Using biparametric MRI radiomics signature to differentiate between benign and malignant prostate lesions.

PURPOSE: To investigate the efficiency of radiomics signature in discriminating between benign and malignant prostate lesions with similar biparametric magnetic resonance imaging (bp-MRI) findings. EXPERIMENTAL DESIGN: Our study consisted of 331 patients underwent bp-MRI before pathological examination from January 2013 to November 2016. Radiomics features were extracted from peripheral zone (PZ), transition zone (TZ), and lesion areas segmented on images obtained by T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and its derivative apparent-diffusion coefficient (ADC) imaging. The individual prediction model, built using the clinical data and biparametric MRI features (Bp signature), was prepared using data of 232 patients and validated using data of 99 patients. The predictive performance was calculated and demonstrated using receiver operating characteristic (ROC) curves, calibration curves, and decision curves. RESULTS: The Bp signature, based on the six selected radiomics features of bp-MRI, showed better discrimination in the validation cohort (area under the curve [AUC], 0.92) than on each subcategory images (AUC, 0.81 on T2WI; AUC, 0.77 on DWI; AUC, 0.89 on ADC). The differential diagnostic efficiency was poorer with the clinical model (AUC, 0.73), built using the selected independent clinical risk factors with statistical significance (P < 0.05), than with the Bp signature. Discrimination efficiency improved when including the Bp signature and clinical factors [i.e., the individual prediction model (AUC, 0.93)]. CONCLUSION: The Bp signature, based on bp-MRI, performed better than each single imaging modality. The individual prediction model including the radiomics signatures and clinical factors showed better preoperative diagnostic performance, which could contribute to clinical individualized treatment.

Radiomics in multiple sclerosis and neuromyelitis optica spectrum disorder.

OBJECTIVE: To develop and validate an individual radiomics nomogram for differential diagnosis between multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD). METHODS: We retrospectively collected 67 MS and 68 NMOSD with spinal cord lesions as a primary cohort and prospectively recruited 28 MS and 26 NMOSD patients as a validation cohort. Radiomic features were extracted from the spinal cord lesions. A prediction model for differentiating MS and NMOSD was built by combining the radiomic features with several clinical and routine MRI measurements. The performance of the model was assessed with respect to its calibration plot and clinical discrimination in the primary and validation cohorts. RESULTS: Nine radiomics features extracted from an initial set of 485, predominantly reflecting lesion heterogeneity, combined with lesion length, patient sex, and EDSS, were selected to build the model for differentiating MS and NMOSD. The areas under the ROC curves (AUC) for differentiating the two diseases were 0.8808 and 0.7115, for the primary and validation cohort, respectively. This model demonstrated good calibration (C-index was 0.906 and 0.802 in primary and validation cohort). CONCLUSIONS: A validated nomogram that incorporates the radiomic signature of spinal cord lesions, as well as cord lesion length, sex, and EDSS score, can usefully differentiate MS and NMOSD. KEY POINTS: • Radiomic features of spinal cord lesions in MS and NMOSD were different. • Radiomic signatures can capture pathological alterations and help differentiate MS and NMOSD.

Radiomic signature as a predictive factor for lymph node metastasis in early-stage cervical cancer.

