This study aimed to compare clinical courses and outcomes between pregnant and reproductive-aged non-pregnant women with COVID-19, and to assess the vertical transmission potential of COVID-19 in pregnancy. Methods: Medical records of pregnant and reproductive-aged non-pregnant women hospitalized with COVID-19 from January 15 to March 15, 2020 were retrospectively reviewed. The severity of disease, virus clearance time, and length of hospital stay were measured as the primary objective, while the vertical transmission potential of COVID-19 was also assessed. Results: Eighty-two patients (28 pregnant women, 54 reproductive-aged non-pregnant women) with laboratory-confirmed COVID-19 were enrolled in this study. Univariate regression indicated no association between pregnancy and severity of disease (OR 0.73, 95% CI 0.08-5.15; p = 0.76), virus clearance time (HR 1.16, 95% CI 0.65-2.01; p = 0.62), and length of hospital stay (HR 1.10, 95% CI 0.66-1.84; p = 0.71). Of the pregnant women, 22 delivered 23 live births, either by cesarean section (17, 60.7%) or vaginal delivery (5, 17.9%), and no neonate was infected with SARS-CoV-2. Conclusions: Pregnant women have comparable clinical courses and outcomes with reproductive-aged non-pregnant women when infected with SARS-CoV-2. No evidence supported vertical transmission of COVID-19 in the late stage of pregnancy, including vaginal delivery.

No abstract

Purpose The purpose of this educational report is to provide an overview of the present state-of-the-art PET auto-segmentation (PET-AS) algorithms and their respective validation, with an emphasis on providing the user with help in understanding the challenges and pitfalls associated with selecting and implementing a PET-AS algorithm for a particular application. Approach A brief description of the different types of PET-AS algorithms is provided using a classification based on method complexity and type. The advantages and the limitations of the current PET-AS algorithms are highlighted based on current publications and existing comparison studies. A review of the available image datasets and contour evaluation metrics in terms of their applicability for establishing a standardized evaluation of PET-AS algorithms is provided. The performance requirements for the algorithms and their dependence on the application, the radiotracer used and the evaluation criteria are described and discussed. Finally, a procedure for algorithm acceptance and implementation, as well as the complementary role of manual and auto-segmentation are addressed. Findings A large number of PET-AS algorithms have been developed within the last 20 years. Many of the proposed algorithms are based on either fixed or adaptively selected thresholds. More recently, numerous papers have proposed the use of more advanced image analysis paradigms to perform semi-automated delineation of the PET images. However, the level of algorithm validation is variable and for most published algorithms is either insufficient or inconsistent which prevents recommending a single algorithm. This is compounded by the fact that realistic image configurations with low signal-to-noise ratios (SNR) and heterogeneous tracer distributions have rarely been used. Large variations in the evaluation methods used in the literature point to the need for a standardized evaluation protocol. Conclusions Available comparison studies suggest that PET-AS algorithms relying on advanced image analysis paradigms provide generally more accurate segmentation than approaches based on PET activity thresholds, particularly for realistic configurations. However, this may not be the case for simple shape lesions in situations with a narrower range of parameters, where simpler methods may also perform well. Recent algorithms which employ some type of consensus or automatic selection between several PET-AS methods have potential to overcome the limitations of the individual methods when appropriately trained. In either case, accuracy evaluation is required for each different PET scanner and scanning and image reconstruction protocol. For the simpler, less robust approaches, adaptation to scanning conditions, tumor type, and tumor location by optimization of parameters is necessary. The results from the method evaluation stage can be used to estimate the contouring uncertainty. All PET-AS contours should be critically verified by a physician. A standard test, i.e., a benchmark dedicated to ...

Respiratory motion can cause significant dose delivery errors in conformal radiation therapy for thoracic and upper abdominal tumors. Four-dimensional computed tomography (4D CT) has been proposed to provide the image data necessary to model tumor motion and consequently reduce these errors. The purpose of this work was to compare 4D CT reconstruction methods using amplitude sorting and phase angle sorting. A 16-slice CT scanner was operated in ciné mode to acquire 25 scans consecutively at each couch position through the thorax. The patient underwent synchronized external respiratory measurements. The scans were sorted into 12 phases based, respectively, on the amplitude and direction (inhalation or exhalation) or on the phase angle (0-360 degrees) of the external respiratory signal. With the assumption that lung motion is largely proportional to the measured respiratory amplitude, the variation in amplitude corresponds to the variation in motion for each phase. A smaller variation in amplitude would associate with an improved reconstructed image. Air content, defined as the amount of air within the lungs, bronchi, and trachea in a 16-slice CT segment and used by our group as a surrogate for internal motion, was correlated to the respiratory amplitude and phase angle throughout the lungs. For the 35 patients who underwent quiet breathing, images (similar to those used for treatment planning) and animations (used to display respiratory motion) generated using amplitude sorting displayed fewer reconstruction artifacts than those generated using phase angle sorting. The variations in respiratory amplitude were significantly smaller (P < 0.001) with amplitude sorting than those with phase angle sorting. The subdivision of the breathing cycle into more (finer) phases improved the consistency in respiratory amplitude for amplitude sorting, but not for phase angle sorting. For 33 of the 35 patients, the air content showed significantly improved (P < 0.001) correlation with the respiratory amplitude than with the phase angle, suggesting a stronger relationship between internal motion and amplitude. Overall, amplitude sorting performed better than phase angle sorting for 33 of the 35 patients and equally well for two patients who were immobilized with a stereotactic body frame and an abdominal compression plate.

We present DeepICP -a novel end-to-end learningbased 3D point cloud registration framework that achieves comparable registration accuracy to prior state-of-the-art geometric methods. Different from other keypoint based methods where a RANSAC procedure is usually needed, we implement the use of various deep neural network structures to establish an end-to-end trainable network. Our keypoint detector is trained through this end-to-end structure and enables the system to avoid the inference of dynamic objects, leverages the help of sufficiently salient features on stationary objects, and as a result, achieves high robustness. Rather than searching the corresponding points among existing points, the key contribution is that we innovatively generate them based on learned matching probabilities among a group of candidates, which can boost the registration accuracy. Our loss function incorporates both the local similarity and the global geometric constraints to ensure all above network designs can converge towards the right direction. We comprehensively validate the effectiveness of our approach using both the KITTI dataset and the Apollo-SouthBay dataset. Results demonstrate that our method achieves comparable or better performance than the state-of-the-art geometry-based methods. Detailed ablation and visualization analysis are included to further illustrate the behavior and insights of our network. The low registration error and high robustness of our method makes it attractive for substantial applications relying on the point cloud registration task.