A radiomics model utilizing CT for the early detection and diagnosis of severe community-acquired pneumonia.

BACKGROUND: Community-Acquired Pneumonia (CAP) remains a significant global health concern, with a subset of cases progressing to Severe Community-Acquired Pneumonia (SCAP). This study aims to develop and validate a CT-based radiomics model for the early detection of SCAP to enable timely intervention and improve patient outcomes. METHODS: A retrospective study was conducted on 115 CAP and SCAP patients at Southern Medical University Shunde Hospital from January to December 2021. Using the Pyradiomics package, 107 radiomic features were extracted from CT scans, refined via intra-class and inter-class correlation coefficients, and narrowed down using the Least Absolute Shrinkage and Selection Operator (LASSO) regression model. The predictive performance of the radiomics-based model was assessed through receiver operating characteristic (ROC) analysis, employing machine learning classifiers such as k-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF), trained and validated on datasets split 7:3, with a training set (n = 80) and a validation set (n = 35). RESULTS: The radiomics model exhibited robust predictive performance, with the RF classifier achieving superior precision and accuracy compared to LR, SVM, and KNN classifiers. Specifically, the RF classifier demonstrated a precision of 0.977 (training set) and 0.833 (validation set), as well as an accuracy of 0.925 (training set) and 0.857 (validation set), suggesting its superior performance in both metrics. Decision Curve Analysis (DCA) was utilized to evaluate the clinical efficacy of the RF classifier, demonstrating a favorable net benefit within the threshold ranges of 0.1 to 0.8 for the training set and 0.2 to 0.7 for the validation set. CONCLUSIONS: The radiomics model developed in this study shows promise for early SCAP detection and can improve clinical decision-making.

The severity assessment and nucleic acid turning-negative-time prediction in COVID-19 patients with COPD using a fused deep learning model.

BACKGROUND: Previous studies have shown that patients with pre-existing chronic obstructive pulmonary diseases (COPD) were more likely to be infected with coronavirus disease (COVID-19) and lead to more severe lung lesions. However, few studies have explored the severity and prognosis of COVID-19 patients with different phenotypes of COPD. PURPOSE: The aim of this study is to investigate the value of the deep learning and radiomics features for the severity evaluation and the nucleic acid turning-negative time prediction in COVID-19 patients with COPD including two phenotypes of chronic bronchitis predominant patients and emphysema predominant patients. METHODS: A total of 281 patients were retrospectively collected from Hohhot First Hospital between October 2022 and January 2023. They were divided to three groups: COVID-19 group of 95 patients, COVID-19 with emphysema group of 94 patients, COVID-19 with chronic bronchitis group of 92 patients. All patients underwent chest computed tomography (CT) scans and recorded clinical data. The U-net model was pretrained to segment the pulmonary involvement area on CT images and the severity of pneumonia were evaluated by the percentage of pulmonary involvement volume to lung volume. The 107 radiomics features were extracted by pyradiomics package. The Spearman method was employed to analyze the correlation of the data and visualize it through a heatmap. Then we establish a deep learning model (model 1) and a fusion model (model 2) combined deep learning with radiomics features to predict nucleic acid turning-negative time. RESULTS: COVID-19 patients with emphysema was lowest in the lymphocyte count compared to COVID-19 patients and COVID-19 companied with chronic bronchitis, and they have the most extensive range of pulmonary inflammation. The lymphocyte count was significantly correlated with pulmonary involvement and the time for nucleic acid turning negative (r=-0.145, P < 0.05). Importantly, our results demonstrated that model 2 achieved an accuracy of 80.9% in predicting nucleic acid turning-negative time. CONCLUSION: The pre-existing emphysema phenotype of COPD severely aggravated the pulmonary involvement of COVID-19 patients. Deep learning and radiomics features may provide more information to accurately predict the nucleic acid turning-negative time, which is expected to play an important role in clinical practice.

Radiomics as a measure superior to common similarity metrics for tumor segmentation performance evaluation.