BACKGROUND: Lymph node metastasis (LNM) is the principal risk factor for poor outcomes in early-stage cervical cancer. Radiomics may offer a noninvasive way for predicting the stage of LNM. PURPOSE: To evaluate a radiomic signature of LN involvement based on sagittal T1 contrast-enhanced (CE) and T2 MRI sequences. STUDY TYPE: Retrospective. POPULATION: In all, 143 patients were randomly divided into two primary and validation cohorts with 100 patients in the primary cohort and 43 patients in the validation cohort. FIELD STRENGTH/SEQUENCE: T1 CE and T2 MRI sequences at 3T. ASSESSMENT: The gold standard of LN status was based on histologic results. A radiologist with 10 years of experience used the ITK-SNAP software for 3D manual segmentation. A senior radiologist with 15 years of experience validated all segmentations. The area under the receiver operating characteristics curve (ROC AUC), classification accuracy, sensitivity, and specificity were used between LNM and non-LNM groups. STATISTICAL TESTS: A total of 970 radiomic features and seven clinical characteristics were extracted. Minimum redundancy / maximum relevance and support vector machine algorithms were applied to select features and construct a radiomic signature. The Mann-Whitney U-test and the chi-square test were used to test the performance of clinical characteristics and potential prognostic outcomes. The results were used to assess the quantitative discrimination performance of the SVM-based radiomic signature. RESULTS: The radiomic signatures allowed good discrimination between LNM and non-LNM groups. The ROC AUC was 0.753 (95% confidence interval [CI], 0.656-0.850) in the primary cohort and 0.754 (95% CI, 0584-0.924) in the validation cohort. DATA CONCLUSIONS: A multiple-sequence MRI radiomic signature can be used as a noninvasive biomarker for preoperative assessment of LN status and potentially influence the therapeutic decision-making in early-stage cervical cancer patients. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:304-310.

Prognostic value of computed tomography radiomics features in patients with gastric cancer following curative resection.

OBJECTIVES: The present study aimed to investigate the clinical prognostic significance of radiomics signature (R-signature) in patients with gastric cancer who had undergone radical resection. METHODS: A total of 181 patients with gastric cancer who had undergone radical resection were enrolled in this retrospective study. The association between the R-signature and overall survival (OS) was assessed in the primary cohort and verified in the validation cohort. Furthermore, the performance of a radiomics nomogram integrating the R-signature and significant clinicopathological risk factors was evaluated. RESULTS: The R-signature, which consisted of six imaging features, stratified patients with gastric cancer who had undergone radical resection into two prognostic risk groups in both cohorts. The radiomics nomogram incorporating R-signature and significant clinicopathological risk factors (T stage, N stage, and differentiation) exhibited significant prognostic superiority over clinical nomogram and R-signature alone (Harrell concordance index, 0.82 vs 0.71 and 0.82 vs 0.74, respectively, p < 0.001 in both analyses). All calibration curves showed remarkable consistency between predicted and actual survival, and decision curve analysis verified the usefulness of the radiomics nomogram for clinical practice. CONCLUSIONS: The R-signature could be used to stratify patients with gastric cancer following radical resection into high- and low-risk groups. Furthermore, the radiomics nomogram provided better predictive accuracy than other predictive models and might aid clinicians with therapeutic decision-making and patient counseling. KEY POINTS: • Radiomics can stratify the gastric cancer patients following radical resection into high- and low-risk groups. • Radiomics can improve the prognostic value of TNM staging system. • Radiomics may facilitate personalized treatment of gastric cancer patients.

Preoperative prediction of cavernous sinus invasion by pituitary adenomas using a radiomics method based on magnetic resonance images.

OBJECTIVES: To predict cavernous sinus (CS) invasion by pituitary adenomas (PAs) pre-operatively using a radiomics method based on contrast-enhanced T1 (CE-T1) and T2-weighted magnetic resonance (MR) imaging. METHODS: A total of 194 patients with Knosp grade two and three PAs (training set: n = 97; test set: n = 97) were enrolled in this retrospective study. From CE-T1 and T2 MR images, 2553 quantitative imaging features were extracted. To select the most informative features, least absolute shrinkage and selection operator (LASSO) was performed. Subsequently, a linear support vector machine (SVM) was used to fit the predictive model. Furthermore, a nomogram was constructed by incorporating clinico-radiological risk factors and radiomics signature, and the clinical usefulness of the nomogram was validated using decision curve analysis (DCA). RESULTS: Three imaging features were selected in the training set, based on which the radiomics model yielded area under the curve (AUC) values of 0.852 and 0.826 for the training and test sets. The nomogram based on the radiomics signature and the clinico-radiological risk factors yielded an AUC of 0.899 in the training set and 0.871 in the test set. CONCLUSIONS: The nomogram developed in this study might aid neurosurgeons in the pre-operative prediction of CS invasion by Knosp grade two and three PAs, which might contribute to creating surgical strategies. KEY POINTS: • Pre-operative diagnosis of CS invasion by PAs might affect creating surgical strategies • MRI might help for diagnosis of CS invasion by PAs before surgery • Radiomics might improve the CS invasion detection by MR images.

