A multi-organ cancer study of the classification performance using 2D and 3D image features in radiomics analysis

Exploring the biological basis of CT imaging features in pancreatic neuroendocrine tumors: a two-center study

Objective.Medical imaging offered a non-invasive window to visualize tumors, with radiomics transforming these images into quantitative data for tumor phenotyping. However, the intricate web linking imaging features, clinical endpoints, and tumor biology was mostly uncharted. This study aimed to unravel the connections between CT imaging features and clinical characteristics, including tumor histopathological grading, clinical stage, and endocrine symptoms, alongside immunohistochemical markers of tumor cell growth, such as the Ki-67 index and nuclear mitosis rate.Approach.We conducted a retrospective analysis of data from 137 patients with pancreatic neuroendocrine tumors who had undergone contrast-enhanced CT scans across two institutions. Our study focused on three clinical factors: pathological grade, clinical stage, and endocrine symptom status, in addition to two immunohistochemical markers: the Ki-67 index and the rate of nuclear mitosis. We computed both predefined (2D and 3D) and learning-based features (via sparse autoencoder, or SAE) from the scans. To unearth the relationships between imaging features, clinical factors, and immunohistochemical markers, we employed the Spearman rank correlation along with the Benjamini-Hochberg method. Furthermore, we developed and validated radiomics signatures to foresee these clinical factors.Main results.The 3D imaging features showed the strongest relationships with clinical factors and immunohistochemical markers. For the association with pathological grade, the mean absolute value of the correlation coefficient (CC) of 2D, SAE, and 3D features was 0.3318 ± 0.1196, 0.2149 ± 0.0361, and 0.4189 ± 0.0882, respectively. While for the association with Ki-67 index and rate of nuclear mitosis, the 3D features also showed higher correlations, with CC as 0.4053 ± 0.0786 and 0.4061 ± 0.0806. In addition, the 3D feature-based signatures showed optimal performance in clinical factor prediction.Significance.We found relationships between imaging features, clinical factors, and immunohistochemical markers. The 3D features showed higher relationships with clinical factors and immunohistochemical markers.

Preoperative prediction of perineural invasion and lymphovascular invasion with CT radiomics in gastric cancer

Objectives

To determine whether contrast-enhanced CT radiomics features can preoperatively predict lymphovascular invasion (LVI) and perineural invasion (PNI) in gastric cancer (GC).

Methods

A total of 148 patients were included in the LVI group, and 143 patients were included in the PNI group. Three predictive models were constructed, including clinical, radiomics, and combined models. A nomogram was developed with clinical risk factors to predict LVI and PNI status. The predictive performance of the three models was mainly evaluated using the mean area under the curve (AUC). The performance of three predictive models was assessed concerning calibration and clinical usefulness.

Results

In the LVI group, the predictive power of the combined model (AUC=0.871, 0.822) outperformed the clinical model (AUC=0.792, 0.728) and the radiomics model (AUC=0.792, 0.728) in both the training and testing cohorts. In the PNI group, the combined model (AUC=0.834, 0.828) also had better predictive power than the clinical model (AUC=0.764, 0.632) and the radiomics model (AUC=0.764, 0.632) in both the training and testing cohorts. The combined models also showed good calibration and clinical usefulness for LVI and PNI prediction.

Conclusion

CECT-based radiomics analysis might serve as a non-invasive method to predict LVI and PNI status in GC.

Radiomics-based lymph nodes prognostic models from three MRI regions in nasopharyngeal carcinoma

Accurate prediction of the prognosis of nasopharyngeal carcinoma (NPC) is important for treatment. Lymph nodes metastasis is an important predictor for distant failure and regional recurrence in patients with NPC. Traditionally, subjective radiological evaluation increases concerns regarding the accuracy and consistency of predictions. Radiomics is an objective and quantitative evaluation algorithm for medical images. This retrospective analysis was conducted based on the data of 729 patients newly diagnosed with NPC without distant metastases to evaluate the performance of radiomics pretreatment using magnetic resonance imaging (MRI)-determined metastatic lymph nodes models to predict NPC prognosis with three delineation methods. Radiomics features were extracted from all lymph nodes (ALN), largest lymph node (LLN), and largest slice of the largest lymph node (LSLN) to generate three radiomics signatures. The radiomics signatures, clinical model, and radiomics-clinic merged models were developed in training cohort for predicting overall survival (OS). The results showed that LSLN signature with clinical factors predicted OS with high accuracy and robustness using pretreatment MR-determined metastatic lymph nodes (C-index [95 % confidence interval]: 0.762[0.760-0.763]), providing a new tool for treatment planning in NPC.

Deep Learning Radiomics Model of Contrast-Enhanced CT for Differentiating the Primary Source of Liver Metastases

RATIONALE AND OBJECTIVES

To develop and validate a deep learning radiomics (DLR) model based on contrast-enhanced computed tomography (CT) to identify the primary source of liver metastases.

MATERIALS AND METHODS

In total, 657 liver metastatic lesions, including breast cancer (BC), lung cancer (LC), colorectal cancer (CRC), gastric cancer (GC), and pancreatic cancer (PC), from 428 patients were collected at three clinical centers from January 2018 to October 2023 series. The lesions were randomly assigned to the training and validation sets in a 7:3 ratio. An additional 112 lesions from 61 patients at another clinical center served as an external test set. A DLR model based on contrast-enhanced CT of the liver was developed to distinguish the five pathological types of liver metastases. Stepwise classification was performed to improve the classification efficiency of the model. Lesions were first classified as digestive tract cancer (DTC) and non-digestive tract cancer (non-DTC). DTCs were divided into CRC, GC, and PC and non-DTCs were divided into LC and BC. To verify the feasibility of the DLR model, we trained classical machine learning (ML) models as comparison models. Model performance was evaluated using accuracy (ACC) and area under the receiver operating characteristic curve (AUC).

RESULTS

The classification model constructed by the DLR algorithm showed excellent performance in the classification task compared to ML models. Among the five categories task, highest ACC and average AUC were achieved at 0.563 and 0.796 in the validation set, respectively. In the DTC and non-DTC and the LC and BC classification tasks, AUC was achieved at 0.907 and 0.809 and ACC was achieved at 0.843 and 0.772, respectively. In the CRC, GC, and PC classification task, ACC and average AUC were the highest, at 0.714 and 0.811, respectively.

CONCLUSION

The DLR model is an effective method for identifying the primary source of liver metastases.

The value of machine learning based on CT radiomics in the preoperative identification of peripheral nerve invasion in colorectal cancer: a two-center study

BACKGROUND

We aimed to explore the application value of various machine learning (ML) algorithms based on multicenter CT radiomics in identifying peripheral nerve invasion (PNI) of colorectal cancer (CRC).

METHODS

A total of 268 patients with colorectal cancer who underwent CT examination in two hospitals from January 2016 to December 2022 were considered. Imaging and clinicopathological data were collected through the Picture Archiving and Communication System (PACS). The Feature Explorer software (FAE) was used to identify the peripheral nerve invasion of colorectal patients in center 1, and the best feature selection and classification channels were selected. Finally, the best feature selection and classifier pipeline were verified in center 2.

