Search

Titanium alloys have emerged as a significant aerospace material due to the high strength, good corrosion resistance and high temperature resistance thereof, but such alloys also have poor machinability because of the unique properties. Rapid tool wear is a serious problem for titanium alloy machining, with tool wear resulting in different tool edges. In the present study, finite element technology was used to establish a 2D cutting numerical model, so as to investigate the influence of the different cutting edges caused by tool wear during the machining process of titanium alloy TC21. In the cutting model, four different types of tool edges, including sharp edge, round edge, chamfer edge and crater edge, were established to analyze the influence of different tool edges on the cutting process of TC21 alloy. Additionally, the material model, chip separation model, friction model and heat transfer model have been included in the established model. A series of cutting simulations based on the model were conducted, through which the chip morphology, cutting temperature, cutting force, surface morphology and residual stress under the different tool edges were analyzed. The simulation results were compared with the experimental results, and indicated that the tool edge is a significant factor in the machining process of TC21 alloy. A proper cutting edge can improve the cutting quality.

The current theory of carcinogenesis for the deadliest of 'ovarian' cancers-high-grade serous carcinoma (HGSC)-holds that the malignancy develops first in the fallopian tube and spreads to the ovaries, peritoneum, and/or regional lymph nodes. This is based primarily on the observation of early forms of serous neoplasia (serous tubal intraepithelial lesions [STILs], and serous tubal intraepithelial carcinomas [STICS]) in the fimbria of women undergoing risk reduction surgery. However, these lesions are uncommon in the general population, confer a low risk (5%) of HGSC following their removal in at-risk women with germ-line BRCA1/2 mutations, and require 4 or more years to recur as intraperitoneal HGSC. These features suggest that isolated STILs and STICs behave as precursors, with uncertain cancer risk rather than carcinomas. Their evolution to HGSC within, or after, escape from the tube could proceed stepwise with multiple biologic events; however, it is unclear whether tubal or ovarian HGSCs encountered in the setting of advanced disease evolved in the same fashion. The latter scenario could also be explained by a 'catastrophic' model in which STICs suddenly develop with invasive and metastatic potential, overwhelming or obscuring the site of origin. Moreover, a similar model might explain the sudden emergence of HGSC in the peritoneal cavity following escape of precursor cells years before. Long-term follow-up data from opportunistic or prophylactic salpingectomy should shed light on where malignant transformation occurs, as well as the timeline from precursor to metastatic HGSC. © 2022 The Pathological Society of Great Britain and Ireland.

Abstract Allergic rhinitis (AR) is an allergic disease characterized as (immunoglobulin, IgE)-mediated type I hypersensitivity disorder. Regulatory T cells (Tregs) play a crucial role in AR. In the present study, we aimed to investigate the mechanism of how Tregs are regulated by long noncoding RNA HCP5 and the regulatory role of HCP5 in IL-13-induced inflammatory response in nasal epithelial cells (NECs) from AR patients. Peripheral blood mononuclear cells (PBMCs) and NECs were obtained from collected blood samples and nasal epithelial tissues. CD4+ T cells and Tregs were purified using certain cell isolation kits from PBMCs and Tregs were also differentiated from CD4+ T cells using recombinant human IL-2 and TGF-β. The expression levels of HCP5, miR-16, ATXN2L, GM-CSF, eotaxin, and MUC5AC were detected by real-time PCR and western blot. The concentrations of inflammatory cytokines were detected by enzyme-linked immunosorbent assay (ELISA). The interaction among HCP5, miR-16, and ATXN2L were verified by dual-luciferase reporter assay. lncRNA HCP5 expression dramatically downregulated in PBMCs, CD4+ T cells, Tregs, and nasal tissues of AR patients, as well as in IL-13-treated NECs. HCP5 promoted Tregs differentiation and proliferation via targeting miR-16/ATXN2L axis. Additionally, HCP5 inhibited IL-13-induced GM-CSF, eotaxin, and MUC5AC production in NECs. HCP5 sponged miR-16 and negatively regulated its expression, and miR-16 targeted ATXN2L and inhibition of miR-16 suppressed IL-13-induced GM-CSF, eotaxin, and MUC5AC expression. HCP5/miR-16/ATXN2L axis mediated Tregs proliferation and functions in AR. Besides, the regulation of IL-13-induced dysfunction of NECs by lncRNA HCP5 depended on miR-16/ATXN2L in the inflammatory response of AR.

Automated assessment of patients with Parkinson's disease (PD) is urgently required in clinical practice to improve the diagnostic efficiency and objectivity and to remotely monitor the motor disorder symptoms and general health of these patients, especially in view of the travel restrictions due to the recent coronavirus epidemic. Gait motor disorder is one of the critical manifestations of PD, and automated assessment of gait is vital to realize automated assessment of PD patients. To this end, we propose a novel two-stream spatial-temporal attention graph convolutional network (2s-ST-AGCN) for video assessment of PD gait motor disorder. Specifically, the skeleton sequence of human body is extracted from videos to construct spatial-temporal graphs of joints and bones, and a two-stream spatial-temporal graph convolutional network is then built to simultaneously model the static spatial information and dynamic temporal variations. The multi-scale spatial-temporal attention-aware mechanism is also designed to effectively extract the discriminative spatial-temporal features. The deep supervision strategy is then embedded to minimize classification errors, thereby guiding the weight update process of the hidden layer to promote significant discriminative features. Besides, two model-driven terms are integrated into this deep learning framework to strengthen multi-scale similarity in the deep supervision and realize sparsification of discriminative features. Extensive experiments on the clinical video dataset show that the proposed model exhibits good performance with an accuracy of 65.66% and an acceptable accuracy of 98.90%, which is much better than that of the existing sensor- and vision-based methods for Parkinsonian gait assessment. Thus, the proposed method is potentially useful for assessing PD gait motor disorder in clinical practice.