Quantitative radiomic biomarkers for discrimination between neuromyelitis optica spectrum disorder and multiple sclerosis.

BACKGROUND: Precise diagnosis and early appropriate treatment are of importance to reduce neuromyelitis optica spectrum disorder (NMOSD) and multiple sclerosis (MS) morbidity. Distinguishing NMOSD from MS based on clinical manifestations and neuroimaging remains challenging. PURPOSE: To investigate radiomic signatures as potential imaging biomarkers for distinguishing NMOSD from MS, and to develop and validate a diagnostic radiomic-signature-based nomogram for individualized disease discrimination. STUDY TYPE: Retrospective, cross-sectional study. SUBJECTS: Seventy-seven NMOSD patients and 73 MS patients. FIELD STRENGTH/SEQUENCE: 3T/T2 -weighted imaging. ASSESSMENT: Eighty-eight patients and 62 patients were respectively enrolled in the primary and validation cohorts. Quantitative radiomic features were automatically extracted from lesioned regions on T2 -weighted imaging. A least absolute shrinkage and selection operator analysis was used to reduce the dimensionality of features. Finally, we constructed a radiomic nomogram for disease discrimination. STATISTICAL TESTS: Features were compared using the Mann-Whitney U-test with a nonnormal distribution. We depicted the nomogram on the basis of the results of the logistic regression using the rms package in R. The Hmisc package was used to investigate the performance of the nomogram via Harrell's C-index. RESULTS: A total of 273 quantitative radiomic features were extracted from lesions. A multivariable analysis selected 11 radiomic features and five clinical features to be included in the model. The radiomic signature (P < 0.001 for both the primary and validation cohorts) showed good potential for building a classification model for disease discrimination. The area under the receiver operating characteristic curve was 0.9880 for the training cohort and 0.9363 for the validation cohort. The nomogram exhibited good discrimination, a concordance index of 0.9363, and good calibration in the primary cohort. The nomogram showed similar discrimination, concordance (0.9940), and calibration in the validation cohort. DATA CONCLUSION: The diagnostic radiomic-signature-based nomogram has potential utility for individualized disease discrimination of NMOSD from MS in clinical practice. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1113-1121.

A Novel MRI-Based Radiomics Model for Predicting Recurrence in Chordoma.

Chordoma is a rare primary malignant tumor. For evaluating the related factors of postoperative recurrence probability of chordoma before surgery, we retrospective collected 80 patients to analyze by using a novel radiomics method. A total of 620 3D imaging features used for radiomics analysis were extracted, and 5 features were selected from T2-weighted (T2-w) magnetic resonance imaging (MRI) that were most strongly associated with 4-year recurrence probability to build a radiomics signature. Verification by logistic regression classification model, the area under the receiver operating characteristic curve and accuracy was 0.8600 (95% CI: 0.7226-0.9824) and 85.00% in the training cohort, respectively, while in the validation cohort was 0.8568 (95% CI: 0.7327-0.9758) and 85.00%. Experimental results show that T2-w MRI-based radiomics signature is closely associated with the recurrence of chordoma. It is possible to prejudge the recurrence of chordoma before surgery.

Radiomics: a Novel CT-Based Method of Predicting Postoperative Recurrence in Ovarian Cancer.

