Automated Fast Prediction of Bone Mineral Density From Low-dose Computed Tomography.

Authors

Zhou K,Xin E,Yang S,Luo X,Zhu Y,Zeng Y,Fu J,Ruan Z,Wang R,Geng D,Yang L

Affiliations (5)

  • Academy for Engineering and Technology, Fudan University, Shanghai, China (K.Z., E.X., X.L., D.G.).
  • Academy for Engineering and Technology, Fudan University, Shanghai, China (K.Z., E.X., X.L., D.G.); Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai 200232, China (E.X.).
  • Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China (S.Y., Y.Z., Y.Z., J.F., Z.R., R.W., D.G., L.Y.).
  • Academy for Engineering and Technology, Fudan University, Shanghai, China (K.Z., E.X., X.L., D.G.); Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China (S.Y., Y.Z., Y.Z., J.F., Z.R., R.W., D.G., L.Y.); Shanghai Engineering Research Center of Intelligent Imaging for Critical Brain Diseases, Shanghai, China (D.G., L.Y.); Institute of Functional and Molecular Medical Imaging, Fudan University, Shanghai, China (D.G., L.Y.).
  • Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China (S.Y., Y.Z., Y.Z., J.F., Z.R., R.W., D.G., L.Y.); Shanghai Engineering Research Center of Intelligent Imaging for Critical Brain Diseases, Shanghai, China (D.G., L.Y.); Institute of Functional and Molecular Medical Imaging, Fudan University, Shanghai, China (D.G., L.Y.). Electronic address: [email protected].

Abstract

Low-dose chest CT (LDCT) is commonly employed for the early screening of lung cancer. However, it has rarely been utilized in the assessment of volumetric bone mineral density (vBMD) and the diagnosis of osteoporosis (OP). This study investigated the feasibility of using deep learning to establish a system for vBMD prediction and OP classification based on LDCT scans. This study included 551 subjects who underwent both LDCT and QCT examinations. First, the U-net was developed to automatically segment lumbar vertebrae from single 2D LDCT slices near the mid-vertebral level. Then, a prediction model was proposed to estimate vBMD, which was subsequently employed for detecting OP and osteopenia (OA). Specifically, two input modalities were constructed for the prediction model. The performance metrics of the models were calculated and evaluated. The segmentation model exhibited a strong correlation with manual segmentation, achieving a mean Dice similarity coefficient (DSC) of 0.974, sensitivity of 0.964, positive predictive value (PPV) of 0.985, and Hausdorff distance of 3.261 in the test set. Linear regression and Bland-Altman analysis demonstrated strong agreement between the predicted vBMD from two-channel inputs and QCT-derived vBMD, with a root mean square error of 8.958 mg/mm<sup>3</sup> and an R<sup>2</sup> of 0.944. The areas under the curve for detecting OP and OA were 0.800 and 0.878, respectively, with an overall accuracy of 94.2%. The average processing time for this system was 1.5 s. This prediction system could automatically estimate vBMD and detect OP and OA on LDCT scans, providing great potential for the osteoporosis screening.

Topics

Bone DensityTomography, X-Ray ComputedOsteoporosisDeep LearningRadiographic Image Interpretation, Computer-AssistedJournal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.