Comparative study of radiomics,tumor morphology,and clinicopathological factors in predicting overall survival of patients with rectal cancer before surgery

We compared the ability of a radiomics model, morphological imaging model, and clinicopathological risk model to predict 3-year overall survival (OS) in 206 patients with rectal cancer who underwent radical surgery and had magnetic resonance imaging, clinicopathological, and OS data available. The patients were randomized to a training cohort (n = 146) and a verification cohort (n = 60). Radiomics features were extracted from preoperative T2-weighted images, and a radiomics score model was constructed. Factors that were significant in the Cox multivariate analysis were used to construct the final morphological tumor model and clinicopathological model. A comprehensive model in the form of a line chart was established by combining the three models. Ten radiomics features significantly related to OS were selected to construct the radiomics feature model and calculate the radiomics score. In the morphological model, mesorectal extension depth and distance between the lower tumor margin and the anal margin were significant prognostic factors. N stage was the only significant clinicopathological factor. The comprehensive model combined with the above factors had the best prediction performance for OS. The C-index had a predictive performance of 0.872 (95% confidence interval [CI]: 0.832–0.912) in the training cohort and 0.944 (95% CI: 0.890–0.990) in the verification cohort, which was better than for any single model. The comprehensive model was divided into high-risk and low-risk groups. Kaplan-Meier curve analysis showed that all factors were significantly correlated with poor OS in the high-risk group. A comprehensive nomogram based on multi-model radiomics features can predict 3-year OS after rectal cancer surgery.     

Radiomics nomograms of tumors and peritumoral regions for the preoperative prediction of spread through air spaces in lung adenocarcinoma

To evaluate the clinical features and radiomics nomograms of tumors and peritumoral regions for the preoperative prediction of the presence of spread through air spaces (STAS) in patients with lung adenocarcinoma. A total of 107 STAS-positive lung adenocarcinomas were selected and matched to 105 STAS-negative lung adenocarcinomas. Thin-slice CT imaging annotation and region of interest (ROI) segmentation were performed with semi-automatic in-house software. Radiomics features were extracted from all nodules and incremental distances of 5, 10, and 15 mm outside the lesion segmentation. A radiomics nomogram was established with multivariable logistic regression based on clinical and radiomics features. The maximum diameter of the solid component and mediastinal lymphadenectasis were selected as independent predictors of STAS. The radiomics nomogram of lung nodules showed especially good prediction in the training set [area under the curve (AUC), 0.98; 95% confidence interval (CI), 0.97–1.00] and test set (AUC, 0.99; 95% CI, 0.97–1.00). The radiomics nomogram of peritumoral regions also showed good prediction, but the fitting degrees of the calibration curves were not good. Our study may provide guidance for surgical methods in patients with lung adenocarcinoma.     

A computer-aided diagnosis scheme of breast lesion classification using GLGLM and shape features: Combined-view and multi-classifiers

PurposeTo address high false-positive results of FFDM issue, we make the first effort to develop a computer-aided diagnosis (CAD) scheme to analyze and distinguish breast lesions.MethodThe breast lesion regions were first segmented and depicted on FFDM images from 106 patients. In this work, 11 gray-level gap-length matrix texture features and 12 shape features were extracted form craniocaudal view and mediolateral oblique view, and then Student’s t-test, Fisher-score and Relief-F were introduced to select features. We also investigated the effect of three factors, i.e., discretisation, selection methods and classifier methods, of the classification performance via analysis of variance. Finally, a classification model was constructed. Spearman’s correlation coefficient analysis was conducted to assess the internal relevance of features.ResultsThe proposed scheme using Student’s t-test achieved an area under the receiver operating characteristic curve (AUC) value of 0.923 at 512 bins. The AUC values are 0.884, 0.867, 0.874 and 0.901 for the low gray-level gaps emphasis (LGGE), solidity, extent, and the combined set, respectively. Solidity and extent depicts the correlation coefficient of 0.86 (P < 0.05).ConclusionsWe present a new CAD scheme based on the contribution of the significant factors. The experimental results demonstrate that the presented scheme can be used to successfully distinguish breast carcinoma lesions and benign fibroadenoma lesions in our FFDM dataset and the MIAS dataset, which may provide a CAD method to assist radiologists in diagnosing and interpreting screening mammograms. Moreover, we found that LGGE, solidity and extent features show great potential for breast lesion classification.     

CT radiomics combined with clinical variables for predicting the overall survival of hepatocellular carcinoma patients after hepatectomy

PurposeTo establish a model for assessing the overall survival (OS) of the hepatocellular carcinoma (HCC) patients after hepatectomy based on the clinical and radiomics features.MethodsThis study recruited a total of 267 patients with HCC, which were randomly divided into the training (N = 188) and validation (N = 79) cohorts. In the training cohort, radiomic features were selected with the intra-reader and inter-reader correlation coefficient (ICC), Spearman's correlation coefficient, and the least absolute shrinkage and selection operator (LASSO). The radiomics signatures were built by COX regression analysis and compared the predictive potential in the different phases (arterial, portal, and double-phase) and regions of interest (tumor, peritumor 3 mm, peritumor 5 mm). A clinical-radiomics model (CR model) was established by combining the radiomics signatures and clinical risk factors. The validation cohort was used to validate the proposed models.ResultsA total of 267 patients 86 (45.74%) and 37 (46.84%) patients died in the training and validation cohorts, respectively. Among all the radiomics signatures, those based on the tumor and peritumor (5 mm) (AP-TP5-Signature) showed the best prognostic potential (training cohort 1–3 years AUC:0.774–0.837; validation cohort 1–3 years AUC:0.754–0.810). The CR model showed better discrimination, calibration, and clinical applicability as compared to the clinical model and radiomics features. In addition, the CR model could perform risk-stratification and also allowed for significant discrimination between the Kaplan-Meier curves in most of the subgroups.ConclusionsThe CR model could predict the OS of the HCC patients after hepatectomy.     

A deep survival interpretable radiomics model of hepatocellular carcinoma patients

This work aims to identify a new radiomics signature using imaging phenotypes and clinical variables for risk prediction of overall survival (OS) in hepatocellular carcinoma (HCC) patients treated with stereotactic body radiation therapy (SBRT). 167 patients were retrospectively analyzed with repeated nested cross-validation to mitigate overfitting issues. 56 radiomic features were extracted from pre-treatment contrast-enhanced (CE) CT images. 37 clinical factors were obtained from patients' electronic records. Variational autoencoders (VAE) based survival models were designed for radiomics and clinical features and a convolutional neural network (CNN) survival model was used for the CECT. Finally, radiomics, clinical and raw image deep learning network (DNN) models were combined to predict the risk probability for OS. The final models yielded c-indices of 0.579 (95%CI: 0.544–0.621), 0.629 (95%CI: 0.601–0.643), 0.581 (95%CI: 0.553–0.613) and 0.650 (95%CI: 0.635–0.683) for radiomics, clinical, image input and combined models on nested cross validation scheme, respectively. Integrated gradients method was used to interpret the trained models. Our interpretability analysis of the DNN showed that the top ranked features were clinical liver function and liver exclusive of tumor radiomics features, which suggests a prominent role of side effects and toxicities in liver outside the tumor region in determining the survival rate of these patients. In summary, novel deep radiomic analysis provides improved performance for risk assessment of HCC prognosis compared with Cox survival models and may facilitate stratification of HCC patients and personalization of their treatment strategies. Liver function was found to contribute most to the OS for these HCC patients and radiomics can aid in their management.     

Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach

PurposeTo evaluate the potential of 2D texture features extracted from magnetic resonance (MR) images for differentiating brain metastasis (BM) and glioblastomas (GBM) following a radiomics approach.MethodsThis retrospective study included 50 patients with BM and 50 with GBM who underwent T1-weighted MRI between December 2010 and January 2017. Eighty-eight rotation-invariant texture features were computed for each segmented lesion using six texture analysis methods. These features were also extracted from the four images obtained after applying the discrete wavelet transform (88 features × 4 images). Three feature selection methods and five predictive models were evaluated. A 5-fold cross-validation scheme was used to randomly split the study group into training (80 patients) and testing (20 patients), repeating the process ten times. Classification was evaluated computing the average area under the receiver operating characteristic curve. Sensibility, specificity and accuracy were also computed. The whole process was tested quantizing the images with different gray-level values to evaluate their influence in the final results.ResultsHighest classification accuracy was obtained using the original images quantized with 128 gray-levels and a feature selection method based on the p-value. The best overall performance was achieved using a support vector machine model with a subset of 32 features (AUC = 0.896 ± 0.067, sensitivity of 82% and specificity of 80%). Naïve Bayes and k-nearest neighbors models showed also valuable results (AUC ≈ 0.8) with a lower number of features (<13), thus suggesting that these models may be more generalizable when using external validations.ConclusionThe proposed radiomics MRI approach is able to discriminate between GBM and BM with high accuracy employing a set of 2D texture features, thus helping in the diagnosis of brain lesions in a fast and non-invasive way.     

Radiomics classifier to quantify automatic segmentation quality of cardiac sub-structures for radiotherapy treatment planning

PurposeA radiomics features classifier was implemented to evaluate segmentation quality of heart structures. A robust feature set sensitive to incorrect contouring would provide an ideal quantitative index to drive autocontouring optimization.MethodsTwenty-five cardiac sub-structures were contoured as regions of interest in 36 CTs. Radiomic features were extracted from manually-contoured (MC) and Hierarchical-Clustering automatic-contouring (AC) structures. A robust feature-set was identified from correctly contoured CT datasets. Features variation was analyzed over a MC/AC dataset. A supervised-learning approach was used to train an Artificial-Intelligence (AI) classifier; incorrect contouring cases were generated from the gold-standard MC datasets with translations, expansions and contractions. ROC curves and confusion matrices were used to evaluate the AI-classifier performance.ResultsTwenty radiomics features, were found to be robust across structures, showing a good/excellent intra-class correlation coefficient (ICC) index comparing MC/AC. A significant correlation was obtained with quantitative indexes (Dice-Index, Hausdorff-distance). The trained AI-classifier detected correct contours (CC) and not correct contours (NCC) with an accuracy of 82.6% and AUC of 0.91. True positive rate (TPR) was 85.1% and 81.3% for CC and NCC. Detection of NCC at this point of the development still depended strongly on degree of contouring imperfection.ConclusionsA set of radiomics features, robust on “gold-standard” contour and sensitive to incorrect contouring was identified and implemented in an AI-workflow to quantify segmentation accuracy. This workflow permits an automatic assessment of segmentation quality and may accelerate expansion of an existing autocontouring atlas database as well as improve dosimetric analyses of large treatment plan databases.     

CT-based radiomics model with machine learning for predicting primary treatment failure in diffuse large B-cell Lymphoma

Biomarkers which can identify Diffuse Large B-Cell Lymphoma (DLBCL) likely to be refractory to first-line therapy are essential for selecting this population prior to therapy initiation to offer alternate therapeutic options that can improve prognosis. We tested the ability of a CT-based radiomics approach with machine learning to predict Primary Treatment Failure (PTF)-DLBCL from initial imaging evaluation. Twenty-six refractory patients were matched to 26 non-refractory patients, yielding 180 lymph nodes for analysis. Manual 3D delineation of the total node volume was performed by two independent readers to test the reproducibility. Then, 1218 hand-crafted radiomic features were extracted. The Random Forests machine learning approach was used as a classifier for constructing the prediction models. Seventy percent of the nodes were randomly assigned to a training set and the remaining 30% were assigned to an independent test set. The final model was tested on the dataset from the 2 readers, showing a mean accuracy, sensitivity and specificity of 73%, 62% and 82%, respectively, for distinguishing between refractory and non-refractory patients. The area under the receiver operating characteristic curve (AUC) was 0.83 and 0.79 for the two readers. We conclude that machine learning CT-based radiomics analysis is able to identify a priori PTF-DLBCL with a good accuracy.     

The Potential Value of Preoperative MRI Texture and Shape Analysis in Grading Meningiomas: A Preliminary Investigation

OBJECT: Preoperative knowledge of meningioma grade is essential for planning treatment and surgery. The purpose of this study was to investigate the diagnostic value of MRI texture and shape analysis in grading meningiomas. METHODS: A surgical database was reviewed to identify meningioma patients who had undergone tumor resection between January 2015 and December 2016. Preoperative MR images were retrieved and analyzed. Texture and shape analysis was conducted to quantitatively evaluate tumor heterogeneity and morphology. Three machine learning classifiers were trained with these features to build classification models. The performance of the features and classification models was assessed. RESULTS: A total of 131 patients were included in this study: 21 with high-grade meningiomas and 110 with low-grade meningiomas. Three texture features were selected: Horzl_RLNonUni, S(2,2)SumOfSqs, and WavEnHL_s-3; three shape features were selected: GeoFv, GeoW4, and GeoW5b. The Mann–Whitney test indicated that all six features were significantly different between high-grade and low-grade meningiomas. AUC values were generally greater than 0.50 (range, 0.73 to 0.88). Sensitivities and specificities ranged from 47.62% to 90.48% and 69.09% to 96.36%, respectively. Among the nine classification models obtained, the one built by training the SVM classifier with all six features achieved the best performance, with a sensitivity, specificity, diagnostic accuracy, and AUC of 0.86, 0.87, 0.87, and 0.87, respectively. CONCLUSIONS: Texture and shape analysis, especially when combined with a SVM classifier, can provide satisfactory performance in the preoperative determination of meningioma grade and is thus potentially useful for clinical application.     

Building CT Radiomics Based Nomogram for Preoperative Esophageal Cancer Patients Lymph Node Metastasis Prediction

PURPOSE: To build and validate a radiomics-based nomogram for the prediction of pre-operation lymph node (LN) metastasis in esophageal cancer. PATIENTS AND METHODS: A total of 197 esophageal cancer patients were enrolled in this study, and their LN metastases have been pathologically confirmed. The data were collected from January 2016 to May 2016; patients in the first three months were set in the training cohort, and patients in April 2016 were set in the validation cohort. About 788 radiomics features were extracted from computed tomography (CT) images of the patients. The elastic-net approach was exploited for dimension reduction and selection of the feature space. The multivariable logistic regression analysis was adopted to build the radiomics signature and another predictive nomogram model. The predictive nomogram model was composed of three factors with the radiomics signature, where CT reported the LN number and position risk level. The performance and usefulness of the built model were assessed by the calibration and decision curve analysis. RESULTS: Thirteen radiomics features were selected to build the radiomics signature. The radiomics signature was significantly associated with the LN metastasis (P<0.001). The area under the curve (AUC) of the radiomics signature performance in the training cohort was 0.806 (95% CI: 0.732-0.881), and in the validation cohort it was 0.771 (95% CI: 0.632-0.910). The model showed good discrimination, with a Harrell’s Concordance Index of 0.768 (0.672 to 0.864, 95% CI) in the training cohort and 0.754 (0.603 to 0.895, 95% CI) in the validation cohort. Decision curve analysis showed our model will receive benefit when the threshold probability was larger than 0.15. CONCLUSION: The present study proposed a radiomics-based nomogram involving the radiomics signature, so the CT reported the status of the suspected LN and the dummy variable of the tumor position. It can be potentially applied in the individual preoperative prediction of the LN metastasis status in esophageal cancer patients.     

A nomogram model integrating LI-RADS features and radiomics based on contrast-enhanced magnetic resonance imaging for predicting microvascular invasion in hepatocellular carcinoma falling the Milan criteria

PurposeTo establish and validate a nomogram model incorporating both liver imaging reporting and data system (LI-RADS) features and contrast enhanced magnetic resonance imaging (CEMRI)-based radiomics for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC) falling the Milan criteria.MethodsIn total, 161 patients with 165 HCCs diagnosed with MVI (n = 99) or without MVI (n = 66) were assigned to a training and a test group. MRI LI-RADS characteristics and radiomics features selected by the LASSO algorithm were used to establish the MRI and Rad-score models, respectively, and the independent features were integrated to develop the nomogram model. The predictive ability of the nomogram was evaluated with receiver operating characteristic (ROC) curves.ResultsThe risk factors associated with MVI (P<0.05) were related to larger tumor size, nonsmooth margin, mosaic architecture, corona enhancement and higher Rad-score. The areas under the ROC curve (AUCs) of the MRI feature model for predicting MVI were 0.85 (95% CI: 0.78–0.92) and 0.85 (95% CI: 0.74–0.95), and those for the Rad-score were 0.82 (95% CI: 0.73–0.90) and 0.80 (95% CI: 0.67–0.93) in the training and test groups, respectively. The nomogram presented improved AUC values of 0.87 (95% CI: 0.81–0.94) in the training group and 0.89 (95% CI: 0.81–0.98) in the test group (P<0.05) for predicting MVI. The calibration curve and decision curve analysis demonstrated that the nomogram model had high goodness-of-fit and clinical benefits.ConclusionsThe nomogram model can effectively predict MVI in patients with HCC falling within the Milan criteria and serves as a valuable imaging biomarker for facilitating individualized decision-making.     

Computer-based malignancy grading of astrocytomas employing a support vector machine classifier, the WHO grading system and the regular hematoxylin-eosin diagnostic staining procedure

OBJECTIVE: To investigate and develop an automated technique for astrocytoma malignancy grading compatible with the clinical routine. STUDY DESIGN: One hundred forty biopsies of astrocytomas were collected from 2 hospitals. The degree of tumor malignancy was defined as low or high according to the World Health Organization grading system. From each biopsy, images were digitized and segmented to isolate nuclei from background tissue. Morphologic and textural nuclear features were quantified to encode tumor malignancy. Each case was represented by a 40-dimensional feature vector. An exhaustive search procedure in feature space was utilized to determine the best feature combination that resulted in the smallest classification error. Low and high grade tumors were discriminated using support vector machines (SVMs). To evaluate the system performance, all available data were split randomly into training and test sets. RESULTS: The best vector combination consisted of 3 textural and 2 morphologic features. Low and high grade cases were discriminated with an accuracy of 90.7% and 88.9%, respectively, using an SVM classifier with polynomial kernel of degree 2. CONCLUSION: The proposed methodology was based on standards that are common in daily clinical practice and might be used in parallel with conventional grading as a second-opinion tool to reduce subjectivity in the classification of astrocytomas.     

Patient-specific IMRT QA verification using machine learning and gamma radiomics

Gamma function is the standard methodology for comparing dose distributions. It is calculated in dedicated software, and its results verification is not performed. Thus we developed an automatic tool for patient-specific QA results verification through high accuracy machine learning (ML) models based on the radiomics characteristics extraction from gamma images. We used 158 patient-specific QA tests and extracted 105 radiomics features from each gamma image. Three random forest models were developed (ML I, ML II, and ML III). ML I and ML II verified the gamma image approval using criteria of 2%/2mm/15% threshold and 3%/3mm/15% threshold, respectively. ML III verified if the gamma analyzes software recommended protocol was followed to detect if the TPS grid modification step was done. The models were based on the most important features selected using the mean decreased impurity, and their performances were evaluated. ML I included 25 features. Its accuracy was 0.85 using the test set and 0.84 using dataset B. ML II included 10 features, and its accuracy with the test set was 0.98; the same value was achieved using the never seen data (dataset B). The First-order 10th percentile feature was identified as a feature strongly related to the approved classification. ML III selected 23 features with an accuracy of 0.99 for test set and 0.98 for dataset B. An automatic workflow example for gamma analyses QA results verification could be proposed combining the models to detect grid inconsistencies on software evaluation, followed by the test approval classification.     

Development and validation of a novel model incorporating MRI-based radiomics signature with clinical biomarkers for distinguishing pancreatic carcinoma from mass-forming chronic pancreatitis

PurposeIt is difficult to make a clear differential diagnosis of pancreatic carcinoma (PC) and mass-forming chronic pancreatitis (MFCP) via conventional examinations. We aimed to develop a novel model incorporating an MRI-based radiomics signature with clinical biomarkers for distinguishing the two lesions.MethodsA total of 102 patients were retrospectively enrolled and randomly divided into the training and validation cohorts. Radiomics features were extracted from four different sequences. Individual imaging modality radiomics signature, multiparametric MRI (mp-MRI) radiomics signature, and a final mixed model based on mp-MRI and clinically independent risk factors were established to discriminate between PC and MFCP. The diagnostic performance of each model and model discrimination were assessed in both the training and validation cohorts.ResultsADC had the best predictive performance among the four individual radiomics models, but there were no significant differences between the pairs of models (all p > 0.05). Six potential radiomics features were finally selected from the 960 texture features to formulate the radiomics score (rad-score) of the mp-MRI model. In addition, the boxplot results of the distributions of rad-scores identified the rad-score as an independent predictive factor for the differentiation of PC and MFCP (p< 0.001). Notably, the nomogram integrating rad-score and clinically independent risk factors had a better diagnostic performance than the mp-MRI and clinical models. These results were further confirmed by the validation group.ConclusionThe mixed model was developed and preliminarily validated to distinguish PC from MFCP, which may benefit the formulation of treatment strategies and nonsurgical procedures.     