RESULTS

The six-feature models using RFE feature selection and GP classifier had the highest AUC values, which were 0.610, 0.699, and 0.640, respectively. FAE generated a more concise model based on one feature (wavelet-HLL-glszm-LargeAreaHighGrayLevelEmphasis) and achieved AUC values of 0.614 and 0.663 on the validation and test sets, respectively, using the "one standard error" rule. Using ANOVA feature selection, the GP classifier had the best AUC value in a one-feature model, with AUC values of 0.611, 0.663, and 0.643 on the validation, internal test, and external test sets, respectively. Similarly, when using the "one standard error" rule, the model based on one feature (wave-let-HLL-glszm-LargeAreaHighGrayLevelEmphasis) achieved AUC values of 0.614 and 0.663 on the validation and test sets, respectively.

CONCLUSIONS

Combining artificial intelligence and radiomics features is a promising approach for identifying peripheral nerve invasion in colorectal cancer. This innovative technique holds significant potential for clinical medicine, offering broader application prospects in the field.

CRITICAL RELEVANCE STATEMENT

The multi-channel ML method based on CT radiomics has a simple operation process and can be used to assist in the clinical screening of patients with CRC accompanied by PNI.

KEY POINTS

• Multi-channel ML in the identification of peripheral nerve invasion in CRC. • Multi-channel ML method based on CT-radiomics can detect the PNI of CRC. • Early preoperative identification of PNI in CRC is helpful to improve the formulation of treatment strategies and the prognosis of patients.

Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer

Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies. Results Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology. Conclusion Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue.

Radiomics in Musculoskeletal Tumors

Sarcomas are heterogeneous rare tumors predominantly affecting the musculoskeletal (MSK) system. Due to significant variations in their natural history and variable response to conventional treatments, the discovery of novel diagnostic and prognostic biomarkers to guide therapeutic decision-making is an active and ongoing field of research. As new cellular, molecular, and metabolic biomarkers continue to be discovered, quantitative radiologic imaging is becoming increasingly important in sarcoma management. Radiomics offers the potential for discovering novel imaging diagnostic and predictive biomarkers using standard-of-care medical imaging. In this review, we detail the core concepts of radiomics and the application of radiomics to date in MSK sarcoma research. Also described are specific challenges related to radiomic studies, as well as viewpoints on clinical adoption and future perspectives in the field.

Bronchiolar adenoma/ciliated muconodular papillary tumour: advancing clinical, pathological, and imaging insights for future perspectives

Bronchiolar adenoma/ciliated muconodular papillary tumour (BA/CMPT) is a benign peripheral lung tumour composed of bilayered bronchiolar-type epithelium containing a continuous basal cell layer; however, the similarities in imaging and tissue biopsy findings at histopathology between BA/CMPT and malignant tumours, including lung adenocarcinoma, pose significant challenges in accurately diagnosing BA/CMPT preoperatively. This difficulty in differentiation often results in misdiagnosis and unnecessary overtreatment. The objective of this article is to provide a comprehensive and systematic review of BA/CMPT, encompassing its clinical manifestations, pathological basis, imaging features, and differential diagnosis. By enhancing healthcare professionals' understanding of this disease, we aim to improve the accuracy of preoperative BA/CMPT diagnosis. This improvement is crucial for the development of appropriate therapeutic strategies and the overall improvement of patient prognosis.

Computed tomography radiomics identification of T1-2 and T3-4 stages of esophageal squamous cell carcinoma: two-dimensional or three-dimensional?

BACKGROUND

To evaluate two-dimensional (2D) and three-dimensional (3D) computed tomography (CT) radiomics analysis for the T stage of esophageal squamous cell carcinoma (ESCC).

METHODS

398 patients with pathologically confirmed ESCC were divided into training and testing sets. All patients underwent chest CT scans preoperatively. For each tumor, based on CT images, a 2D region of interest (ROI) was outlined on the largest cross-sectional area, and a 3D ROI was outlined layer by layer on each section of the tumor. The radiomics platform was used for feature extraction. For feature selection, stepwise logistic regression was used. The receiver operating characteristic (ROC) curve was used to assess the diagnostic performance of the 2D radiomics model versus the 3D radiomics model. The differences were compared using the DeLong test. The value of the clinical utility of the two radiomics models was evaluated.

RESULTS

1595 radiomics features were extracted. After screening, two radiomics models were constructed. In the training set, the difference between the area under the curve (AUC) of the 2D radiomics model (AUC = 0.831) and the 3D radiomics model (AUC = 0.830) was not statistically significant (p = 0.973). In the testing set, the difference between the AUC of the 2D radiomics model (AUC = 0.807) and the 3D radiomics model (AUC = 0.797) was also not statistically significant (p = 0.748). A 2D model was equally useful as a 3D model in clinical situations.

CONCLUSION

The performance of 2D radiomics model is comparable to that of 3D radiomics model in distinguishing between the T1-2 and T3-4 stages of ESCC. In addition, 2D radiomics model may be a more feasible option due to the shorter time required for segmenting the ROI.

Evaluating the Effectiveness of 2D and 3D CT Image Features for Predicting Tumor Response to Chemotherapy

Background and Objective: 2D and 3D tumor features are widely used in a variety of medical image analysis tasks. However, for chemotherapy response prediction, the effectiveness between different kinds of 2D and 3D features are not comprehensively assessed, especially in ovarian-cancer-related applications. This investigation aims to accomplish such a comprehensive evaluation. Methods: For this purpose, CT images were collected retrospectively from 188 advanced-stage ovarian cancer patients. All the metastatic tumors that occurred in each patient were segmented and then processed by a set of six filters. Next, three categories of features, namely geometric, density, and texture features, were calculated from both the filtered results and the original segmented tumors, generating a total of 1403 and 1595 features for the 2D and 3D tumors, respectively. In addition to the conventional single-slice 2D and full-volume 3D tumor features, we also computed the incomplete-3D tumor features, which were achieved by sequentially adding one individual CT slice and calculating the corresponding features. Support vector machine (SVM)-based prediction models were developed and optimized for each feature set. Five-fold cross-validation was used to assess the performance of each individual model. Results: The results show that the 2D feature-based model achieved an AUC (area under the ROC curve (receiver operating characteristic)) of 0.84 ± 0.02. When adding more slices, the AUC first increased to reach the maximum and then gradually decreased to 0.86 ± 0.02. The maximum AUC was yielded when adding two adjacent slices, with a value of 0.91 ± 0.01. Conclusions: This initial result provides meaningful information for optimizing machine learning-based decision-making support tools in the future.

Radiomics under 2D regions, 3D regions, and peritumoral regions reveal tumor heterogeneity in non-small cell lung cancer: a multicenter study

PURPOSE

Lung cancer has significant genetic and phenotypic heterogeneity, leading to poor prognosis. Radiomic features have emerged as promising predictors of the tumor phenotype. However, the role of underlying information surrounding the cancer remains unclear.

