Fully automatic and robust segmentation of the clinical target volume for radiotherapy of breast cancer using big data and deep learning

PurposeTo train and evaluate a very deep dilated residual network (DD-ResNet) for fast and consistent auto-segmentation of the clinical target volume (CTV) for breast cancer (BC) radiotherapy with big data.MethodsDD-ResNet was an end-to-end model enabling fast training and testing. We used big data comprising 800 patients who underwent breast-conserving therapy for evaluation. The CTV were validated by experienced radiation oncologists. We performed a fivefold cross-validation to test the performance of the model. The segmentation accuracy was quantified by the Dice similarity coefficient (DSC) and the Hausdorff distance (HD). The performance of the proposed model was evaluated against two different deep learning models: deep dilated convolutional neural network (DDCNN) and deep deconvolutional neural network (DDNN).ResultsMean DSC values of DD-ResNet (0.91 and 0.91) were higher than the other two networks (DDCNN: 0.85 and 0.85; DDNN: 0.88 and 0.87) for both right-sided and left-sided BC. It also has smaller mean HD values of 10.5 mm and 10.7 mm compared with DDCNN (15.1 mm and 15.6 mm) and DDNN (13.5 mm and 14.1 mm). Mean segmentation time was 4 s, 21 s and 15 s per patient with DDCNN, DDNN and DD-ResNet, respectively. The DD-ResNet was also superior with regard to results in the literature.ConclusionsThe proposed method could segment the CTV accurately with acceptable time consumption. It was invariant to the body size and shape of patients and could improve the consistency of target delineation and streamline radiotherapy workflows.     

NELDA：基于网络嵌入的lncRNA-疾病关联关系预测

目的 长非编码RNA（lncRNAs）参与多种重要的生物学过程并与各种人类疾病密切相关,因此,lncRNA-疾病关联预测研究有助于疾病的诊断、治疗和在分子水平理解人类疾病的发生发展机制。目前,大多数lncRNA-疾病关联预测方法倾向于浅层整合lncRNA和疾病的相关信息,忽略网络拓扑结构中的深层嵌入特征;另外通过随机选取lncRNA-疾病非关联对构建负样本训练集合,影响预测方法的鲁棒性。方法 本文提出一种基于网络嵌入的NELDA方法,预测潜在的lncRNA-疾病关联关系。NELDA首先利用lncRNA 表达谱、疾病本体论和已知的lncRNA-疾病关联关系,构建lncRNA相似性网络、疾病相似性网络和lncRNA-疾病关联网络。然后,通过设计4个深度自编码器分别从lncRNA/疾病的相似性网络、lncRNA-疾病关联网络学习lncRNA和疾病的低维网络嵌入特征。串联lncRNA和疾病的相似性网络嵌入特征及lncRNA和疾病的关联网络嵌入特征,分别输入两个支持向量机分类器预测lncRNA-疾病关联。最后,采用加权融合策略融合两个支持向量机分类器的预测结果,给出lncRNA-疾病关联关系的最终预测结果。另外,根据已知的lncRNA-疾病关联对和疾病语义相似性,设计一种负样本选取策略构建可信度相对较高的lncRNA-疾病非关联对样本集,用以改善分类器的鲁棒性,该策略通过设计一种打分函数为每对lncRNA-疾病进行打分,选取得分较低的lncRNA-疾病对作为lncRNA-疾病非关联对样本（即负样本）。结果 十折交叉验证实验结果表明：NELDA能够有效预测lncRNA-疾病关联关系,其AUC达到0.982 7,比现有LDASR和 LDNFSGB方法分别提高了0.062 7和0.020 7。另外,负样本选取策略与决策级加权融合策略能够有效改善NELDA预测性能。胃癌和乳腺癌案例研究中,29/40（72.5%）预测的与胃癌和乳腺癌关联lncRNAs,在近期文献和公共数据库中能够发现相关的支撑证据。结论 这些实验结果表明,NELDA是一种有效的lncRNA-疾病关联关系预测方法,具有挖掘潜在lncRNA-疾病关联关系的能力。     