Alzheimer's disease (AD) is the most common cognitive disorder. In recent years, many computer-aided diagnosis techniques have been proposed for AD diagnosis and progression predictions. Among them, graph neural networks (GNNs) have received extensive attention owing to their ability to effectively fuse multimodal features and model the correlation between samples. However, many GNNs for node classification use an entire dataset to construct a large fixed-graph structure, which cannot be used for independent testing. To overcome this limitation while maintaining the advantages of the GNN, we propose an auto-metric GNN (AMGNN) model for AD diagnosis. First, a metric-based meta-learning strategy is introduced to realize inductive learning for independent testing through multiple node classification tasks. In the meta-tasks, the small graphs help make the model insensitive to the sample size, thus improving the performance under small sample size conditions. Furthermore, an AMGNN layer with a probability constraint is designed to realize node similarity metric learning and effectively fuse multimodal data. We verified the model on two tasks based on the TADPOLE dataset: early AD diagnosis and mild cognitive impairment (MCI) conversion prediction. Our model provides excellent performance on both tasks with accuracies of 94.44% and 87.50% and median accuracies of 94.19% and 86.25%, respectively. These results show that our model improves flexibility while ensuring a good classification performance, thus promoting the development of graph-based deep learning algorithms for disease diagnosis.

Glioblastoma multiforme (GBM) is the most common type of brain tumors with high recurrence and mortality rates. After chemotherapy treatment, GBM patients still show a high rate of differentiating pseudoprogression (PsP), which is often confused as true tumor progression (TTP) due to high phenotypical similarities. Thus, it is crucial to construct an automated diagnosis model for differentiating between these two types of glioma progression. However, attaining this goal is impeded by the limited data availability and the high demand for interpretability in clinical settings. In this work, we propose an interpretable structure-constrained graph neural network (ISGNN) with enhanced features to automatically discriminate between PsP and TTP. This network employs a metric-based meta-learning strategy to aggregate class-specific graph nodes, focus on meta-tasks associated with various small graphs, thus improving the classification performance on small-scale datasets. Specifically, a node feature enhancement module is proposed to account for the relative importance of node features and enhance their distinguishability through inductive learning. A graph generation constraint module enables learning reasonable graph structures to improve the efficiency of information diffusion while avoiding propagation errors. Furthermore, model interpretability can be naturally enhanced based on the learned node features and graph structures that are closely related to the classification results. Comprehensive experimental evaluation of our method demonstrated excellent interpretable results in the diagnosis of glioma progression. In general, our work provides a novel systematic GNN approach for dealing with data scarcity and enhancing decision interpretability. Our source codes will be released at https://github.com/SJTUBME-QianLab/GBM-GNN.

Objectives The SWI/SNF complex core subunit SMARCB1 is inactivated in a variety of neoplasms that share characteristic “rhabdoid” cytomorphology. The aim of this study was to evaluate SMARCB1-deficient soft tissue neoplasms on cytology to identify diagnostic clues. Methods Eleven SMARCB1-deficient tumors, including six epithelioid sarcomas, three malignant rhabdoid tumors, one epithelioid malignant peripheral nerve sheath tumor (MPNST), and one poorly differentiated chordoma with fine-needle aspiration (FNA), serous effusion, or touch prep (TP) from two institutions, were included. Targeted next-generation sequencing (NGS) was performed in two cases. Results Evaluation of FNA (n = 4), effusion (n = 4), and TP (n = 3) in nine adult and two pediatric patients demonstrated cellular samples (n = 11), epithelioid cells with rhabdoid morphology (n = 9), eccentrically located nuclei with prominent nucleoli (n = 7), and cytoplasmic bodies (n = 4); two patients were diagnosed on FNA with cell block. Immunohistochemistry (IHC) demonstrated SMARCB1 loss in all cases and keratin and/or EMA expression in all but the epithelioid MPNST; NGS identified SMARCB1 inactivation in both cases. Conclusions SMARCB1-deficient soft tissue neoplasms comprise a variety of tumors with epithelioid morphology and frequent expression of keratin and/or EMA. Recognition of characteristic rhabdoid morphology on cytology can prompt IHC and/or NGS testing for SMARCB1 deficiency and help establish the diagnosis.

This study aims to develop a clinically practical model to predict EGFR mutation in lung adenocarcinoma patients according to radiomics signatures based on PET/CT and clinical risk factors. This retrospective study included 583 lung adenocarcinoma patients, including 295 (50.60%) patients with EGFR mutation and 288 (49.40%) patients without EGFR mutation. The clinical risk factors associated with lung adenocarcinoma were collected at the same time. We developed PET/CT, CT, and PET radiomics models for the prediction of EGFR mutation using multivariate logistic regression analysis, respectively. We also constructed a combined PET/CT radiomics-clinical model by nomogram analysis. The diagnostic performance and clinical net benefit of this risk-scoring model were examined via receiver operating characteristic (ROC) curve analysis while the clinical usefulness of this model was evaluated by decision curve analysis (DCA). The ROC analysis showed predictive performance for the PET/CT radiomics model (AUC = 0.76), better than the PET model (AUC = 0.71, Delong test: Z = 3.03, p value = 0.002) and the CT model (AUC = 0.74, Delong test: Z = 1.66, p value = 0.098). Also, the PET/CT radiomics-clinical combined model has a better performance (AUC = 0.84) to predict EGFR mutation than the PET/CT radiomics model (AUC = 0.76, Delong test: D = 2.70, df = 790.81, p value < 0.001) or the clinical model (AUC = 0.81, Delong test: Z = 3.46, p value < 0.001). We demonstrated that the combined PET/CT radiomics-clinical model has an advantage to predict EGFR mutation in lung adenocarcinoma. • Radiomics from lung tumor increase the efficiency of the prediction for EGFR mutation in clinical lung adenocarcinoma on PET/CT. • A radiomic nomogram was developed to predict EGFR mutation. • Combining PET/CT radiomics-clinical model has an advantage to predict EGFR mutation.

Titanium alloys have high corrosion resistance and specific strength, leading to a wide range of uses in a variety of industrial fields. However, machining performance is often very poor, causing serious difficulty during the cutting process. In particular, high cutting temperature and high chemical activity of titanium alloys during the cutting process lead to rapid tool wear. Within this research, specific tool microstructures cut onto the tool rake surface is explored to improve the cutting performance of titanium alloy TC21. In order to isolate the influence of particular tool microstructures on the cutting performance of titanium alloy TC21, a 3D orthogonal finite element model (OFEM) is utilized to simulate the cutting process of TC21 alloy. The impact of tool microstructure on chip formation, cutting force and temperature is thoroughly analyzed through turning simulations and experiments on titanium alloy TC21. Finally, a comprehensive comparison of cutting behaviors between textured and untextured tools during the cutting of titanium alloy TC21 was carried out. Cutting simulations indicate that tool microstructure can improve the cutting properties, reducing cutting temperature and cutting force. Research results confirm that chip serration and tool wear noticeably decreased, indicating tool texture can significantly improve cutting performance of titanium alloy TC21.