MATERIALS AND METHODS

We conducted a retrospective study of 508 patients with NSCLC from three institutions. Radiomics models were built using features from six tumor regions and seven classifiers to predict three prognostically significant tumor phenotypes. The models were evaluated and interpreted by the mean area under the receiver operating characteristic curve (AUC) under nested cross-validation and Shapley values. The best-performing predictive models corresponding to six tumor regions and three tumor phenotypes were identified for further comparative analysis. In addition, we designed five experiments with different voxel spacing to assess the sensitivity of the experimental results to the spatial resolution of the voxels.

RESULTS

Our results demonstrated that models based on 2D, 3D, and peritumoral region features yielded mean AUCs and 95% confidence intervals of 0.759 and [0.747-0.771] for lymphovascular invasion, 0.889 and [0.882-0.896] for pleural invasion, and 0.839 and [0.829-0.849] for T-staging in the testing cohort, which was significantly higher than all other models. Similar results were obtained for the model combining the three regional features at five voxel spacings.

CONCLUSION

Our study revealed the predictive role of the developed methods with multi-regional features for the preoperative assessment of prognostic factors in NSCLC. The analysis of different voxel spacing and model interpretability strengthens the experimental findings and contributes to understanding the biological significance of the radiological phenotype.

Radiomic Analysis of Intrahepatic Cholangiocarcinoma: Non-Invasive Prediction of Pathology Data: A Multicenter Study to Develop a Clinical-Radiomic Model

Standard imaging cannot assess the pathology details of intrahepatic cholangiocarcinoma (ICC). We investigated whether CT-based radiomics may improve the prediction of tumor characteristics. All consecutive patients undergoing liver resection for ICC (2009-2019) in six high-volume centers were evaluated for inclusion. On the preoperative CT, we segmented the ICC (Tumor-VOI, i.e., volume-of-interest) and a 5-mm parenchyma rim around the tumor (Margin-VOI). We considered two types of pathology data: tumor grading (G) and microvascular invasion (MVI). The predictive models were internally validated. Overall, 244 patients were analyzed: 82 (34%) had G3 tumors and 139 (57%) had MVI. For G3 prediction, the clinical model had an AUC = 0.69 and an Accuracy = 0.68 at internal cross-validation. The addition of radiomic features extracted from the portal phase of CT improved the model performance (Clinical data+Tumor-VOI: AUC = 0.73/Accuracy = 0.72; +Tumor-/Margin-VOI: AUC = 0.77/Accuracy = 0.77). Also for MVI prediction, the addition of portal phase radiomics improved the model performance (Clinical data: AUC = 0.75/Accuracy = 0.70; +Tumor-VOI: AUC = 0.82/Accuracy = 0.73; +Tumor-/Margin-VOI: AUC = 0.82/Accuracy = 0.75). The permutation tests confirmed that a combined clinical-radiomic model outperforms a purely clinical one (p < 0.05). The addition of the textural features extracted from the arterial phase had no impact. In conclusion, the radiomic features of the tumor and peritumoral tissue extracted from the portal phase of preoperative CT improve the prediction of ICC grading and MVI.

Delta-radiomics models based on multi-phase contrast-enhanced magnetic resonance imaging can preoperatively predict glypican-3-positive hepatocellular carcinoma

Objectives: The aim of this study is to investigate the value of multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) based on the delta radiomics model for identifying glypican-3 (GPC3)-positive hepatocellular carcinoma (HCC). Methods: One hundred and twenty-six patients with pathologically confirmed HCC (training cohort: n = 88 and validation cohort: n = 38) were retrospectively recruited. Basic information was obtained from medical records. Preoperative multi-phase CE-MRI images were reviewed, and the 3D volumes of interest (VOIs) of the whole tumor were delineated on non-contrast T1-weighted imaging (T1), arterial phase (AP), portal venous phase (PVP), delayed phase (DP), and hepatobiliary phase (HBP). One hundred and seven original radiomics features were extracted from each phase, and delta-radiomics features were calculated. After a two-step feature selection strategy, radiomics models were built using two classification algorithms. A nomogram was constructed by combining the best radiomics model and clinical risk factors. Results: Serum alpha-fetoprotein (AFP) (p = 0.013) was significantly related to GPC3-positive HCC. The optimal radiomics model is composed of eight delta-radiomics features with the AUC of 0.805 and 0.857 in the training and validation cohorts, respectively. The nomogram integrated the radiomics score, and AFP performed excellently (training cohort: AUC = 0.844 and validation cohort: AUC = 0.862). The calibration curve showed good agreement between the nomogram-predicted probabilities and GPC3 actual expression in both training and validation cohorts. Decision curve analysis further demonstrates the clinical practicality of the nomogram. Conclusion: Multi-phase CE-MRI based on the delta-radiomics model can non-invasively predict GPC3-positive HCC and can be a useful method for individualized diagnosis and treatment.

Contrast-Enhanced Imaging in the Management of Intrahepatic Cholangiocarcinoma: State of Art and Future Perspectives

Intrahepatic cholangiocarcinoma (iCCA) represents the second most common liver cancer after hepatocellular carcinoma, accounting for 15% of primary liver neoplasms. Its incidence and mortality rate have been rising during the last years, and total new cases are expected to increase up to 10-fold during the next two or three decades. Considering iCCA's poor prognosis and rapid spread, early diagnosis is still a crucial issue and can be very challenging due to the heterogeneity of tumor presentation at imaging exams and the need to assess a correct differential diagnosis with other liver lesions. Abdominal contrast-enhanced computed tomography (CT) and magnetic resonance imaging (MRI) plays an irreplaceable role in the evaluation of liver masses. iCCA's most typical imaging patterns are well-described, but atypical features are not uncommon at both CT and MRI; on the other hand, contrast-enhanced ultrasound (CEUS) has shown a great diagnostic value, with the interesting advantage of lower costs and no renal toxicity, but there is still no agreement regarding the most accurate contrastographic patterns for iCCA detection. Besides diagnostic accuracy, all these imaging techniques play a pivotal role in the choice of the therapeutic approach and eligibility for surgery, and there is an increasing interest in the specific imaging features which can predict tumor behavior or histologic subtypes. Further prognostic information may also be provided by the extraction of quantitative data through radiomic analysis, creating prognostic multi-parametric models, including clinical and serological parameters. In this review, we aim to summarize the role of contrast-enhanced imaging in the diagnosis and management of iCCA, from the actual issues in the differential diagnosis of liver masses to the newest prognostic implications.

Development and Validation of CT-Based Radiomics Signature for Overall Survival Prediction in Multi-organ Cancer

The malignant tumors in nature share some common morphological characteristics. Radiomics is not only images but also data; we think that a probability exists in a set of radiomics signatures extracted from CT scan images of one cancer tumor in one specific organ also be utilized for overall survival prediction in different types of cancers in different organs. The retrospective study enrolled four data sets of cancer patients in three different organs (420, 157, 137, and 191 patients for lung 1 training, lung 2 testing, and two external validation set: kidney and head and neck, respectively). In the training set, radiomics features were obtained from CT scan images, and essential features were chosen by LASSO algorithm. Univariable and multivariable analyses were then conducted to find a radiomics signature via Cox proportional hazard regression. The Kaplan-Meier curve was performed based on the risk score. The integrated time-dependent area under the ROC curve (iAUC) was calculated for each predictive model. In the training set, Kaplan-Meier curve classified patients as high or low-risk groups (p-value < 0.001; log-rank test). The risk score of radiomics signature was locked and independently evaluated in the testing set, and two external validation sets showed significant differences (p-value < 0.05; log-rank test). A combined model (radiomics + clinical) showed improved iAUC in lung 1, lung 2, head and neck, and kidney data set are 0.621 (95% CI 0.588, 0.654), 0.736 (95% CI 0.654, 0.819), 0.732 (95% CI 0.655, 0.809), and 0.834 (95% CI 0.722, 0.946), respectively. We believe that CT-based radiomics signatures for predicting overall survival in various cancer sites may exist.

