Dataset Information

Radiomics assessment of bladder cancer grade using texture features from diffusion-weighted imaging.

ABSTRACT: PURPOSE:To 1) describe textural features from diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) maps that can distinguish low-grade bladder cancer from high-grade, and 2) propose a radiomics-based strategy for cancer grading using texture features. MATERIALS AND METHODS:In all, 61 patients with bladder cancer (29 in high- and 32 in low-grade groups) were enrolled in this retrospective study. Histogram- and gray-level co-occurrence matrix (GLCM)-based radiomics features were extracted from cancerous volumes of interest (VOIs) on DWI and corresponding ADC maps of each patient acquired from 3.0T magnetic resonance imaging (MRI). A Mann-Whitney U-test was applied to select features with significant differences between low- and high-grade groups (P < 0.05). Then support vector machine with recursive feature elimination (SVM-RFE) and classification strategy was adopted to find an optimal feature subset and then to establish a classification model for grading. RESULTS:A total 102 features were derived from each VOI and among them, 47 candidate features were selected, which showed significant intergroup differences (P < 0.05). By the SVM-RFE method, an optimal feature subset including 22 features was further selected from candidate features. The SVM classifier using the optimal feature subset achieved the best performance in bladder cancer grading, with an area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity of 0.861, 82.9%, 78.4%, and 87.1%, respectively. CONCLUSION:Textural features from DWI and ADC maps can reflect the difference between low- and high-grade bladder cancer, especially those GLCM features from ADC maps. The proposed radiomics strategy using these features, combined with the SVM classifier, may better facilitate image-based bladder cancer grading preoperatively. LEVEL OF EVIDENCE:3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;46:1281-1288.

SUBMITTER: Zhang X

PROVIDER: S-EPMC5557707 | biostudies-literature | 2017 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Radiomics assessment of bladder cancer grade using texture features from diffusion-weighted imaging.

Zhang Xi X Xu Xiaopan X Tian Qiang Q Li Baojuan B Wu Yuxia Y Yang Zengyue Z Liang Zhengrong Z Liu Yang Y Cui Guangbin G Lu Hongbing H

Journal of magnetic resonance imaging : JMRI 20170215 5

<h4>Purpose</h4>To 1) describe textural features from diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) maps that can distinguish low-grade bladder cancer from high-grade, and 2) propose a radiomics-based strategy for cancer grading using texture features.<h4>Materials and methods</h4>In all, 61 patients with bladder cancer (29 in high- and 32 in low-grade groups) were enrolled in this retrospective study. Histogram- and gray-level co-occurrence matrix (GLCM)-based radiomi ...[more]

PMID: 28199039

Similar Datasets

Project description:Background1p/19q co-deletion in low-grade gliomas (LGG, World Health Organization grade II and III) is of great significance in clinical decision making. We aim to use radiomics analysis to predict 1p/19q co-deletion in LGG based on amide proton transfer weighted (APTw), diffusion weighted imaging (DWI), and conventional MRI.MethodsThis retrospective study included 90 patients histopathologically diagnosed with LGG. We performed a radiomics analysis by extracting 8454 MRI-based features form APTw, DWI and conventional MR images and applied a least absolute shrinkage and selection operator (LASSO) algorithm to select radiomics signature. A radiomics score (Rad-score) was generated using a linear combination of the values of the selected features weighted for each of the patients. Three neuroradiologists, including one experienced neuroradiologist and two resident physicians, independently evaluated the MR features of LGG and provided predictions on whether the tumor had 1p/19q co-deletion or 1p/19q intact status. A clinical model was then constructed based on the significant variables identified in this analysis. A combined model incorporating both the Rad-score and clinical factors was also constructed. The predictive performance was validated by receiver operating characteristic curve analysis, DeLong analysis and decision curve analysis. P < 0.05 was statistically significant.ResultsThe radiomics model and the combined model both exhibited excellent performance on both the training and test sets, achieving areas under the curve (AUCs) of 0.948 and 0.966, as well as 0.909 and 0.896, respectively. These results surpassed the performance of the clinical model, which achieved AUCs of 0.760 and 0.766 on the training and test sets, respectively. After performing Delong analysis, the clinical model did not significantly differ in predictive performance from three neuroradiologists. In the training set, both the radiomic and combined models performed better than all neuroradiologists. In the test set, the models exhibited higher AUCs than the neuroradiologists, with the radiomics model significantly outperforming resident physicians B and C, but not differing significantly from experienced neuroradiologist.ConclusionsOur results suggest that our algorithm can noninvasively predict the 1p/19q co-deletion status of LGG. The predictive performance of radiomics model was comparable to that of experienced neuroradiologist, significantly outperforming the diagnostic accuracy of resident physicians, thereby offering the potential to facilitate non-invasive 1p/19q co-deletion prediction of LGG.

