Abstract #1560

AutoML Radiomics-Based Classification for Opportunistic Osteoporosis Screening with Lumbar Fat and Water using IDEAL-IQ MRI

Yung-Yin Cheng^1,2, Chun-Wen Chen³, Chun-Han Liao^1,4,5, Ming-Cheng Liu^1,6, Shao-Chieh Lin¹, Pin-Sian Lyu⁷, Tzu-Yu Chiu⁷, Chen Chung Ou⁷, and Yi-Jui Liu⁷

¹Ph.D. program in Electrical and Communication Engineering in Feng Chia University, Taichung, Taiwan, taichung, Taiwan, ²Department of Medical Imaging, Chung Shan Medical University Hospital,Taichung, Taiwan, taichung, Taiwan, ³Department of Radiology, School of Medicine, National Defense Medical Center, Taipei, Taiwan, taichung, Taiwan, ⁴Department of Medical Imaging, Yuanlin Christian Hospital, Changhua, Taiwan, taichung, Taiwan, ⁵Department of Medical Imaging, Changhua Christian Hospital, Changhua, Taiwan, taichung, Taiwan, ⁶Department of Radiology, Taichung Veterans General Hospital, Taichung, Taiwan, taichung, Taiwan, ⁷Department of Automatic Control Engineering, Feng Chia University, Taichung, Taiwan, taichung, Taiwan

Synopsis

Keywords: Skeletal, Skeletal

Motivation: Could lumbar fat and water MRI be as an opportunistic screening tool?

Goal(s): To develop autoML radiomics-Based Classification for osteoporosis prediction using lumbar fat and water MRI.

Approach: A TPOP-radiomics classification model was trained using lumbar fat and water images obtained through the IDEAL-IQ method in normal and osteoporosis patients identified by DeXA. Three datasets of radiomics features were used, categorized based on their dimension (2D, 3D, and projection map)

Results: Our results indicate that the best model from the AutoML process demonstrated mean sensitivity of 0.745 and mean specificity of 0.758 in distinguishing between normal and osteroporosis.

Impact: Because osteoporosis is often considered a 'silent' disease, routine IDEAL-IQ lumbar scans have the potential to serve as an opportunistic screening tool for reducing the risk of fragility fractures, which are associated with morbidity and mortality.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.