Artificial intelligence-driven radiomics study in cancer: the role of feature engineering and modeling

Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients' anatomy. However, the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians. Moreover, some potentially useful quantitative information in medical images, especially that which is not visible to the naked eye, is often ignored during clinical practice. In contrast, radiomics performs high-throughput feature extraction from medical images, which enables quantitative analysis of medical images and prediction of various clinical endpoints. Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis, demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine. However, radiomics remains in a developmental phase as numerous technical challenges have yet to be solved, especially in feature engineering and statistical modeling. In this review, we introduce the current utility of radiomics by summarizing research on its application in the diagnosis, prognosis, and prediction of treatment responses in patients with cancer. We focus on machine learning approaches, for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling. Furthermore, we introduce the stability, reproducibility, and interpretability of features, and the generalizability and interpretability of models. Finally, we offer possible solutions to current challenges in radiomics research.

Predicting prostate cancer in men with PSA levels of 4-10 ng/mL: MRI-based radiomics can help junior radiologists improve the diagnostic performance

To develop MRI-based radiomics model for predicting prostate cancer (PCa) in men with prostate-specific antigen (PSA) levels of 4-10 ng/mL, to compare the performance of radiomics model and PI-RADS v2.1, and to further verify the predictive ability of radiomics model for lesions with different PI-RADS v2.1 score. 171 patients with PSA levels of 4-10 ng/mL were divided into training (n = 119) and testing (n = 52) groups. PI-RADS v2.1 score was assessed by two radiologists. All volumes of interest were segmented on T₂-weighted imaging, diffusion weighted imaging, and apparent diffusion coefficient sequences, from which quantitative radiomics features were extracted. Multivariate logistic regression analysis was performed to establish radiomics model for predicting PCa. The diagnostic performance was assessed using receiver operating characteristic curve analysis. The radiomics model exhibited the best performance in predicting PCa, which was better than the performance of PI-RADS v2.1 scoring by the junior radiologist in the training group [area under the curve (AUC): 0.932 vs 0.803], testing group (AUC: 0.922 vs 0.797), and the entire cohort (AUC: 0.927 vs 0.801) (P < 0.05). The radiomics model performed well for lesions with PI-RADS v2.1 score of 3 (AUC = 0.854, sensitivity = 84.62%, specificity = 84.34%) and PI-RADS v2.1 score of 4-5 (AUC = 0.967, sensitivity = 98.11%, specificity = 86.36%) assigned by junior radiologist. The radiomics model quantitatively outperformed PI-RADS v2.1 for noninvasive prediction of PCa in men with PSA levels of 4-10 ng/mL. The model can help improve the diagnostic performance of junior radiologists and facilitate better decision-making by urologists for management of lesions with different PI-RADS v2.1 score.

Radiomics Analysis of Multiphasic Computed Tomography Images for Distinguishing High-Risk Thymic Epithelial Tumors From Low-Risk Thymic Epithelial Tumors

OBJECTIVES

The objective of this study is to preoperatively investigate the value of multiphasic contrast-enhanced computed tomography (CT)-based radiomics signatures for distinguishing high-risk thymic epithelial tumors (HTET) from low-risk thymic epithelial tumors (LTET) compared with conventional CT signatures.

MATERIALS AND METHODS

Pathologically confirmed 305 thymic epithelial tumors (TETs), including 147 LTET (Type A/AB/B1) and 158 HTET (Type B2/B3/C), were retrospectively analyzed, and were randomly divided into training (n = 214) and validation cohorts (n = 91). All patients underwent nonenhanced, arterial contrast-enhanced, and venous contrast-enhanced CT analysis. The least absolute shrinkage and selection operator regression with 10-fold cross-validation was performed for radiomic models building, and multivariate logistic regression analysis was performed for radiological and combined models building. The performance of the model was evaluated by the area under the receiver operating characteristic curve (AUC of ROC), and the AUCs were compared using the Delong test. Decision curve analysis was used to evaluate the clinical value of each model. Nomogram and calibration curves were plotted for the combined model.

RESULTS

The AUCs for radiological model in the training and validation cohorts were 0.756 and 0.733, respectively. For nonenhanced, arterial contrast-enhanced, venous contrast-enhanced CT and 3-phase images combined radiomics models, the AUCs were 0.940, 0.946, 0.960, and 0.986, respectively, in the training cohort, whereas 0.859, 0.876, 0.930, and 0.923, respectively, in the validation cohort. The combined model, including CT morphology and radiomics signature, showed AUCs of 0.990 and 0.943 in the training and validation cohorts, respectively. Delong test and decision curve analysis showed that the predictive performance and clinical value of the 4 radiomics models and combined model were greater than the radiological model ( P < 0.05).

CONCLUSIONS

The combined model, including CT morphology and radiomics signature, greatly improved the predictive performance for distinguishing HTET from LTET. Radiomics texture analysis can be used as a noninvasive method for preoperative prediction of the pathological subtypes of TET.

T2-weighted MRI radiomics in high-grade intramedullary osteosarcoma: predictive accuracy in assessing histologic response to chemotherapy, overall survival, and disease-free survival

OBJECTIVE

To analyze radiomic features obtained from pre-treatment T2-weighted MRI acquisitions in patients with histologically proven intramedullary high-grade osteosarcomas and assess the accuracy of radiomic modelling as predictive biomarker of tumor necrosis following neoadjuvant chemotherapy (NAC), overall survival (OS), and disease-free survival (DFS).

MATERIALS AND METHODS

Pre-treatment MRI exams in 105 consecutive patients who underwent NAC and resection of high-grade intramedullary osteosarcoma were evaluated. Histologic necrosis following NAC, and clinical outcome-survival data was collected for each case. Radiomic features were extracted from segmentations performed by two readers, with poorly reproducible features excluded from further analysis. Cox proportional hazard model and Spearman correlation with multivariable modelling were used for assessing relationships of radiomics features with OS, DFS, and histologic tumor necrosis.

RESULTS

Study included 74 males, 31 females (mean 32.5yrs, range 15-77 years). Histologic assessment of tumor necrosis following NAC was available in 104 cases, with good response (≥ 90% necrosis) in 41, and poor response in 63. Fifty-three of 105 patients were alive at follow-up (median 40 months, range: 2-213 months). Median OS was 89 months. Excluding 14 patients with metastases at presentation, median DFS was 19 months. Eleven radiomics features were employed in final radiomics model predicting histologic tumor necrosis (mean AUC 0.708 ± 0.046). Thirteen radiomic features were used in model predicting OS (mean concordance index 0.741 ± 0.011), and 12 features retained in predicting DFS (mean concordance index 0.745 ± 0.010).

