Radiomics-based Machine Learning Research Articles

MRI-Based Radiomics Approach Predicts Tumor Recurrence in ER + /HER2 − Early Breast Cancer Patients

Oncotype Dx Recurrence Score (RS) has been validated in patients with ER + /HER2 − invasive breast carcinoma to estimate patient risk of recurrence and guide the use of adjuvant chemotherapy. We investigated the role of MRI-based radiomics features extracted from the tumor and the peritumoral tissues to predict the risk of tumor recurrence. A total of 62 patients with biopsy-proved ER + /HER2 − breast cancer who underwent pre-treatment MRI and Oncotype Dx were included. An RS > 25 was considered discriminant between low-intermediate and high risk of tumor recurrence. Two readers segmented each tumor. Radiomics features were extracted from the tumor and the peritumoral tissues. Partial least square (PLS) regression was used as the multivariate machine learning algorithm. PLS β-weights of radiomics features included the 5% features with the largest β-weights in magnitude (top 5%). Leave-one-out nested cross-validation (nCV) was used to achieve hyperparameter optimization and evaluate the generalizable performance of the procedure. The diagnostic performance of the radiomics model was assessed through receiver operating characteristic (ROC) analysis. A null hypothesis probability threshold of 5% was chosen (p < 0.05). The exploratory analysis for the complete dataset revealed an average absolute correlation among features of 0.51. The nCV framework delivered an AUC of 0.76 (p = 1.1∙10−3). When combining “early” and “peak” DCE images of only T or TST, a tendency toward statistical significance was obtained for TST with an AUC of 0.61 (p = 0.05). The 47 features included in the top 5% were balanced between T and TST (23 and 24, respectively). Moreover, 33/47 (70%) were texture-related, and 25/47 (53%) were derived from high-resolution images (1 mm). A radiomics-based machine learning approach shows the potential to accurately predict the recurrence risk in early ER + /HER2 − breast cancer patients.

Radiomics-based machine learning models in STEMI: a promising tool for the prediction of major adverse cardiac events.

To evaluate the potential value of the machine learning (ML) models using radiomic features of late gadolinium enhancement (LGE) and cine images on magnetic resonance imaging (MRI) along with relevant clinical information and conventional MRI parameters for the prediction of major adverse cardiac events (MACE) in ST-segment elevation myocardial infarction (STEMI) patients. This retrospective study included 60 patients with the first STEMI. MACE consisted of new-onset congestive heart failure, ventricular arrhythmia, and cardiac death. Radiomic features were extracted from cine and LGE images. Inter-class correlation coefficients (ICCs) were calculated to assess inter-observer reproducibility. LASSO (least absolute shrinkage and selection operator) method was used for radiomic feature selection. Seven separate models using a different combination of the available information were investigated. Classifications with repeat random sampling were done using adaptive boosting, k-nearest neighbor, naive Bayes, neural network, random forest, stochastic gradient descent, and support vector machine algorithms. Of the 1748 extracted radiomic features, 1393 showed good inter-observer agreement. With LASSO, 25 features were selected. Among the ML algorithms, the neural network showed the highest predictive performance on average (area under the curve (AUC) 0.822 ± 0.181). Of the best-calculated model, the one using clinical parameters, CMRI parameters, and selected radiomic features (model 7), the diagnostic performance was as follows: 0.965 AUC, 0.894 classification accuracy, 0.906 sensitivity, 0.883 specificity, 0.875 positive predictive value (PPV), and 0.912 negative predictive value (NPV). The radiomics-based ML models incorporating clinical and conventional MRI parameters are promising for predicting MACE occurrence in STEMI patients in the follow-up period. • Acute coronary occlusion results in variable changes at the cellular level ranging from myocyte swelling to myonecrosis depending on the duration of the ischemia and the metabolic state of the heart, which causes subtle heterogeneous signal changes that are imperceptible to the human eye with cardiac MRI. • Radiomics-based machine learning analysis of cardiac MR images is promising for risk prediction. • Combining MRI-derived parameters and clinical variables increases the accuracy of predictive models.

Radiomic-based machine learning model for the accurate prediction of prostate cancer risk stratification.