In order to predict the 3-year recurrence of advanced ovarian cancer before surgery, we retrospective collected 94 patients to analyze by using a novel radiomics method. A total of 575 3D imaging features used for radiomics analysis were extracted, and 7 features were selected from computed tomography (CT) images that were most strongly associated with 3-year clinical recurrence-free survival (CRFS) probability to build a radiomics signature. The area under the Receiver Operating Characteristic (ROC) curve (AUC) of 0.8567 (95% CI: 0.7251-0.9498) and 0.8533 (95% CI: 0.7231-0.9671) were obtained in the training cohort and validation cohort with the logistic regression classification model respectively. Experimental results show that CT-based radiomics features were closely associated with the recurrence of advanced ovarian cancer. It is possible to prejudge the recurrence of ovarian cancer before surgery.

Non-invasive genotype prediction of chromosome 1p/19q co-deletion by development and validation of an MRI-based radiomics signature in lower-grade gliomas.

PURPOSE: To perform radiomics analysis for non-invasively predicting chromosome 1p/19q co-deletion in World Health Organization grade II and III (lower-grade) gliomas. METHODS: This retrospective study included 277 patients histopathologically diagnosed with lower-grade glioma. Clinical parameters were recorded for each patient. We performed a radiomics analysis by extracting 647 MRI-based features and applied the random forest algorithm to generate a radiomics signature for predicting 1p/19q co-deletion in the training cohort (n = 184). The clinical model consisted of pertinent clinical factors, and was built using a logistic regression algorithm. A combined model, incorporating both the radiomics signature and related clinical factors, was also constructed. The receiver operating characteristics curve was used to evaluate the predictive performance. We further validated the predictability of the three developed models using a time-independent validation cohort (n = 93). RESULTS: The radiomics signature was constructed as an independent predictor for differentiating 1p/19q co-deletion genotypes, which demonstrated superior performance on both the training and validation cohorts with areas under curve (AUCs) of 0.887 and 0.760, respectively. These results outperformed the clinical model (AUCs of 0.580 and 0.627 on training and validation cohorts). The AUCs of the combined model were 0.885 and 0.753 on training and validation cohorts, respectively, which indicated that clinical factors did not present additional improvement for the prediction. CONCLUSION: Our study highlighted that an MRI-based radiomics signature can effectively identify the 1p/19q co-deletion in histopathologically diagnosed lower-grade gliomas, thereby offering the potential to facilitate non-invasive molecular subtype prediction of gliomas.

Radiomics analysis allows for precise prediction of epilepsy in patients with low-grade gliomas.

Purpose: To investigate the association between imaging features and low-grade gliomas (LGG) related epilepsy, and to propose a radiomics-based model for the prediction of LGG-associated epilepsy. Methods: This retrospective study consecutively enrolled 286 patients with LGGs (194 in the primary cohort and 92 in the validation cohort). T2-weighted MR images (T2WI) were used to characterize risk factors for LGG-related epilepsy: Tumor location features and 3-D imaging features were determined, following which the interactions between these two kinds of features were analyzed. Elastic net was applied to generate a radiomics signature combining key imaging features associated with the LGG-related epilepsy with the primary cohort, and then a nomogram incorporating radiomics signature and clinical characteristics was developed. The radiomics signature and nomogram were validated in the validation cohort. Results: A total of 475 features associated with LGG-related epilepsy were obtained for each patient. A radiomics signature with eleven selected features allowed for discriminating patients with epilepsy or not was detected, which performed better than location and 3-D imaging features. The nomogram incorporating radiomics signature and clinical characteristics achieved a high degree of discrimination with area under receiver operating characteristic (ROC) curve (AUC) at 0.8769 in the primary cohort and 0.8152 in the validation cohort. The nomogram also allowed for good calibration in the primary cohort. Conclusion: We developed and validated an effective prediction model for LGG-related epilepsy. Our results suggested that radiomics analysis may enable more precise and individualized prediction of LGG-related epilepsy.

Non-invasive radiomics approach potentially predicts non-functioning pituitary adenomas subtypes before surgery.