CONCLUSIONS

T2-weighted MRI radiomic models demonstrate promising results as potential prognostic biomarkers of prospective tumor response to neoadjuvant chemotherapy and prediction of clinical outcomes in conventional osteosarcoma.

Personalized intrahepatic cholangiocarcinoma prognosis prediction using radiomics: Application and development trend

Radiomics was proposed by Lambin et al. in 2012 and since then there has been an explosion of related research. There has been significant interest in developing high-throughput methods that can automatically extract a large number of quantitative image features from medical images for better diagnostic or predictive performance. There have also been numerous radiomics investigations on intrahepatic cholangiocarcinoma in recent years, but no pertinent review materials are readily available. This work discusses the modeling analysis of radiomics for the prediction of lymph node metastasis, microvascular invasion, and early recurrence of intrahepatic cholangiocarcinoma, as well as the use of deep learning. This paper briefly reviews the current status of radiomics research to provide a reference for future studies.

A radiomics nomogram analysis based on CT images and clinical features for preoperative Lauren classification in gastric cancer

PURPOSE

To develop a combined radiomics nomogram based on computed tomography (CT) images and clinical features to preoperatively distinguish Lauren's diffuse-type gastric cancer (GC) from intestinal-type GC.

METHODS

Ninety-five patients with Lauren's intestinal or diffuse-type GC confirmed by postoperative pathology had their preoperative clinical information and dynamic contrast CT images retrospectively analyzed and were subdivided into training and test groups in a 7:3 ratio. To select the optimal features and construct the radiomic signatures, we extracted, filtered, and minimized the radiomic features from arterial phase (AP) and venous phase (VP) CT images. We constructed four models (clinical model, AP radiomics model, VP radiomics model, and radiomics-clinical model) to assess and compare their predictive performance between the intestinal- and diffuse-type GC. Receiver-operating characteristic (ROC) curve, area under the ROC curve (AUC), and the DeLong test were used for assessment and comparison. In this study, radiomic nomograms integrating combined radiomic signatures and clinical characteristics were developed.

RESULTS

Compared to the AP radiomics model, the VP radiomics model had better performance, with an AUC of 0.832 (95% confidence interval [CI], 0.735, 0.929) in the training cohort and 0.760 (95% CI 0.580, 0.940) in the test cohort. Among the combined models that assessed Lauren's type GC, the model including age and VP radiomics showed the best performance, with an AUC of 0.849 (95% CI 0.758, 0.940) in the training cohort and 0.793 (95% CI 0.629, 0.957) in the test cohort.

CONCLUSIONS

Nomogram incorporating radiomic signatures and clinical features effectively differentiated Lauren's diffuse-type from intestinal-type GC.

Computed tomography-based radiomics nomogram for the preoperative prediction of perineural invasion in colorectal cancer: a multicentre study

PURPOSE

To develop and validate a computed tomography (CT) radiomics nomogram from multicentre datasets for preoperative prediction of perineural invasion (PNI) in colorectal cancer.

METHODS

A total of 299 patients with histologically confirmed colorectal cancer from three hospitals were enrolled in this retrospective study. Radiomic features were extracted from the whole tumour volume. The least absolute shrinkage and selection operator logistic regression was applied for feature selection and radiomics signature construction. Finally, a radiomics nomogram combining the radiomics score and clinical predictors was established. The receiver operating characteristic curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the radiomics nomogram in the training cohort, internal validation and external validation cohorts.

RESULTS

Twelve radiomics features extracted from the whole tumour volume were used to construct the radiomics model. The area under the curve (AUC) values of the radiomics model in the training cohort, internal validation cohort, external validation cohort 1, and external validation cohort 2 were 0.82 (0.75-0.90), 0.77 (0.62-0.92), 0.71 (0.56-0.85), and 0.73 (0.60-0.85), respectively. The nomogram, which combined the radiomics score with T category and N category by CT, yielded better performance in the training cohort (AUC = 0.88), internal validation cohort (AUC = 0.80), external validation cohort 1 (AUC = 0.75), and external validation cohort 2 (AUC = 0.76). DCA confirmed the clinical utility of the nomogram.

CONCLUSIONS

The CT-based radiomics nomogram has the potential to accurately predict PNI in patients with colorectal cancer.

Application of computed tomography-based radiomics in differential diagnosis of adenocarcinoma and squamous cell carcinoma at the esophagogastric junction

BACKGROUND

The biological behavior of carcinoma of the esophagogastric junction (CEGJ) is different from that of gastric or esophageal cancer. Differentiating squamous cell carcinoma of the esophagogastric junction (SCCEG) from adenocarcinoma of the esophagogastric junction (AEG) can indicate Siewert stage and whether the surgical route for patients with CEGJ is transthoracic or transabdominal, as well as aid in determining the extent of lymph node dissection. With the development of neoadjuvant therapy, preoperative determination of pathological type can help in the selection of neoadjuvant radiotherapy and chemotherapy regimens.

AIM

To establish and evaluate computed tomography (CT)-based multiscale and multiphase radiomics models to distinguish SCCEG and AEG preoperatively.

METHODS

We retrospectively analyzed the preoperative contrasted-enhanced CT imaging data of single-center patients with pathologically confirmed SCCEG (n = 130) and AEG (n = 130). The data were divided into either a training (n = 182) or a test group (n = 78) at a ratio of 7:3. A total of 1409 radiomics features were separately extracted from two dimensional (2D) or three dimensional (3D) regions of interest in arterial and venous phases. Intra-/inter-observer consistency analysis, correlation analysis, univariate analysis, least absolute shrinkage and selection operator regression, and backward stepwise logical regression were applied for feature selection. Totally, six logistic regression models were established based on 2D and 3D multi-phase features. The receiver operating characteristic curve analysis, the continuous net reclassification improvement (NRI), and the integrated discrimination improvement (IDI) were used for assessing model discrimination performance. Calibration and decision curves were used to assess the calibration and clinical usefulness of the model, respectively.

RESULTS

The 2D-venous model (5 features, AUC: 0.849) performed better than 2D-arterial (5 features, AUC: 0.808). The 2D-arterial-venous combined model could further enhance the performance (AUC: 0.869). The 3D-venous model (7 features, AUC: 0.877) performed better than 3D-arterial (10 features, AUC: 0.876). And the 3D-arterial-venous combined model (AUC: 0.904) outperformed other single-phase-based models. The venous model showed a positive improvement compared with the arterial model (NRI > 0, IDI > 0), and the 3D-venous and combined models showed a significant positive improvement compared with the 2D-venous and combined models (P < 0.05). Decision curve analysis showed that combined 3D-arterial-venous model and 3D-venous model had a higher net clinical benefit within the same threshold probability range in the test group.

CONCLUSION

The combined arterial-venous CT radiomics model based on 3D segmentation can improve the performance in differentiating EGJ squamous cell carcinoma from adenocarcinoma.

An updated systematic review of radiomics in osteosarcoma: utilizing CLAIM to adapt the increasing trend of deep learning application in radiomics

Objective

To update the systematic review of radiomics in osteosarcoma.