To precisely predict prostate cancer (PCa) risk stratification, we constructed a machine learning (ML) model based on magnetic resonance imaging (MRI) radiomic features. Between August 2016 and May 2021, patients with histologically proven PCa who underwent pre-operative MRI and prostate-specific antigen screening were included. The patients were grouped into different risk categories as defined by the European Association of Urology-European Association of Nuclear Medicine-European Society for Radiotherapy and Oncology-European Society of Urogenital Radiology-International Society of Geriatric Oncology guidelines. Using Artificial Intelligence Kit software, PCa regions of interest were delineated and radiomic features were extracted. Subsequently, predictable models were built by utilising five traditional ML approaches: support vector machine, logistic regression, gradient boosting decision tree, k-nearest neighbour and random forest (RF) classifiers. The classification capacity of the developed models was assessed by area under the receiver operating characteristic curve (AUC) analysis. A total of 213 patients were enrolled, including 16 low-risk, 65 intermediate-risk, and 132 high-risk PCa patients. The risk stratification of PCa could be revealed by MRI radiomic features, and second-order features accounted for most of the selected features. Among the five established ML models, the RF model showed the best overall predictive performance (AUC = 0.87). After further analysis of the subgroups based on the RF model, the prediction of the high-risk group was the best (AUC = 0.89). This study demonstrated that the MR radiomics-based ML method could be a promising tool for predicting PCa risk stratification precisely. The ML models have valuable prospect for accurate PCa risk assessment, which might contribute to customize treatment and surveillance strategies.

Cystic renal mass screening: machine-learning-based radiomics on unenhanced computed tomography

The present study compares the diagnostic performance of unenhanced computed tomography (CT) radiomics-based machine learning (ML) classifiers and a radiologist in cystic renal masses (CRMs). Patients with pathologically diagnosed CRMs from two hospitals were enrolled in the study. Unenhanced CT radiomic features were extracted for ML modeling in the training set (Guangzhou; 162 CRMs, 85 malignant). Total tumor segmentation was performed by two radiologists. Features with intraclass correlation coefficients of >0.75 were screened using univariate analysis, least absolute shrinkage and selection operator, and bidirectional elimination to construct random forest (RF), decision tree (DT), and k-nearest neighbor (KNN) models. External validation was performed in the Zhuhai set (45 CRMs, 30 malignant). All images were assessed by a radiologist. The ML models were evaluated using calibration curves, decision curves, and receiver operating characteristic (ROC) curves. Of the 207 patients (102 women; 59.1 ± 11.5 years), 92 (41 women; 58.0 ± 13.7 years) had benign CRMs, and 115 (61 women; 59.8 ± 11.4 years) had malignant CRMs. The accuracy, sensitivity, and specificity of the radiologist's diagnoses were 85.5%, 84.2%, and 91.1%, respectively [area under the (ROC) curve (AUC), 0.87]. The ML classifiers showed similar sensitivity (94.2%-100%), specificity (94.7%-100%), and accuracy (94.3%-100%) in the training set. In the validation set, KNN showed better sensitivity, accuracy, and AUC than DT and RF but weaker specificity. Calibration and decision curves showed excellent and good results in the training and validation set, respectively. Unenhanced CT radiomics-based ML classifiers, especially KNN, may aid in screening CRMs.

Predictive value of magnetic resonance imaging radiomics-based machine learning for disease progression in patients with high-grade glioma

Accurately predicting the prognosis of patients with high-grade glioma (HGG) is potentially important for treatment. However, the predictive value of images of various magnetic resonance imaging (MRI) sequences for prognosis at different time points is unknown. We established predictive machine learning models of HGG disease progression and recurrence using MRI radiomics and explored the factors influencing prediction accuracy. Radiomics features were extracted from T1-weighted (T1WI), contrast-enhanced T1-weighted (CE-T1WI), T2-weighted (T2WI), and fluid-attenuated inversion recovery (FLAIR) images (postoperative radiotherapy planning MRI images) obtained from 162 patients with HGG. The Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) algorithm were used for feature selection. Machine learning models were used to build prediction models to estimate disease progression or recurrence. The influence of different MRI sequences, regions of interest (ROIs), and prediction time points was also explored. The receiver operating characteristic (ROC) curve was used to evaluate the discriminative performance of each model, and the DeLong test was employed to compare the ROC curves. Radiomics features from T2WI and FLAIR demonstrated greater predictive value for disease progression compared with T1WI or CE-TIWI. The best predictive models, with areas under the ROC curves (AUCs) of 0.70, 0.68, 0.78, 0.78, and 0.78 for predicting disease progression at the 6th, 9th, 12th, 15th, and 18th month after radiotherapy, respectively, were obtained by combining clinical features with gross tumor volume (GTV) and clinical target volume (CTV) features extracted from T2WI and FLAIR. Structural MRI obtained before radiotherapy can be used to predict the disease progression or posttreatment recurrence of HGG. When using MRI radiomics to predict long-term outcomes as opposed to short-term outcomes, better predictive results may be obtained.