Project description:Objectives: Magnetic resonance-guided focused ultrasound (MRgFUS) is a non-invasive targeted tissue ablation technique that can be applied to the nervous system. Diffusion weighted imaging (DWI) can visualize and evaluate nervous system microstructure. Tractography algorithms can reconstruct fiber bundles which can be used for treatment navigation and diffusion tensor imaging (DTI) metrics permit the quantitative assessment of nerve microstructure in vivo. There is a need for imaging tools to aid in the visualization and quantitative assessment of treatment-related nerve changes in MRgFUS. We present a method of peripheral nerve tract reconstruction and use DTI metrics to evaluate the MRgFUS treatment effect. Materials and Methods: MRgFUS was applied bilaterally to the sciatic nerves in 6 piglets (12 nerves total). T1-weighted and diffusion images were acquired before and after treatment. Tensor-based and constrained spherical deconvolution (CSD) tractography algorithms were used to reconstruct the nerves. DTI metrics of fractional anisotropy (FA), and mean (MD), axial (AD), and radial diffusivities (RD) were measured to assess acute (<1-2 h) treatment effects. Temperature was measured in vivo via MR thermometry. Histological data was collected for lesion assessment. Results: The sciatic nerves were successfully reconstructed in all subjects. Tract disruption was observed after treatment using both CSD and tensor models. DTI metrics in the targeted nerve segments showed significantly decreased FA and increased MD, AD, and RD. Transducer output power was positively correlated with lesion volume and temperature and negatively correlated with MD, AD, and RD. No correlations were observed between FA and other measured parameters. Conclusions: DWI and tractography are effective tools for visualizing peripheral nerve segments for targeting in non-invasive surgical methods and for assessing the microstructural changes that occur following MRgFUS treatment.

Project description:BackgroundMetastatic complications are a major cause of cancer-related morbidity, with up to 40% of cancer patients experiencing at least one brain metastasis. Earlier detection may significantly improve patient outcomes and overall survival. We investigated machine learning (ML) models for early detection of brain metastases based on diffusion weighted imaging (DWI) radiomics.MethodsLongitudinal diffusion imaging from 116 patients previously treated with stereotactic radiosurgery (SRS) for brain metastases were retrospectively analyzed. Clinical contours from 600 metastases were extracted from radiosurgery planning computed tomography, and rigidly registered to corresponding contrast enhanced-T1 and apparent diffusion coefficient (ADC) maps. Contralateral contours located in healthy brain tissue were used as control. The dataset consisted of (I) radiomic features using ADC maps, (II) radiomic feature change calculated using timepoints before the metastasis manifested on contrast enhanced-T1, (III) primary cancer, and (IV) anatomical location. The dataset was divided into training and internal validation sets using an 80/20 split with stratification. Four classification algorithms [Linear Support Vector Machine (SVM), Random Forest (RF), AdaBoost, and XGBoost] underwent supervised classification training, with contours labeled either 'control' or 'metastasis'. Hyperparameters were optimized towards balanced accuracy. Various model metrics (receiver operating characteristic curve area scores, accuracy, recall, and precision) were calculated to gauge performance.ResultsThe radiomic and clinical data set, feature engineering, and ML models developed were able to identify metastases with an accuracy of up to 87.7% on the training set, and 85.8% on an unseen test set. XGBoost and RF showed superior accuracy (XGBoost: 0.877±0.021 and 0.833±0.47, RF: 0.823±0.024 and 0.858±0.045) for training and validation sets, respectively. XGBoost and RF also showed strong area under the receiver operating characteristic curve (AUC) performance on the validation set (0.910±0.037 and 0.922±0.034, respectively). AdaBoost performed slightly lower in all metrics. SVM model generalized poorly with the internal validation set. Important features involved changes in radiomics months before manifesting on contrast enhanced-T1.ConclusionsThe proposed models using diffusion-based radiomics showed encouraging results in differentiating healthy brain tissue from metastases using clinical imaging data. These findings suggest that longitudinal diffusion imaging and ML may help improve patient care through earlier diagnosis and increased patient monitoring/follow-up. Future work aims to improve model classification metrics, robustness, user-interface, and clinical applicability.

Project description:PurposeTo investigate radiomics based on DWI (diffusion-weighted imaging) for predicting 1-year ischemic stroke recurrence.MethodsA total of 1,580 ischemic stroke patients were enrolled in this retrospective study conducted from January 2018 to April 2021. Demographic and clinical characteristics were compared between recurrence and non-recurrence groups. On DWI, lesions were segmented using a 2D U-Net automatic segmentation network. Further, radiomics feature extraction was done using the segmented mask matrix on DWI and the corresponding ADC map. Additionally, radiomics features were extracted. The study participants were divided into a training cohort (n = 157, 57 recurrence patients, and 100 non-recurrence patients) and a test cohort (n = 846, 28 recurrence patients, 818 non-recurrence patients). A sparse representation feature selection model was performed to select features. Further classification was accomplished using a recurrent neural network (RNN). The area under the receiver operating characteristic curve values was obtained for model performance.ResultsA total of 1,003 ischemic stroke patients (682 men and 321 women; mean age: 65.90 ± 12.44 years) were included in the final analysis. About 85 patients (8.5%) recurred in 1 year, and patients in the recurrence group were older than the non-recurrence group (P = 0.003). The stroke subtype was significantly different between recurrence and non-recurrence groups, and cardioembolic stroke (11.3%) and large artery atherosclerosis patients (10.3%) showed a higher recurrence percentage (P = 0.005). Secondary prevention after discharge (statins, antiplatelets, and anticoagulants) was found significantly different between the two groups (P = 0.004). The area under the curve (AUC) of clinical-based model and radiomics-based model were 0.675 (95% CI: 0.643-0.707) and 0.779 (95% CI: 0.750-0.807), respectively. With an AUC of 0.847 (95% CI: 0.821-0.870), the model that combined clinical and radiomic characteristics performed better.ConclusionDWI-based radiomics could help to predict 1-year ischemic stroke recurrence.

