Search

• A novel cascade method is proposed for automatic localization and segmentation of L3 vertebra's body tissue. • Vertebra localization network applies Gaussian cube to spine detection and infers the location of L3 vertebra through vertebra segmentation. • The tissue segmentation network uses adversarial modeling with two sub-networks and a novel Cross-Stage Attention block with both spatial- and channel-wise information to quantize body tissue of the L3 vertebra. • The experimental results show the outperformance of our proposed method, exceeding existing body tissue segmentation networks. Objective: The impact of body composition on disease prognosis is increasingly recognized. Analysis of computed tomography (CT) scans at the level of the third lumbar (L3) spine is considered a standard approach to measure muscle and adipose tissue body composition parameters. However, existing approaches need manually select the L3 vertebra and then analyze body composition, which is time-consuming. Thus, how to automatically analyze body composition becomes the problem. Methods: In this paper, a novel two-step method is proposed and can automatically localize the L3 vertebra and segment body tissue accurately. Initially, the lumbar spine region is coarsely detected, and then each lumbar vertebra is determined. Secondly, the slice at the L3 vertebra is selected to quantize tissue (muscle, subcutaneous adipose tissue, visceral adipose tissue, etc.) based on a segmentation network. To achieve high performance, a Cross-Stage Attention (CSA) block and an adversarial structure are jointly utilized in tissue segmentation. Results: The experimental results show that the L3 vertebra localization result achieves 95.08 % Dice. The CSA block and adversarial structure play positive roles in improving the tissue segmentation performance with an average Dice from 95.15 % to 97.44 %. Conclusion: The results demonstrate that our method outperforms other existing body tissue segmentation approaches in terms of sensitivity, positive predictive value (PPV), Dice score, and Jaccard score. Significance: The time cost of data collection and annotation can be significantly reduced due to integrating L3 vertebra localization before tissue segmentation. Simultaneously, our method can be extended to all lumbar vertebrae and quantize each tissue volume in the abdomen. [ABSTRACT FROM AUTHOR]

Deep learning-based in silico alternatives have been demonstrated to be of significant importance in the acceleration of the drug discovery process and enhancement of success rates. Cyclin-dependent kinase 12 (CDK12) is a transcription-related cyclin-dependent kinase that may act as a biomarker and therapeutic target for cancers. However, currently, there is no high selective CDK12 inhibitor in clinical development and the identification of new specific CDK12 inhibitors has become increasingly challenging due to their similarity with CDK13. In this study, we developed a virtual screening workflow that combines deep learning with virtual screening tools and can be applied rapidly to millions of molecules. We designed a Transformer architecture Drug-Target Interaction (DTI) model with dual-branched self-supervised pre-trained molecular graph models and protein sequence models. Our predictive model produced satisfactory predictions for various targets, including CDK12, with several novel hits. We screened a large compound library consisting of 4.5 million drug-like molecules and recommended a list of potential CDK12 inhibitors for further experimental testing. In kinase assay, compared to the positive CDK12 inhibitor THZ531, the compounds CICAMPA-01, 02, 03 displayed more effective inhibition of CDK12, up to three times as much as THZ531. The compounds CICAMPA-03, 05, 04, 07 showed less inhibition of CDK13 compare to THZ531. In vitro , the IC50 of CICAMPA-01, 04, 05, 06, 09 was less than 3 μM in the HER2 positive CDK12 amplification breast cancer cell line BT-474. Overall, this study provides a highly efficient and end-to-end deep learning protocol, in conjunction with molecular docking, for discovering CDK12 inhibitors in cancers. Additionally, we disclose five novel CDK12 inhibitors. These results may accelerate the discovery of novel chemical-class drugs for cancer treatment. [Display omitted] • Dual-branched pre-training deep learning framework improves drug-target interaction prediction on enzyme. • Virtual screening on 4.5 million molecules using deep learning, docking and MMGBSA scoring. • Disclose five novel and promising CDK12 inhibitors through kinase assays and in vitro tests. [ABSTRACT FROM AUTHOR]

