A novel MRI-based deep learning networks combined with attention mechanism for predicting CDKN2A/B homozygous deletion status in IDH-mutant astrocytoma.

OBJECTIVES: To develop a high-accuracy MRI-based deep learning method for predicting cyclin-dependent kinase inhibitor 2A/B (CDKN2A/B) homozygous deletion status in isocitrate dehydrogenase (IDH)-mutant astrocytoma. METHODS: Multiparametric brain MRI data and corresponding genomic information of 234 subjects (111 positives for CDKN2A/B homozygous deletion and 123 negatives for CDKN2A/B homozygous deletion) were obtained from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA) respectively. Two independent multi-sequence networks (ResFN-Net and FN-Net) are built on the basis of ResNet and ConvNeXt network combined with attention mechanism to classify CDKN2A/B homozygous deletion status using MR images including contrast-enhanced T1-weighted imaging (CE-T1WI) and T2-weighted imaging (T2WI). The performance of the network is summarized by three-way cross-validation; ROC analysis is also performed. RESULTS: The average cross-validation accuracy (ACC) of ResFN-Net is 0.813. The average cross-validation area under curve (AUC) of ResFN-Net is 0.8804. The average cross-validation ACC and AUC of FN-Net is 0.9236 and 0.9704, respectively. Comparing all sequence combinations of the two networks (ResFN-Net and FN-Net), the sequence combination of CE-T1WI and T2WI performed the best, and the ACC and AUC were 0.8244, 0.8975 and 0.8971, 0.9574, respectively. CONCLUSIONS: The FN-Net deep learning networks based on ConvNeXt network achieved promising performance for predicting CDKN2A/B homozygous deletion status of IDH-mutant astrocytoma. CLINICAL RELEVANCE STATEMENT: A novel deep learning network (FN-Net) based on preoperative MRI was developed to predict the CDKN2A/B homozygous deletion status. This network has the potential to be a practical tool for the noninvasive characterization of CDKN2A/B in glioma to support personalized classification and treatment planning. KEY POINTS: • CDKN2A/B homozygous deletion status is an important marker for glioma grading and prognosis. • An MRI-based deep learning approach was developed to predict CDKN2A/B homozygous deletion status. • The predictive performance based on ConvNeXt network was better than that of ResNet network.

S3-Net: A Self-Supervised Dual-Stream Network for Radiology Report Generation.

Intelligent medicine is eager to automatically generate radiology reports to ease the tedious work of radiologists. Previous researches mainly focused on the text generation with encoder-decoder structure, while CNN networks for visual features ignored the long-range dependencies correlated with textual information. Besides, few studies exploit cross-modal mappings to promote radiology report generation. To alleviate the above problems, we propose a novel end-to-end radiology report generation model dubbed Self-Supervised dual-Stream Network (S3-Net). Specifically, a Dual-Stream Visual Feature Extractor (DSVFE) composed of ResNet and SwinTransformer is proposed to capture more abundant and effective visual features, where the former focuses on local response and the latter explores long-range dependencies. Then, we introduced the Fusion Alignment Module (FAM) to fuse the dual-stream visual features and facilitate alignment between visual features and text features. Furthermore, the Self-Supervised Learning with Mask(SSLM) is introduced to further enhance the visual feature representation ability. Experimental results on two mainstream radiology reporting datasets (IU X-ray and MIMIC-CXR) show that our proposed approach outperforms previous models in terms of language generation metrics.

A clinical-radiomics model based on noncontrast computed tomography to predict hemorrhagic transformation after stroke by machine learning: a multicenter study.