Project description:PURPOSE:Diffusion-weighted imaging (DWI) plays an important role in the preoperative assessment of gliomas; however, the diagnostic performance of histogram-derived parameters from mono-, bi-, and stretched-exponential DWI models in the grading of gliomas has not been fully investigated. Therefore, we compared these models' ability to differentiate between high-grade and low-grade gliomas. METHODS:This retrospective study included 22 patients with diffuse gliomas (age, 23-74 years; 12 males; 11 high-grade and 11 low-grade gliomas) who underwent preoperative 3 T-magnetic resonance imaging from October 2014 to August 2019. The apparent diffusion coefficient was calculated from the mono-exponential model. Using 13 b-values, the true-diffusion coefficient, pseudo-diffusion coefficient, and perfusion fraction were obtained from the bi-exponential model, and the distributed-diffusion coefficient and heterogeneity index were obtained from the stretched-exponential model. Region-of-interests were drawn on each imaging parameter map for subsequent histogram analyses. RESULTS:The skewness of the apparent diffusion, true-diffusion, and distributed-diffusion coefficients was significantly higher in high-grade than in low-grade gliomas (0.67?±?0.67 vs. -?0.18?±?0.63, 0.68?±?0.74 vs. -?0.08?±?0.66, 0.63?±?0.72 vs. -?0.15?±?0.73; P?=?0.0066, 0.0192, and 0.0128, respectively). The 10th percentile of the heterogeneity index was significantly lower (0.77?±?0.08 vs. 0.88?±?0.04; P?=?0.0004), and the 90th percentile of the perfusion fraction was significantly higher (12.64?±?3.44 vs. 7.14?±?1.70%: P?<?0.0001), in high-grade than in low-grade gliomas. The combination of the 10th percentile of the true-diffusion coefficient and 90th percentile of the perfusion fraction showed the best area under the receiver operating characteristic curve (0.96). CONCLUSION:The bi-exponential model exhibited the best diagnostic performance for differentiating high-grade from low-grade gliomas.

Project description:PurposeGlioblastoma and anaplastic astrocytoma represent the most commonly encountered high-grade-glioma (HGG) in adults. Although both neoplasms are very distinct entities in context of epidemiology, clinical course and prognosis, their appearance in conventional magnetic resonance imaging (MRI) is very similar. In search for additional information aiding the distinction of potentially confusable neoplasms, histogram analysis of apparent diffusion coefficient (ADC) maps recently proved to be auxiliary in a number of entities. Therefore, our present exploratory retrospective study investigated whether ADC histogram profile parameters differ significantly between anaplastic astrocytoma and glioblastoma, reflect the proliferation index Ki-67, or are associated with the prognostic relevant MGMT (methylguanine-DNA methyl-transferase) promotor methylation status.MethodsPre-surgical ADC volumes of 56 HGG patients were analyzed by histogram-profiling. Association between extracted histogram parameters and neuropathology including WHO-grade, Ki-67 expression and MGMT promotor methylation status was investigated due to comparative and correlative statistics.ResultsGrade IV gliomas were more heterogeneous than grade III tumors. More specifically, ADCmin and the lowest percentile ADCp10 were significantly lower, whereas ADCmax, ADC standard deviation and Skewness were significantly higher in the glioblastoma group. ADCmin, ADCmax, ADC standard deviation, Kurtosis and Entropy of ADC histogram were significantly correlated with Ki-67 expression. No significant difference could be revealed by comparison of ADC histogram parameters between MGMT promotor methylated and unmethylated HGG.ConclusionsADC histogram parameters differ significantly between glioblastoma and anaplastic astrocytoma and show distinct associations with the proliferative activity in both HGG. Our results suggest ADC histogram profiling as promising biomarker for differentiation of both, however, further studies with prospective multicenter design are wanted to confirm and further elaborate this hypothesis.

Dataset Information

Radiomics assessment of bladder cancer grade using texture features from diffusion-weighted imaging.

Publications

Radiomics assessment of bladder cancer grade using texture features from diffusion-weighted imaging.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets