Prediction of treatment response after stereotactic radiosurgery of brain metastasis using deep learning and radiomics on longitudinal MRI data.

We developed artificial intelligence models to predict the brain metastasis (BM) treatment response after stereotactic radiosurgery (SRS) using longitudinal magnetic resonance imaging (MRI) data and evaluated prediction accuracy changes according to the number of sequential MRI scans. We included four sequential MRI scans for 194 patients with BM and 369 target lesions for the Developmental dataset. The data were randomly split (8:2 ratio) for training and testing. For external validation, 172 MRI scans from 43 patients with BM and 62 target lesions were additionally enrolled. The maximum axial diameter (Dmax), radiomics, and deep learning (DL) models were generated for comparison. We evaluated the simple convolutional neural network (CNN) model and a gated recurrent unit (Conv-GRU)-based CNN model in the DL arm. The Conv-GRU model performed superior to the simple CNN models. For both datasets, the area under the curve (AUC) was significantly higher for the two-dimensional (2D) Conv-GRU model than for the 3D Conv-GRU, Dmax, and radiomics models. The accuracy of the 2D Conv-GRU model increased with the number of follow-up studies. In conclusion, using longitudinal MRI data, the 2D Conv-GRU model outperformed all other models in predicting the treatment response after SRS of BM.

Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: Glioblastoma, lymphoma, and metastasis.

BACKGROUND AND PURPOSE: To investigate the diagnostic performance of fully automated radiomics-based models for multiclass classification of a single enhancing brain tumor among glioblastoma, central nervous system lymphoma, and metastasis. MATERIALS AND METHODS: The training and test sets were comprised of 538 cases (300 glioblastomas, 73 lymphomas, and 165 metastases) and 169 cases (101 glioblastomas, 29 lymphomas, and 39 metastases), respectively. After fully automated segmentation, radiomic features were extracted. Three conventional machine learning classifiers, including least absolute shrinkage and selection operator (LASSO), adaptive boosting (Adaboost), and support vector machine with the linear kernel (SVC), combined with one of four feature selection methods, including forward sequential feature selection, F score, mutual information, and LASSO, were trained. Additionally, one ensemble classifier based on the three classifiers was used. The diagnostic performance of the optimized models was tested in the test set using the accuracy, F1-macro score, and the area under the receiver operating characteristic curve (AUCROC). RESULTS: The best performance was achieved when the LASSO was used as a feature selection method. In the test set, the best performance was achieved by the ensemble classifier, showing an accuracy of 76.3% (95% CI, 70.0-82.7), a F1-macro score of 0.704, and an AUCROC of 0.878. CONCLUSION: Our fully automated radiomics-based models for multiclass classification might be useful for differential diagnosis of a single enhancing brain tumor with a good diagnostic performance and generalizability.

Performance Evaluation of a Deep Learning System for Differential Diagnosis of Lung Cancer With Conventional CT and FDG PET/CT Using Transfer Learning and Metadata.

PURPOSE: We aimed to evaluate the performance of a deep learning system for differential diagnosis of lung cancer with conventional CT and FDG PET/CT using transfer learning (TL) and metadata. METHODS: A total of 359 patients with a lung mass or nodule who underwent noncontrast chest CT and FDG PET/CT prior to treatment were enrolled retrospectively. All pulmonary lesions were classified by pathology (257 malignant, 102 benign). Deep learning classification models based on ResNet-18 were developed using the pretrained weights obtained from ImageNet data set. We propose a deep TL model for differential diagnosis of lung cancer using CT imaging data and metadata with SUVmax and lesion size derived from PET/CT. The area under the receiver operating characteristic curve (AUC) of the deep learning model was measured as a performance metric and verified by 5-fold cross-validation. RESULTS: The performance metrics of the conventional CT model were generally better than those of the CT of PET/CT model. Introducing metadata with SUVmax and lesion size derived from PET/CT into baseline CT models improved the diagnostic performance of the CT of PET/CT model (AUC = 0.837 vs 0.762) and the conventional CT model (AUC = 0.877 vs 0.817). CONCLUSIONS: Deep TL models with CT imaging data provide good diagnostic performance for lung cancer, and the conventional CT model showed overall better performance than the CT of PET/CT model. Metadata information derived from PET/CT can improve the performance of deep learning systems.