Radiomics-Based Machine Learning for Predicting the Injury Time of Rib Fractures in Gemstone Spectral Imaging Scans.

This retrospective study aimed to predict the injury time of rib fractures in distinguishing fresh (30 days) or old (90 days) rib fractures. We enrolled 111 patients with chest trauma who had been scanned for rib fractures at our hospital between January 2018 and December 2018 using gemstone spectral imaging (GSI). The volume of interest of each broken end of the rib fractures was segmented using calcium-based material decomposition images derived from the GSI scans. The training and testing sets were randomly assigned in a 7:3 ratio. All cases were divided into groups distinguishing the injury time at 30 and 90 days. We constructed radiomics-based models to predict the injury time of rib fractures. The model performance was assessed by the area under the curve (AUC) obtained by the receiver operating characteristic analysis. We included 54 patients with 259 rib fracture segmentations (34 men; mean age, 52 years ± 12.02; and range, 19-72 years). Nine features were excluded by the least absolute shrinkage and selection operator logistic regression to build the radiomics signature. For distinguishing the injury time at 30 days, the Support Vector Machine (SVM) model and human-model collaboration resulted in an accuracy and AUC of 0.85 and 0.871 and 0.91 and 0.912, respectively, and 0.81 and 0.804 and 0.83 and 0.85, respectively, at 90 days in the testing set. The radiomics-based model displayed good accuracy in differentiating between the injury time of rib fractures at 30 and 90 days, and the human-model collaboration generated more accurate outcomes, which may help to add value to clinical practice and distinguish artificial injury in forensic medicine.

Radiomics-based machine learning models for prediction of medulloblastoma subgroups: a systematic review and meta-analysis of the diagnostic test performance.

Medulloblastomas are a major cause of cancer-related mortality in the pediatric population. Four molecular groups have been identified, and these molecular groups drive risk stratification, prognostic modeling, and the development of novel treatment modalities. It has been demonstrated that radiomics-based machine learning (ML) models are effective at predicting the diagnosis, molecular class, and grades of CNS tumors. To assess radiomics-based ML models' diagnostic performance in predicting medulloblastoma subgroups and the methodological quality of the studies. A comprehensive literature search was performed on PubMed; the last search was conducted on 1 May 2022. Studies that predicted all four medulloblastoma subgroups in patients with histopathologically confirmed medulloblastoma and reporting area under the curve (AUC) values were included in the study. The quality assessments were conducted according to the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) and Checklist for Artificial Intelligence in Medical Imaging (CLAIM). A meta-analysis of radiomics-based ML studies' diagnostic performance for the preoperative evaluation of medulloblastoma subgrouping was performed. Five studies were included in this meta-analysis. Regarding patient selection, two studies indicated an unclear risk of bias according to the QUADAS-2. The five studies had an average CLAIM score and compliance score of 23.2 and 0.57, respectively. The meta-analysis showed pooled AUCs of 0.88, 0.82, 0.83, and 0.88 for WNT, SHH, group 3, and group 4 for classification, respectively. Radiomics-based ML studies have good classification performance in predicting medulloblastoma subgroups, with AUCs >0.80 in every subgroup. To be applied to clinical practice, they need methodological quality improvement and stability.

Value of genomics- and radiomics-based machine learning models in the identification of breast cancer molecular subtypes: a systematic review and meta-analysis.

