Evaluation of generalization ability for deep learning-based auto-segmentation accuracy in limited field of view CBCT of male pelvic region.

PURPOSE: The aim of this study was to evaluate generalization ability of segmentation accuracy for limited FOV CBCT in the male pelvic region using a full-image CNN. Auto-segmentation accuracy was evaluated using various datasets with different intensity distributions and FOV sizes. METHODS: A total of 171 CBCT datasets from patients with prostate cancer were enrolled. There were 151, 10, and 10 CBCT datasets acquired from Vero4DRT, TrueBeam STx, and Clinac-iX, respectively. The FOV for Vero4DRT, TrueBeam STx, and Clinac-iX was 20, 26, and 25 cm, respectively. The ROIs, including the bladder, prostate, rectum, and seminal vesicles, were manually delineated. The U2 -Net CNN network architecture was used to train the segmentation model. A total of 131 limited FOV CBCT datasets from Vero4DRT were used for training (104 datasets) and validation (27 datasets); thereafter the rest were for testing. The training routine was set to save the best weight values when the DSC in the validation set was maximized. Segmentation accuracy was qualitatively and quantitatively evaluated between the ground truth and predicted ROIs in the different testing datasets. RESULTS: The mean scores ± standard deviation of visual evaluation for bladder, prostate, rectum, and seminal vesicle in all treatment machines were 1.0 ± 0.7, 1.5 ± 0.6, 1.4 ± 0.6, and 2.1 ± 0.8 points, respectively. The median DSC values for all imaging devices were ≥0.94 for the bladder, 0.84-0.87 for the prostate and rectum, and 0.48-0.69 for the seminal vesicles. Although the DSC values for the bladder and seminal vesicles were significantly different among the three imaging devices, the DSC value of the bladder changed by less than 1% point. The median MSD values for all imaging devices were ≤1.2 mm for the bladder and 1.4-2.2 mm for the prostate, rectum, and seminal vesicles. The MSD values for the seminal vesicles were significantly different between the three imaging devices. CONCLUSION: The proposed method is effective for testing datasets with different intensity distributions and FOV from training datasets.

Improvement of Image Quality of Cone-beam CT Images by Three-dimensional Generative Adversarial Network.

Artifacts and defects in Cone-beam Computed Tomography (CBCT) images are a problem in radiotherapy and surgical procedures. Unsupervised learning-based image translation techniques have been studied to improve the image quality of head and neck CBCT images, but there have been few studies on improving the image quality of abdominal CBCT images, which are strongly affected by organ deformation due to posture and breathing. In this study, we propose a method for improving the image quality of abdominal CBCT images by translating the numerical values to the values of corresponding paired CT images using an unsupervised CycleGAN framework. This method preserves anatomical structure through adversarial learning that translates voxel values according to corresponding regions between CBCT and CT images of the same case. The image translation model was trained on 68 CT-CBCT datasets and then applied to 8 test datasets, and the effectiveness of the proposed method for improving the image quality of CBCT images was confirmed.

Geometric and dosimetric impact of 3D generative adversarial network-based metal artifact reduction algorithm on VMAT and IMPT for the head and neck region.