Aims MYC is a proto-oncogene that is frequently dysregulated in various malignancies, through translocation or amplification. Radiation-associated angiosarcoma frequently shows MYC amplification, and immunohistochemical expression has been shown to be a reliable surrogate marker for amplification, but less is known about MYC expression in other sarcoma types, despite reports of MYC amplification in some undifferentiated/unclassified radiation-associated sarcomas (RASs). Distinguishing putative RAS from non-radiation-associated sarcoma or sarcomatoid carcinoma can be difficult. The aim of this study was to determine the prevalence and potential diagnostic utility of MYC in this context, by evaluating MYC expression in a cohort of RASs, non-radiation-associated sarcomas, and sarcomatoid carcinomas. Methods and results Three hundred and eighty-five neoplasms were evaluated, including 81 RASs (18 angiosarcomas; 57 undifferentiated sarcomas; three leiomyosarcomas; and three malignant peripheral nerve sheath tumours), 267 non-radiation-associated sarcomas, and 37 sarcomatoid carcinomas. Immunohistochemistry was performed with a monoclonal anti-MYC antibody. Staining in tumour cells was scored on the basis of extent (focal, 1-4%; multifocal, 5-49%; and diffuse, ≥50%) and intensity (strong, moderate, and weak). One hundred percent of radiation-associated angiosarcomas expressed MYC diffusely. Expression was infrequent among other types of RAS (9.5%), and the frequency was similar to that in non-radiation-associated sarcomas (9.7%). MYC expression was more common in sarcomatoid carcinomas, occurring in 43%. The extent and intensity of staining were variable in all groups. Conclusion MYC expression is infrequent among RASs other than angiosarcoma, and has a similar prevalence in sporadic sarcomas. Given the frequency of expression in sarcomatoid carcinomas, MYC expression outside the context of radiation-associated angiosarcoma is of limited diagnostic utility, and should be interpreted with caution after exclusion of sarcomatoid carcinoma where relevant.

Rationale and Objectives To evaluate the value of texture analysis on preoperative magnetic resonance imaging (MRI) for identifying nonfunctional pancreatic neuroendocrine neoplasms (NF-PNENs) and solid pseudopapillary neoplasms (SPNs). Materials and Methods This retrospective study included 119 patients who underwent MRI, including T2-weighted imaging with fat-suppression, diffusion-weighted imaging (DWI), apparent diffusion coefficient, precontrast T1-weighted imaging with fat-suppression (T1WI+fs), and dynamic contrast-enhanced (DCE)-T1WI+fs. Raw data analysis, principal component analysis, linear discriminant analysis, and nonlinear discriminant analysis (NDA) were used to classify NF-PNENs and SPNs. The results are reported as misclassification rates. The images were simultaneously evaluated by an experienced senior radiologist without knowledge of the pathological results. The misclassification rate of the radiologist was compared to the MaZda (texture analysis software) results. Neural network classifier testing was used for validation. In addition, 30 textures for each MRI sequence were investigated. Results The misclassification rate of NDA was lower than that of other analyses. In NDA, DWI obtained the lowest value of 7.92%, but there was no significant difference among the sequences. The misclassification rate of the radiologist (34.65%) was significantly higher than that of NDA for all sequences. The validation results were good in the arterial phase and delayed phase. In the training set, entropy and sum entropy were optimal texture features on DWI and precontrast T1WI+fs, while the mean and percentile seemed to be the more discriminative features on DCE-T1WI+fs. Conclusion Texture analysis can sensitively distinguish between NF-PNENs and SPNs on MRI, and percentile and mean of DCE-T1WI+fs images were informative for differentiation of neoplasms.

Lung adenocarcinoma (LUAD) is one of the most common types of lung cancer and its poor prognosis largely depends on the tumor pathological stage. Critical roles of microRNAs (miRNAs) have been reported in the tumorigenesis and progression of lung cancer. However, whether the differential expression pattern of miRNAs could be used to distinguish early‑stage (stage I) from mid‑late‑stage (stages II‑IV) LUAD tumors is still unclear. In this study, clinical information and miRNA expression profiles of patients with LUAD were downloaded from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus databases. TCGA‑LUAD (n=470) dataset was used for model training and validation, and the GSE62182 (n=94) and GSE83527 (n=36) datasets were used as external independent test datasets. The diagnostic model was created through miRNA feature selection followed by SVM classifier and was confirmed by 5‑fold cross‑validation. A receiver operating characteristic curve was calculated to evaluate the accuracy and robustness of the model. Using the DX score and LIBSVM tool, a 16‑miRNA signature that could distinguish LUAD pathological stages was identified. The area under the curve rates were 0.62 [95% confidence interval (CI): 0.56‑0.67], 0.66 (95% CI: 0.54‑0.76) and 0.63 (95% CI: 0.43‑0.82) in TCGA‑LUAD internal validation dataset, the GSE62182 external validation dataset, and the GSE83527 external validation dataset, respectively. Kyoto Encyclopedia of Genes and Genomes and Gene Ontology enrichment analyses suggested that the target genes of the 16‑miRNA signature were mainly involved in metabolic pathways. The present findings demonstrate that a 16‑miRNA signature could serve as a promising diagnostic biomarker for pathological staging in LUAD.