PURPOSE: To propose radiomics features as a superior measure for evaluating the segmentation ability of physicians and auto-segmentation tools and to compare its performance with the most commonly used metrics: Dice similarity coefficient (DSC), surface Dice similarity coefficient (sDSC), and Hausdorff distance (HD). MATERIALS/METHODS: The data of 10 lung cancer patients' CT images with nine tumor segmentations per tumor were downloaded from the RIDER (Reference Database to Evaluate Response) database. Radiomics features of 90 segmented tumors were extracted using the PyRadiomics program. The intraclass correlation coefficient (ICC) of radiomics features were used to evaluate the segmentation similarity and compare their performance with DSC, sDSC, and HD. We calculated one ICC per radiomics feature and per tumor for nine segmentations and 36 ICCs per radiomics feature for 36 pairs of nine segmentations. Meanwhile, there were 360 DSC, sDSC, and HD values calculated for 36 pairs for 10 tumors. RESULTS: The ICC of radiomics features exhibited greater sensitivity to segmentation changes than DSC and sDSC. The ICCs of the wavelet-LLL first order Maximum, wavelet-LLL glcm MCC, wavelet-LLL glcm Cluster Shade features ranged from 0.130 to 0.997, 0.033 to 0.978, and 0.160 to 0.998, respectively. On the other hand, all DSC and sDSC were larger than 0.778 and 0.700, respectively, while HD varied from 0 to 1.9 mm. The results indicated that the radiomics features could capture subtle variations in tumor segmentation characteristics, which could not be easily detected by DSC and sDSC. CONCLUSIONS: This study demonstrates the superiority of radiomics features with ICC as a measure for evaluating a physician's tumor segmentation ability and the performance of auto-segmentation tools. Radiomics features offer a more sensitive and comprehensive evaluation, providing valuable insights into tumor characteristics. Therefore, the new metrics can be used to evaluate new auto-segmentation methods and enhance trainees' segmentation skills in medical training and education.

Presurgical MRI-Based Radiomics Models for Predicting Cerebellar Mutism Syndrome in Children With Posterior Fossa Tumors.

BACKGROUND: Current studies have indicated that tumoral morphologic features are associated with cerebellar mutism syndrome (CMS), but the radiomics application in CMS is scarce. PURPOSE: To develop a model for CMS discrimination based on multiparametric MRI radiomics in patients with posterior fossa tumors. STUDY TYPE: Retrospective. POPULATION: A total of 218 patients (males 132, females 86) with posterior fossa tumors, 169 of which were included in the MRI radiomics analysis. The MRI radiomics study cohort (169) was split into training (119) and testing (50) sets with a ratio of 7:3. FIELD/SEQUENCE: All the MRI were acquired under 1.5/3.0 T scanners. T2-weighted image (T2W), T1-weighted (T1W), fluid attenuated inversion recovery (FLAIR), diffusion-weighted imaging (DWI). ASSESSMENT: Apparent diffusion coefficient (ADC) maps were generated from DWI. Each MRI dataset generated 1561 radiomics characteristics. Feature selection was performed with univariable logistic analysis, correlation analysis, and least absolute shrinkage and selection operator (LASSO) penalized logistic regression. Significant clinical features were selected with multivariable logistic analysis and used to constructed the clinical model. Radiomics models (based on T1W, T2W, FLAIR, DWI, ADC) were constructed with selected radiomics features. The mix model was based on the multiparametric MRI radiomics features. STATISTICAL TEST: Multivariable logistic analysis was utilized during clinical features selection. Models' performance was evaluated using the area under the receiver operating characteristic (AUC) curve. Interobserver variability was assessed using Cohen's kappa. Significant threshold was set as P < 0.05. RESULTS: Sex (aOR = 3.72), tumor location (aOR = 2.81), hydrocephalus (aOR = 2.14), and tumor texture (aOR = 5.08) were significant features in the multivariable analysis and were used to construct the clinical model (AUC = 0.79); totally, 33 radiomics features were selected to construct radiomics models (AUC = 0.63-0.93). Seven of the 33 radiomics features were selected for the mix model (AUC = 0.93). DATA CONCLUSION: Multiparametric MRI radiomics may be better at predicting CMS than single-parameter MRI models and clinical model. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: 2.

Quantitative evaluation of the hemodynamic differences between ruptured and unruptured cerebral arteriovenous malformations using angiographic parametric imaging-derived radiomics features.

PURPOSE: Imaging features of cerebral arteriovenous malformations (AVMs) are mainly interpreted according to demographic and qualitative anatomical characteristics. This study aimed to use angiographic parametric imaging (API)-derived radiomics features to explore whether these features extracted from digital subtraction angiography (DSA) were associated with the hemorrhagic presentation of AVMs. METHODS: Patients with AVM were retrospectively evaluated. Among them, 80% were randomly assigned to a training dataset, and the remaining 20% were assigned to an independent test dataset. Radiomics features were extracted from DSA by API. Then, informative features were selected from radiomics features and clinical features using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. A model was constructed based on the selected features to classify the dichotomous hemorrhagic presentation in the training dataset. The model performance was evaluated in the test dataset with confusion matrix-related metrics. RESULTS: A total of 529 consecutive patients with AVMs between July 2011 and December 2020 were included in this study. After being selected by the LASSO algorithm and analyzed by multivariable logistic regression, three clinical features, namely, age (p = 0.01), nidus size (p < 0.001), and venous drainage patterns (p < 0.001), and four radiomics features were used to construct a model in the training dataset. On the independent test dataset, the model demonstrated a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 0.852, 0.844, 0.881, 0.809, and 0.849, respectively. CONCLUSION: The radiomics features extracted from DSA by API could be potential indicators for the hemorrhagic presentation of AVMs.

Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI.