In the era of precision therapy, early classification of breast cancer (BRCA) molecular subtypes has clinical significance for disease management and prognosis. We explored the accuracy of machine learning (ML) models for early classification of BRCA molecular subtypes through a systematic review of the literature currently available. We retrieved relevant studies published in PubMed, EMBASE, Cochrane, and Web of Science until 15 April 2022. A prediction model risk of bias assessment tool (PROBAST) was applied for the assessment of risk of bias of a genomics-based ML model, and the Radiomics Quality Score (RQS) was simultaneously used to evaluate the quality of this radiomics-based ML model. A random effects model was adopted to analyze the predictive accuracy of genomics-based ML and radiomics-based ML for Luminal A, Luminal B, Basal-like or triple-negative breast cancer (TNBC), and human epidermal growth factor receptor 2 (HER2). The PROSPERO of our study was prospectively registered (CRD42022333611). Of the 38 studies were selected for analysis, 14 ML models were based on gene-transcriptomic, with only 4 external validations; and 43 ML models were based on radiomics, with only 14 external validations. Meta-analysis results showed that c-statistic values of the ML based on radiomics for the identification of BRCA molecular subtypes Luminal A, Luminal B, Basal-like or TNBC, and HER2 were 0.76 [95% confidence interval (CI): 0.60-0.96], 0.78 (95% CI: 0.69-0.87), 0.89 (95% CI: 0.83-0.91), and 0.83 (95% CI: 0.81-0.86), respectively. The c-statistic values of ML based on the gene-transcriptomic analysis cohort for the identification of the previously described BRCA molecular subtypes were 0.96 (95% CI: 0.93-0.99), 0.96 (95% CI: 0.93-0.99), 0.98 (95% CI: 0.95-1.00), and 0.97 (95% CI: 0.96-0.98) respectively. Additionally, the sensitivity of the ML model based on radiomics for each molecular subtype ranged from 0.79 to 0.85, while the sensitivity of the ML model based on gene-transcriptomic was between 0.92 and 0.99. Both radiomics and gene transcriptomics produced ideal effects on BRCA molecular subtype prediction. Compared with radiomics, gene transcriptomics yielded better prediction results, but radiomics was simpler and more convenient from a clinical point of view.

Neuroimaging biomarkers for detecting schizophrenia: A resting-state functional MRI-based radiomics analysis

Schizophrenia (SZ) is a common psychiatric disorder that is difficult to accurately diagnose in clinical practice. Quantifiable biomarkers are urgently required to explore the potential physiological mechanism of SZ and improve its diagnostic accuracy. Thus, this study aimed to identify biomarkers that classify SZ patients and healthy control subjects and investigate the potential neural mechanisms of SZ using degree centrality (DC)- and voxel-mirrored homotopic connectivity (VMHC)-based radiomics. Radiomics features were extracted from DC and VMHC metrics generated via resting-state functional magnetic resonance imaging, and significant features were selected and dimensionality was reduced using t-tests and least absolute shrinkage and selection operator. Subsequently, we built our model using a support vector machine classifier. We observed that our method obtained great classification performance (area under the curve, 0.808; accuracy, 74.02%), and it could be generalized to different brain atlases. The regions that we identified as discriminative features mainly included bilateral dorsal caudate and front-parietal, somatomotor, limbic, and default mode networks. Our findings showed that the radiomics-based machine learning method could facilitate us to understand the potential pathological mechanism of SZ more comprehensively and contribute to the accurate diagnosis of patients with SZ.

Feasibility of ultrasound radiomics-based models for classification of hepatic echinococcosis

To investigate the feasibility of establishment of ultrasound radiomics-based models for classification of hepatic echinococcosis, so as to provide insights into precision ultrasound diagnosis of hepatic echinococcosis. The ultrasonographic images were retrospectively collected from 200 patients with hepatic echinococcosis in Shiqu County, Ganzi Tibetan Autonomous Prefecture, Sichuan Province in October 2014, and the regions of interest were plotted in ultrasonographic images of hepatic echinococcosis lesions. The ultrasound radiomics features of hepatic echinococcosis were extracted with 25 methods, and screened using pre-selection and the least absolute shrinkage and selection operator. Then, all ultrasonographic images were randomly assigned into the training and independent test sets according to the type of lesions at a ratio of 7:3. Machine learning models for classification of hepatic echinococcosis were created based on two classifiers, including kernel logistic regression (KLR) and medium Gaussian support vector machine (MGSVM). The receiver operating characteristic (ROC) curves were plotted, and the sensitivity, specificity and areas under the curves (AUC) of the created machine learning models for classification of hepatic echinococcosis were calculated. A total of 5 005 ultrasound radiomics features were extracted from 200 patients with hepatic echinococcosis using 25 methods, and 36 optimal radiomics features were screened through feature selection, based on which two machine learning models were created, including KLR and MGSVM. ROC curve analysis showed that MGS-VM presented a higher efficacy for hepatic echinococcosis classification than KLR in the training set, with a sensitivity of 0.82, a specificity of 0.78 and AUC of 0.88, while KLR presented a higher efficacy for hepatic echinococcosis classification than MGSVM in the independent test set, with a sensitivity of 0.82, a specificity of 0.72 and AUC of 0.86, respectively. Ultrasound radiomics-based machine learning models are feasible for hepatic echinococcosis classification.

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

Background and purposeTo 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 methodsThe 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). ResultsThe 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. ConclusionOur 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.

EO1 - Multicenter validation of 18F-DCFPyL radiomics-based machine learning models in intermediate - To high risk primary prostate cancer

EO1 - Multicenter validation of 18F-DCFPyL radiomics-based machine learning models in intermediate - To high risk primary prostate cancer

Radiomics-based machine learning approach in differentiating fibro-adipose vascular anomaly from venous malformation.

As a complex vascular malformation, fibro-adipose vascular anomaly was first proposed in 2014. Its overlap with other vascular malformations regarding imaging and clinical features often leads to misdiagnosis and improper management. To construct a radiomics-based machine learning model to help radiologists differentiate fibro-adipose vascular anomaly from common venous malformations. We retrospectively analyzed 178 children, adolescents and young adults with vascular malformations (41 fibro-adipose vascular anomaly and 137 common vascular malformation cases) who underwent MRI before surgery between May 2012 to January 2021. We extracted radiomics features from T1-weighted images and fat-saturated (FS) T2-weighted images and further selected features through least absolute shrinkage and selection operator (LASSO) and Boruta methods. We established eight weighted logistic regression classification models based on various combinations of feature-selection strategies (LASSO or Boruta) and sequence types (single- or multi-sequence). Finally, we evaluated the performance of each model by the mean area under the receiver operating characteristics curve (ROC-AUC), sensitivity and specificity in 10 runs of repeated k-fold (k = 10) cross-validation. Two multi-sequence models based on axial FS T2-W, coronal FS T2-W and axial T1-W images showed promising performance. The LASSO-based multi-sequence model achieved an AUC of 97%±3.8, a sensitivity of 94%±12.4 and a specificity of 89%±9.0. The Boruta-based multi-sequence model achieved an AUC of 97%±3.7, a sensitivity of 95%±10.5 and a specificity of 87%±9.0. The radiomics-based machine learning model can provide a promising tool to help distinguish fibro-adipose vascular anomaly from common venous malformations.

Radiomics analysis of contrast-enhanced CT scans can distinguish between clear cell and non-clear cell renal cell carcinoma in different imaging protocols.

IntroductionThis study aimed to construct a radiomics-based machine learning (ML) model for differentiation between non-clear cell and clear cell renal cell carcinomas (ccRCC) that is robust against institutional imaging protocols and scanners.Materials and methodsPreoperative unenhanced (UN), corticomedullary (CM), and excretory (EX) phase CT scans from 209 patients diagnosed with RCCs were retrospectively collected. After the three-dimensional segmentation, 107 radiomics features (RFs) were extracted from the tumor volumes in each contrast phase. For the ML analysis, the cases were randomly split into training and test sets with a 3:1 ratio. Highly correlated RFs were filtered out based on Pearson’s correlation coefficient (r > 0.95). Intraclass correlation coefficient analysis was used to select RFs with excellent reproducibility (ICC ≥ 0.90). The most predictive RFs were selected by the least absolute shrinkage and selection operator (LASSO). A support vector machine algorithm-based binary classifier (SVC) was constructed to predict tumor types and its performance was evaluated based-on receiver operating characteristic curve (ROC) analysis. The “Kidney Tumor Segmentation 2019” (KiTS19) publicly available dataset was used during external validation of the model. The performance of the SVC was also compared with an expert radiologist’s.ResultsThe training set consisted of 121 ccRCCs and 38 non-ccRCCs, while the independent internal test set contained 40 ccRCCs and 13 non-ccRCCs. For external validation, 50 ccRCCs and 23 non-ccRCCs were identified from the KiTS19 dataset with the available UN, CM, and EX phase CTs. After filtering out the highly correlated and poorly reproducible features, the LASSO algorithm selected 10 CM phase RFs that were then used for model construction. During external validation, the SVC achieved an area under the ROC curve (AUC) value, accuracy, sensitivity, and specificity of 0.83, 0.78, 0.80, and 0.74, respectively. UN and/or EX phase RFs did not further increase the model’s performance. Meanwhile, in the same comparison, the expert radiologist achieved similar performance with an AUC of 0.77, an accuracy of 0.79, a sensitivity of 0.84, and a specificity of 0.69.ConclusionRadiomics analysis of CM phase CT scans combined with ML can achieve comparable performance with an expert radiologist in differentiating ccRCCs from non-ccRCCs.

MRI radiomics-based machine learning model integrated with clinic-radiological features for preoperative differentiation of sinonasal inverted papilloma and malignant sinonasal tumors.

ObjectiveTo explore the best MRI radiomics-based machine learning model for differentiation of sinonasal inverted papilloma (SNIP) and malignant sinonasal tumor (MST), and investigate whether the combination of radiomics features and clinic–radiological features can produce a superior diagnostic performance.MethodsThe database of 247 patients with SNIP (n=106) or MST (n=141) were analyzed. Dataset from scanner A were randomly divided into training set (n=135) and test set 1 (n=58) in a ratio of 7:3, and dataset from scanner B and C were used as an additional independent test set 2 (n=54). Fourteen clinic-radiological features were analyzed by using univariate analysis, and those with significant differences were applied to construct clinical model. Based on the radiomics features extracted from single sequence (T2WI or CE-T1WI) and combined sequence, four commonly used classifiers (logistic regression (LR), support vector machine (SVM), decision tree (DT) and k-nearest neighbor (KNN)) were employed to constitute twelve different machine learning models, and the best-performing one was confirmed as the optimal radiomics model. Furthermore, a combined model incorporated best radiomics feature subsets and clinic-radiological features was developed. The diagnostic performances of these models were assessed by the area under the receiver operating characteristic (ROC) curve (AUC) and the calibration curves.ResultsFive clinic-radiological features (age, convoluted cerebriform pattern sign, heterogeneity, adjacent bone involvement and infiltration of surrounding tissue) were considered to be significantly different between the tumor groups (P < 0.05). Among the twelve machine learning models, the T2WI-SVM model exhibited optimal predictive efficacy for classification tasks on the two test sets, with the AUC of 0.878 and 0.914, respectively. For three types of diagnostic models, the combined model achieved highest AUC of 0.912 (95%CI: 0.807-0.970) and 0.927 (95%CI: 0.823-0.980) for differentiation of SNIP and MST in test 1 and test 2 sets, which performed prominently better than clinical model (P=0.011, 0.005), but not significantly different from the optimal radiomics model (P=0.100, 0.452).ConclusionThe machine learning model based on T2WI sequence and SVM classifier achieved best performance in differentiation of SNIP and MST, and the combination of radiomics features and clinic-radiological features significantly improved the diagnostic capability of the model.

Radiomics-Based Machine Learning to Predict Recurrence in Glioma Patients Using Magnetic Resonance Imaging.

Recurrence is a major factor in the poor prognosis of patients with glioma. The aim of this study was to predict glioma recurrence using machine learning based on radiomic features. We recruited 77 glioma patients, consisting of 57 newly diagnosed patients and 20 patients with recurrence. After extracting the radiomic features from T2-weighted images, the data set was randomly divided into training (58 patients) and testing (19 patients) cohorts. An automated machine learning method (the Tree-based Pipeline Optimization Tool) was applied to generate 10 independent recurrence prediction models. The final model was determined based on the area under the curve (AUC) and average specificity. Moreover, an independent validation set of 20 patients with glioma was used to verify the model performance. Recurrence in glioma patients was successfully predicting by machine learning using radiomic features. Among the 10 recurrence prediction models, the best model achieved an accuracy of 0.81, an AUC value of 0.85, and a specificity of 0.69 in the testing cohort, but an accuracy of 0.75 and an AUC value of 0.87 in the independent validation set. Our algorithm that is generated by machine learning exhibits promising power and may predict recurrence noninvasively, thereby offering potential value for the early development of interventions to delay or prevent recurrence in glioma patients.

Hepatocellular carcinoma pathologic grade prediction using radiomics and machine learning models of gadoxetic acid-enhanced MRI: a two-center study.