Digital polymerase chain reaction (digital PCR) can provide absolute quantification of target nucleic acids with high sensitivity, excellent precision, and superior resolution. Digital PCR has broad applications in both life science research and clinical molecular diagnostics. However, limited by current fluorescence imaging methods, parallel quantification of multiple target molecules in a single digital PCR remains challenging. Here, we present a multiplex digital PCR method using digital melting curve analysis (digital MCA) with a SlipChip microfluidic system. The self-partitioning SlipChip (sp-SlipChip) can generate an array of nanoliter microdroplets with trackable physical positions using a simple loading-and-slipping operation. A fluorescence imaging adaptor and an

Accurate diagnosis of cancer subtypes is a great guide for the development of surgical plans and prognosis in the clinic. Raman spectroscopy, combined with the machine learning algorithm, has been demonstrated to be a powerful tool for tumor identification. However, the analysis and classification of Raman spectra for biological samples with complex compositions are still challenges. In addition, the signal-to-noise ratio of the spectra also influences the accuracy of the classification. Herein, we applied the variational autoencoder (VAE) to Raman spectra for downscaling and noise reduction simultaneously. We validated the performance of the VAE algorithm at the cellular and tissue levels. VAE successfully downscaled high-dimensional Raman spectral data to two-dimensional (2D) data for three subtypes of non-small cell lung cancer cells and two subtypes of kidney cancer tissues. Gaussian naïve bayes was applied to subtype discrimination with the 2D data after VAE encoding at both the cellular and tissue levels, significantly outperforming the discrimination results using original spectra. Therefore, the analysis of Raman spectroscopy based on VAE and machine learning has great potential for rapid diagnosis of tumor subtypes.

Bradykinesia is one of the core motor symptoms of Parkinson's disease (PD). Neurologists typically perform face-to-face bradykinesia assessment in PD patients according to the Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS). As this human-expert assessment lacks objectivity and consistency, an automated and objective assessment scheme for bradykinesia is critically needed. In this paper, we propose a tree-structure-guided graph convolutional network with contrastive learning scheme to solve the challenge of difficulty in fine-grained feature extraction and insufficient model stability, finally achieving the video-based automated assessment of Parkinsonian hand movements, which represent a vital MDS-UPDRS component for examining upper-limb bradykinesia. Specifically, a tri-directional skeleton tree scheme is proposed to achieve effective fine-grained modeling of spatial hand dependencies. In this scheme, hand skeletons are extracted from videos, and then the spatial structures of these skeletons are constructed through depth-first tree traversal. Afterwards, a tree max-pooling module is employed to establish remote exchange between outer and inner nodes, hierarchically gather the most salient motion features, and hence achieve fine-grained mining. Finally, a group-sparsity-induced momentum contrast is also developed to learn similar motion patterns under different interference through contrastive learning. This can promote stable learning of discriminative spatial-temporal features with invariant motion semantics. Comprehensive experiments on a large clinical video dataset reveal that our method achieves competitive results, and outperforms other sensor-based and RGB-depth methods. The proposed method leads to accurate assessment of PD bradykinesia through videos collected by low-cost consumer cameras of limited capabilities. Hence, our work provides a convenient tool for PD telemedicine applications with modest hardware requirements.

Titanium alloys are widely used in the aviation field due to the excellent properties, such as high specific-strength and high-temperature resistance. But the poor machinability of titanium alloys has brought the great difficulty to its machining process. In the cutting process of titanium alloys, tool wear is very serious, and the machining quality is difficult to be guaranteed. As a new type titanium alloy, TC21 alloy has the higher strength and its machinability is less than other titanium alloys. Aiming at the cutting defects in the cutting process of TC21 alloy, three different microstructures, including parallel, perpendicular and wavy grooves, are presented and cut on the rake surface of tools by the laser texturing method. A series of precision turning process of TC21 alloy are implemented on the precision machine using the inserts with different microstructures. The effects of the different microstructures on the chip morphology, turning force, surface morphology, and surface roughness are investigated deeply. The results demonstrates that the tool microstructures have very important role on the turning process of titanium alloys and the wavy microstructure has the best effect in improving the machinability of titanium alloy TC21.

To investigate the PET/CT findings in lung invasive adenocarcinoma with minor components of micropapillary or solid contents and its association with lymph node metastasis. A total of 506 lung invasive adenocarcinoma (≤ 3 cm) patients who underwent a PET/CT examination and resection surgery were included. According to the proportion of solid/micropapillary components, the patients were classified into three groups: solid/micropapillary-negative (SMPN) (n = 258), solid/micropapillary-minor (SMPM; > 5% not predominant) (n = 158) and solid/micropapillary-predominant (SMPP; > 5% most dominant) (n = 90). The patients’ PET/CT findings, including SUVmax, MTV, TLG and CT characteristics, and other clinical factors were compared by one-way ANOVA test. Logistic regression analysis was done to identify the most predictive findings for lymph node metastasis. The value of SUVmax, MTV, TLG and tumor size was highest in SMPP group, followed by SMPM and SMPN group (P

Pancreatic cancer is a lethal malignant tumor with one of the worst prognoses. Accurate segmentation of pancreatic cancer is vital in clinical diagnosis and treatment. Due to the unclear boundary and small size of cancers, it is challenging to both manually annotate and automatically segment cancers. Considering 3D information utilization and small sample sizes, we propose a model-driven deep learning method for pancreatic cancer segmentation based on spiral transformation. Specifically, a spiral-transformation algorithm with uniform sampling was developed to map 3D images onto 2D planes while preserving the spatial relationship between textures, thus addressing the challenge in effectively applying 3D contextual information in a 2D model. This study is the first to introduce spiral transformation in a segmentation task to provide effective data augmentation, alleviating the issue of small sample size. Moreover, a transformation-weight-corrected module was embedded into the deep learning model to unify the entire framework. It can achieve 2D segmentation and corresponding 3D rebuilding constraint to overcome non-unique 3D rebuilding results due to the uniform and dense sampling. A smooth regularization based on rebuilding prior knowledge was also designed to optimize segmentation results. The extensive experiments showed that the proposed method achieved a promising segmentation performance on multi-parametric MRIs, where T2, T1, ADC, DWI images obtained the DSC of 65.6%, 64.0%, 64.5%, 65.3%, respectively. This method can provide a novel paradigm to efficiently apply 3D information and augment sample sizes in the development of artificial intelligence for cancer segmentation. Our source codes will be released at https://github.com/SJTUBME-QianLab/ Spiral-Segmentation.