BACKGROUND: We investigated the geometric and dosimetric impact of three-dimensional (3D) generative adversarial network (GAN)-based metal artifact reduction (MAR) algorithms on volumetric-modulated arc therapy (VMAT) and intensity-modulated proton therapy (IMPT) for the head and neck region, based on artifact-free computed tomography (CT) volumes with dental fillings. METHODS: Thirteen metal-free CT volumes of the head and neck regions were obtained from The Cancer Imaging Archive. To simulate metal artifacts on CT volumes, we defined 3D regions of the teeth for pseudo-dental fillings from the metal-free CT volumes. HU values of 4000 HU were assigned to the selected teeth region of interest. Two different CT volumes, one with four (m4) and the other with eight (m8) pseudo-dental fillings, were generated for each case. These CT volumes were used as the Reference. CT volumes with metal artifacts were then generated from the Reference CT volumes (Artifacts). On the Artifacts CT volumes, metal artifacts were manually corrected for using the water density override method with a value of 1.0 g/cm3 (Water). By contrast, the CT volumes with reduced metal artifacts using 3D GAN model extension of CycleGAN were also generated (GAN-MAR). The structural similarity (SSIM) index within the planning target volume was calculated as quantitative error metric between the Reference CT volumes and the other volumes. After creating VMAT and IMPT plans on the Reference CT volumes, the reference plans were recalculated for the remaining CT volumes. RESULTS: The time required to generate a single GAN-MAR CT volume was approximately 30 s. The median SSIMs were lower in the m8 group than those in the m4 group, and ANOVA showed a significant difference in the SSIM for the m8 group (p < 0.05). Although the median differences in D98%, D50% and D2% were larger in the m8 group than the m4 group, those from the reference plans were within 3% for VMAT and 1% for IMPT. CONCLUSIONS: The GAN-MAR CT volumes generated in a short time were closer to the Reference CT volumes than the Water and Artifacts CT volumes. The observed dosimetric differences compared to the reference plan were clinically acceptable.

Deep Learning Based Lung Region Segmentation with Data Preprocessing by Generative Adversarial Nets.

In endoscopic surgery, it is necessary to understand the three-dimensional structure of the target region to improve safety. For organs that do not deform much during surgery, preoperative computed tomography (CT) images can be used to understand their three-dimensional structure, however, deformation estimation is necessary for organs that deform substantially. Even though the intraoperative deformation estimation of organs has been widely studied, two-dimensional organ region segmentations from camera images are necessary to perform this estimation. In this paper, we propose a region segmentation method using U-net for the lung, which is an organ that deforms substantially during surgery. Because the accuracy of the results for smoker lungs is lower than that for non-smoker lungs, we improved the accuracy by translating the texture of the lung surface using a CycleGAN.

Interactive bone drilling using a 2D pointing device to support Microendoscopic Discectomy planning.

PURPOSE: To support preoperative planning of bone drilling for Microendoscopic Discectomy, we present a set of interactive bone-drilling methods using a general 2D pointing device. METHODS: Unlike the existing methods, our framework has the following features: (1) the user can directly cut away arbitrary 3D regions on the volumetrically rendered image, (2) in order to provide a simple interface to end-users, our algorithms make 3D drilling possible through only a general-purpose wheel mouse, (3) to reduce both over-drilling and unnatural drilling of an unintended region, we introduce a smart depth control to ensure the continuity of the cutting operation and (4) a GPU-based rendering scheme for high-quality shading of clipped boundaries. RESULTS: We applied our techniques to some CT data of specific patients. Several experiments confirmed that the user was able to directly drill a 3D complex region on a volumetrically rendered lumber spine through simple mouse operation. Also, our rendering scheme clearly visualizes time-varying drilled surfaces at interactive rates. By comparing simulation results to actual postoperative CT images, we confirmed the user interactively simulates similar cutting to that carried out in real surgery. CONCLUSION: We concluded our techniques perform mouse-based, direct drilling of complex 3D regions with high-quality rendering of drilled boundaries and contribute to preoperative planning of Microendoscopic Discectomy.

Practical haptic navigation with clickable 3D region input interface for supporting master-slave type robotic surgery.

Conventional display in robotic surgery such as flat displays or stereoscopic displays decreases obtainable information around target tissue. For supporting manipulation and performing safe surgery, this paper proposes a haptic navigation method, which enables surgeons to avoid collision with untouchable regions around target tissue by producing force feedback through a master manipulator. This paper also developed an input interface for assignment of 3D untouchable regions through 2D device. Simulator based experiment clears effectiveness of the proposed haptic navigation for improving safety of robotic surgery.