Differentiation of recurrent glioblastoma from radiation necrosis using diffusion radiomics with machine learning model development and external validation.

The purpose of this study was to establish a high-performing radiomics strategy with machine learning from conventional and diffusion MRI to differentiate recurrent glioblastoma (GBM) from radiation necrosis (RN) after concurrent chemoradiotherapy (CCRT) or radiotherapy. Eighty-six patients with GBM were enrolled in the training set after they underwent CCRT or radiotherapy and presented with new or enlarging contrast enhancement within the radiation field on follow-up MRI. A diagnosis was established either pathologically or clinicoradiologically (63 recurrent GBM and 23 RN). Another 41 patients (23 recurrent GBM and 18 RN) from a different institution were enrolled in the test set. Conventional MRI sequences (T2-weighted and postcontrast T1-weighted images) and ADC were analyzed to extract 263 radiomic features. After feature selection, various machine learning models with oversampling methods were trained with combinations of MRI sequences and subsequently validated in the test set. In the independent test set, the model using ADC sequence showed the best diagnostic performance, with an AUC, accuracy, sensitivity, specificity of 0.80, 78%, 66.7%, and 87%, respectively. In conclusion, the radiomics models models using other MRI sequences showed AUCs ranging from 0.65 to 0.66 in the test set. The diffusion radiomics may be helpful in differentiating recurrent GBM from RN..

Diffusion tensor and postcontrast T1-weighted imaging radiomics to differentiate the epidermal growth factor receptor mutation status of brain metastases from non-small cell lung cancer.

PURPOSE: To assess whether the radiomic features of diffusion tensor imaging (DTI) and conventional postcontrast T1-weighted (T1C) images can differentiate the epidermal growth factor receptor (EGFR) mutation status in brain metastases from non-small cell lung cancer (NSCLC). METHODS: A total of 99 brain metastases in 51 patients who underwent surgery or biopsy with underlying NSCLC and known EGFR mutation statuses (57 from EGFR wild type, 42 from EGFR mutant) were allocated to the training (57 lesions in 31 patients) and test (42 lesions in 20 patients) sets. Radiomic features (n = 526) were extracted from preoperative MR images including T1C and DTI. Radiomics classifiers were constructed by combinations of five feature selectors and four machine learning algorithms. The trained classifiers were validated on the test set, and the classifier performance was assessed by determining the area under the curve (AUC). RESULTS: EGFR mutation status showed an overall discordance rate of 12% between the primary tumors and corresponding brain metastases. The best performing classifier was a combination of the tree-based feature selection and linear discriminant algorithm and 5 features were selected (1 from ADC, 2 from fractional anisotropy, and 2 from T1C images), resulting in an AUC, accuracy, sensitivity, and specificity of 0.73, 78.6%, 81.3%, and 76.9% in the test set, respectively. CONCLUSIONS: Radiomics classifiers integrating multiparametric MRI parameters may have potential in differentiating the EGFR mutation status in brain metastases from NSCLC.

Zinc Oxide Nanoparticles Induce Autophagy and Apoptosis via Oxidative Injury and Pro-Inflammatory Cytokines in Primary Astrocyte Cultures.