Prediction of regulation relationship between protein interactions in signaling networks

The discovery of regulation relationship of protein interactions is crucial for the mechanism research in signaling network. Bioinformatics methods can be used to accelerate the discovery of regulation relationship between protein interactions, to distinguish the activation relations from inhibition relations. In this paper, we describe a novel method to predict the regulation relations of protein interactions in the signaling network. We detected 4,417 domain pairs that were significantly enriched in the activation or inhibition dataset. Three machine learning methods, logistic regression, support vector machines(SVMs), and naïve bayes, were explored in the classifier models. The prediction power of three different models was evaluated by 5-fold cross-validation and the independent test dataset. The area under the receiver operating characteristic curve for logistic regression, SVM, and naïve bayes models was 0.946, 0.905 and 0.809, respectively. Finally, the logistic regression classifier was applied to the human proteome-wide interaction dataset, and 2,591 interactions were predicted with their regulation relations, with 2,048 in activation and 543 in inhibition. This model based on domains can be used to identify the regulation relations between protein interactions and furthermore reconstruct signaling pathways.     

Fetal head moulding: finite element analysis of a fetal skull subjected to uterine pressures during the first stage of labour

Fetal head moulding is a phenomenon which may contribute to satisfactory progress during delivery as it allows the fetal head to accommodate to the geometry of the passage. In contrast, excessive head moulding may result in cranial birth injuries and thus affect the infant shortly or even long after birth. One group of researchers in the past investigated the biomechanics of fetal head moulding from an engineering point of view and limited themselves to a static, linear model of the parietal bones. In this paper, we present a non-linear model of the deformation of a complete fetal skull, when subjected to pressures exerted by the cervix, during the first stage of labour. The design of the model involves four main steps: shape recovery of the fetal skull, the generation of a valid and compatible mesh for finite element analysis (FEA), the specification of a physical model and the analysis of deformation. Results of the analysis show good agreement with those obtained from clinical experiments on the quantitative assessment of fetal head moulding. The model also displays shapes after moulding which have been reported in previous studies and which are generally known in the obstetric and paediatric communities.     

Roles for modularity and constraint in the evolution of cranial diversity among Anolis lizards

Complex organismal structures are organized into modules, suites of traits that develop, function, and vary in a coordinated fashion. By limiting or directing covariation among component traits, modules are expected to represent evolutionary building blocks and to play an important role in morphological diversification. But how stable are patterns of modularity over macroevolutionary timescales? Comparative analyses are needed to address the macroevolutionary effect of modularity, but to date few have been conducted. We describe patterns of skull diversity and modularity in Caribbean Anolis lizards. We first diagnose the primary axes of variation in skull shape and then examine whether diversification of skull shape is concentrated to changes within modules or whether changes arose across the structure as a whole. We find no support for the hypothesis that cranial modules are conserved as species diversify in overall skull shape. Instead we find that anole skull shape and modularity patterns independently converge. In anoles, skull modularity is evolutionarily labile and may reflect the functional demands of unique skull shapes. Our results suggest that constraints have played little role in limiting or directing the diversification of head shape in Anolis lizards.     

Evaluation of a multi-atlas CT synthesis approach for MRI-only radiotherapy treatment planning

Background and purposeComputed tomography (CT) imaging is the current gold standard for radiotherapy treatment planning (RTP). The establishment of a magnetic resonance imaging (MRI) only RTP workflow requires the generation of a synthetic CT (sCT) for dose calculation. This study evaluates the feasibility of using a multi-atlas sCT synthesis approach (sCT_a) for head and neck and prostate patients.Material and methodsThe multi-atlas method was based on pairs of non-rigidly aligned MR and CT images. The sCT_a was obtained by registering the MRI atlases to the patient’s MRI and by fusing the mapped atlases according to morphological similarity to the patient. For comparison, a bulk density assignment approach (sCT_bda) was also evaluated. The sCT_bda was obtained by assigning density values to MRI tissue classes (air, bone and soft-tissue). After evaluating the synthesis accuracy of the sCTs (mean absolute error), sCT-based delineations were geometrically compared to the CT-based delineations. Clinical plans were re-calculated on both sCTs and a dose-volume histogram and a gamma analysis was performed using the CT dose as ground truth.ResultsResults showed that both sCTs were suitable to perform clinical dose calculations with mean dose differences less than 1% for both the planning target volume and the organs at risk. However, only the sCT_a provided an accurate and automatic delineation of bone.ConclusionsCombining MR delineations with our multi-atlas CT synthesis method could enable MRI-only treatment planning and thus improve the dosimetric and geometric accuracy of the treatment, and reduce the number of imaging procedures.     