Automated diagnosis of brain tumours astrocytomas using probabilistic neural network clustering and support vector machines

A computer-aided diagnosis system was developed for assisting brain astrocytomas malignancy grading. Microscopy images from 140 astrocytic biopsies were digitized and cell nuclei were automatically segmented using a Probabilistic Neural Network pixel-based clustering algorithm. A decision tree classification scheme was constructed to discriminate low, intermediate and high-grade tumours by analyzing nuclear features extracted from segmented nuclei with a Support Vector Machine classifier. Nuclei were segmented with an average accuracy of 86.5%. Low, intermediate, and high-grade tumours were identified with 95%, 88.3%, and 91% accuracies respectively. The proposed algorithm could be used as a second opinion tool for the histopathologists.     

Construction of a prognostic immune signature for lower grade glioma that can be recognized by MRI radiomics features to predict survival in LGG patients

BackgroundThis study aimed to identify a series of prognostically relevant immune features by immunophenoscore. Immune features were explored using MRI radiomics features to prediction the overall survival (OS) of lower-grade glioma (LGG) patients and their response to immune checkpoints.MethodLGG data were retrieved from TCGA and categorized into training and internal validation datasets. Patients attending the First Affiliated Hospital of Harbin Medical University were included in an external validation cohort. An immunophenoscore-based signature was built to predict malignant potential and response to immune checkpoint inhibitors in LGG patients. In addition, a deep learning neural network prediction model was built for validation of the immunophenoscore-based signature.ResultsImmunophenotype-associated mRNA signatures (IMriskScore) for outcome prediction and ICB therapeutic effects in LGG patients were constructed. Deep learning of neural networks based on radiomics showed that MRI radiomic features determined IMriskScore. Enrichment analysis and ssGSEA correlation analysis were performed. Mutations in CIC significantly improved the prognosis of patients in the high IMriskScore group. Therefore, CIC is a potential therapeutic target for patients in the high IMriskScore group. Moreover, IMriskScore is an independent risk factor that can be used clinically to predict LGG patient outcomes.ConclusionsThe IMriskScore model consisting of a sets of biomarkers, can independently predict the prognosis of LGG patients and provides a basis for the development of personalized immunotherapy strategies. In addition, IMriskScore features were predicted by MRI radiomics using a deep learning approach using neural networks. Therefore, they can be used for the prognosis of LGG patients.     

Prediction of minimal hepatic encephalopathy by using an radiomics nomogram in chronic hepatic schistosomiasis patients

ObjectiveTo construct an MR-radiomics nomogram to predict minimal hepatic encephalopathy (MHE) in patients with chronic hepatic schistosomiasis (CHS).MethodsFrom July 2017 to July 2020, 236 CHS patients with non-HE (n = 140) and MHE (n = 96) were retrospective collected and randomly divided into training group and testing group. Radiomics features were extracted from substantia nigra-striatum system of a brain diffusion weighted images (DWI) and combined with clinical predictors to build a radiomics nomogram for predicting MHE in CHS patients. The ROC curve was used to evaluate the predicting performance in training group and testing group. The clinical decisive curve (CDC) was used to assess the clinical net benefit of using radiomics nomogram in predicting MHE.ResultsLow seralbumin (P < 0.05), low platelet count (P < 0.05) and high plasma ammonia (P < 0.05) was the significant clinical predictors for MHE in CHS patients. The AUC, specificity and sensitivity of the radiomics nomogram were 0.89, 0.90 and 0.86 in the training group, and were 0.83, 0.85 and 0.75 in the training group. The CDC analysis showed clinical net benefits for the radiomics nomogram in predicting MHE.ConclusionsThe radiomics nomogram combining DWI radiomics features and clinical predictors could be useful tool to predict MHE in CHS patients.