Abstract
The purpose of this study was to directly and quantitatively measure BMD from Cone-beam CT (CBCT) images by enhancing the linearity and uniformity of the bone intensities based on a hybrid deep-learning model (QCBCT-NET) of combining the generative adversarial network (Cycle-GAN) and U-Net, and to compare the bone images enhanced by the QCBCT-NET with those by Cycle-GAN and U-Net. We used two phantoms of human skulls encased in acrylic, one for the training and validation datasets, and the other for the test dataset. We proposed the QCBCT-NET consisting of Cycle-GAN with residual blocks and a multi-channel U-Net using paired training data of quantitative CT (QCT) and CBCT images. The BMD images produced by QCBCT-NET significantly outperformed the images produced by the Cycle-GAN or the U-Net in mean absolute difference (MAD), peak signal to noise ratio (PSNR), normalized cross-correlation (NCC), structural similarity (SSIM), and linearity when compared to the original QCT image. The QCBCT-NET improved the contrast of the bone images by reflecting the original BMD distribution of the QCT image locally using the Cycle-GAN, and also spatial uniformity of the bone images by globally suppressing image artifacts and noise using the two-channel U-Net. The QCBCT-NET substantially enhanced the linearity, uniformity, and contrast as well as the anatomical and quantitative accuracy of the bone images, and demonstrated more accuracy than the Cycle-GAN and the U-Net for quantitatively measuring BMD in CBCT.
Highlights
The purpose of this study was to directly and quantitatively measure Bone mineral density (BMD) from Cone-beam CT (CBCT) images by enhancing the linearity and uniformity of the bone intensities based on a hybrid deep-learning model (QCBCT-NET) of combining the generative adversarial network (Cycle-GAN) and U-Net, and to compare the bone images enhanced by the QCBCT-NET with those by Cycle-GAN and U-Net
The BMD images of QCBCTs significantly outperformed the CYC_CBCT and U_CBCT images in mean absolute difference (MAD), peak signal to noise ratio (PSNR), structural similarity (SSIM), and normalized cross-correlation (NCC) at both the maxilla and mandible area when compared to the original quantitative CT (QCT) images (Table 1)
Compared to the BMD measurements from the CYC_CBCT image, the BMD from the QCBCT showed increases of 38% MAD, 20% PSNR, 45% SSIM, 40% NCC, 80% Spatial nonuniformity (SNU), and 84% Slope at the maxilla, and 39% MAD, 20% PSNR, 50% SSIM, 40% NCC, 47% SNU, and 102% Slope at the mandible for CBCT images under condition of 80 kVp and 8 mA (Table 2)
Summary
The purpose of this study was to directly and quantitatively measure BMD from Cone-beam CT (CBCT) images by enhancing the linearity and uniformity of the bone intensities based on a hybrid deep-learning model (QCBCT-NET) of combining the generative adversarial network (Cycle-GAN) and U-Net, and to compare the bone images enhanced by the QCBCT-NET with those by Cycle-GAN and U-Net. We used two phantoms of human skulls encased in acrylic, one for the training and validation datasets, and the other for the test dataset. Some studies investigated the relationship between CBCT voxel intensity values and MDCT HUs using a BMD calibration phantom with material inserts of different attenuation coefficients[17,23,24,25,26,27]. The U-Net based approach could efficiently synthesize artifact-suppressed CT-like CBCT images from CBCT images containing global scattering and local artifacts[43,44]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have