Methods

PubMed, Embase, Web of Science, China National Knowledge Infrastructure, and Wanfang Data were searched to identify articles on osteosarcoma radiomics until May 15, 2022. The studies were assessed by Radiomics Quality Score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement, Checklist for Artificial Intelligence in Medical Imaging (CLAIM), and modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. The evidence supporting radiomics application for osteosarcoma was rated according to meta-analysis results.

Results

Twenty-nine articles were included. The average of the ideal percentage of RQS, the TRIPOD adherence rate and the CLAIM adherence rate were 29.2%, 59.2%, and 63.7%, respectively. RQS identified a radiomics-specific issue of phantom study. TRIPOD addressed deficiency in blindness of assessment. CLAIM and TRIPOD both pointed out shortness in missing data handling and sample size or power calculation. CLAIM identified extra disadvantages in data de-identification and failure analysis. External validation and open science were emphasized by all the above three tools. The risk of bias and applicability concerns were mainly related to the index test. The meta-analysis of radiomics predicting neoadjuvant chemotherapy response by MRI presented a diagnostic odds ratio (95% confidence interval) of 28.83 (10.27–80.95) on testing datasets and was rated as weak evidence.

Conclusions

The quality of osteosarcoma radiomics studies is insufficient. More investigation is needed before using radiomics to optimize osteosarcoma treatment. CLAIM is recommended to guide the design and reporting of radiomics research.

GEP-NET radiomics: a systematic review and radiomics quality score assessment

OBJECTIVE

The number of radiomics studies in gastroenteropancreatic neuroendocrine tumours (GEP-NETs) is rapidly increasing. This systematic review aims to provide an overview of the available evidence of radiomics for clinical outcome measures in GEP-NETs, to understand which applications hold the most promise and which areas lack evidence.

METHODS

PubMed, Embase, and Wiley/Cochrane Library databases were searched and a forward and backward reference check of the identified studies was executed. Inclusion criteria were (1) patients with GEP-NETs and (2) radiomics analysis on CT, MRI or PET. Two reviewers independently agreed on eligibility and assessed methodological quality with the radiomics quality score (RQS) and extracted outcome data.

RESULTS

In total, 1364 unique studies were identified and 45 were included for analysis. Most studies focused on GEP-NET grade and differential diagnosis of GEP-NETs from other neoplasms, while only a minority analysed treatment response or long-term outcomes. Several studies were able to predict tumour grade or to differentiate GEP-NETs from other lesions with a good performance (AUCs 0.74-0.96 and AUCs 0.80-0.99, respectively). Only one study developed a model to predict recurrence in pancreas NETs (AUC 0.77). The included studies reached a mean RQS of 18%.

CONCLUSION

Although radiomics for GEP-NETs is still a relatively new area, some promising models have been developed. Future research should focus on developing robust models for clinically relevant aims such as prediction of response or long-term outcome in GEP-NET, since evidence for these aims is still scarce.

KEY POINTS

• The majority of radiomics studies in gastroenteropancreatic neuroendocrine tumours is of low quality. • Most evidence for radiomics is available for the identification of tumour grade or differentiation of gastroenteropancreatic neuroendocrine tumours from other neoplasms. • Radiomics for the prediction of response or long-term outcome in gastroenteropancreatic neuroendocrine tumours warrants further research.

Radiomics of Biliary Tumors: A Systematic Review of Current Evidence

Biliary tumors are rare diseases with major clinical unmet needs. Standard imaging modalities provide neither a conclusive diagnosis nor robust biomarkers to drive treatment planning. In several neoplasms, texture analyses non-invasively unveiled tumor characteristics and aggressiveness. The present manuscript aims to summarize the available evidence about the role of radiomics in the management of biliary tumors. A systematic review was carried out through the most relevant databases. Original, English-language articles published before May 2021 were considered. Three main outcome measures were evaluated: prediction of pathology data; prediction of survival; and differential diagnosis. Twenty-seven studies, including a total of 3605 subjects, were identified. Mass-forming intrahepatic cholangiocarcinoma (ICC) was the subject of most studies (n = 21). Radiomics reliably predicted lymph node metastases (range, AUC = 0.729−0.900, accuracy = 0.69−0.83), tumor grading (AUC = 0.680−0.890, accuracy = 0.70−0.82), and survival (C-index = 0.673−0.889). Textural features allowed for the accurate differentiation of ICC from HCC, mixed HCC-ICC, and inflammatory masses (AUC > 0.800). For all endpoints (pathology/survival/diagnosis), the predictive/prognostic models combining radiomic and clinical data outperformed the standard clinical models. Some limitations must be acknowledged: all studies are retrospective; the analyzed imaging modalities and phases are heterogeneous; the adoption of signatures/scores limits the interpretability and applicability of results. In conclusion, radiomics may play a relevant role in the management of biliary tumors, from diagnosis to treatment planning. It provides new non-invasive biomarkers, which are complementary to the standard clinical biomarkers; however, further studies are needed for their implementation in clinical practice.

Diagnostic Performance of 2D and 3D T2WI-Based Radiomics Features With Machine Learning Algorithms to Distinguish Solid Solitary Pulmonary Lesion

Objective

To evaluate the performance of 2D and 3D radiomics features with different machine learning approaches to classify SPLs based on magnetic resonance(MR) T2 weighted imaging (T2WI).

Material and Methods

A total of 132 patients with pathologically confirmed SPLs were examined and randomly divided into training (n = 92) and test datasets (n = 40). A total of 1692 3D and 1231 2D radiomics features per patient were extracted. Both radiomics features and clinical data were evaluated. A total of 1260 classification models, comprising 3 normalization methods, 2 dimension reduction algorithms, 3 feature selection methods, and 10 classifiers with 7 different feature numbers (confined to 3–9), were compared. The ten-fold cross-validation on the training dataset was applied to choose the candidate final model. The area under the receiver operating characteristic curve (AUC), precision-recall plot, and Matthews Correlation Coefficient were used to evaluate the performance of machine learning approaches.

Results

The 3D features were significantly superior to 2D features, showing much more machine learning combinations with AUC greater than 0.7 in both validation and test groups (129 vs. 11). The feature selection method Analysis of Variance(ANOVA), Recursive Feature Elimination(RFE) and the classifier Logistic Regression(LR), Linear Discriminant Analysis(LDA), Support Vector Machine(SVM), Gaussian Process(GP) had relatively better performance. The best performance of 3D radiomics features in the test dataset (AUC = 0.824, AUC-PR = 0.927, MCC = 0.514) was higher than that of 2D features (AUC = 0.740, AUC-PR = 0.846, MCC = 0.404). The joint 3D and 2D features (AUC=0.813, AUC-PR = 0.926, MCC = 0.563) showed similar results as 3D features. Incorporating clinical features with 3D and 2D radiomics features slightly improved the AUC to 0.836 (AUC-PR = 0.918, MCC = 0.620) and 0.780 (AUC-PR = 0.900, MCC = 0.574), respectively.

Conclusions

After algorithm optimization, 2D feature-based radiomics models yield favorable results in differentiating malignant and benign SPLs, but 3D features are still preferred because of the availability of more machine learning algorithmic combinations with better performance. Feature selection methods ANOVA and RFE, and classifier LR, LDA, SVM and GP are more likely to demonstrate better diagnostic performance for 3D features in the current study.

