Cervical cancer is the fifth most common cancer among women, which is the third leading cause of cancer death in women worldwide. Brachytherapy is the most effective treatment for cervical cancer. For brachytherapy, computed tomography (CT) imaging is necessary since it conveys tissue density information which can be used for dose planning. However, the metal artifacts caused by brachytherapy applicators remain a challenge for the automatic processing of image data for image-guided procedures or accurate dose calculations. Therefore, developing an effective metal artifact reduction (MAR) algorithm in cervical CT images is of high demand. A novel residual learning method based on convolutional neural network (RL-ARCNN) is proposed to reduce metal artifacts in cervical CT images. For MAR, a dataset is generated by simulating various metal artifacts in the first step, which will be applied to train the CNN. This dataset includes artifact-insert, artifact-free, and artifact-residual images. Numerous image patches are extracted from the dataset for training on deep residual learning artifact reduction based on CNN (RL-ARCNN). Afterwards, the trained model can be used for MAR on cervical CT images. The proposed method provides a good MAR result with a PSNR of 38.09 on the test set of simulated artifact images. The PSNR of residual learning (38.09) is higher than that of ordinary learning (37.79) which shows that CNN-based residual images achieve favorable artifact reduction. Moreover, for a 512 × 512 image, the average removal artifact time is less than 1 s. The RL-ARCNN indicates that residual learning of CNN remarkably reduces metal artifacts and improves critical structure visualization and confidence of radiation oncologists in target delineation. Metal artifacts are eliminated efficiently free of sinogram data and complicated post-processing procedure.

As a highly heterogeneous disease, clear cell renal cell carcinoma (ccRCC) has quite variable clinical behaviors. The prognostic biomarkers play a crucial role in stratifying patients suffering from ccRCC to avoid over- and under-treatment. Researches based on hand-crafted features and single-modal data have been widely conducted to predict the prognosis of ccRCC. However, these experience-dependent methods, neglecting the synergy among multimodal data, have limited capacity to perform accurate prediction. Inspired by complementary information among multimodal data and the successful application of convolutional neural networks (CNNs) in medical image analysis, a novel framework was proposed to improve prediction performance. We proposed a cross-modal feature-based integrative framework, in which deep features extracted from computed tomography/histopathological images by using CNNs were combined with eigengenes generated from functional genomic data, to construct a prognostic model for ccRCC. Results showed that our proposed model can stratify high- and low-risk subgroups with significant difference (P-value < 0.05) and outperform the predictive performance of those models based on single-modality features in the independent testing cohort [C-index, 0.808 (0.728–0.888)]. In addition, we also explored the relationship between deep image features and eigengenes, and make an attempt to explain deep image features from the view of genomic data. Notably, the integrative framework is available to the task of prognosis prediction of other cancer with matched multimodal data. https://github.com/zhang-de-lab/zhang-lab? from=singlemessage Supplementary data are available at Bioinformatics online.

Background: To investigate the feasibility of integrating global radiomics and local deep features based on multi-modal magnetic resonance imaging (MRI) for developing a noninvasive glioma grading model. Methods: In this study, 567 patients [211 patients with glioblastomas (GBMs) and 356 patients with low-grade gliomas (LGGs)] between May 2006 and September 2018, were enrolled and divided into training (n=186), validation (n=47), and testing cohorts (n=334), respectively. All patients underwent postcontrast enhanced T1-weighted and T2 fluid-attenuated inversion recovery MRI scanning. Radiomics and deep features (trained by 8,510 3D patches) were extracted to quantify the global and local information of gliomas, respectively. A kernel fusion-based support vector machine (SVM) classifier was used to integrate these multi-modal features for grading gliomas. The performance of the grading model was assessed using the area under receiver operating curve (AUC), sensitivity, specificity, Delong test, and t-test. Results: The AUC, sensitivity, and specificity of the model based on combination of radiomics and deep features were 0.94 [95% confidence interval (CI): 0.85, 0.99], 86% (95% CI: 64%, 97%), and 92% (95% CI: 75%, 99%), respectively, for the validation cohort; and 0.88 (95% CI: 0.84, 0.91), 88% (95% CI: 80%, 93%), and 81% (95% CI: 76%, 86%), respectively, for the independent testing cohort from a local hospital. The developed model outperformed the models based only on either radiomics or deep features (Delong test, both of P<0.001), and was also comparable to the clinical radiologists. Conclusions: This study demonstrated the feasibility of integrating multi-modal MRI radiomics and deep features to develop a promising noninvasive grading model for gliomas.

The phthalate derivative di-n-pentyl phthalate (DNPP) is an extensively distributed environmental contaminant that has been implicated in various pathological conditions. The immune system critically regulates disease pathogenesis through complex interactions. However, current toxicological research has failed to comprehensively characterize DNPP-induced immunotoxicity. Therefore, we aimed to systematically assess DNPP-induced alterations within the immune landscape, by conducting single-cell RNA sequencing (scRNA-seq) on murine splenic tissues. We established a DNPP-exposed mouse model by administering various doses of DNPP, alongside complementary in vitro experiments. We found that DNPP exposure markedly decreased peripheral blood leukocyte populations, which notably affected lymphocytes, neutrophils, and monocytes. Moreover, DNPP might attenuate the cytotoxic capacity of CD8⁺ T cells and reduce the proportions of CD4⁺ T_Tem and CD4⁺ T_Treg cells. Furthermore, DNPP may impair immunoglobulin production of B cells, impact the cytotoxicity of NK cells, and alter the antigen-presenting capacity of myeloid cells. Overall, these findings demonstrate that DNPP functions as an environmental immune disruptor and may increase the susceptibility to infectious diseases, malignancies, and immune-related pathologies. Our study provides novel, impactful insights into DNPP-associated health hazards.

Purpose: We aimed to integrate cross-module data for predicting the prognosis of clear cell renal cell carcinoma (ccRCC) based on deep learning and to explore the relationship between deep features from images and eigengenes form gene data. Experimental design: A total of 209 patients with ccRCC with computed tomography (CT), histopathological images and RNA sequences were enrolled. A deep biomarker-based integrative framework was proposed to construct a prognostic model. Deep features extracted from CT and histopathological images by using deep learning combined with eigengenes generated from functional genomic data were used to predict ccRCC prognosis. Furthermore, the relationship between deep features and eigengenes was explored, and two survival subgroups identified by integrative cross-module biomarkers were subjected to functional analysis. Results: The model based on the integrative framework stratified two subgroups of patients with a significant prognostic difference ( P = 6.51e-6, concordance index [C-index] = 0.808, 95% confidence interval [CI] = 0.728-0.888) and outperformed the prediction based on their individual biomarkers in the independent validation cohort (n = 70, gene data: C-index = 0.452, CI = 0.336-0.567; histopathological images: C-index = 0.677, CI = 0.577-0.776; CT images: C-index = 0.774, CI = 0.670-0.879). On the basis of statistical relationship, deep features correlated or complemented with eigengenes both enhanced the predictive performance of eigengenes ( P = 0.439, correlated: C-index = 0.785, CI = 0.685-0.886; complemented: C-index = 0.778, CI = 0.683-0.872). The functional analysis of subgroups also exhibited reasonable results. Conclusion: The model based on the integrative framework of cross-module deep biomarkers can efficiently predict ccRCC prognosis, and the framework with a code is shared to act as a reliable and powerful tool for further studies.