Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning
Cardiovascular diseases (CVD) are the leading cause of death worldwide. People affected by CVDs may go undiagnosed until the occurrence of a serious heart failure event such as stroke, heart attack, and myocardial infraction. In Qatar, there is a lack of studies focusing on CVD diagnosis based on no...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/12/4310 |
| _version_ | 1827656829175332864 |
|---|---|
| author | Hamada R. H. Al-Absi Mohammad Tariqul Islam Mahmoud Ahmed Refaee Muhammad E. H. Chowdhury Tanvir Alam |
| author_facet | Hamada R. H. Al-Absi Mohammad Tariqul Islam Mahmoud Ahmed Refaee Muhammad E. H. Chowdhury Tanvir Alam |
| author_sort | Hamada R. H. Al-Absi |
| collection | DOAJ |
| description | Cardiovascular diseases (CVD) are the leading cause of death worldwide. People affected by CVDs may go undiagnosed until the occurrence of a serious heart failure event such as stroke, heart attack, and myocardial infraction. In Qatar, there is a lack of studies focusing on CVD diagnosis based on non-invasive methods such as retinal image or dual-energy X-ray absorptiometry (DXA). In this study, we aimed at diagnosing CVD using a novel approach integrating information from retinal images and DXA data. We considered an adult Qatari cohort of 500 participants from Qatar Biobank (QBB) with an equal number of participants from the CVD and the control groups. We designed a case-control study with a novel multi-modal (combining data from multiple modalities—DXA and retinal images)—to propose a deep learning (DL)-based technique to distinguish the CVD group from the control group. Uni-modal models based on retinal images and DXA data achieved 75.6% and 77.4% accuracy, respectively. The multi-modal model showed an improved accuracy of 78.3% in classifying CVD group and the control group. We used gradient class activation map (GradCAM) to highlight the areas of interest in the retinal images that influenced the decisions of the proposed DL model most. It was observed that the model focused mostly on the centre of the retinal images where signs of CVD such as hemorrhages were present. This indicates that our model can identify and make use of certain prognosis markers for hypertension and ischemic heart disease. From DXA data, we found higher values for bone mineral density, fat content, muscle mass and bone area across majority of the body parts in CVD group compared to the control group indicating better bone health in the Qatari CVD cohort. This seminal method based on DXA scans and retinal images demonstrate major potentials for the early detection of CVD in a fast and relatively non-invasive manner. |
| first_indexed | 2024-03-09T22:33:50Z |
| format | Article |
| id | doaj.art-6875afabd1d143e3a71d9c11c4093388 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T22:33:50Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6875afabd1d143e3a71d9c11c40933882023-11-23T18:51:20ZengMDPI AGSensors1424-82202022-06-012212431010.3390/s22124310Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep LearningHamada R. H. Al-Absi0Mohammad Tariqul Islam1Mahmoud Ahmed Refaee2Muhammad E. H. Chowdhury3Tanvir Alam4College of Science and Engineering, Hamad Bin Khalifa University, Doha 34110, QatarComputer Science Department, Southern Connecticut State University, New Haven, CT 06515, USAGeriatric Department, Hamad Medical Corporation, Doha 3050, QatarDepartment of Electrical Engineering, Qatar University, Doha 2713, QatarCollege of Science and Engineering, Hamad Bin Khalifa University, Doha 34110, QatarCardiovascular diseases (CVD) are the leading cause of death worldwide. People affected by CVDs may go undiagnosed until the occurrence of a serious heart failure event such as stroke, heart attack, and myocardial infraction. In Qatar, there is a lack of studies focusing on CVD diagnosis based on non-invasive methods such as retinal image or dual-energy X-ray absorptiometry (DXA). In this study, we aimed at diagnosing CVD using a novel approach integrating information from retinal images and DXA data. We considered an adult Qatari cohort of 500 participants from Qatar Biobank (QBB) with an equal number of participants from the CVD and the control groups. We designed a case-control study with a novel multi-modal (combining data from multiple modalities—DXA and retinal images)—to propose a deep learning (DL)-based technique to distinguish the CVD group from the control group. Uni-modal models based on retinal images and DXA data achieved 75.6% and 77.4% accuracy, respectively. The multi-modal model showed an improved accuracy of 78.3% in classifying CVD group and the control group. We used gradient class activation map (GradCAM) to highlight the areas of interest in the retinal images that influenced the decisions of the proposed DL model most. It was observed that the model focused mostly on the centre of the retinal images where signs of CVD such as hemorrhages were present. This indicates that our model can identify and make use of certain prognosis markers for hypertension and ischemic heart disease. From DXA data, we found higher values for bone mineral density, fat content, muscle mass and bone area across majority of the body parts in CVD group compared to the control group indicating better bone health in the Qatari CVD cohort. This seminal method based on DXA scans and retinal images demonstrate major potentials for the early detection of CVD in a fast and relatively non-invasive manner.https://www.mdpi.com/1424-8220/22/12/4310cardiovascular diseasesDXAretinadeep learningmachine learningQatar Biobank (QBB) |
| spellingShingle | Hamada R. H. Al-Absi Mohammad Tariqul Islam Mahmoud Ahmed Refaee Muhammad E. H. Chowdhury Tanvir Alam Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning Sensors cardiovascular diseases DXA retina deep learning machine learning Qatar Biobank (QBB) |
| title | Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning |
| title_full | Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning |
| title_fullStr | Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning |
| title_full_unstemmed | Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning |
| title_short | Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning |
| title_sort | cardiovascular disease diagnosis from dxa scan and retinal images using deep learning |
| topic | cardiovascular diseases DXA retina deep learning machine learning Qatar Biobank (QBB) |
| url | https://www.mdpi.com/1424-8220/22/12/4310 |
| work_keys_str_mv | AT hamadarhalabsi cardiovasculardiseasediagnosisfromdxascanandretinalimagesusingdeeplearning AT mohammadtariqulislam cardiovasculardiseasediagnosisfromdxascanandretinalimagesusingdeeplearning AT mahmoudahmedrefaee cardiovasculardiseasediagnosisfromdxascanandretinalimagesusingdeeplearning AT muhammadehchowdhury cardiovasculardiseasediagnosisfromdxascanandretinalimagesusingdeeplearning AT tanviralam cardiovasculardiseasediagnosisfromdxascanandretinalimagesusingdeeplearning |