BACKGROUND: The purpose of this study is to investigate the use of radiomics and deep features obtained from multiparametric magnetic resonance imaging (mpMRI) for grading prostate cancer. We propose a novel approach called multi-flavored feature extraction or tensor, which combines four mpMRI images using eight different fusion techniques to create 52 images or datasets for each patient. We evaluate the effectiveness of this approach in grading prostate cancer and compare it to traditional methods. METHODS: We used the PROSTATEx-2 dataset consisting of 111 patients' images from T2W-transverse, T2W-sagittal, DWI, and ADC images. We used eight fusion techniques to merge T2W, DWI, and ADC images, namely Laplacian Pyramid, Ratio of the low-pass pyramid, Discrete Wavelet Transform, Dual-Tree Complex Wavelet Transform, Curvelet Transform, Wavelet Fusion, Weighted Fusion, and Principal Component Analysis. Prostate cancer images were manually segmented, and radiomics features were extracted using the Pyradiomics library in Python. We also used an Autoencoder for deep feature extraction. We used five different feature sets to train the classifiers: all radiomics features, all deep features, radiomics features linked with PCA, deep features linked with PCA, and a combination of radiomics and deep features. We processed the data, including balancing, standardization, PCA, correlation, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. Finally, we used nine classifiers to classify different Gleason grades. RESULTS: Our results show that the SVM classifier with deep features linked with PCA achieved the most promising results, with an AUC of 0.94 and a balanced accuracy of 0.79. Logistic regression performed best when using only the deep features, with an AUC of 0.93 and balanced accuracy of 0.76. Gaussian Naive Bayes had lower performance compared to other classifiers, while KNN achieved high performance using deep features linked with PCA. Random Forest performed well with the combination of deep features and radiomics features, achieving an AUC of 0.94 and balanced accuracy of 0.76. The Voting classifiers showed higher performance when using only the deep features, with Voting 2 achieving the highest performance, with an AUC of 0.95 and balanced accuracy of 0.78. CONCLUSION: Our study concludes that the proposed multi-flavored feature extraction or tensor approach using radiomics and deep features can be an effective method for grading prostate cancer. Our findings suggest that deep features may be more effective than radiomics features alone in accurately classifying prostate cancer.

Delta computed tomography radiomics features-based nomogram predicts long-term efficacy after neoadjuvant chemotherapy in advanced gastric cancer.

BACKGROUND AND OBJECTIVE: No effective preoperative tool is available for predicting the prognosis of advanced gastric cancer (AGC) treated by neoadjuvant chemotherapy (NAC). We aimed to explore the association between change values ("delta") in the radiomic signatures of computed tomography (CT) (delCT-RS) before and after NAC for AGC and overall survival(OS). METHODS AND DESIGN: A total of 132 AGC patients with AGC were studied as a training cohort in our center, and 45 patients from another center were used as an external validation set. A radiomic signatures-clinical-nomogram(RS-CN) was established using delCT-RS and preoperative clinical variables. The prediction performance of RS-CN was evaluated using the area under the receiver operating characteristic (ROC)curve (AUC values), time-dependent ROC, decision curve analysis(DCA) and C-index. RESULTS: Multivariable Cox regression analyses showed that delCT-RS, cT-stage, cN-stage, Lauren-type and the value of variation of carcinoma embryonic antigen (CEA) between NAC were independent risk factors for 3-year OS of AGC. In the training cohort, RS-CN had a good prediction performance for OS (C-Index 0.73) and AUC values were significantly better than those of delCT-RS, ypTNM-stage and tumor regression grade(TRG) (0.827 vs 0.704 vs 0.749 vs 0.571, p < 0.001). DCA and time-dependent ROC of RS-CN were better than those of ypTNM stage, TRG grade and delCT-RS. The prediction performance of the validation set was equivalent to that of the training set. The cut-off (177.2) of RS-CN score was obtained from X-Tile software, a score of > 177.2 was defined as high-risk group(HRG), and scores of ≤ 177.2 were defined as the low-risk group(LRG). The 3-year OS and disease free survival(DFS) of patients in the LRG were significantly better than those in the HRG. Adjuvant chemotherapy(AC) can only significantly improve the 3-year OS and DFS of the LRG. (p < 0.05). CONCLUSIONS: Our nomogram based on delCT-RS has good prediction of prognosis before surgery and helps identify patients that are most likely to benefit from AC. It works well in precise and individualised NAC in AGC.

Functional MRI radiomics-based assessment of pelvic bone marrow changes after concurrent chemoradiotherapy for cervical cancer.