The present study examined the potential toxic concentrations of zinc oxide nanoparticles (ZnO NPs) and associated autophagy and apoptosis-related injuries in primary neocortical astrocyte cultures. Concentrations of ZnO NPs ≥3 µg/mL induced significant toxicity in the astrocytes. At 24 h after exposure to the ZnO NPs, transmission electron microscopy revealed swelling of the endoplasmic reticulum (ER) and increased numbers of autophagolysosomes in the cultured astrocytes, and increased levels of LC3 (microtubule-associated protein 1 light chain 3)-mediated autophagy were identified by flow cytometry. Apoptosis induced by ZnO NP exposure was confirmed by the elevation of caspase-3/7 activity and 4',6'-diamidino-2-phenylindole (DAPI) staining. Significant (p < 0.05) changes in the levels of glutathione peroxidase, superoxide dismutase, tumor necrosis factor (TNF-α), and interleukin-6 were observed by enzyme-linked immunoassay (ELISA) assay following the exposure of astrocyte cultures to ZnO NPs. Phosphatidylinositol 3-kinase (PI3K)/mitogen-activated protein kinase (MAPK) dual activation was induced by ZnO NPs in a dose-dependent manner. Additionally, the Akt (protein kinase B) inhibitor BML257 and the mTOR (mammalian target of rapamycin) inhibitor rapamycin contributed to the survival of astrocytes. Inhibitors of cyclooxygenase-2 and lipoxygenase attenuated ZnO NP-induced toxicity. Calcium-modulating compounds, antioxidants, and zinc/iron chelators also decreased ZnO NP-induced toxicity. Together, these results suggest that ZnO NP-induced autophagy and apoptosis may be associated with oxidative stress and the inflammatory process in primary astrocyte cultures.

Vibrations Generated by Several Nickel-titanium Endodontic File Systems during Canal Shaping in an Ex Vivo Model.

INTRODUCTION: This study aimed to compare the vibration generated by several nickel-titanium (NiTi) file systems and transmitted to teeth under 2 different motions (continuous rotation motion and reciprocating motion). METHODS: Sixty J-shaped resin blocks (Endo Training Bloc-J; Dentsply Maillefer, Ballaigues, Switzerland) were trimmed to a root-shaped form and divided into 2 groups according to the types of electric motors: WaveOne motor (WOM, Dentsply Maillefer) and X-Smart Plus motor (XSM, Dentsply Maillefer). Each group was further subdivided into 3 subgroups (n = 10 each) according to the designated file systems: ProTaper Next (PTN, Dentsply Maillefer), ProTaper Universal (PTU, Dentsply Maillefer), and WaveOne (WOP, Dentsply Maillefer) systems. Vibration was measured during the pecking motion using an accelerometer attached to a predetermined consistent position. The average vibration values were subjected to 2-way analysis of variance as well as the t test and Duncan test for post hoc comparison at the 95% confidence interval. RESULTS: Both motor types and instrument types produced significantly different ranges of average vibrations. Regardless of the instrument types, the WOM group generated greater vibration than the XSM group (P < .05). Although PTN and PTU did not show significant differences, the WOP group showed significantly greater vibration than the other groups regardless of motor types (P < .05). CONCLUSIONS: Under the limitations of this study design, the reciprocating NiTi file system may generate greater vibration than the continuous rotation NiTi file systems. The motor type also has a significant effect to amplify the vibrations.

An energy-efficient and compact clustering scheme with temporary support nodes for cognitive radio sensor networks.

A cognitive radio sensor network (CRSN) is a wireless sensor network whose sensor nodes are equipped with cognitive radio capability. Clustering is one of the most challenging issues in CRSNs, as all sensor nodes, including the cluster head, have to use the same frequency band in order to form a cluster. However, due to the nature of heterogeneous channels in cognitive radio, it is difficult for sensor nodes to find a cluster head. This paper proposes a novel energy-efficient and compact clustering scheme named clustering with temporary support nodes (CENTRE). CENTRE efficiently achieves a compact cluster formation by adopting two-phase cluster formation with fixed duration. By introducing a novel concept of temporary support nodes to improve the cluster formation, the proposed scheme enables sensor nodes in a network to find a cluster head efficiently. The performance study shows that not only is the clustering process efficient and compact but it also results in remarkable energy savings that prolong the overall network lifetime. In addition, the proposed scheme decreases both the clustering overhead and the average distance between cluster heads and their members.