• This paper proposed an efficient scheme for fine-grained lesion recognition in kidney pathology to help pathologists make more objective and effective clinical diagnoses. • The proposed method has improved segmentation performance by optimizing the structural integrity through instance. • The proposed method has addressed the fine-grained lesion classification by incorporating uncertainty assessment and data reconstitution, without any bounding box annotation or adversarial model. Recognition of glomeruli lesions is the key for diagnosis and treatment planning in kidney pathology; however, the coexisting glomerular structures such as mesangial regions exacerbate the difficulties of this task. In this paper, we introduce a scheme to recognize fine-grained glomeruli lesions from whole slide images. First, a focal instance structural similarity loss is proposed to drive the model to locate all types of glomeruli precisely. Then an Uncertainty Aided Apportionment Network is designed to carry out the fine-grained visual classification without bounding-box annotations. This double branch-shaped structure extracts common features of the child class from the parent class and produces the uncertainty factor for reconstituting the training dataset. Results of slide-wise evaluation illustrate the effectiveness of the entire scheme, with an 8–22% improvement of the mean Average Precision compared with remarkable detection methods. The comprehensive results clearly demonstrate the effectiveness of the proposed method. [Display omitted]. [ABSTRACT FROM AUTHOR]

Objectives: We aimed to build a survival system by combining a highly-accurate machine learning (ML) model with explainable artificial intelligence (AI) techniques to predict distant metastasis in locoregionally advanced nasopharyngeal carcinoma (NPC) patients using magnetic resonance imaging (MRI)-based tumor burden features.Materials and Methods: 1643 patients from three hospitals were enrolled according to set criteria. We employed ML to develop a survival model based on tumor burden signatures and all clinical factors. Shapley Additive exPlanations (SHAP) was utilized to explain prediction results and interpret the complex non-linear relationship among features and distant metastasis. We also constructed other models based on routinely used cancer stages, Epstein-Barr virus (EBV) DNA, or other clinical features for comparison. Concordance index (C-index), receiver operating curve (ROC) analysis and decision curve analysis (DCA) were executed to assess the effectiveness of the models.Results: Our proposed system consistently demonstrated promising performance across independent cohorts. The concordance indexes were 0.773, 0.766 and 0.760 in the training, internal validation and external validation sets. SHAP provided personalized protective and risk factors for each NPC patient and uncovered some novel non-linear relationships between features and distant metastasis. Furthermore, high-risk patients who received induction chemotherapy (ICT) and concurrent chemoradiotherapy (CCRT) had better 5-year distant metastasis-free survival (DMFS) than those who only received CCRT, whereas ICT + CCRT and CCRT had similar DMFS in low-risk patients.Conclusions: The interpretable machine learning system demonstrated superior performance in predicting metastasis in locoregionally advanced NPC. High-risk patients might benefit from ICT. [ABSTRACT FROM AUTHOR]

• A novel lesion synthesis method is proposed by applying image inpainting technology. • An automatically Artificial Mask Generator (AMG) is proposed to define artificial masks from a shape pool in unrestricted size, location and shape. • A Lesion Synthesis Network (LSN) is proposed to apply artificial masks to generate hemorrhage lesions on non-lesion images. • A Residual Score Evaluation is presented to select the high reality of the synthetic images. Synthetic images with Residual Scores are combined with real images as the training set. • Experimental results demonstrate the effectiveness of our approach to improve the performances of ICH detection and classification, especially for the micro bleedings. Computer-aided diagnosis (CAD) for intracranial hemorrhage (ICH) is needed due to its high mortality rate and time sensitivity. Training a stable and robust deep learning-based model usually requires enough training examples, which may be impractical in many real-world scenarios. Lesion synthesis offers a possible solution to solve this problem, especially for the issue of the lack of micro bleedings. In this paper, we propose a novel strategy to generate artificial lesions on non-lesion CT images so as to produce additional labeled training examples. Artificial masks in any location, size, or shape can be generated through Artificial Mask Generator (AMG) and then be converted into hemorrhage lesions through Lesion Synthesis Network (LSN). Images with and without artificial lesions are combined for training an ICH detection with a novel Residual Score. We evaluate our method by the auxiliary diagnosis task of ICH. Our experiments demonstrate that the proposed approach can improve the AUC value from 84% to 91% in the ICH detection task and from 89% to 96% in the classification task. Moreover, by adding artificial lesions of small size, the sensitivity of micro bleeding is remarkably improved from 49% to 70%. Besides, the proposed method overcomes the other three synthetic approaches by a large margin. [ABSTRACT FROM AUTHOR]