OBJECTIVES: To quantify the dose-response relationship of changes in pelvic bone marrow (PBM) functional MR radiomic features (RF) during concurrent chemoradiotherapy (CCRT) for patients with cervical cancer and establish the correlation with hematologic toxicity to provide a basis for PBM sparing. METHODS: A total of 54 cervical cancer patients who received CCRT were studied retrospectively. Patients underwent MRI IDEAL IQ and T2 fat suppression (T2fs) scanning pre- and post-CCRT. The PBM RFs were extracted from each region of interest at dose gradients of 5-10 Gy, 10-15 Gy, 15-20 Gy, 20-30 Gy, 30-40 Gy, 40-50 Gy, and > 50 Gy, and changes in peripheral blood cell (PBC) counts during radiotherapy were assessed. The dose-response relationship of RF changes and their correlation with PBC changes were investigated. RESULTS: White blood cell, neutrophils (ANC) and lymphocyte counts during treatment were decreased by 49.4%, 41.4%, and 76.3%, respectively. Most firstorder features exhibited a significant dose-response relationship, particularly FatFrac IDEAL IQ, which had a maximum dose-response curve slope of 10.09, and WATER IDEAL IQ had a slope of - 7.93. The firstorder-Range in FAT IDEAL IQ and firstorder-10Percentile in T2fs, showed a significant correlation between the changes in ANC counts under the low dose gradient of 5-10 Gy (r = 0.744, -0.654, respectively, p < 0.05). CONCLUSION: Functional MR radiomics can detect microscopic changes in PBM at various dose gradients and provide an objective reference for bone marrow sparing and dose limitation in cervical cancer CCRT.

Elaboration of Multiparametric MRI-Based Radiomics Signature for the Preoperative Quantitative Identification of the Histological Grade in Patients With Non-Small-Cell Lung Cancer.

BACKGROUND: The histological grading plays an essential role in the treatment decision of lung cancer. Detected tumors are usually biopsied to confirm histologic grade. How to use MRI extracted radiomics features for accurately grading lung cancer is still challenging. PURPOSE: To examine the diagnostic utility of multiparametric MRI radiomics and clinical factors for grading non-small-cell lung cancer (NSCLC). STUDY TYPE: Retrospective. POPULATION: A total of 148 patients (25.7% female) with postoperative pathologically confirmed NSCLC and divided into the training cohort (N = 110) and the validation cohort (N = 38). FIELD STRENGTH/SEQUENCE: A 1.5 T; single-shot turbo spin-echo (TSE), T2-weighted imaging (T2WI), and integrated shimming-echo planar imaging (ISHIM-EPI) diffusion-weighted imaging (DWI). ASSESSMENT: A total of 2775 radiomics features were extracted from carcinomatous regions of interest on T2WI, DWI, and the apparent diffusion coefficient (ADC) maps. The five optimal features were selected by using the Student' s t-test, the least absolute shrinkage and selection operator (LASSO) and stepwise regression. The Radscore combined with clinical factors, which selected by univariate and multivariate analyses, to develop a radiomics-clinical nomogram. Its performance was evaluated in the training cohort and the validation cohort. The potential clinical usefulness was analyzed by the receiver operating characteristic curve (ROC), area under the curve (AUC), and the Hosmer-Lemeshow test. STATISTICAL TESTS: Student's t-test, univariate analyses, multivariate analyses, LASSO, ROC, AUC, and the Hosmer-Lemeshow test. P < 0.05 was considered statistically significant. RESULTS: Favorable discrimination performance was obtained for five optimal features (out of the 2775 features), using the training cohorts (AUC 0.761) and validation cohorts (AUC 0.753). In addition, the radiomics-clinical nomogram significantly improved the ability to identify histological grades in the training cohort (AUC 0.814) and the validation cohort (AUC 0.767). DATA CONCLUSIONS: The radiomics-clinical nomogram based on multiparametric MRI might have the potential to distinguish the histological grade of NSCLC. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Differentiation of renal cell carcinoma subtypes through MRI-based radiomics analysis.