Automated segmentation of pancreatic cancer is vital for clinical diagnosis and treatment. However, the small size and inconspicuous boundaries limit the segmentation performance, which is further exacerbated for deep learning techniques with the few training samples due to the high threshold of image acquisition and annotation. To alleviate this issue caused by the small-scale dataset, we collect idle multi-parametric MRIs of pancreatic cancer from different studies to construct a relatively large dataset for enhancing the CT pancreatic cancer segmentation. Therefore, we propose a deep learning segmentation model with the dual meta-learning framework for pancreatic cancer. It can integrate the common knowledge of tumors obtained from idle MRIs and salient knowledge from CT images, making high-level features more discriminative. Specifically, the random intermediate modalities between MRIs and CT are first generated to smoothly fill in the gaps in visual appearance and provide rich intermediate representations for ensuing meta-learning scheme. Subsequently, we employ intermediate modalities-based model-agnostic meta-learning to capture and transfer commonalities. At last, a meta-optimizer is utilized to adaptively learn the salient features within CT data, thus alleviating the interference due to internal differences. Comprehensive experimental results demonstrated our method achieved the promising segmentation performance, with a max Dice score of 64.94% on our private dataset, and outperformed state-of-the-art methods on a public pancreatic cancer CT dataset. The proposed method is an effective pancreatic cancer segmentation framework, which can be easily integrated into other segmentation networks and thus promises to be a potential paradigm for alleviating data scarcity challenges using idle data.

Automated pancreatic cancer segmentation is highly crucial for computer-assisted diagnosis. The general practice is to label images from selected modalities since it is expensive to label all modalities. This practice brought about a significant interest in learning the knowledge transfer from the labeled modalities to unlabeled ones. However, the imaging parameter inconsistency between modalities leads to a domain shift, limiting the transfer learning performance. Therefore, we propose an unsupervised domain adaptation segmentation framework for pancreatic cancer based on GCN and meta-learning strategy. Our model first transforms the source image into a target-like visual appearance through the synergistic collaboration between image and feature adaptation. Specifically, we employ encoders incorporating adversarial learning to separate domain-invariant features from domain-specific ones to achieve visual appearance translation. Then, the meta-learning strategy with good generalization capabilities is exploited to strike a reasonable balance in the training of the source and transformed images. Thus, the model acquires more correlated features and improve the adaptability to the target images. Moreover, a GCN is introduced to supervise the high-dimensional abstract features directly related to the segmentation outcomes, and hence ensure the integrity of key structural features. Extensive experiments on four multi-parameter pancreatic-cancer magnetic resonance imaging datasets demonstrate improved performance in all adaptation directions, confirming our model's effectiveness for unlabeled pancreatic cancer images. The results are promising for reducing the burden of annotation and improving the performance of computer-aided diagnosis of pancreatic cancer. Our source codes will be released at https://github.com/SJTUBME-QianLab/UDAseg, once this manuscript is accepted for publication.

Purpose To investigate the value of 18F-FDG PET/CT molecular radiomics combined with the clinical model in predicting local lymph node metastasis (LLNM) with invasive lung adenocarcinoma (≤3cm). Methods 528 lung adenocarcinoma patients were enrolled in this retrospective study. Five models, including integrated PET/CT molecular radiomics-clinical, PET/CT radiomics, PET radiomics, CT radiomics, and clinical models, were developed for the prediction of LLNM. The predictive performance was examined by ROC curve analysis and clinical utility was validated by nomogram and decision curve analysis (DCA) analyses. Results 10 PET/CT radiomics features and 2 clinical characteristics were selected for the construction of the integrated PET/CT molecular radiomics-clinical model. This integrated model performed better than the clinical model and three other radiomics models, and the AUC value of the integrated model was 0.95 (95% CI: 0.93-0.97) in the training group and 0.94 (95% CI: 0.89-0.97) in the test group, respectively. The clinical application of this integrated model in predicting LLNM was also confirmed by nomogram and DCA analyses. Conclusions The integrated PET/CT molecular radiomic-clinical model developed here has the greater advantage to predict LLNM of clinical invasive lung adenocarcinoma (≤3cm) when compared with the simple radiomics model or clinical model.

Motor disorder is a typical symptom of Parkinson’s disease (PD). Neurologists assess the severity of PD motor symptoms using the clinical rating scale, i.e., MDS-UPDRS. However, this assessment method is time-consuming and easily affected by the perception difference of assessors. In the recent outbreak of coronavirus disease 2019, telemedicine for PD has become extremely urgent for clinical practice. To solve these problems, we developed an automated and objective assessment method of the leg agility task in the MDS-UPDRS using videos and a graph neural network. In this study, a sparse adaptive graph convolutional network (SA-GCN) was proposed to achieve fine-grained quantitative assessment of skeleton sequences extracted from videos. Specifically, the sparse adaptive graph convolutional unit with a prior knowledge constraint was proposed to perform adaptive spatial modeling of physical and logical dependency for skeleton sequences, thus achieving the sparse modeling of the discriminative spatial relationships. Subsequently, a temporal context module was introduced to construct the remote context dependency in the temporal dimension, hence determining the global changes of the task. A multi-domain attention learning module was also developed to integrate the static spatial features and dynamic temporal features, and then to emphasize the salient feature selection in the channel domain, thereby capturing the multi-domain fine-grained information. Finally, the evaluation results using a dataset with 148 patients and 870 samples confirmed the effectiveness and reliability of our scheme, and the method outperformed other related state-of-the-art methods. Our contactless method provides a new potential tool for automated PD assessment and telemedicine.

Pancreatic cancer is a malignant form of cancer with one of the worst prognoses. The poor prognosis and resistance to therapeutic modalities have been linked to TP53 mutation. Pathological examinations, such as biopsies, cannot be frequently performed in clinical practice; therefore, noninvasive and reproducible methods are desired. However, automatic prediction methods based on imaging have drawbacks such as poor 3D information utilization, small sample size, and ineffectiveness multi-modal fusion. In this study, we proposed a model-driven multi-modal deep learning scheme to overcome these challenges. A spiral transformation algorithm was developed to obtain 2D images from 3D data, with the transformed image inheriting and retaining the spatial correlation of the original texture and edge information. The spiral transformation could be used to effectively apply the 3D information with less computational resources and conveniently augment the data size with high quality. Moreover, model-driven items were designed to introduce prior knowledge in the deep learning framework for multi-modal fusion. The model-driven strategy and spiral transformation-based data augmentation can improve the performance of the small sample size. A bilinear pooling module was introduced to improve the performance of fine-grained prediction. The experimental results show that the proposed model gives the desired performance in predicting TP53 mutation in pancreatic cancer, providing a new approach for noninvasive gene prediction. The proposed methodologies of spiral transformation and model-driven deep learning can also be used for the artificial intelligence community dealing with oncological applications. Our source codes with a demon will be released at https://github.com/SJTUBME-QianLab/SpiralTransform .

