Quantifying tumour heterogeneity with CT

The Feasibility of Combining ADC Value With Texture Analysis of T2WI, DWI and CE-T1WI to Preoperatively Predict the Expression Levels of Ki-67 and p53 of Endometrial Carcinoma

PURPOSE

To evaluate the feasibility of apparent diffusion coefficient (ADC) value combined with texture analysis (TA) in preoperatively predicting the expression levels of Ki-67 and p53 in endometrial carcinoma (EC) patients.

METHODS

Clinical, pathological and MRI findings of 110 EC patients were analyzed retrospectively. The expression levels of Ki-67 and p53 in EC tissues were detected by immunohistochemistry. ADC value was calculated, and three-dimensional (3D) texture features were measured on T₂-weighted images (T₂WI), diffusion-weighted images (DWI), and contrast-enhanced T₁-weighted images (CE-T₁WI). The univariate and multivariate logistic regression and cross-validations were used for the selection of texture features. The receiver operating characteristic (ROC) curve was performed to estimate the diagnostic efficiency of prediction model by the area under the curve (AUC) in the training and validation cohorts.

RESULTS

Significant differences of the ADC values were found in predicting Ki-67 and p53 (P=0.039, P=0.007). The AUC of the ADC value in predicting the expression levels of Ki-67 and p53 were 0.698, 0.853 and 0.626, 0.702 in the training and validation cohorts. The AUC of the TA model based on T₂WI, DWI, CE-T₁WI, and ADC value combined with T₂WI + DWI + CE-T₁WI in the training and validation cohorts for predicting the expression of Ki-67 were 0.741, 0.765, 0.733, 0.922 and 0.688, 0.691, 0.651, 0.938, respectively, and for predicting the expression of p53 were 0.763, 0.805, 0.781, 0.901 and 0.796, 0.713, 0.657, 0.922, respectively.

CONCLUSION

ADC values combined with TA are beneficial for predicting the expression levels of Ki-67 and p53 in EC patients before surgery, and they provide higher auxiliary diagnostic values for clinical application.

A review on advances in 18F-FDG PET/CT radiomics standardisation and application in lung disease management

Radiomics analysis quantifies the interpolation of multiple and invisible molecular features present in diagnostic and therapeutic images. Implementation of 18-fluorine-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) radiomics captures various disorders in non-invasive and high-throughput manner. ¹⁸F-FDG PET/CT accurately identifies the metabolic and anatomical changes during cancer progression. Therefore, the application of ¹⁸F-FDG PET/CT in the field of oncology is well established. Clinical application of ¹⁸F-FDG PET/CT radiomics in lung infection and inflammation is also an emerging field. Combination of bioinformatics approaches or textual analysis allows radiomics to extract additional information to predict cell biology at the micro-level. However, radiomics texture analysis is affected by several factors associated with image acquisition and processing. At present, researchers are working on mitigating these interrupters and developing standardised workflow for texture biomarker establishment. This review article focuses on the application of ¹⁸F-FDG PET/CT in detecting lung diseases specifically on cancer, infection and inflammation. An overview of different approaches and challenges encountered on standardisation of ¹⁸F-FDG PET/CT technique has also been highlighted. The review article provides insights about radiomics standardisation and application of ¹⁸F-FDG PET/CT in lung disease management.

Machine intelligence in non-invasive endocrine cancer diagnostics

Artificial intelligence (AI) has illuminated a clear path towards an evolving health-care system replete with enhanced precision and computing capabilities. Medical imaging analysis can be strengthened by machine learning as the multidimensional data generated by imaging naturally lends itself to hierarchical classification. In this Review, we describe the role of machine intelligence in image-based endocrine cancer diagnostics. We first provide a brief overview of AI and consider its intuitive incorporation into the clinical workflow. We then discuss how AI can be applied for the characterization of adrenal, pancreatic, pituitary and thyroid masses in order to support clinicians in their diagnostic interpretations. This Review also puts forth a number of key evaluation criteria for machine learning in medicine that physicians can use in their appraisals of these algorithms. We identify mitigation strategies to address ongoing challenges around data availability and model interpretability in the context of endocrine cancer diagnosis. Finally, we delve into frontiers in systems integration for AI, discussing automated pipelines and evolving computing platforms that leverage distributed, decentralized and quantum techniques.

A Combined-Radiomics Approach of CT Images to Predict Response to Anti-PD-1 Immunotherapy in NSCLC: A Retrospective Multicenter Study

OBJECTIVE

Based on non-contrast-enhanced (NCE)/contrast-enhanced (CE) computed tomography (CT) images, we try to identify a combined-radiomics model and evaluate its predictive capacity regarding response to anti-PD1 immunotherapy of patients with non-small-cell lung cancer (NSCLC).

METHODS

131 patients with NSCLC undergoing anti-PD1 immunotherapy were retrospectively enrolled from 7 institutions. Using largest lesion (LL) and target lesions (TL) approaches, we performed a radiomics analysis based on pretreatment NCE-CT (NCE-radiomics) and CE-CT images (CE-radiomics), respectively. Meanwhile, a combined-radiomics model based on NCE-CT and CE-CT images was constructed. Finally, we developed their corresponding nomograms incorporating clinical factors. ROC was used to evaluate models' predictive performance in the training and testing set, and a DeLong test was employed to compare the differences between different models.