Prediction of BRCA gene mutation status in epithelial ovarian cancer by radiomics models based on 2D and 3D CT images

Background

The objective of this study is to explore the value of two-dimensional (2D) and three-dimensional (3D) radiomics models based on enhanced computed tomography (CT) images in predicting BRCA gene mutations in patients with epithelial ovarian cancer.

Methods

The clinical and imaging data of 106 patients with ovarian cancer confirmed by surgery and pathology were retrospectively analyzed and genetic testing was performed. Radiomics features extracted from the 2D and 3D regions of interest of the patients’ primary tumor lesions were selected in the training set using the maximum correlation and minimum redundancy method. Then, the best features were selected through Lasso tenfold cross-validation. Feature subsets were employed to establish a radiomics model. The model’s performance was evaluated via area under the receiver operating characteristic curve analysis and its clinical validity was assessed by using the model’s decision curve.

Results

On the validation set, the area under the curve values of the 2D, 3D, and 2D + 3D combined models were 0.78 (0.61–0.96), 0.75 (0.55–0.92), and 0.82 (0.61–0.96), respectively. However, the DeLong test P values between the three pairs of models were all > 0.05. The decision curve analysis showed that the radiomics model had a high net benefit across all high-risk threshold probabilities.

Conclusions

The three radiomics models can predict the BRCA gene mutation in ovarian cancer, and there were no statistically significant differences between the prediction performance of the three models.

Role of noninvasive imaging in the evaluation of intrahepatic cholangiocarcinoma: from diagnosis and prognosis to treatment response

INTRODUCTION

Intrahepatic cholangiocarcinoma is the second most common liver cancer. Desmoplastic stroma may be revealed as distinctive histopathologic findings favoring intrahepatic cholangiocarcinoma. Meanwhile, a range of imaging manifestations is often accompanied with rich desmoplastic stroma in intrahepatic cholangiocarcinoma, which can indicate large bile duct ICC, and a higher level of cancer-associated fibroblasts with poor prognosis and weak treatment response.

AREAS COVERED

We provide a comprehensive review of current state-of-the-art and recent advances in the imaging evaluation for diagnosis, staging, prognosis and treatment response of intrahepatic cholangiocarcinoma. In addition, we discuss precursor lesions, cells of origin, molecular mutation, which would cause the different histological classification. Moreover, histological classification and tumor microenvironment, which are related to the proportion of desmoplastic stroma with many imaging manifestations, would be also discussed.

EXPERT OPINION

The diagnosis, prognosis, treatment response of intrahepatic cholangiocarcinoma may be revealed as the presence and the proportion of desmoplastic stroma with a range of imaging manifestations. With the utility of radiomics and artificial intelligence, imaging is helpful for ICC evaluation. Multicentre, large-scale, prospective studies with external validation are in need to develop comprehensive prediction models based on clinical data, imaging findings, genetic parameters, molecular, metabolic, and immune biomarkers.

Evaluation and optimization of radiomics features stability to respiratory motion in 18 F-FDG 3D PET imaging

PURPOSE

To evaluate the impact of respiratory motion on radiomics features in ¹⁸ F-fluoro-2-deoxy-D-glucose three dimensional positron emission tomography (¹⁸ F-FDG 3D PET) imaging and optimize feature stability by combining preprocessing configurations and aggregation strategies.

METHODS

An in-house developed respiratory motion phantom was imaged in 3D PET scanner under nine respiratory patterns including one reference pattern. In total, 487 radiomics features were extracted for each respiratory pattern. Feature stability to respiratory motion was first evaluated by metrics of coefficient of variation (COV) and relative difference (RD) in a fixed preprocessing configuration. Further, one-way ANOVA and trend analysis were performed to evaluate the impact of preprocessing configuration (voxel size, discretization scheme) and aggregation strategy on feature stability. Finally, an optimization framework was proposed by selected feature-specific configurations with minimum COV value, and the diagnostic performance was validated in stable versus unstable features and fixed versus optimal features by a set of 46 patients with lung disease.

RESULTS

PET radiomics features were sensitive to respiratory motion, only 79/487 (16%) features were identified to be very stable in the fixed configuration. Preprocessing configuration and aggregation strategy had an impact on feature stability. For different voxel size, bin number, bin size and aggregation strategy, 188/487 (39%), 70/487 (15%), 148/487 (30%), and 38/95 (29%) features appeared significant changes in feature stability. The optimized configuration had the potential to improve feature stability compared to fixed configuration, with the COV decreased from 22% ±24% to 16% ±20%. Regarding the diagnostic performance, the stable and optimal configuration features outperformed the unstable and fixed configuration features, respectively (AUC 0.88, 0.87 vs. 0.83, 0.85).

CONCLUSIONS

Respiratory motion shows considerable impact on feature stability in 3D PET imaging, while optimizing preprocessing configuration may improve feature stability and diagnostic performance.

TCGA-TCIA-Based CT Radiomics Study for Noninvasively Predicting Epstein-Barr Virus Status in Gastric Cancer

OBJECTIVE. The purpose of this study was to investigate the value of TCGA-TCIA (The Cancer Genome Atlas and The Cancer Imaging Archive)-based CT radiomics for noninvasive prediction of Epstein-Barr virus (EBV) status in gastric cancer (GC). MATERIALS AND METHODS. A total of 133 patients with pathologically confirmed GC (94 in the training cohort and 39 in the validation cohort) who were identified from the TCGA-TCIA public data repository and two hospitals were retrospectively enrolled in the study. Two-dimensional and 3D radiomics features were extracted to construct corresponding radiomics signatures. Then, 2D and 3D nomograms were built by combining radiomics signatures and clinical information on the basis of multivariable analysis. Their performance and clinical practicability were determined, validated, and compared with respect to discrimination, calibration, reclassification, and time spent on tumor segmentation. RESULTS. Both 2D and 3D nomograms were robust and showed good calibration. The AUCs of the 2D and 3D nomograms showed no significant difference in the training cohort (0.919 vs 0.945, respectively; p = .41) or validation cohort (0.939 vs 0.955, respectively; p = .71). The net reclassification index showed that the 3D nomogram revealed no significant improvement in risk reclassification when compared with the 2D nomogram in the training cohort (net reclassification index, 0.68%; p = .14) and the validation cohort (net reclassification index, 6.06%; p = .08). Of note, the time spent on 3D segmentation (median, 907 seconds) was higher than that spent on 2D segmentation (median, 129 seconds). CONCLUSION. The 2D and 3D radiomics nomograms might have the potential to be used as effective tools for prediction of EBV in GC. When time spent on segmentation is considered, the 2D nomogram is more highly recommended for clinical application.

Are radiomics features universally applicable to different organs?

BACKGROUND

Many studies have successfully identified radiomics features reflecting macroscale tumor features and tumor microenvironment for various organs. There is an increased interest in applying these radiomics features found in a given organ to other organs. Here, we explored whether common radiomics features could be identified over target organs in vastly different environments.