Pancreas segmentation in medical imaging data is of great significance for clinical pancreas diagnostics and treatment. However, the large population variations in the pancreas shape and volume cause enormous segmentation difficulties, even for state-of-the-art algorithms utilizing fully-convolutional neural networks (FCNs). Specifically, pancreas segmentation suffers from the loss of spatial information in 2D methods, and the high computational cost of 3D methods. To alleviate these problems, we propose a probabilistic-map-guided bi-directional recurrent UNet (PBR-UNet) architecture, which fuses intra-slice information and inter-slice probabilistic maps into a local 3D hybrid regularization scheme, which is followed by bi-directional recurrent network optimization. The PBR-UNet method consists of an initial estimation module for efficiently extracting pixel-level probabilistic maps and a primary segmentation module for propagating hybrid information through a 2.5D U-Net architecture. Specifically, local 3D information is inferred by combining an input image with the probabilistic maps of the adjacent slices into multichannel hybrid data, and then hierarchically aggregating the hybrid information of the entire segmentation network. Besides, a bi-directional recurrent optimization mechanism is developed to update the hybrid information in both the forward and the backward directions. This allows the proposed network to make full and optimal use of the local context information. Quantitative and qualitative evaluation was performed on the NIH Pancreas-CT dataset, and our proposed PBR-UNet method achieved better segmentation results with less computational cost compared to other state-of-the-art methods., Comment: accepted by Physics in Medicine & Biology

This study aims to develop a clinically practical model to predict EGFR mutation in lung adenocarcinoma patients according to radiomics signatures based on PET/CT and clinical risk factors.This retrospective study included 583 lung adenocarcinoma patients, including 295 (50.60%) patients with EGFR mutation and 288 (49.40%) patients without EGFR mutation. The clinical risk factors associated with lung adenocarcinoma were collected at the same time. We developed PET/CT, CT, and PET radiomics models for the prediction of EGFR mutation using multivariate logistic regression analysis, respectively. We also constructed a combined PET/CT radiomics-clinical model by nomogram analysis. The diagnostic performance and clinical net benefit of this risk-scoring model were examined via receiver operating characteristic (ROC) curve analysis while the clinical usefulness of this model was evaluated by decision curve analysis (DCA).The ROC analysis showed predictive performance for the PET/CT radiomics model (AUC = 0.76), better than the PET model (AUC = 0.71, Delong test: Z = 3.03, p value = 0.002) and the CT model (AUC = 0.74, Delong test: Z = 1.66, p value = 0.098). Also, the PET/CT radiomics-clinical combined model has a better performance (AUC = 0.84) to predict EGFR mutation than the PET/CT radiomics model (AUC = 0.76, Delong test: D = 2.70, df = 790.81, p value0.001) or the clinical model (AUC = 0.81, Delong test: Z = 3.46, p value0.001).We demonstrated that the combined PET/CT radiomics-clinical model has an advantage to predict EGFR mutation in lung adenocarcinoma.• Radiomics from lung tumor increase the efficiency of the prediction for EGFR mutation in clinical lung adenocarcinoma on PET/CT. • A radiomic nomogram was developed to predict EGFR mutation. • Combining PET/CT radiomics-clinical model has an advantage to predict EGFR mutation.

In this paper, we propose a novel method to estimate the disparity maps from a light field image pair captured by a pair of light field cameras. Our method integrates two types of critical depth cues, which are separately inferred from the epipolar plane images and binocular stereo vision into a global solution. At the same time, in order to produce highly accurate disparity maps, we adopt a generative model, which can estimate a light field image only with the central subaperture view and corresponding hypothesized disparity map. The objective function of our method is formulated to minimize two energy terms/differences. One is the difference between the two types of previously extracted disparity maps and the target disparity maps, directly optimized in the gray-scale disparity space. The other indicates the difference between the estimated light field images and the input light field images, optimized in the RGB color space. Comprehensive experiments conducted on real and virtual scene light field image pairs demonstrate the effectiveness of our method.

Background Ewing sarcoma (ES) is a round cell sarcoma that can be challenging to diagnose on cytologic material given its significant overlap with numerous mesenchymal, epithelial, and lymphoid cytomorphologic mimics. The objective of this study was to assess the utility of a novel marker, NKX2.2, in the diagnosis of ES in cytologic material and its ability to distinguish ES from its mimics. Methods NKX2.2 immunohistochemistry was performed on cell blocks from 107 fine-needle aspirations, and nuclear expression was scored semiquantitatively for extent and intensity. The study cohort included ES (n = 10), well differentiated neuroendocrine tumor (n = 20), melanoma (n = 11), Merkel cell carcinoma (n = 10), small cell carcinoma (n = 10), alveolar rhabdomyosarcoma (n = 2), spindle cell/sclerosing rhabdomyosarcoma (n = 2), synovial sarcoma (n = 12), solitary fibrous tumor (n = 2), chronic lymphocytic leukemia (n = 10), lymphoblastic lymphoma (n = 11), adenoid cystic carcinoma (n = 6), and CIC-rearranged sarcoma (n = 1). Results NKX2.2 had high sensitivity (100%) and moderate specificity (85%) for the diagnosis of ES in cytologic material. NKX2.2 expression also was present in a subset of mesenchymal and epithelial mimics, and staining was most commonly observed in small cell carcinoma (80%) and well differentiated neuroendocrine tumor (45%). Among mesenchymal mimics, 42% exhibited NKX2.2 expression. NKX2.2 staining was absent in melanoma, adenoid cystic carcinoma, and lymphoproliferative neoplasms. Conclusions NKX2.2 is a highly sensitive but only moderately specific marker for ES. Neuroendocrine neoplasms exhibit variable NKX2.2 expression and remain a significant potential diagnostic pitfall. Thus, NKX2.2 expression should be interpreted in the context of an appropriate immunohistochemical panel (and often with confirmatory molecular testing) for the accurate diagnosis of ES.

