineering and Technology, Swinburne University of Technology Sydney, Parramatta, NSW, AustraliaSchool of Health and Rehabilitation Sciences, The University of Queensland, Brisbane, QLD, AustraliaInherently ultrasound images are susceptible to noise which leads to several image quality issues. Hence, rating of an image’s quality is crucial since diagnosing diseases requires accurate and high-quality ultrasound images. This research presents an intelligent architecture to rate the quality of ultrasound images. The formulated image quality recognition approach fuses feature from a Fuzzy convolutional neural network (fuzzy CNN) and a handcrafted feature extraction method. We implement the fuzzy layer in between the last max pooling and the fully connected layer of the multiple state-of-the-art CNN models to handle the uncertainty of information. Moreover, the fuzzy CNN uses Particle swarm optimization (PSO) as an optimizer. In addition, a novel Quantitative feature extraction machine (QFEM) extracts hand-crafted features from ultrasound images. Next, the proposed method uses different classifiers to predict the image quality. The classifiers categories ultrasound images into four types (normal, noisy, blurry, and distorted) instead of binary classification into good or poor-quality images. The results of the proposed method exhibit a significant performance in accuracy (99.62%), precision (99.62%), recall (99.61%), and f1-score (99.61%). This method will assist a physician in automatically rating informative ultrasound images with steadfast operation in real-time medical diagnosis.https://ieeexplore.ieee.org/document/9853521/Ultrasound imagequantitative feature extraction machine (QFEM)particle swarm optimization (PSO)feature fusionfuzzy convolutional neural networkfeature extraction |
spellingShingle | Muhammad Minoar Hossain Md. Mahmodul Hasan Md. Abdur Rahim Mohammad Motiur Rahman Mohammad Abu Yousuf Samer Al-Ashhab Hanan F. Akhdar Salem A. Alyami Akm Azad Mohammad Ali Moni Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification IEEE Journal of Translational Engineering in Health and Medicine Ultrasound image quantitative feature extraction machine (QFEM) particle swarm optimization (PSO) feature fusion fuzzy convolutional neural network feature extraction |
title | Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification |
title_full | Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification |
title_fullStr | Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification |
title_full_unstemmed | Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification |
title_short | Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification |
title_sort | particle swarm optimized fuzzy cnn with quantitative feature fusion for ultrasound image quality identification |
topic | Ultrasound image quantitative feature extraction machine (QFEM) particle swarm optimization (PSO) feature fusion fuzzy convolutional neural network feature extraction |
url | https://ieeexplore.ieee.org/document/9853521/ |
work_keys_str_mv | AT muhammadminoarhossain particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT mdmahmodulhasan particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT mdabdurrahim particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT mohammadmotiurrahman particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT mohammadabuyousuf particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT sameralashhab particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT hananfakhdar particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT salemaalyami particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT akmazad particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification AT mohammadalimoni particleswarmoptimizedfuzzycnnwithquantitativefeaturefusionforultrasoundimagequalityidentification |