OBJECTIVES: To explore whether clear cell renal cell carcinoma (ccRCC), papillary renal cell carcinoma (pRCC), and chromophobe renal cell carcinoma (cRCC) can be distinguished using radiomics features extracted from magnetic resonance (MR) images. METHODS: Seventy-seven patients (ccRCC = 32, pRCC = 23, cRCC = 22) underwent MRI before surgery between May 2013 and August 2018 in this retrospective study. Thirty-nine radiomics features were extracted from tumor volumes on three sequences (T2WI, EN-T1WI CMP, and EN-T1WI NP). The Kruskal-Wallis test with Bonferonni correction and variance threshold were used for feature selection among the three RCC subtypes. ROC curves for the three subtypes were generated based on radiomics features. AUC, accuracy, sensitivity, and specificity for subtype differentiation are reported. Linear discriminant analysis (LDA) was used to assess the discriminative ability of these radiomics features. RESULTS: Significant radiomics features among the three subtypes were identified, and ROC curves achieved excellent AUCs for T2WI, EN-T1WI CMP, EN-T1WI NP, and combined three MR sequences (0.631, 0.790, 0.959, and 0.959 between ccRCC and cRCC; 0.688, 0.854, 0.909, and 0.955 between pRCC and cRCC; 0.747, 0.810, 0.814, and 0.890 between ccRCC and pRCC). In addition, LDA demonstrated the three RCC subtypes were correctly classified by radiomics analysis (66.2% for EN-T1WI CMP, 71.4% for EN-T1WI NP, 55.8% for T2WI, and 71.4% for the combined three MR sequences). CONCLUSIONS: Radiomics analysis can be used to differentiate among ccRCC, pRCC, and cRCC based on radiomics features extracted from multiple-sequence MRI and may help diagnose and treat RCC patients in the future, while further study is still needed. KEY POINTS: • Radiomics features on multiple-sequence MRI can help differentiate the three subtypes of renal cell carcinoma (clear cell, papillary renal cell, and chromophobe renal cell carcinoma). • Radiomics features based on MRI indicate greater textural heterogeneity on ccRCCs than pRCCs and cRCCs (the highest AUCs on EN-T1WI NP are 0.814 for ccRCCs vs pRCCs and 0.959 for ccRCCs vs cRCCs, respectively). • There is a significant difference in the textural heterogeneity of radiomics features between pRCCs and cRCCs (the AUC is 0.909, 0.854, and 0.688 on EN-T1WI NP, EN-T1WI CMP, and T2WI, respectively).

Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer.

BACKGROUND: Non-invasive discrimination between lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD) subtypes of non-small-cell lung cancer (NSCLC) could be very beneficial to the patients unfit for the invasive diagnostic procedures. The aim of this study was to investigate the feasibility of utilizing the multimodal magnetic resonance imaging (MRI) radiomics and clinical features in classifying NSCLC. This retrospective study involved 148 eligible patients with postoperative pathologically confirmed NSCLC. The study was conducted in three steps: (1) feature extraction was performed using the online freely available package with the multimodal MRI data; (2) feature selection was performed using the Student's t test and support vector machine (SVM)-based recursive feature elimination method with the training cohort (n = 100), and the performance of these selected features was evaluated using both the training and the validation cohorts (n = 48) with a non-linear SVM classifier; (3) a Radscore model was then generated using logistic regression algorithm; (4) Integrating the Radscore with the semantic clinical features, a radiomics-clinical nomogram was developed, and its overall performance was evaluated with both cohorts. RESULTS: Thirteen optimal features achieved favorable discrimination performance with both cohorts, with area under the curve (AUC) of 0.819 and 0.824, respectively. The radiomics-clinical nomogram integrating the Radscore with the independent clinical predictors exhibited more favorable discriminative power, with AUC improved to 0.901 and 0.872 in both cohorts, respectively. The Hosmer-Lemeshow test and decision curve analysis results furtherly showed good predictive precision and clinical usefulness of the nomogram. CONCLUSION: Non-invasive histological subtype stratification of NSCLC can be done favorably using multimodal MRI radiomics features. Integrating the radiomics features with the clinical features could further improve the performance of the histological subtype stratification in patients with NSCLC.

Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor.

BACKGROUND: This study is to distinguish peripheral lung cancer and pulmonary inflammatory pseudotumor using CT-radiomics features extracted from PET/CT images. METHODS: In this study, the standard 18F-fluorodeoxyglucose positron emission tomography/ computed tomography (18 F-FDG PET/CT) images of 21 patients with pulmonary inflammatory pseudotumor (PIPT) and 21 patients with peripheral lung cancer were retrospectively collected. The dataset was used to extract CT-radiomics features from regions of interest (ROI), The intra-class correlation coefficient (ICC) was used to screen the robust feature from all the radiomic features. Using, then, statistical methods to screen CT-radiomics features, which could distinguish peripheral lung cancer and PIPT. And the ability of radiomics features distinguished peripheral lung cancer and PIPT was estimated by receiver operating characteristic (ROC) curve and compared by the Delong test. RESULTS: A total of 435 radiomics features were extracted, of which 361 features showed relatively good repeatability (ICC ≥ 0.6). 20 features showed the ability to distinguish peripheral lung cancer from PIPT. these features were seen in 14 of 330 Gray-Level Co-occurrence Matrix features, 1 of 49 Intensity Histogram features, 5 of 18 Shape features. The area under the curves (AUC) of these features were 0.731 ± 0.075, 0.717, 0.748 ± 0.038, respectively. The P values of statistical differences among ROC were 0.0499 (F9, F20), 0.0472 (F10, F11) and 0.0145 (F11, Mean4). The discrimination ability of forming new features (Parent Features) after averaging the features extracted at different angles and distances was moderate compared to the previous features (Child features). CONCLUSION: Radiomics features extracted from non-contrast CT based on PET/CT images can help distinguish peripheral lung cancer and PIPT.

Correlation between CT based radiomics features and gene expression data in non-small cell lung cancer.