The review summarizes the current diagnostic challenges in fine-needle aspiration of primary bone tumors, with focus on the application of new molecular and immunohistochemical techniques in the diagnosis of giant cell-rich neoplasms, chondrosarcomas, and notochordal tumors.

Background Diagnosing giant cell-rich bone tumors can be challenging on limited biopsies. H3 histone family member 3A (H3F3A) (G34W/V/R/L) mutations are present in the majority of giant cell tumors (GCTs) of bone and H3 histone family member 3B (H3F3B) (K36M) mutations are present in nearly all chondroblastomas, but are absent in histologic mimics. Mutation-specific immunohistochemistry (IHC) is highly specific for GCT and chondroblastoma in surgical excisions. The objective of the current study was to validate H3G34W and H3K36M IHC in the diagnosis of giant cell-rich bone tumors on fine-needle aspiration and core needle biopsy specimens. Methods IHC was performed using monoclonal antibodies against histone H3.3 G34W and K36M in GCTs of bone (26 cases, including 2 malignant cases), GCT of Paget disease (1 case), chondroblastoma (8 cases), aneurysmal bone cyst (7 cases), and osteosarcoma (13 cases) with available fine-needle aspiration and/or core needle biopsy specimens from 2 institutions. H3F3A and H3F3B Sanger sequencing was performed on all 4 H3G34W IHC-negative GCTs. Results IHC for H3G34W was positive in 22 of 26 GCTs (85%) and negative in all histologic mimics. IHC for H3K36M was positive in all 8 chondroblastomas and negative in all histologic mimics. IHC results were concordant between biopsy and surgical specimens in 152 of 158 samples (96%). Sequencing identified alternate H3F3A G34L and G34V mutations in 1 IHC-negative GCT each, but no mutation was found in the remaining 2 cases. Conclusions H3G34W and H3K36M IHC is highly specific for GCT and chondroblastoma, respectively, among giant cell-rich bone tumors, and is useful for confirming the diagnosis in limited biopsies. The presence of alternate H3F3A mutations accounts for the H3G34W IHC negativity in a subset of GCT of bone cases. Cancer Cytopathol 2018. © 2018 American Cancer Society.

The success of fuzzy clustering heavily relies on the features of the input data. Based on the fact that deep architectures are able to more accurately characterize the data representations in a layer-by-layer manner, this paper proposes a novel feature mapping technique called cascaded hidden-space (CHS) feature mapping and investigates its combination with classical fuzzy c-means (FCM) and fuzzy c-regressions (FCR). Since the parameters between the layers of CHS feature mapping are randomly generated and need not be tuned layer-by-layer, CHS is easily implemented with less training data. By performing classical FCM in CHS, a novel fuzzy clustering framework called CHS-FCM is developed; several of its variants are presented using different dimension-reduction methods in a CHS-FCM clustering framework. The combination of CHS-FCM with nonlinear switch regressions is called CHS-FCR, and it performs FCR in CHS. The proposed CHS-FCR provides better results than FCR for nonlinear process modeling. Both CHS-FCM and CHS-FCR exhibit low memory consumption and require less training data. The experimental results verify the superiority of the proposed methods over classical fuzzy clustering methods.

Background The characterization of poorly differentiated neoplasms in fine-needle aspiration (FNA) and small biopsy specimens usually requires immunohistochemistry (IHC) with a panel of markers. Because of an increasing need to preserve limited diagnostic material for tumor genotyping and a mounting demand for cost containment, the authors investigated the usefulness of dual-color IHC with antibodies directed against broad-spectrum keratins and SOX10, a neuroectodermal transcription factor consistently expressed in melanoma, in the workup of epithelioid malignant neoplasms. Methods A total of 107 cases of FNA cell blocks (49 cases) and small biopsies (58 cases) were selected, including 34 melanomas, 31 epithelioid/pleomorphic sarcomas, and 42 carcinomas. IHC was performed on all specimens using a peroxidase-based brown chromogen for SOX10 and an alkaline phosphatase-based red chromogen for keratins AE1/AE3. The presence or absence of staining in lesional cells was scored. Results The majority of tumors demonstrated 1 of 3 distinct patterns: 1) malignant melanomas with nuclear SOX10 (sensitivity of 94% and specificity of 95%); 2) epithelioid/pleomorphic sarcomas negative for both SOX10 and AE1/AE3 (sensitivity of 84% and specificity of 88%); and 3) carcinomas with cytoplasmic AE1/AE3 (sensitivity of 76% and specificity of 98%). In addition, a fourth pattern with cytoplasmic AE1/AE3 and nuclear SOX10 was observed in a subset of carcinomas, most notably triple-negative breast cancers. Conclusions SOX10/keratin dual-color IHC appears to be an effective, sensitive, and specific test to distinguish between melanoma, sarcoma, and carcinoma. This approach can identify melanoma, prioritize additional studies, and limit the number of markers needed to workup an epithelioid malignant neoplasm, thereby potentially reducing costs and preserving valuable tissue for ancillary studies with which to guide therapy. Cancer Cytopathol 2018;126:179-89. © 2018 American Cancer Society.

In this paper, we introduced an intermittent wave energy generator (IWEG) system with hydraulic power take-off (PTO) including accumulator storage parts. To convert unsteady wave energy into intermittent but stable electrical output power, theoretical models, including wave energy capture, hydraulic energy storage, and torque balance between hydraulic motor and electrical generator, have been developed. Then, the integrated IWEG simulator was constructed and tested at the Ningbo Institute of Technology. Through a series of experimental tests, the relationship between operating flow rates and pressure drops across the hydraulic motor was established. Furthermore, on the basis of the pressure drop signal, we proposed a feedback control method on the basis of the pressure drop database as the feedback control signal to eliminate the disturbance of periodic peak pressure impulse through the regulation of the opening ratio of a proportional flow valve and achieved the effective and stable electric power output, albeit intermittently. Compared with the previous complex control theories and algorithms, this method can keep the power output more stable over a wide range of operating conditions. Furthermore, experimental tests indicate that the IWEG system, with hydraulic PTO, including hydraulic accumulator and proportional flow control valve, is simple, reliable, and easy to control. Most importantly, the real-time power output is stable, and power quality and generation efficiency are significantly improved.

