Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning

Abstract

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.

Deep learning based phenotyping of medical images improves power for gene discovery of complex disease

“…While computer vision approaches to extract and analyze DXA scan derived phenotypes are not themselves novel 16,17,29,30 , this work is amongst the first to use this approach on a disease for which diagnosis is primarily radiographic, to demonstrate that having a quantitative endophenotype that captures additional information about variation in disease severity improves power for genomic and epidemiological analysis. Although not based on the imaging data, two novel phenotyping methods leveraging deep learning to impute missing data in the UKB and to generate disease liability scores from binary case-control data in the EHR have shown significant boosts in statistical power for genomic studies 31,32 .…”

Deep learning-based fundus image analysis for cardiovascular disease: a review

“…To the best of our knowledge, only one study has reported an excellent algorithm performance in CVD detection after integrating fundus images and dual-energy X-ray absorptiometry scans. 108 Second, the studies cited above showed good predicting performance of CVD risk factors, biomarkers, and other CVD-related conditions. Nevertheless, the studies did not adequately evaluate the added diagnostic value of the DL models by directly comparing the algorithms with the existing CVD risk assessment tools or stratification methods; this may impact the perceived applicability and acceptance by patients, regulatory agencies, and other healthcare providers involved in managing CVD.…”

“…To the best of our knowledge, only one study has reported an excellent algorithm performance in CVD detection after integrating fundus images and dual-energy X-ray absorptiometry scans. 108…”

Advancing systemic disease diagnosis through ophthalmic image‐based artificial intelligence

“…It was found that the accuracy of the classification model trained on retina images alone and DXA data alone was 75.6% and 77.4%, respectively, whereas the introduction of the multimodal model improved accuracy to 78.3%. These noninvasive combination methods provide a new approach to the early detection of CVDs 92 …”

“…These noninvasive combination methods provide a new approach to the early detection of CVDs. 92 The analysis of CVDs through AI-assisted ophthalmic imaging lags notably behind its application in neurological disorders. Current analyses primarily focus on fundus imaging, where accuracy in disease classification and severity assessment falls within the range of 0.7 to 0.9, matching expert-level evaluations in some studies.…”