Automated Detection and Visualization of Local Kidney Images with Artificial Intelligence Models
Kidney disease is a global health concern, often leading to kidney failure and impaired function. Artificial intelligence and deep learning have been extensively researched, with numerous proposed models and methods to improve kidney disease diagnosis. This work aims to enhance the efficiency and a...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Al-Nahrain Journal for Engineering Sciences
2024-12-01
|
| Series: | مجلة النهرين للعلوم الهندسية |
| Subjects: | |
| Online Access: | https://nahje.com/index.php/main/article/view/1275 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841545859548839936 |
|---|---|
| author | Hawraa Saleh Hadeel Kassim Aljobouri Hani M. Amasha |
| author_facet | Hawraa Saleh Hadeel Kassim Aljobouri Hani M. Amasha |
| author_sort | Hawraa Saleh |
| collection | DOAJ |
| description |
Kidney disease is a global health concern, often leading to kidney failure and impaired function. Artificial intelligence and deep learning have been extensively researched, with numerous proposed models and methods to improve kidney disease diagnosis. This work aims to enhance the efficiency and accuracy of the diagnostic system for kidney disease by using Deep Learning, thereby contributing to effective healthcare delivery. This work proposed three models: CNN, CNN-XGBoost and CNN-RF to extract features and classify kidney Ultrasound images into four categories: three abnormal cases (stones, hydronephrosis, and cysts) and one normal case. The models were tested on a real dataset of 1260 kidney ultrasound images (from 1000 patients) collected from the Lithotripsy Centre in Iraq. CNN models are often viewed as black boxes due to the challenge of understanding their learned behaviors, Visualizing Intermediate Activations (VIA) was used to address this issue. The proposed framework was assessed based on precision, recall, F1-score, and accuracy. CNN-RF is the most accurate model, with an accuracy of 99.6%. This study can potentially assist radiologists in high-volume medical facilities and enhance the accuracy of the diagnostic system for kidney disease.
|
| format | Article |
| id | doaj-art-d3c80c50f4ce4a8da30ad0b91da559e5 |
| institution | Kabale University |
| issn | 2521-9154 2521-9162 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Al-Nahrain Journal for Engineering Sciences |
| record_format | Article |
| series | مجلة النهرين للعلوم الهندسية |
| spelling | doaj-art-d3c80c50f4ce4a8da30ad0b91da559e52025-01-11T14:13:17ZengAl-Nahrain Journal for Engineering Sciencesمجلة النهرين للعلوم الهندسية2521-91542521-91622024-12-0127410.29194/NJES.27040465Automated Detection and Visualization of Local Kidney Images with Artificial Intelligence ModelsHawraa Saleh0Hadeel Kassim Aljobouri1https://orcid.org/0000-0003-1792-9230Hani M. Amasha2Department of Computer Engineering, College of Engineering, Al-Nahrain University, Baghdad, Iraq.Department of Biomedical Engineering, College of Engineering, Al-Nahrain University, Baghdad, Iraq.Biomedical Engineering Department, FMEE, Damascus University, Damascus, Syria Kidney disease is a global health concern, often leading to kidney failure and impaired function. Artificial intelligence and deep learning have been extensively researched, with numerous proposed models and methods to improve kidney disease diagnosis. This work aims to enhance the efficiency and accuracy of the diagnostic system for kidney disease by using Deep Learning, thereby contributing to effective healthcare delivery. This work proposed three models: CNN, CNN-XGBoost and CNN-RF to extract features and classify kidney Ultrasound images into four categories: three abnormal cases (stones, hydronephrosis, and cysts) and one normal case. The models were tested on a real dataset of 1260 kidney ultrasound images (from 1000 patients) collected from the Lithotripsy Centre in Iraq. CNN models are often viewed as black boxes due to the challenge of understanding their learned behaviors, Visualizing Intermediate Activations (VIA) was used to address this issue. The proposed framework was assessed based on precision, recall, F1-score, and accuracy. CNN-RF is the most accurate model, with an accuracy of 99.6%. This study can potentially assist radiologists in high-volume medical facilities and enhance the accuracy of the diagnostic system for kidney disease. https://nahje.com/index.php/main/article/view/1275CNNDeep LearningFeature ExtractionKidney DiseasesRFUltrasound Images |
| spellingShingle | Hawraa Saleh Hadeel Kassim Aljobouri Hani M. Amasha Automated Detection and Visualization of Local Kidney Images with Artificial Intelligence Models مجلة النهرين للعلوم الهندسية CNN Deep Learning Feature Extraction Kidney Diseases RF Ultrasound Images |
| title | Automated Detection and Visualization of Local Kidney Images with Artificial Intelligence Models |
| title_full | Automated Detection and Visualization of Local Kidney Images with Artificial Intelligence Models |
| title_fullStr | Automated Detection and Visualization of Local Kidney Images with Artificial Intelligence Models |
| title_full_unstemmed | Automated Detection and Visualization of Local Kidney Images with Artificial Intelligence Models |
| title_short | Automated Detection and Visualization of Local Kidney Images with Artificial Intelligence Models |
| title_sort | automated detection and visualization of local kidney images with artificial intelligence models |
| topic | CNN Deep Learning Feature Extraction Kidney Diseases RF Ultrasound Images |
| url | https://nahje.com/index.php/main/article/view/1275 |
| work_keys_str_mv | AT hawraasaleh automateddetectionandvisualizationoflocalkidneyimageswithartificialintelligencemodels AT hadeelkassimaljobouri automateddetectionandvisualizationoflocalkidneyimageswithartificialintelligencemodels AT hanimamasha automateddetectionandvisualizationoflocalkidneyimageswithartificialintelligencemodels |