OBJECTIVE: Radiogenomics investigates radiographic imaging phenotypes associated with gene expression patterns. This study aims to explore relationships between CT imaging radiomics features and gene expression data in non-small cell lung cancer (NSCLC). METHODS: Eighty-nine NSCLC patients are included in the study. Radiomics features are extracted and selected to quantify the phenotype of tumors on CT-scans. Co-expressed genes are also clustered and the first principal component of the cluster is represented, which is defined as a metagene. Then, statistical analysis was performed to assess association of CT radiomics features with metagenes. In addition, predictive models are built and metagene enrichment are conducted to further evaluate performance of NSCLC radiogenomics statistically and biologically. RESULTS: There are 187 significant pairwise correlations between a CT radiomics feature and a metagene of NSCLC, where eighteen metagenes are annotated with Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) terms. Metagenes are predicted in terms of radiomics features with an accuracy of 41.89% -89.93%. CONCLUSIONS: This study reveals the associations between CT imaging radiomics features and NSCLC co-expressed gene sets. The findings suggest that CT radiomics features can reflect important biological information of NSCLC patients, which may have a significant clinical impact as CT is routinely used in clinical practice, assisting in improving medical decision-support at low cost.

TMM: A comprehensive CAD system for hepatic fibrosis 5-grade METAVIR staging based on liver MRI.

BACKGROUND: Precise staging of hepatic fibrosis with MRI is necessary as it can assist precision medicine. Computer aided diagnosis (CAD) system with distinguishing radiomics features and radiologists domain knowledge is expected to obtain 5-grade meta-analysis of histological data in viral hepatitis (METAVIR) staging. PURPOSE: This study aims to obtain the precise staging of hepatic fibrosis based on MRI as it predicts the risk of future liver-related morbidity and the need for treatment, monitoring and surveillance. Based on METAVIR score, fibrosis can be divided into five stages. Most previous researches focus on binary classification, such as cirrhosis versus non-cirrhosis, early versus advanced fibrosis, and substantial fibrosis or not. In this paper, a comprehensive CAD system TMM is proposed to precisely class hepatic fibrosis into five stages for precision medicine instead of the common binary classification. METHODS: We propose a novel hepatic fibrosis staging CAD system TMM which includes three modules, Two-level Image Statistical Radiomics Feature (TISRF), Monotonic Error Correcting Output Codes (MECOC) and Monotone Multiclassification with Deep Forest (MMDF). TISRF extracts radiomics features for distinguishing different hepatic fibrosis stages. MECOC is proposed to encode monotonic multiclass by making full use of the progressive severity of hepatic fibrosis and increase the fault tolerance and error correction ability. MMDF combines multiple Deep Forest network to ensure the final five-class classification, which can achieve more precise classification than the common binary classification. The performance of the proposed hepatic fibrosis CAD system is tested on the hepatic data collected from our rabbits models of fibrosis. RESULTS: A total of 140 regions of interest (ROI) are selected from MRI T1W of liver fibrosis models in 35 rabbits with F0(n = 16), F1(n = 28), F2(n = 29), F3(n = 44) and F4(n = 23). The performance is evaluated by five-fold cross-validation. TMM can achieve the highest total accuracy of 72.14% for five fibrosis stages compared with other popular classifications. To make a comprehensive comparison, a binary classification experiment have been carried out. CONCLUSIONS: T1WI can obtain precise staging of hepatic fibrosis with the help of comprehensive CAD including radiomics features extraction inspired by radiologists, monotonic multiclass according to the severity of hepatic fibrosis, and deep learning classification.

Independent and reproducible hippocampal radiomics biomarkers for multisite multiple sclerosis and neuromyelitis optica spectrum disorders.

OBJECTIVE: To investigate the abnormal radiomics features of the hippocampus in patients with multiple sclerosis (MS) and neuromyelitis optica spectrum disorders (NMOSD) and to explore the clinical implications of these features. METHODS: 752 participants were recruited in this retrospective multicenter study (7 centers), which included 236 MS, 236 NMOSD, and 280 normal controls (NC). Radiomics features of each side of the hippocampus were extracted, including intensity, shape, texture, and wavelet features (N = 431). To identify the variations in these features, two-sample t-tests were performed between the NMOSD vs. NC, MS vs. NC, and NMOSD vs. MS groups at each site. The statistical results from each site were then integrated through meta-analysis. To investigate the clinical significance of the hippocampal radiomics features, we conducted further analysis to examine the correlations between these features and clinical measures such as Expanded Disability Status Scale (EDSS), Brief Visuospatial Memory Test (BVMT), California Verbal Learning Test (CVLT), and Paced Auditory Serial Addition Task (PASAT). RESULTS: Compared with NC, patients with MS exhibited significant differences in 78 radiomics features (P < 0.05/862), with the majority of these being texture features. Patients with NMOSD showed significant differences in 137 radiomics features (P < 0.05/862), most of which were intensity features. The difference between MS and NMOSD patients was observed in 47 radiomics features (P < 0.05/862), mainly texture features. In patients with MS and NMOSD, the most significant features related to the EDSS were intensity and textural features, and the most significant features related to the PASAT were intensity features. Meanwhile, both disease groups observed a weak correlation between radiomics data and BVMT. CONCLUSION: Variations in the microstructure of the hippocampus can be detected through radiomics, offering a new approach to investigating the abnormal pattern of the hippocampus in MS and NMOSD.

