Related Experiment Video
Updated: Jun 15, 2025
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Deep learning-derived splenic radiomics, genomics, and coronary artery disease
Meghana Kamineni1, Vineet Raghu2,3, Buu Truong4,5
1Harvard Medical School, Boston, MA.
Insights
The spleen plays a role in coronary artery disease (CAD) risk. Deep learning radiomics identified splenic features linked to CAD genetics, revealing new insights into disease mechanisms and the 9p21 locus.
Area of Science:
- Medical Imaging
- Genomics
- Cardiovascular Disease Research
Background:
- Coronary artery disease (CAD) remains a leading cause of mortality despite advances in managing traditional risk factors.
- The role of the spleen, a key organ in the hematopoietic system, in CAD risk is largely unknown.
- The spleen's structure makes it suitable for radiologic investigation to uncover novel mechanistic insights into CAD.
Purpose of the Study:
- To investigate the association between splenic radiomic features and CAD.
- To explore the genetic underpinnings of the spleen's role in CAD using genome-wide association analyses.
- To establish a novel framework for understanding the splenic axis in CAD pathogenesis.
Main Methods:
- Utilized deep learning-based image segmentation and radiomics to extract 107 splenic features from abdominal MRIs of 42,059 UK Biobank participants.
- Applied regression analysis to identify splenic radiomic features associated with CAD.
- Conducted genome-wide association analyses to identify genetic loci associated with these radiomic features and explored overlap with known CAD loci.
Main Results:
- Identified 10 splenic radiomic features associated with CAD.
- Genome-wide association analysis revealed 219 loci associated with CAD-related splenic features, including 35 previously reported CAD loci.
- Discovered that variants at the 9p21 locus are associated with specific splenic features, such as run length non-uniformity, offering insight into its elusive mechanism.
Conclusions:
- The study presents a novel framework combining deep learning radiomics and genomics to uncover the splenic axis in CAD.
- Provides evidence for a genetic connection between the spleen and CAD, highlighting the spleen as a potential causal tissue.
- Offers new insights into the mechanisms of the 9p21 locus in CAD pathogenesis and demonstrates the utility of non-invasive radiomics for linking imaging, genetics, and clinical outcomes.
Background:
Despite advances in managing traditional risk factors, coronary artery disease (CAD) remains the leading cause of mortality. Circulating hematopoietic cells influence risk for CAD, but the role of a key regulating organ, spleen, is unknown. The understudied spleen is a 3-dimensional structure of the hematopoietic system optimally suited for unbiased radiologic investigations toward novel mechanistic insights.
Methods:
Deep learning-based image segmentation and radiomics techniques were utilized to extract splenic radiomic features from abdominal MRIs of 42,059 UK Biobank participants. Regression analysis was used to identify splenic radiomics features associated with CAD. Genome-wide association analyses were applied to identify loci associated with these radiomics features. Overlap between loci associated with CAD and the splenic radiomics features was explored to understand the underlying genetic mechanisms of the role of the spleen in CAD.
Results:
We extracted 107 splenic radiomics features from abdominal MRIs, and of these, 10 features were associated with CAD. Genome-wide association analysis of CAD-associated features identified 219 loci, including 35 previously reported CAD loci, 7 of which were not associated with conventional CAD risk factors. Notably, variants at 9p21 were associated with splenic features such as run length non-uniformity.
Conclusions:
Our study, combining deep learning with genomics, presents a new framework to uncover the splenic axis of CAD. Notably, our study provides evidence for the underlying genetic connection between the spleen as a candidate causal tissue-type and CAD with insight into the mechanisms of 9p21, whose mechanism is still elusive despite its initial discovery in 2007. More broadly, our study provides a unique application of deep learning radiomics to non-invasively find associations between imaging, genetics, and clinical outcomes.