METHODS

Four datasets of three organs were analyzed. One radiomics model was constructed from the training set (lungs, n = 401), and was further evaluated in three independent test sets spanning three organs (lungs, n = 59; kidneys, n = 48; and brains, n = 43). Intensity histograms derived from the whole organ were compared to establish organ-level differences. We constructed a radiomics score based on selected features using training lung data over the tumor region. A total of 143 features were computed for each tumor. We adopted a feature selection approach that favored stable features, which can also capture survival. The radiomics score was applied to three independent test data from lung, kidney, and brain tumors, and whether the score could be used to separate high- and low-risk groups, was evaluated.

RESULTS

Each organ showed a distinct pattern in the histogram and the derived parameters (mean and median) at the organ-level. The radiomics score trained from the lung data of the tumor region included seven features, and the score was only effective in stratifying survival for other lung data, not in other organs such as the kidney and brain. Eliminating the lung-specific feature (2.5 percentile) from the radiomics score led to similar results. There were no common features between training and test sets, but a common category of features (texture category) was identified.

CONCLUSION

Although the possibility of a generally applicable model cannot be excluded, we suggest that radiomics score models for survival were mostly specific for a given organ; applying them to other organs would require careful consideration of organ-specific properties.

A combined radiomics and clinical variables model for prediction of malignancy in T2 hyperintense uterine mesenchymal tumors on MRI

OBJECTIVE

This study aims to develop a machine learning model for prediction of malignancy in T2 hyperintense mesenchymal uterine tumors based on T2-weighted image (T2WI) features and clinical information.

METHODS

This retrospective study included 134 patients with T2 hyperintense uterine mesenchymal tumors (104 patients in training cohort and 30 in testing cohort). A total of 960 radiomics features were initially computed and extracted from each 3D segmented tumor depicting on T2WI. The support vector machine (SVM) classifier was applied to build computer-aided diagnosis (CAD) models by using selected clinical and radiomics features, respectively. Finally, an observer study was conducted by comparing with two radiologists to evaluate the diagnostic performance. The area under the receiver operating characteristic (ROC) curve (AUC) was computed to assess the performance of each model.

RESULTS

Comparing with the T2WI-based radiomics model (AUC: 0.76 ± 0.09) and the clinical model (AUC: 0.79 ± 0.09), the combined model significantly improved the AUC value to 0.91 ± 0.05 (p < 0.05). The clinical-radiomics combined model yielded equivalent or higher performance than two radiologists (AUC: 0.78 vs. 0.91, p = 0.03; 0.90 vs.0.91, p = 0.13). There was a significant difference between the AUC values of two radiologists (p < 0.05).

CONCLUSIONS

It is feasible to predict malignancy risk of T2 hyperintense uterine mesenchymal tumors by combining clinical variables and T2WI-based radiomics features. Machine learning-based classification model may be useful to assist radiologists in decision-making.

KEY POINTS

• Radiomics approach has the potential to distinguish between benign and malignant mesenchymal uterine tumors. • T2WI-based radiomics analysis combined with clinical variables performed well in predicting malignancy risk of T2 hyperintense uterine mesenchymal tumors. • Machine learning-based classification model may be useful to assist radiologists in characterization of a T2 hyperintense uterine mesenchymal tumor.

Multi-marker quantitative radiomics for mass characterization in dedicated breast CT imaging

Purpose

To develop and evaluate the diagnostic performance of an algorithm for multi‐marker radiomic‐based classification of breast masses in dedicated breast computed tomography (bCT) images.

Methods

Over 1000 radiomic descriptors aimed at quantifying mass and border heterogeneity, morphology, and margin sharpness were developed and implemented. These included well‐established texture and shape feature descriptors, which were supplemented with additional approaches for contour irregularity quantification, spicule and lobe detection, characterization of degree of infiltration, and differences in peritumoral compartments. All descriptors were extracted from a training set of 202 bCT masses (133 benign and 69 malignant), and their individual diagnostic performance was investigated in terms of area under the receiver operating characteristics (ROC) curve (AUC) of single‐feature‐based linear discriminant analysis (LDA) classifiers. Subsequently, the most relevant descriptors were selected through a multiple‐step feature selection process (including stability analysis, statistical significance, evaluation of feature interaction, and dimensionality reduction), and used to develop a final LDA radiomic model for classification of benign and malignant masses, which was then tested on an independent test set of 82 cases (45 benign and 37 malignant).

Results

The majority of the individual radiomic descriptors showed, on the training set, an AUC value deriving from a linear decision boundary higher than 0.65, with the lower limit of the associated 95% confidence interval (C.I.) not overlapping with random chance (AUC = 0.5). The final LDA radiomic model resulted in a test set AUC of 0.90 (95% C.I. 0.80–0.96).

Conclusions

The proposed multi‐marker radiomic approach achieved high diagnostic accuracy in bCT mass classification, using a radiomic signature based on different feature types. While future studies with larger datasets are needed to further validate these results, quantitative radiomics applied to bCT shows potential to improve the breast cancer diagnosis pipeline.

A systematic review of radiomics in osteosarcoma: utilizing radiomics quality score as a tool promoting clinical translation

OBJECTIVES

To assess the methodological quality and risk of bias in radiomics studies investigating diagnosis, therapy response, and survival of patients with osteosarcoma.

METHODS

In this systematic review, literatures on radiomics in osteosarcoma were included and assessed for methodological quality through the radiomics quality score (RQS). The risk of bias and concern of application was assessed using the Quality Assessment of Diagnostic Accuracy Studies tool. A meta-analysis of studies focusing on predicting osteosarcoma response to neoadjuvant chemotherapy was performed.

RESULTS

Twelve radiomics studies exploring osteosarcoma were identified, and five were included in meta-analysis. The RQS reached an average of 20.4% (6.92 of 36) with good inter-rater agreement (ICC 0.95, 95% CI 0.85-0.99). Four studies validated results with an internal dataset, none of which used external dataset; one study was prospectively designed, and another one shared part of the dataset. The risk of bias and concern of application were mainly related to index test aspect. The meta-analysis showed a diagnostic odds ratio of 43.68 (95%CI 13.5-141.31) for predicting response to neoadjuvant chemotherapy with high heterogeneity and low methodological quality.

CONCLUSIONS

The overall scientific quality of included studies is insufficient; however, radiomics remains a promising technology for predicting treatment response, which might guide therapeutic decision-making and related to prognosis. Improvements in study design, validation, and open science needs to be made to demonstrate the generalizability of findings and to achieve clinical applications. Widespread application of RQS, pre-trained RQS scoring procedure, and modification of RQS in response to clinical needs are necessary.

KEY POINTS

• Limited radiomics studies were established in osteosarcoma with mean RQS of 20.4%, commonly due to unvalidated results, retrospective study design, and absence of open science. • Meta-analysis of radiomics studies predicting osteosarcoma response to neoadjuvant chemotherapy showed high diagnostic odds ratio 43.68, while high heterogeneity and low methodological quality were the main concerns. • A previously trained data extraction instrument allowed reaching moderate inter-rater agreement in RQS applications, while RQS still needs improvement to become a wide adaptive tool in reviews of radiomics studies, in routine self-check before manuscript submitting and in study design.