Multi-instance learning for identifying high-risk subregions associated with synchronous distant metastasis in clear cell renal cell carcinoma.

BACKGROUND: Clear cell renal cell carcinoma (ccRCC) is one of the most common histological subtypes of renal tumors. PURPOSE: To identify high-risk subregions associated with synchronous distant metastasis. METHODS: This study enrolled a total of 277 patients with ccRCC. Voxel intensity and local entropy values were compiled within the region of interest for all patients. Unsupervised k-means clustering yielded three subregions per tumor. Radiomic features were extracted, and random forest-based feature selection was conducted. The selected features were used in a multi-instance support vector machine (mi-SVM) model for training, and predictions were made on the validation cohort. Model performance was evaluated using five-fold cross-validation. The subregion with the highest score for patients with synchronous distant metastasis was identified across all cohorts. RESULTS: The mi-SVM model yielded an average area under the curve (AUC) of 0.812 in the training cohort and 0.805 in the validation cohort. In the entire cohort of patients with synchronous distant metastasis, subregion 2, characterized by tumor periphery and intratumoral transitional components, accounted for the highest proportion (48.57%, 30.6/63) among all subregions. It represents a high-risk subregion for synchronous distant metastasis of clear cell renal cell carcinoma. CONCLUSION: The peripheral and intratumoral transition zones of clear cell renal cell carcinoma are high-risk subregions associated with synchronous distant metastasis.

Radiomic features of the hippocampal based on magnetic resonance imaging in the menopausal mouse model linked to neuronal damage and cognitive deficits.

Estrogen deficiency in the early postmenopausal phase is associated with an increased long-term risk of cognitive decline or dementia. Non-invasive characterization of the pathological features of the pathological hallmarks in the brain associated with postmenopausal women (PMW) could enhance patient management and the development of therapeutic strategies. Radiomics is a means to quantify the radiographic phenotype of a diseased tissue via the high-throughput extraction and mining of quantitative features from images acquired from modalities such as CT and magnetic resonance imaging (MRI). This study set out to explore the correlation between radiomics features based on MRI and pathological features of the hippocampus and cognitive function in the PMW mouse model. Ovariectomized (OVX) mice were used as PWM models. MRI scans were performed two months after surgery. The brain's hippocampal region was manually annotated, and the radiomic features were extracted with PyRadiomics. Chemiluminescence was used to evaluate the peripheral blood estrogen level of mice, and the Morris water maze test was used to evaluate the cognitive ability of mice. Nissl staining and immunofluorescence were used to quantify neuronal damage and COX1 expression in brain sections of mice. The OVX mice exhibited marked cognitive decline, brain neuronal damage, and increased expression of mitochondrial complex IV subunit COX1, which are pathological phenomena commonly observed in the brains of AD patients, and these phenotypes were significantly correlated with radiomics features (p < 0.05, |r|>0.5), including Original_firstorder_Interquartile Range, Original_glcm_Difference Average, Original_glcm_Difference Average and Wavelet-LHH_glszm_Small Area Emphasis. Meanwhile, the above radiomics features were significantly different between the sham-operated and OVX groups (p < 0.01) and were associated with decreased serum estrogen levels (p < 0.05, |r|>0.5). This initial study indicates that the above radiomics features may have a role in the assessment of the pathology of brain damage caused by estrogen deficiency using routinely acquired structural MR images.

Radiomics and Deep Features: Robust Classification of Brain Hemorrhages and Reproducibility Analysis Using a 3D Autoencoder Neural Network.

