Tunable image quality control of 3-D ultrasound using switchable CycleGAN.

In contrast to 2-D ultrasound (US) for uniaxial plane imaging, a 3-D US imaging system can visualize a volume along three axial planes. This allows for a full view of the anatomy, which is useful for gynecological (GYN) and obstetrical (OB) applications. Unfortunately, the 3-D US has an inherent limitation in resolution compared to the 2-D US. In the case of 3-D US with a 3-D mechanical probe, for example, the image quality is comparable along the beam direction, but significant deterioration in image quality is often observed in the other two axial image planes. To address this, here we propose a novel unsupervised deep learning approach to improve 3-D US image quality. In particular, using unmatched high-quality 2-D US images as a reference, we trained a recently proposed switchable CycleGAN architecture so that every mapping plane in 3-D US can learn the image quality of 2-D US images. Thanks to the switchable architecture, our network can also provide real-time control of image enhancement level based on user preference, which is ideal for a user-centric scanner setup. Extensive experiments with clinical evaluation confirm that our method offers significantly improved image quality as well user-friendly flexibility.

Endometrium segmentation on transvaginal ultrasound image using key-point discriminator.

PURPOSE: Transvaginal ultrasound imaging provides useful information for diagnosing endometrial pathologies and reproductive health. Endometrium segmentation in transvaginal ultrasound (TVUS) images is very challenging due to ambiguous boundaries and heterogeneous textures. In this study, we developed a new segmentation framework which provides robust segmentation against ambiguous boundaries and heterogeneous textures of TVUS images. METHODS: To achieve endometrium segmentation from TVUS images, we propose a new segmentation framework with a discriminator guided by four key points of the endometrium (namely, the endometrium cavity tip, the internal os of the cervix, and the two thickest points between the two basal layers on the anterior and posterior uterine walls). The key points of the endometrium are defined as meaningful points that are related to the characteristics of the endometrial morphology, namely the length and thickness of the endometrium. In the proposed segmentation framework, the key-point discriminator distinguishes a predicted segmentation map from a ground-truth segmentation map according to the key-point maps. Meanwhile, the endometrium segmentation network predicts accurate segmentation results that the key-point discriminator cannot discriminate. In this adversarial way, the key-point information containing endometrial morphology characteristics is effectively incorporated in the segmentation network. The segmentation network can accurately find the segmentation boundary while the key-point discriminator learns the shape distribution of the endometrium. Moreover, the endometrium segmentation can be robust to the heterogeneous texture of the endometrium. We conducted an experiment on a TVUS dataset that contained 3,372 sagittal TVUS images and the corresponding key points. The dataset was collected by three hospitals (Ewha Woman's University School of Medicine, Asan Medical Center, and Yonsei University College of Medicine) with the approval of the three hospitals' Institutional Review Board. For verification, fivefold cross-validation was performed. RESULT: The proposed key-point discriminator improved the performance of the endometrium segmentation, achieving 82.67 % for the Dice coefficient and 70.46% for the Jaccard coefficient. In comparison, on the TVUS images UNet, showed 58.69 % for the Dice coefficient and 41.59 % for the Jaccard coefficient. The qualitative performance of the endometrium segmentation was also improved over the conventional deep learning segmentation networks. Our experimental results indicated robust segmentation by the proposed method on TVUS images with heterogeneous texture and unclear boundary. In addition, the effect of the key-point discriminator was verified by an ablation study. CONCLUSION: We proposed a key-point discriminator to train a segmentation network for robust segmentation of the endometrium with TVUS images. By utilizing the key-point information, the proposed method showed more reliable and accurate segmentation performance and outperformed the conventional segmentation networks both in qualitative and quantitative comparisons.

Active contour configuration model for estimating the posterior ablative margin in image fusion of real-time ultrasound and 3D ultrasound or magnetic resonance images for radiofrequency ablation: an experimental study.

PURPOSE: The purpose of this study was to evaluate the accuracy of an active contour model for estimating the posterior ablative margin in images obtained by the fusion of real-time ultrasonography (US) and 3-dimensional (3D) US or magnetic resonance (MR) images of an experimental tumor model for radiofrequency ablation. METHODS: Chickpeas (n=12) and bovine rump meat (n=12) were used as an experimental tumor model. Grayscale 3D US and T1-weighted MR images were pre-acquired for use as reference datasets. US and MR/3D US fusion was performed for one group (n=4), and US and 3D US fusion only (n=8) was performed for the other group. Half of the models in each group were completely ablated, while the other half were incompletely ablated. Hyperechoic ablation areas were extracted using an active contour model from real-time US images, and the posterior margin of the ablation zone was estimated from the anterior margin. After the experiments, the ablated pieces of bovine rump meat were cut along the electrode path and the cut planes were photographed. The US images with the estimated posterior margin were compared with the photographs and post-ablation MR images. The extracted contours of the ablation zones from 12 US fusion videos and post-ablation MR images were also matched. RESULTS: In the four models fused under real-time US with MR/3D US, compression from the transducer and the insertion of an electrode resulted in misregistration between the real-time US and MR images, making the estimation of the ablation zones less accurate than was achieved through fusion between real-time US and 3D US. Eight of the 12 post-ablation 3D US images were graded as good when compared with the sectioned specimens, and 10 of the 12 were graded as good in a comparison with nicotinamide adenine dinucleotide staining and histopathologic results. CONCLUSION: Estimating the posterior ablative margin using an active contour model is a feasible way of predicting the ablation area, and US/3D US fusion was more accurate than US/MR fusion.