OBJECTIVE: To build a clinical-radiomics model based on noncontrast computed tomography images to identify the risk of hemorrhagic transformation (HT) in patients with acute ischemic stroke (AIS) following intravenous thrombolysis (IVT). MATERIALS AND METHODS: A total of 517 consecutive patients with AIS were screened for inclusion. Datasets from six hospitals were randomly divided into a training cohort and an internal cohort with an 8:2 ratio. The dataset of the seventh hospital was used for an independent external verification. The best dimensionality reduction method to choose features and the best machine learning (ML) algorithm to develop a model were selected. Then, the clinical, radiomics and clinical-radiomics models were developed. Finally, the performance of the models was measured using the area under the receiver operating characteristic curve (AUC). RESULTS: Of 517 from seven hospitals, 249 (48%) had HT. The best method for choosing features was recursive feature elimination, and the best ML algorithm to build models was extreme gradient boosting. In distinguishing patients with HT, the AUC of the clinical model was 0.898 (95% CI 0.873-0.921) in the internal validation cohort, and 0.911 (95% CI 0.891-0.928) in the external validation cohort; the AUC of radiomics model was 0.922 (95% CI 0.896-0.941) and 0.883 (95% CI 0.851-0.902), while the AUC of clinical-radiomics model was 0.950 (95% CI 0.925-0.967) and 0.942 (95% CI 0.927-0.958) respectively. CONCLUSION: The proposed clinical-radiomics model is a dependable approach that could provide risk assessment of HT for patients who receive IVT after stroke.

Deep Learning Provides a New Magnetic Resonance Imaging-Based Prognostic Biomarker for Recurrence Prediction in High-Grade Serous Ovarian Cancer.

This study aims to use a deep learning method to develop a signature extract from preoperative magnetic resonance imaging (MRI) and to evaluate its ability as a non-invasive recurrence risk prognostic marker in patients with advanced high-grade serous ovarian cancer (HGSOC). Our study comprises a total of 185 patients with pathologically confirmed HGSOC. A total of 185 patients were randomly assigned in a 5:3:2 ratio to a training cohort (n = 92), validation cohort 1 (n = 56), and validation cohort 2 (n = 37). We built a new deep learning network from 3839 preoperative MRI images (T2-weighted images and diffusion-weighted images) to extract HGSOC prognostic indicators. Following that, a fusion model including clinical and deep learning features is developed to predict patients' individual recurrence risk and 3-year recurrence likelihood. In the two validation cohorts, the consistency index of the fusion model was higher than both the deep learning model and the clinical feature model (0.752, 0.813 vs. 0.625, 0.600 vs. 0.505, 0.501). Among the three models, the fusion model had a higher AUC than either the deep learning model or the clinical model in validation cohorts 1 or 2 (AUC = was 0.986, 0.961 vs. 0.706, 0.676/0.506, 0.506). Using the DeLong method, the difference between them was statistically significant (p < 0.05). The Kaplan-Meier analysis distinguished two patient groups with high and low recurrence risk (p = 0.0008 and 0.0035, respectively). Deep learning may be a low-cost, non-invasive method for predicting risk for advanced HGSOC recurrence. Deep learning based on multi-sequence MRI serves as a prognostic biomarker for advanced HGSOC, which provides a preoperative model for predicting recurrence in HGSOC. Additionally, using the fusion model as a new prognostic analysis means that can use MRI data can be used without the need to follow-up the prognostic biomarker.

Prediction of Hemorrhagic Complication after Thrombolytic Therapy Based on Multimodal Data from Multiple Centers: An Approach to Machine Learning and System Implementation.

Hemorrhagic complication (HC) is the most severe complication of intravenous thrombolysis (IVT) in patients with acute ischemic stroke (AIS). This study aimed to build a machine learning (ML) prediction model and an application system for a personalized analysis of the risk of HC in patients undergoing IVT therapy. We included patients from Chongqing, Hainan and other centers, including Computed Tomography (CT) images, demographics, and other data, before the occurrence of HC. After feature engineering, a better feature subset was obtained, which was used to build a machine learning (ML) prediction model (Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGB)), and then evaluated with relevant indicators. Finally, a prediction model with better performance was obtained. Based on this, an application system was built using the Flask framework. A total of 517 patients were included, of which 332 were in the training cohort, 83 were in the internal validation cohort, and 102 were in the external validation cohort. After evaluation, the performance of the XGB model is better, with an AUC of 0.9454 and ACC of 0.8554 on the internal validation cohort, and 0.9142 and ACC of 0.8431 on the external validation cohort. A total of 18 features were used to construct the model, including hemoglobin and fasting blood sugar. Furthermore, the validity of the model is demonstrated through decision curves. Subsequently, a system prototype is developed to verify the test prediction effect. The clinical decision support system (CDSS) embedded with the XGB model based on clinical data and image features can better carry out personalized analysis of the risk of HC in intravenous injection patients.

Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network.

Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice.

[Denoising worm artifacts of elastogram using 2-D wavelet shrinkage].

This paper proposes a technique to denoise the worm artifacts of elastogram using 2-D wavelet shrinkage denoising method. Firstly, strain estimate matrix including worm artifacts was decomposed to 3 levels by 2-D discrete wavelet transform with Sym8 wavelet function, and the thresholds were obtained using Birg6-Massart algorithm. Secondly, all the high frequency coefficients on different levels were quantized by using hard threshold and soft threshold function. Finally, the strain estimate matrix was reconstructed by using the 3rd layer low frequency coefficients and other layer quantized high frequency coefficients. The simulation results illustrated that the present technique could efficiently denoise the worm artifacts, enhance the elastogram performance indices, such as elastographic signal-to-noise ratio (SNRe) and elastographic contrast-to-noise ratio (CNRe), and could increase the correlation coefficient between the denoised elastogram and the ideal elastogram. In comparison with 2-D low-pass filtering, it could also obtain the higher elastographic SNRe and CNRe, and have clearer hard lesion edge. In addition, the results demonstrated that the proposed technique could suppress worm artifacts of elastograms for various applied strains. This work showed that the 2-D wavelet shrinkage denoising could efficiently denoise the worm artifacts of elastogram and enhance the performance of elastogram.

Measuring the burden of disease using disability-adjusted life years in Shilin County of Yunnan Province, China.

BACKGROUND: Few studies calculating burden of disease (BOD) have been carried out in China. Disability-adjusted life years (DALY) is one of the useful methods used to estimate BOD. This study aims to use DALY for evaluating BOD and to provide useful information for health planning for residents in Shilin Yi Nationality Autonomous County (Shilin County) of Yunnan Province, China. METHODS: Methods developed for the Global Burden of Disease (GBD) Study by the World Bank and World Health Organization (WHO) were adapted and applied to Shilin County population health data. DALY rate per 1,000 was calculated from medical death certificates in 2003 in Shilin County. The geographic coordinates of towns or townships were determined using the geocode function of R2.3.1 geographical information system (GIS) software. RESULTS: Respiratory diseases were by far the leading cause of years of life lost (YLL) in both males and females. The four other leading causes of YLL in descending order were: unintentional injuries, cardiovascular diseases, intentional injuries, and malignant neoplasms. However, the five leading causes of years lived with disability (YLD) were, in descending order: neuropsychiatric conditions, intentional injuries, respiratory diseases, unintentional injuries, and cardiovascular diseases. The leading cause of total disease burden (DALY) was neuropsychiatric conditions. Townships of Muzhuqing, Xijiekou, and Weize were the areas with most serious disease burden in Shilin County. CONCLUSIONS: Prevention and treatment of neuropsychiatric conditions and respiratory diseases for both females and males should be enhanced in Shilin County, so as to decrease injury. More preventive interventions for noninfectious chronic diseases should be emphasized in remote townships.

Noise reduction for ultrasonic elastography using transmit-side frequency compounding: a preliminary study.

Ultrasonic elastography is an imaging technique providing information about the relative stiffness of biological tissues. In general, elastography suffers from noise artifacts, which degrade lesion detectability and increase the likelihood of misdiagnosis. This paper proposes a method called transmit- side frequency compounding for elastography (TSFC). Beamforming is modified to transmit frames with N alternating center frequencies. Pairs of frames with the same center frequency are used to calculate sub-elastograms that are then averaged to produce one compounded elastogram. Simulation results based on an uniformly elastic tissue model demonstrate the decorrelation among sub-elastograms and the improvement in elastographic signal-to-noise ratio (SNRe) achieved by compounding sub-elastograms. An elastic phantom experiment further validates the noise reduction obtained by the proposed technique.