This study evaluates the reproducibility of machine learning models that integrate radiomics and deep features (features extracted from a 3D autoencoder neural network) to classify various brain hemorrhages effectively. Using a dataset of 720 patients, we extracted 215 radiomics features (RFs) and 15,680 deep features (DFs) from CT brain images. With rigorous screening based on Intraclass Correlation Coefficient thresholds (>0.75), we identified 135 RFs and 1054 DFs for analysis. Feature selection techniques such as Boruta, Recursive Feature Elimination (RFE), XGBoost, and ExtraTreesClassifier were utilized alongside 11 classifiers, including AdaBoost, CatBoost, Decision Trees, LightGBM, Logistic Regression, Naive Bayes, Neural Networks, Random Forest, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). Evaluation metrics included Area Under the Curve (AUC), Accuracy (ACC), Sensitivity (SEN), and F1-score. The model evaluation involved hyperparameter optimization, a 70:30 train-test split, and bootstrapping, further validated with the Wilcoxon signed-rank test and q-values. Notably, DFs showed higher accuracy. In the case of RFs, the Boruta + SVM combination emerged as the optimal model for AUC, ACC, and SEN, while XGBoost + Random Forest excelled in F1-score. Specifically, RFs achieved AUC, ACC, SEN, and F1-scores of 0.89, 0.85, 0.82, and 0.80, respectively. Among DFs, the ExtraTreesClassifier + Naive Bayes combination demonstrated remarkable performance, attaining an AUC of 0.96, ACC of 0.93, SEN of 0.92, and an F1-score of 0.92. Distinguished models in the RF category included SVM with Boruta, Logistic Regression with XGBoost, SVM with ExtraTreesClassifier, CatBoost with XGBoost, and Random Forest with XGBoost, each yielding significant q-values of 42. In the DFs realm, ExtraTreesClassifier + Naive Bayes, ExtraTreesClassifier + Random Forest, and Boruta + k-NN exhibited robustness, with 43, 43, and 41 significant q-values, respectively. This investigation underscores the potential of synergizing DFs with machine learning models to serve as valuable screening tools, thereby enhancing the interpretation of head CT scans for patients with brain hemorrhages.

Comparison of the variability and diagnostic efficacy of respiratory-gated PET/CT based radiomics features with ungated PET/CT in lung lesions.

OBJECTIVES: To investigate the variability and diagnostic efficacy of respiratory-gated (RG) PET/CT based radiomics features compared to ungated (UG) PET/CT in the differentiation of non-small cell lung cancer (NSCLC) and benign lesions. METHODS: 117 patients with suspected lung lesions from March 2020 to May 2021 and consent to undergo UG PET/CT and chest RG PET/CT (including phase-based quiescent period gating, pQPG and phase-matched 4D PET/CT, 4DRG) were prospectively included. 377 radiomics features were extracted from PET images of each scan. Paired t test was used to compare UG and RG features for inter-scan variability analysis. We developed three radiomics models with UG and RG features (i.e. UGModel, pQPGModel and 4DRGModel). ROC curves were used to compare diagnostic efficiencies, and the model-level comparison of diagnostic value was performed by five-fold cross-validation. A P value < 0.05 was considered as statistically significant. RESULTS: A total of 111 patients (average age ± standard deviation was 59.1 ± 11.6 y, range, 29 - 88 y, and 63 were males) with 209 lung lesions were analyzed for features variability and the subgroup of 126 non-metastasis lesions in 91 patients without treatment before PET/CT were included for diagnosis analysis. 101/377 (26.8 %) 4DRG features and 82/377 (21.8 %) pQPG features showed significant difference compared to UG features (both P<0.05). 61/377 (16.2 %) and 59/377 (15.6 %) of them showed significantly better discriminant ability (ΔAUC% (i.e. (AUCRG - AUCUG) / AUCUG×100 %) > 0 and P<0.05) in malignant recognition, respectively. For the model-level comparison, 4DRGModel achieved the highest diagnostic efficacy (sen 73.2 %, spe 87.3 %) compared with UGModel (sen 57.7 %, spe 76.4 %) and pQPGModel (sen 63.4 %, spe 81.8 %). CONCLUSION: RG PET/CT performs better in the quantitative assessment of metabolic heterogeneity for lung lesions and the subsequent diagnosis in patients with NSCLC compared with UG PET/CT.

Fast prediction of patient-specific organ doses in brain CT scans using support vector regression algorithm.

Objectives. This study aims to develop a method for predicting patient-specific head organ doses by training a support vector regression (SVR) model based on radiomics features and graphics processing unit (GPU)-calculated reference doses.Methods. In this study, 237 patients who underwent brain CT scans were selected, and their CT data were transferred to an autosegmentation software to segment head regions of interest (ROIs). Subsequently, radiomics features were extracted from the CT data and ROIs, and the benchmark organ doses were computed using fast GPU-accelerated Monte Carlo (MC) simulations. The SVR organ dose prediction model was then trained using the radiomics features and benchmark doses. For the predicted organ doses, the relative root mean squared error (RRMSE), mean absolute percentage error (MAPE), and coefficient of determination (R2) were evaluated. The robustness of organ dose prediction was verified by changing the patient samples on the training and test sets randomly.Results. For all head organs, the maximal difference between the reference and predicted dose was less than 1 mGy. For the brain, the organ dose was predicted with an absolute error of 1.3%, and theR2reached up to 0.88. For the eyes and lens, the organ doses predicted by SVR achieved an RRMSE of less than 13%, the MAPE ranged from 4.5% to 5.5%, and theR2values were more than 0.7.Conclusions. Patient-specific head organ doses from CT examinations can be predicted within one second with high accuracy, speed, and robustness by training an SVR using radiomics features.