A Statistical Skull Geometry Model for Children 0-3 Years Old

Head injury is the leading cause of fatality and long-term disability for children. Pediatric heads change rapidly in both size and shape during growth, especially for children under 3 years old (YO). To accurately assess the head injury risks for children, it is necessary to understand the geometry of the pediatric head and how morphologic features influence injury causation within the 0–3 YO population. In this study, head CT scans from fifty-six 0–3 YO children were used to develop a statistical model of pediatric skull geometry. Geometric features important for injury prediction, including skull size and shape, skull thickness and suture width, along with their variations among the sample population, were quantified through a series of image and statistical analyses. The size and shape of the pediatric skull change significantly with age and head circumference. The skull thickness and suture width vary with age, head circumference and location, which will have important effects on skull stiffness and injury prediction. The statistical geometry model developed in this study can provide a geometrical basis for future development of child anthropomorphic test devices and pediatric head finite element models.     

A machine learning approach to investigate the relationship between shape features and numerically predicted risk of ascending aortic aneurysm

Geometric features of the aorta are linked to patient risk of rupture in the clinical decision to electively repair an ascending aortic aneurysm (AsAA). Previous approaches have focused on relationship between intuitive geometric features (e.g., diameter and curvature) and wall stress. This work investigates the feasibility of a machine learning approach to establish the linkages between shape features and FEA-predicted AsAA rupture risk, and it may serve as a faster surrogate for FEA associated with long simulation time and numerical convergence issues. This method consists of four main steps: (1) constructing a statistical shape model (SSM) from clinical 3D CT images of AsAA patients; (2) generating a dataset of representative aneurysm shapes and obtaining FEA-predicted risk scores defined as systolic pressure divided by rupture pressure (rupture is determined by a threshold criterion); (3) establishing relationship between shape features and risk by using classifiers and regressors; and (4) evaluating such relationship in cross-validation. The results show that SSM parameters can be used as strong shape features to make predictions of risk scores consistent with FEA, which lead to an average risk classification accuracy of 95.58% by using support vector machine and an average regression error of 0.0332 by using support vector regression, while intuitive geometric features have relatively weak performance. Compared to FEA, this machine learning approach is magnitudes faster. In our future studies, material properties and inhomogeneous thickness will be incorporated into the models and learning algorithms, which may lead to a practical system for clinical applications.     

User-controlled pipelines for feature integration and head and neck radiation therapy outcome predictions

PurposePrecision cancer medicine is dependent on accurate prediction of disease and treatment outcome, requiring integration of clinical, imaging and interventional knowledge. User controlled pipelines are capable of feature integration with varied levels of human interaction. In this work we present two pipelines designed to combine clinical, radiomic (quantified imaging), and RTx-omic (quantified radiation therapy (RT) plan) information for prediction of locoregional failure (LRF) in head and neck cancer (H&N).MethodsPipelines were designed to extract information and model patient outcomes based on clinical features, computed tomography (CT) imaging, and planned RT dose volumes. We predict H&N LRF using: 1) a highly user-driven pipeline that leverages modular design and machine learning for feature extraction and model development; and 2) a pipeline with minimal user input that utilizes deep learning convolutional neural networks to extract and combine CT imaging, RT dose and clinical features for model development.ResultsClinical features with logistic regression in our highly user-driven pipeline had the highest precision recall area under the curve (PR-AUC) of 0.66 (0.33–0.93), where a PR-AUC = 0.11 is considered random. CONCLUSIONS: Our work demonstrates the potential to aggregate features from multiple specialties for conditional-outcome predictions using pipelines with varied levels of human interaction. Most importantly, our results provide insights into the importance of data curation and quality, as well as user, data and methodology bias awareness as it pertains to result interpretation in user controlled pipelines.     

