Purpose The purpose of this study was to expedite the contouring process for MRI‐guided adaptive radiotherapy (MR‐IGART), a convolutional neural network (CNN) deep‐learning (DL) model is proposed to accurately segment the liver, kidneys, stomach, bowel and duodenum in 3D MR images. Methods Images and structure contours for 120 patients were collected retrospectively. Treatment sites included pancreas, liver, stomach, adrenal gland, and prostate. The proposed DL model contains a voxel‐wise label prediction CNN and a correction network which consists of two sub‐networks. The prediction CNN and sub‐networks in the correction network each includes a dense block which consists of twelve densely connected convolutional layers. The correction network was designed to improve the voxel‐wise labeling accuracy of a CNN by learning and enforcing implicit anatomical constraints in the segmentation process. Its sub‐networks learn to fix the erroneous classification of its previous network by taking as input both the original images and the softmax probability maps generated from its previous sub‐network. The parameters of each sub‐network were trained independently using piecewise training. The model was trained on 100 datasets, validated on 10 datasets and tested on the remaining 10 datasets. Dice coefficient, Hausdorff distance (HD) were calculated to evaluate the segmentation accuracy. Results The proposed DL model was able to segment the organs with good accuracy. The correction network outperformed the conditional random field (CRF), a most comparable method that is usually applied as a post‐processing step. For the 10 testing patients, the average Dice coefficients were 95.3 ± 0.73, 93.1 ± 2.22, 85.0 ± 3.75, 86.6 ± 2.69, and 65.5 ± 8.90 for liver, kidneys, stomach, bowel, and duodenum, respectively. The mean Hausdorff Distance (HD) were 5.41 ± 2.34, 6.23 ± 4.59, 6.88 ± 4.89, 5.90 ± 4.05, and 7.99 ± 6.84 mm, respectively. Manual contouring, as to correct the automatic segmentation results, was four times as fast as manual contouring from scratch. Conclusion The proposed method can automatically segment the liver, kidneys, stomach, bowel, and duodenum in 3D MR images with good accuracy. It is useful to expedite the manual contouring for MR‐IGART.

Limited-field RT is associated with less lymphopenia after RT plus temozolomide and does not adversely affect PFS or OS. Brain V25 Gy is confirmed as an important dosimetric predictor for ASL.

Deep generative models of 3D shapes have received a great deal of research interest. Yet, almost all of them generate discrete shape representations, such as voxels, point clouds, and polygon meshes. We present the first 3D generative model for a drastically different shape representationdescribing a shape as a sequence of computer-aided design (CAD) operations. Unlike meshes and point clouds, CAD models encode the user creation process of 3D shapes, widely used in numerous industrial and engineering design tasks. However, the sequential and irregular structure of CAD operations poses significant challenges for existing 3D generative models. Drawing an analogy between CAD operations and natural language, we propose a CAD generative network based on the Transformer. We demonstrate the performance of our model for both shape autoencoding and random shape generation. To train our network, we create a new CAD dataset consisting of 179,133 models and their CAD construction sequences. We have made this dataset publicly available to promote future research on this topic.

A decarboxylative protocol has been developed toward a range of carbocycles. The key success is based on the use of a batch of newly designed cyclic carbonates as substrates that can provide carbon–carbon zwitterion intermediate under palladium catalysis. The kinetics of the reactions are controllable toward either strained seven- or thermodynamically more favored five-membered carbocycles. The release of this chemistry will shed light on the synthesis of complex and valuable cyclic structures.

Prostate apoptosis response-4 (Par-4) is a leucine zipper protein that promotes neuronal cell death in Alzheimer's disease (AD). Neuronal degeneration in AD may result from extracellular accumulation of amyloid ␤ peptide (A␤) 1-42. To examine the effect of Par-4 on A␤ secretion and to reconcile amyloid/apoptosis hypotheses of AD, we generated IMR-32 cell lines that overexpress Par-4 and/or its leucine zipper domain. Overexpression of Par-4 did not significantly affect levels of the endogenously expressed ␤ amyloid precursor protein but drastically increased the A␤ 1-42 /A␤ total ratio in the conditioned media about 6 -8 h after trophic factor withdrawal. Time course analysis of caspase activation reveals that Par-4 overexpression exacerbated caspase activation, which is detectable within 2 h after trophic factor withdrawal. Furthermore, inhibition of caspase activity by the broad spectrum caspase inhibitor BDfmk significantly attenuated the Par-4-induced increase in A␤ 1-42 production. In addition, the effects of Par-4 on secretion of A␤ 1-42 were consistently blocked by co-expression of the leucine zipper domain, indicating that the effect of Par-4 on A␤ secretion may require its interaction with other protein(s). These results suggest that Par-4 increases secretion of A␤ 1-42 largely through a caspase-dependent pathway after apoptotic cascades are initiated.Mutations in familial Alzheimer's disease genes, such as ␤-amyloid precursor protein (APP) 1 , presenilin-1, and presenilin-2, have been shown to regulate the processing of APP and result in increased production of the longer form of amyloid ␤ peptide (A␤), A␤ 1-42 (1-5). It is widely accepted that neuronal degeneration in AD is caused by extracellular accumulation of A␤ 1-42. On the other hand, all three familial Alzheimer's disease genes have been shown to regulate neuronal apoptosis, suggesting that dysregulation of apoptotic pathways may play an important role in neuronal degeneration in AD (6 -10). Importantly, abnormal processing of APP and increased production of A␤ may be induced by apoptotic insults (11)(12)(13)(14). Several studies show that APP in neuronal cells can be processed by caspase-6 and -8 and that this processing can be blocked by caspase inhibitors (12, 15).We recently identified Par-4 as a novel cell death-promoting protein associated with neuronal degeneration in AD (16, 17 -42 (18 -20). These data strongly suggest that induction of Par-4 is an important and necessary event in the pathogenic mechanisms of Alzheimer's presenilin-1 mutations and is very likely involved in the abnormal processing of APP during the apoptotic process. To provide better solutions for the treatment of Alzheimer's disease, it is very important to reconcile amyloid/apoptosis hypotheses of AD and examine how Par-4 might alter APP processing during apoptosis, leading to increased production of the neurotoxic A␤ 1-42.The cell types responsible for overproduction of A␤ 1-42 are not completely known, although it has been suggested that A␤ 1-42 is produced by huma...