To develop a radiomics-based hepatocellular carcinoma (HCC) grade classifier model based on data from gadoxetic acid-enhanced MRI. This retrospective study included 137 patients who underwent hepatectomy for a single HCC and gadoxetic acid-enhanced MRI within 60days before surgery. HCC grade was categorized as low or high (modified Edmondson-Steiner grade I-II vs. III-IV). We used the hepatobiliary phase (HBP), portal venous phase, T2-weighted image(T2WI), and T1-weighted image(T1WI). From the volume of interest in HCC, 833 radiomic features were extracted. Radiomic and clinical features were selected using a random forest regressor, and the classification model was trained and validated using a random forest classifier and tenfold stratified cross-validation. Eight models were developed using the radiomic features alone or by combining the radiomic and clinical features. Models were validated with internal enrolled data (internal validation) and a dataset (28 patients) at a separate institution (external validation). The area under the curve (AUC) of the validation results was compared using the DeLong test. In internal and external validation, the HBP radiomics-only model showed the highest AUC (internal 0.80 ± 0.09, external 0.70 ± 0.09). In external validation, all models showed lower AUC than those for internal validation, while the T2WI and T1WI models failed to predict the HCC grade (AUC 0.30-0.58) in contrast to the internal validation results (AUC 0.67-0.78). The radiomics-based machine learning model from gadoxetic acid-enhanced liver MRI could distinguish between low- and high-grade HCCs. The radiomics-only HBP model showed the best AUC among the eight models, good performance in internal validation, and fair performance in external validation.

Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists.

A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist. In this IRB-approved retrospective single-institution study, patients with surgically resected pancreatic cysts who underwent preoperative abdominal CT from 2003 to 2016 were identified. Pancreatic cyst(s) and background pancreas were manually segmented, and 488 radiomics features were extracted. Random forest classification based on radiomics features, age, and gender was evaluated with fourfold cross-validation. An academic radiologist blinded to the final pathologic diagnosis reviewed each case and provided the most likely diagnosis. 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist. Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.

A machine-learning approach using pubic CT based on radiomics to estimate adult ages

PurposeAdult skeletal age estimation is an active research field. To evaluate the performance of a pubic CT radiomics-based machine learning model for estimating age, we established a multiple linear regression model based on radiomics and machine learning methods. MethodsA total of 355 subjects were enrolled in this retrospective study from August 2016 to August 2021, and divided into a training cohort (N = 325) and a testing cohort (N = 30). Computerized texture analysis of the semi-automatically segmentation was performed and 107 texture features were extracted from the regions. Then we used univariate linear regression and multivariate stepwise regression to assess correlations of texture parameters with age. The most vital features were used to make the best predictive model. Eventually, the established radiomics model was tested with an additional 30 patients. ResultsClinical characteristics include age, sex, height, weight and BMI were not statistically significant different between training and testing cohort (p = 0.098–0.888). Through a multivariate regression analysis using stepwise regression, six texture parameters were found to have significant correlations with age. The regression formula estimating the age was constructed. ConclusionsThe radiomics model using machine learning is considered as a new approach forage estimation frompubic symphysis CT features.Digital osteology is obtained in a non-invasive way so that it can be an ideal collection for anthropological studies.

Radiomics-based machine learning (ML) classifier for detection of type 2 diabetes on standard-of-care abdomen CTs: a proof-of-concept study.

To determine if pancreas radiomics-based AI model can detect the CT imaging signature of type 2 diabetes (T2D). Total 107 radiomic features were extracted from volumetrically segmented normal pancreas in 422 T2D patients and 456 age-matched controls. Dataset was randomly split into training (300 T2D, 300 control CTs) and test subsets (122 T2D, 156 control CTs). An XGBoost model trained on 10 features selected through top-K-based selection method and optimized through threefold cross-validation on training subset was evaluated on test subset. Model correctly classified 73 (60%) T2D patients and 96 (62%) controls yielding F1-score, sensitivity, specificity, precision, and AUC of 0.57, 0.62, 0.61, 0.55, and 0.65, respectively. Model's performance was equivalent across gender, CT slice thicknesses, and CT vendors (p values > 0.05). There was no difference between correctly classified versus misclassified patients in the mean (range) T2D duration [4.5 (0-15.4) versus 4.8 (0-15.7) years, p = 0.8], antidiabetic treatment [insulin (22% versus 18%), oral antidiabetics (10% versus 18%), both (41% versus 39%) (p > 0.05)], and treatment duration [5.4 (0-15) versus 5 (0-13) years, p = 0.4]. Pancreas radiomics-based AI model can detect the imaging signature of T2D. Further refinement and validation are needed to evaluate its potential for opportunistic T2D detection on millions of CTs that are performed annually.