PURPOSE: To make individualised preoperative prediction of non-functioning pituitary adenoma (NFPAs) subtypes between null cell adenomas (NCAs) and other subtypes using a radiomics approach. METHODS: We enrolled 112 patients (training set: n = 75; test set: n = 37) with complete T1-weighted magnetic resonance imaging (MRI) and contrast-enhanced T1-weighted MRI (CE-T1). A total of 1482 quantitative imaging features were extracted from T1 and CE-T1 images. Support vector machine trained a predictive model that was validated using a receiver operating characteristics (ROC) analysis on an independent test set. Moreover, a nomogram was constructed incorporating clinical characteristics and the radiomics signature for individual prediction. RESULTS: T1 image features yielded area under the curve (AUC) values of 0.8314 and 0.8042 for the training and test sets, respectively, while CE-T1 image features provided no additional contribution to the predictive model. The nomogram incorporating sex and the T1 radiomics signature yielded good calibration in the training and test sets (concordance index (CI) = 0.854 and 0.857, respectively). CONCLUSION: This study focused on the preoperative prediction of NFPA subtypes between NCAs and others using a radiomics approach. The developed model yielded good performance, indicating that radiomics had good potential for the preoperative diagnosis of NFPAs. KEY POINTS: • MRI may help in the pre-operative diagnosis of NFPAs subtypes • Retrospective study showed T1-weighted MRI more useful than CE-T1 in NCAs diagnosis • Treatment decision making becomes more individualised • Radiomics approach had potential for classification of NFPAs.

Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer.

OBJECTIVES: To distinguish squamous cell carcinoma (SCC) from lung adenocarcinoma (ADC) based on a radiomic signature METHODS: This study involved 129 patients with non-small cell lung cancer (NSCLC) (81 in the training cohort and 48 in the independent validation cohort). Approximately 485 features were extracted from a manually outlined tumor region. The LASSO logistic regression model selected the key features of a radiomic signature. Receiver operating characteristic curve and area under the curve (AUC) were used to evaluate the performance of the radiomic signature in the training and validation cohorts. RESULTS: Five features were selected to construct the radiomic signature for histologic subtype classification. The performance of the radiomic signature to distinguish between lung ADC and SCC in both training and validation cohorts was good, with an AUC of 0.905 (95% confidence interval [CI]: 0.838 to 0.971), sensitivity of 0.830, and specificity of 0.929. In the validation cohort, the radiomic signature showed an AUC of 0.893 (95% CI: 0.789 to 0.996), sensitivity of 0.828, and specificity of 0.900. CONCLUSIONS: A unique radiomic signature was constructed for use as a diagnostic factor for discriminating lung ADC from SCC. Patients with NSCLC will benefit from the proposed radiomic signature. KEY POINTS: • Machine learning can be used for auxiliary distinguish in lung cancer. • Radiomic signature can discriminate lung ADC from SCC. • Radiomics can help to achieve precision medical treatment.

Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer?

OBJECTIVES: To investigate whether CT-based radiomics signature can predict KRAS/NRAS/BRAF mutations in colorectal cancer (CRC). METHODS: This retrospective study consisted of a primary cohort (n = 61) and a validation cohort (n = 56) with pathologically confirmed CRC. Patients underwent KRAS/NRAS/BRAF mutation tests and contrast-enhanced CT before treatment. A total of 346 radiomics features were extracted from portal venous-phase CT images of the entire primary tumour. Associations between the genetic mutations and clinical background, tumour staging, and histological differentiation were assessed using univariate analysis. RELIEFF and support vector machine methods were performed to select key features and build a radiomics signature. RESULTS: The radiomics signature was significantly associated with KRAS/NRAS/BRAF mutations (P < 0.001). The area under the curve, sensitivity, and specificity for predicting KRAS/NRAS/BRAF mutations were 0.869, 0.757, and 0.833 in the primary cohort, respectively, while they were 0.829, 0.686, and 0.857 in the validation cohort, respectively. Clinical background, tumour staging, and histological differentiation were not associated with KRAS/NRAS/BRAF mutations in both cohorts (P>0.05). CONCLUSIONS: The proposed CT-based radiomics signature is associated with KRAS/NRAS/BRAF mutations. CT may be useful for analysis of tumour genotype in CRC and thus helpful to determine therapeutic strategies. KEY POINTS: • Key features were extracted from CT images of the primary colorectal tumour. • The proposed radiomics signature was significantly associated with KRAS/NRAS/BRAF mutations. • In the primary cohort, the proposed radiomics signature predicted mutations. • Clinical background, tumour staging, and histological differentiation were unable to predict mutations.