A Study on the Finite Element Model for Head Injury in Facial Collision Accident

In order to predict and evaluate injury mechanism and biomechanical response of the facial impact on head injury in a crash accident. With the combined modern medical imaging technologies, namely computed tomography (CT) and magnetic resonance imaging (MRI), both geometric and finite element (FE) models for human head-neck with detailed cranio-facial structure were developed. The cadaveric head impact tests were conducted to validate the headneck finite element model. The intracranial pressure, skull dynamic response and skull-brain relative displacement of the whole head-neck model were compared with experimental data. Nine typical cases of facial traffic accidents were simulated, with the individual stress wave propagation paths to the intracranial contents through the facial and cranial skeleton being discussed thoroughly. Intracranial pressure, von Mises stress and shear stress distribution were achieved. It is proved that facial structure dissipates a large amount of impact energy to protect the brain in its most natural way. The propagation path and distribution of stress wave in the skull and brain determine the mechanism of brain impact injury, which provides a theoretic basis for the diagnosis, treatment and protection of craniocerebral injury caused by facial impact.     

DCAMCP: A deep learning model based on capsule network and attention mechanism for molecular carcinogenicity prediction

The carcinogenicity of drugs can have a serious impact on human health, so carcinogenicity testing of new compounds is very necessary before being put on the market. Currently, many methods have been used to predict the carcinogenicity of compounds. However, most methods have limited predictive power and there is still much room for improvement. In this study, we construct a deep learning model based on capsule network and attention mechanism named DCAMCP to discriminate between carcinogenic and non-carcinogenic compounds. We train the DCAMCP on a dataset containing 1564 different compounds through their molecular fingerprints and molecular graph features. The trained model is validated by fivefold cross-validation and external validation. DCAMCP achieves an average accuracy (ACC) of 0.718 ± 0.009, sensitivity (SE) of 0.721 ± 0.006, specificity (SP) of 0.715 ± 0.014 and area under the receiver-operating characteristic curve (AUC) of 0.793 ± 0.012. Meanwhile, comparable results can be achieved on an external validation dataset containing 100 compounds, with an ACC of 0.750, SE of 0.778, SP of 0.727 and AUC of 0.811, which demonstrate the reliability of DCAMCP. The results indicate that our model has made progress in cancer risk assessment and could be used as an efficient tool in drug design.     

Variability,morphometrics, and co-variation of the os lacrimale in Cervidae

In Ruminantia, the lacrimal bone forms a considerable part of the facial skeleton, and the morphology of its facial facet is highly variable when compared to other mammals. In this study, we quantify the species-specific variability in size and shape of the lacrimal facial facet in species of Cervidae (deer) and relate it to systematics and various aspects of their ecology and behavior. We sampled 143 skull specimens from 10 genera; 12 Moschus and 3 Tragulus specimens were used as outgroups. We find that size and shape of the lacrimal facial facet allow differentiating most species analyzed here, except for Mazama gouazoubira and Capreolus capreolus. Size and shape of the lacrimal facial facet vary widely across Cervidae regardless of their systematic relationships, ecology or behavior. Thus, we could not detect a unique signature of adaptational criteria in lacrimal morphology. Our data indicate that the lacrimal facial facet scales allometrically with skull size, in particular, the lacrimojugal length scales positively and the lacrimomaxillar length scales negatively. However, correlation analyses did not reveal any differences in the integration of the lacrimal bone with any specific skull module in any of the species compared. Lastly, we could not ascertain any correlation between the size and position of the preorbital depression with the size and shape of the lacrimal facial facet. We conclude that the lacrimal facial facet is highly flexible and may rapidly adjust to its surrounding bones. Its allometric growth appears to be an example of exaptation: changes in size and shape in the context of the increase of the skull length provide lacrimal contacts, in particular, a lacrimojugal one, which may serve to reduce mechanical loads resulting from increasingly larger antlers in large cervids.     

GVC-Net: Global Vascular Context Network for Cerebrovascular Segmentation Using Sparse Labels

ObjectivesCerebrovascular disease is a serious threat to human health. Because of its high mortality and disability rate, early diagnosis and prevention are very important. The performance of existing cerebrovascular segmentation methods based on deep learning depends on the integrity of labels. However, manual labels are usually of low quality and poor connectivity at small blood vessels, which directly affects the cerebrovascular segmentation results.Material and methodIn this paper, we propose a new segmentation network to segment cerebral vessels from MRA images by using sparse labels. The long-distance dependence between vascular structures is captured by the global vascular context module, and the topology is constrained by the hybrid loss function to segment the cerebral vessels with good connectivity.ResultExperiments show that our method performed with a sensitivity, precision, dice similarity coefficient, intersection over union and centerline dice similarity coefficient of 61.24%, 75.58%, 67.66%, 51.13% and 83.79% respectively.ConclusionThe obtained results reveal that the proposed cerebrovascular segmentation network has better segmentation performance for cerebrovascular segmentation under sparse labels, and can suppress the noise of background to a certain extent.     

Discriminating lysosomal membrane protein types using dynamic neural network

This work presents a dynamic artificial neural network methodology, which classifies the proteins into their classes from their sequences alone: the lysosomal membrane protein classes and the various other membranes protein classes. In this paper, neural networks-based lysosomal-associated membrane protein type prediction system is proposed. Different protein sequence representations are fused to extract the features of a protein sequence, which includes seven feature sets; amino acid (AA) composition, sequence length, hydrophobic group, electronic group, sum of hydrophobicity, R-group, and dipeptide composition. To reduce the dimensionality of the large feature vector, we applied the principal component analysis. The probabilistic neural network, generalized regression neural network, and Elman regression neural network (RNN) are used as classifiers and compared with layer recurrent network (LRN), a dynamic network. The dynamic networks have memory, i.e. its output depends not only on the input but the previous outputs also. Thus, the accuracy of LRN classifier among all other artificial neural networks comes out to be the highest. The overall accuracy of jackknife cross-validation is 93.2% for the data-set. These predicted results suggest that the method can be effectively applied to discriminate lysosomal associated membrane proteins from other membrane proteins (Type-I, Outer membrane proteins, GPI-Anchored) and Globular proteins, and it also indicates that the protein sequence representation can better reflect the core feature of membrane proteins than the classical AA composition.     

A commentary on the growth of the human brain and skull

This paper tests the suggestion put forth by Tanner ('55) and Eichorn and Bayley ('62) to the effect that the brain participates in the parapubertal spurt of growth which characterizes many of the dimensions of the human body. To this end, longitudinal data consisting of oriented head roentgenograms of 11 boys were examined. Two measurements were taken directly from each lateral head film: (1) skull length, measured from glabella to opisthocranion, and (2) endocranial length, the maximum length of the endocranial contour in the mid-sagittal plane. While many of the individual cumulative curves depicting growth in skull length exhibit a parapubertal acceleration, all of the curves for endocranial length comprise segments of a parabolic arc representing a single decelerating phase of growth. Mean incremental curves, mathematically fitted, further emphasize the differences in velocity and pattern of size attainment for the two dimensions tested. The data here presented, then, fail to implicate the brain in the general spurt of growth evident for the external dimensions of the head at adolescence. It is suggested that two discrete systems are evident in the growth of the skull: a rapidly growing neural system essentially completed by adolescence, and a facial system of slower growth and longer duration. The conventional measurement of skull length cuts across both systems, appraising neural growth and the cerebral skeletal envelope prior to adolescence, and then superimposing the facial component, the forward projection of the frontal sinus, during adolescence and post-adolescence.     

不同DNA聚合酶对运用ARTIC工作流的新型冠状病毒纳米孔测序的影响

摘要 目的：为了验证不同高保真DNA聚合酶是否会对运用ARTIC工作流进行新型冠状病毒纳米孔测序产生影响。方法：使用英国Nanopore公司MinION测序仪对2份已获得全基因组序列的新冠肺炎确诊病例核酸样本分别采用KAPA HiFi HotStart ReadyMix,PrimeSTAR?誖GXL DNA Polymerase和NEBNext High-Fidelity 2X PCR Master Mix进行ARTIC工作流的多重PCR扩增,对扩增产物进行测序,并对测序质量进行分析。结果：不同高保真DNA聚合酶在相同扩增条件下,扩增产物的质检结果和测序质量均不相同,NEBNext High-Fidelity 2X PCR Master Mix在覆盖度和测序深度上明显好于另外两种酶。结论：NEBNext High-Fidelity 2X PCR Master Mix在纳米孔新型冠状病毒ARTIC快速测序工作流中的应用效果较好。     

山顶洞101号男性头骨的三维颅面复原

山顶洞101号头骨化石是东亚地区保存最为完整的化石之一,是探讨东亚地区现代人起源的重要研究材料。本文依据数据集中现生人的面部软组织平均分布,提出了计算机三维颅面复原方法,实现了101号头骨生前面貌的预测复原。主要包括三个步骤：首先使用CT完成了101号男性头骨和下颌骨仿制模型的三维重建。然后,利用计算机技术将现生人的面部软组织分布作为101号头骨的面部软组织分布,实现了颅面虚拟复原,并采用手工绘画技巧再现了复原面貌的形态特征。最后,提出了一种基于面部软组织分布和面貌统计形状模型的形态分析方法,实现了颅面复原结果的评估。山顶洞101号头骨的复原面貌具有头部较长、额头前倾、眉弓粗壮等特征,与101号头骨的几何形态基本一致。该技术再现了更新世晚期人类的脑颅及面部的形态特征,为古人类颅面复原的研究提供了技术支持和参考资料。     

A new soft-tissue simulation strategy for cranio-maxillofacial surgery using facial muscle template model

We propose a computationally efficient, bio-mechanically relevant soft-tissue simulation method for cranio-maxillofacial (CMF) surgery. Special emphasis is given to comply with the current clinical workflow. A template-based facial muscle prediction was introduced to avoid laborious segmentation from medical images. In addition, transversely isotropic mass-tensor model (MTM) was applied to realize the directional behavior of facial muscles in short computation time. Finally, sliding contact was incorporated to mimic realistic boundary condition in error-sensitive regions. Mechanical simulation result was compared with commercial finite element software. And retrospective validation study with post-operative scan of four CMF cases was performed.     

Construction of a prognostic immune signature for lower grade glioma that can be recognized by MRI radiomics features to predict survival in LGG patients

BackgroundThis study aimed to identify a series of prognostically relevant immune features by immunophenoscore. Immune features were explored using MRI radiomics features to prediction the overall survival (OS) of lower-grade glioma (LGG) patients and their response to immune checkpoints.MethodLGG data were retrieved from TCGA and categorized into training and internal validation datasets. Patients attending the First Affiliated Hospital of Harbin Medical University were included in an external validation cohort. An immunophenoscore-based signature was built to predict malignant potential and response to immune checkpoint inhibitors in LGG patients. In addition, a deep learning neural network prediction model was built for validation of the immunophenoscore-based signature.ResultsImmunophenotype-associated mRNA signatures (IMriskScore) for outcome prediction and ICB therapeutic effects in LGG patients were constructed. Deep learning of neural networks based on radiomics showed that MRI radiomic features determined IMriskScore. Enrichment analysis and ssGSEA correlation analysis were performed. Mutations in CIC significantly improved the prognosis of patients in the high IMriskScore group. Therefore, CIC is a potential therapeutic target for patients in the high IMriskScore group. Moreover, IMriskScore is an independent risk factor that can be used clinically to predict LGG patient outcomes.ConclusionsThe IMriskScore model consisting of a sets of biomarkers, can independently predict the prognosis of LGG patients and provides a basis for the development of personalized immunotherapy strategies. In addition, IMriskScore features were predicted by MRI radiomics using a deep learning approach using neural networks. Therefore, they can be used for the prognosis of LGG patients.