BACKGROUND Histiocytic sarcoma (HS) is a rare malignant neoplasm showing morphologic and immunophenotypic features of histiocytes. Molecular characteristics of HS and fine-needle aspiration (FNA) criteria for its diagnosis have not been established. METHODS A case series of HS in 8 FNA samples from 6 patients was reviewed along with histopathologic and clinical data. Immunohistochemistry was performed on cell blocks (3 cases), core biopsies (5 cases), and surgical specimens (4 cases). Targeted-exome next-generation sequencing (NGS) was performed on surgical resection specimens in 4 cases. RESULTS Four patients had a known history of hematolymphoid malignancy. Cytomorphologic features included variably cellular smears composed of large epithelioid cells with reniform nuclei and abundant vacuolated cytoplasm, in an inflammatory background, with occasional cytophagocytosis and lymphoglandular bodies. Marked pleomorphism, multinucleated monster cells, and binucleated histiocytoid cells with partially overlapping, eccentrically placed nuclei resembling Pac-Man were common. Most cases expressed histiocytic markers CD68 (6 of 7 cases), CD163 (5 of 5 cases), and PU.1 (3 of 4 cases). In 3 cases, NGS analysis revealed alterations in lysine methyltransferase 2D (KMT2D)/mixed-lineage leukemia 2 (MLL2), a gene involved in chromatin regulation and previously implicated in the pathogenesis of follicular lymphoma. CONCLUSIONS Although diagnosing HS with FNA alone is extremely challenging, the presence of pleomorphic and epithelioid large cells with binucleation and/or multinucleation in an inflammatory background should prompt the diagnosis of HS with judicious use of confirmatory histiocytic lineage markers. The detection of recurrent KMT2D/MLL2 alterations implicates epigenetic regulation in the pathogenesis of HS and supports the notion of transdifferentiation from a genetically similar but phenotypically distinct tumor of a different lineage. Cancer Cytopathol 2017. © 2017 American Cancer Society.

Preoperative diagnosis of soft tissue and bone tumors using needle biopsy techniques, namely fine needle aspiration (FNA) and core needle biopsy (CNB), has gained wider acceptance in recent years. This is achieved in concert with the maturation of various image-guided needle biopsy techniques, development of molecular genetic diagnostics, and expansion of immunohistochemical biomarkers. FNA, however, as a first-line approach to evaluate soft tissue and bone tumors, remains one of the most challenging and controversial areas in cytopathology. Compared with the CNB, FNA is more suitable for smaller lesions, recurrent and/or metastatic tumors, and lesions with a broad differential diagnosis including carcinomas and lymphomas. Enhanced by rapid on-site evaluation (ROSE), and immediate tissue triage for flow cytometry and/or cytogenetic/molecular studies, FNA offers a valuable and fast diagnostic modality for lesions suspicious for high grade malignancy. This chapter focuses on the practical approaches to this extremely diverse set of benign and malignant neoplasms, emphasizing on pattern recognition, effective triage of biopsy material, and judicious use of ancillary studies. General discussion of the clinical and cytomorphologic features of each entity is beyond the scope of this diagnostic approach–orientated chapter, and the readers are directed to other relevant excellent textbooks.

Background To explore the relationship between the lymph node status and preoperative computed tomography images texture features in pancreatic cancer. Methods A total of 155 operable pancreatic cancer patients (104 men, 51 women; mean age 63.8 ± 9.6 years), who had undergone contrast-enhanced computed tomography in the arterial and portal venous phases, were enrolled in this retrospective study. There were 73 patients with lymph node metastases and 82 patients without nodal involvement. Four different data sets, with thin (1.25 mm) and thick (5 mm) slices (at arterial phase and portal venous phase) were analysed. Texture analysis was performed by using MaZda software. A combination of feature selection algorithms was used to determine 30 texture features with the optimal discriminative performance for differentiation between lymph node positive and negative groups. The prediction performance of the selected feature was evaluated by receiver operating characteristic (ROC) curve analysis. Results There were 10 texture features with significant differences between two groups and significance in ROC analysis were identified. They were WavEnLH_s-2(wavelet energy with rows and columns are filtered with low pass and high pass frequency bands with scale factors 2) from wavelet-based features, 135dr_LngREmph (long run emphasis in 135 direction) and 135dr_Fraction (fraction of image in runs in 135 direction) from run length matrix-based features, and seven variables of sum average from coocurrence matrix-based features (SumAverg). The ideal cutoff value for predicting lymph node metastases was 270 for WavEnLH_s-2 (positive likelihood ratio 2.08). In addition, 135dr_LngREmph and 135dr_Fraction were correlated with the ratio of metastatic to examined lymph nodes. Conclusions Preoperative computed tomography high order texture features provide a useful imaging signature for the prediction of nodal involvement in pancreatic cancer.

In the development of personalized medicine, the ultrasensitive detection of point mutations that correlate with diseases is important to improve the efficacy of treatment and guide clinical medication. In this study, locked nucleic acid (LNA) was introduced as an amplification suppressor of a massive number of wild-type alleles in an amplification refractory mutation system (ARMS) to achieve the detection of low-abundance mutations with high specificity and sensitivity of at least 0.1%. By integrating the length of clamp, base type, number and position of LNA modifications, we have established a "shortest length with the fewest LNA bases" principle from which each LNA base would play a key role in the affinity and the ability of single base discrimination could be improve. Finally, based on this LNA design guideline, a series of the most important single point mutation sites of epidermal growth factor receptor (EGFR) was verified to achieve the optimal amplification state which as low as 0.1% mutation gene amplification was not affected under the wild gene amplification was completely inhibited, demonstrating that the proposed design principle has good applicability and versatility and is of great significance for the detection of circulating tumor DNA. This article is protected by copyright. All rights reserved.