Diagnosis of Distant Metastasis of Lung Cancer: Based on Clinical and Radiomic Features.

OBJECTIVES: To analyze the distant metastasis possibility based on computed tomography (CT) radiomic features in patients with lung cancer. METHODS: This was a retrospective analysis of 348 patients with lung cancer enrolled between 2014 and February 2015. A feature set containing clinical features and 485 radiomic features was extracted from the pretherapy CT images. Feature selection via concave minimization (FSV) was used to select effective features. A support vector machine (SVM) was used to evaluate the predictive ability of each feature. RESULTS: Four radiomic features and three clinical features were obtained by FSV feature selection. Classification accuracy by the proposed SVM with SGD method was 71.02%, and the area under the curve was 72.84% with only the radiomic features extracted from CT. After the addition of clinical features, 89.09% can be achieved. CONCLUSION: The radiomic features of the pretherapy CT images may be used as predictors of distant metastasis. And it also can be used in combination with the patient's gender and tumor T and N phase information to diagnose the possibility of distant metastasis in lung cancer.

Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation.

Accurate lung nodule segmentation from computed tomography (CT) images is of great importance for image-driven lung cancer analysis. However, the heterogeneity of lung nodules and the presence of similar visual characteristics between nodules and their surroundings make it difficult for robust nodule segmentation. In this study, we propose a data-driven model, termed the Central Focused Convolutional Neural Networks (CF-CNN), to segment lung nodules from heterogeneous CT images. Our approach combines two key insights: 1) the proposed model captures a diverse set of nodule-sensitive features from both 3-D and 2-D CT images simultaneously; 2) when classifying an image voxel, the effects of its neighbor voxels can vary according to their spatial locations. We describe this phenomenon by proposing a novel central pooling layer retaining much information on voxel patch center, followed by a multi-scale patch learning strategy. Moreover, we design a weighted sampling to facilitate the model training, where training samples are selected according to their degree of segmentation difficulty. The proposed method has been extensively evaluated on the public LIDC dataset including 893 nodules and an independent dataset with 74 nodules from Guangdong General Hospital (GDGH). We showed that CF-CNN achieved superior segmentation performance with average dice scores of 82.15% and 80.02% for the two datasets respectively. Moreover, we compared our results with the inter-radiologists consistency on LIDC dataset, showing a difference in average dice score of only 1.98%.

Stripe artifact elimination based on nonsubsampled contourlet transform for light sheet fluorescence microscopy.

Stripe artifacts, caused by high-absorption or high-scattering structures in the illumination light path, are a common drawback in both unidirectional and multidirectional light sheet fluorescence microscopy (LSFM), significantly deteriorating image quality. To circumvent this problem, we present an effective multidirectional stripe remover (MDSR) method based on nonsubsampled contourlet transform (NSCT), which can be used for both unidirectional and multidirectional LSFM. In MDSR, a fast Fourier transform (FFT) filter is designed in the NSCT domain to shrink the stripe components and eliminate the noise. Benefiting from the properties of being multiscale and multidirectional, MDSR succeeds in eliminating stripe artifacts in both unidirectional and multidirectional LSFM. To validate the method, MDSR has been tested on images from a custom-made unidirectional LSFM system and a commercial multidirectional LSFM system, clearly demonstrating that MDSR effectively removes most of the stripe artifacts. Moreover, we performed a comparative experiment with the variational stationary noise remover and the wavelet-FFT methods and quantitatively analyzed the results with a peak signal-to-noise ratio, showing an improved noise removal when using the MDSR method.