RESULTS

For TL approach, both NCE-radiomics and CE-radiomics performed poorly in predicting response to immunotherapy. For LL approach, NCE-radiomics nomograms and CE-radiomics nomograms incorporating with clinical factor of distant metastasis all showed satisfactory results, reflected by the AUCs in the training (AUC=0.84, 95% CI: 0.75-0.92; AUC=0.77, 95% CI: 0.67-0.87) and test sets (AUC=0.78, 95% CI: 0.64-0.92, AUC=0.73, 95% CI: 0.57-0.88), respectively. Compared with the NCE-radiomics nomograms, the combined-radiomics nomogram showed incremental predictive capacity in the training set (AUC=0.85, 95% CI: 0.77-0.92) and test set (AUC=0.81, 95% CI: 0.67-0.94), respectively, but no statistical difference (P=0.86, P=0.79).

CONCLUSION

Compared with radiomics based on single NCE or CE-CT images, the combined-radiomics model has potential advantages to identify patients with NSCLC most likely to benefit from immunotherapy, and may effectively improve more precise and individualized decision support.

Adrenal Mass Characterization in the Era of Quantitative Imaging: State of the Art

Simple Summary

Non-invasive characterization of adrenal lesions requires a rigorous approach. Although CT is the cornerstone of adrenal lesion characterization, a multimodality multiparametric imaging approach helps improve confidence in adrenal lesion characterization.

Abstract

Detection and characterization of adrenal lesions have evolved during the past two decades. Although the role of imaging in adrenal lesions associated with hormonal secretion is usually straightforward, characterization of non-functioning adrenal lesions may be challenging to confidently identify those that need to be resected. Although many adrenal lesions can be readily diagnosed when they display typical imaging features, the diagnosis may be challenging for atypical lesions. Computed tomography (CT) remains the cornerstone of adrenal imaging, but other morphological or functional modalities can be used in combination to reach a diagnosis and avoid useless biopsy or surgery. Early- and delayed-phase contrast-enhanced CT images are essential for diagnosing lipid-poor adenoma. Ongoing studies are evaluating the capabilities of dual-energy CT to provide valid virtual non-contrast attenuation and iodine density measurements from contrast-enhanced examinations. Adrenal lesions with attenuation values between 10 and 30 Hounsfield units (HU) on unenhanced CT can be characterized by MRI when iodinated contrast material injection cannot be performed. ¹⁸F-FDG PET/CT helps differentiate between atypical benign and malignant adrenal lesions, with the adrenal-to-liver maximum standardized uptake value ratio being the most discriminative variable. Recent studies evaluating the capabilities of radiomics and artificial intelligence have shown encouraging results.

Longitudinal CT Imaging to Explore the Predictive Power of 3D Radiomic Tumour Heterogeneity in Precise Imaging of Mantle Cell Lymphoma (MCL)

The study's primary aim is to evaluate the predictive performance of CT-derived 3D radiomics for MCL risk stratification. The secondary objective is to search for radiomic features associated with sustained remission. Included were 70 patients: 31 MCL patients and 39 control subjects with normal axillary lymph nodes followed over five years. Radiomic analysis of all targets (n = 745) was performed and features selected using the Mann Whitney U test; the discriminative power of identifying "high-risk MCL" was evaluated by receiver operating characteristics (ROC). The four radiomic features, "Uniformity", "Entropy", "Skewness" and "Difference Entropy" showed predictive significance for relapse (p < 0.05)-in contrast to the routine size measurements, which showed no relevant difference. The best prognostication for relapse achieved the feature "Uniformity" (AUC-ROC-curve 0.87; optimal cut-off ≤0.0159 to predict relapse with 87% sensitivity, 65% specificity, 69% accuracy). Several radiomic features, including the parameter "Short Axis," were associated with sustained remission. CT-derived 3D radiomics improves the predictive estimation of MCL patients; in combination with the ability to identify potential radiomic features that are characteristic for sustained remission, it may assist physicians in the clinical management of MCL.

MRI Radiomics in Prostate Cancer: A Reliability Study

BACKGROUND

Radiomics can provide quantitative features from medical imaging that can be correlated to clinical endpoints. The challenges relevant to robustness of radiomics features have been analyzed by many researchers, as it seems to be influenced by acquisition and reconstruction protocols, as well as by the segmentation of the region of interest (ROI). Prostate cancer (PCa) represents a difficult playground for this technique, due to discrepancies in the identification of the cancer lesion and the heterogeneity of the acquisition protocols. The aim of this study was to investigate the reliability of radiomics in PCa magnetic resonance imaging (MRI).

METHODS

A homogeneous cohort of patients with a PSA rise that underwent multiparametric MRI imaging of the prostate before biopsy was tested in this study. All the patients were acquired with the same MRI scanner, with a standardized protocol. The identification and the contouring of the region of interest (ROI) of an MRI suspicious cancer lesion were done by two radiologists with great experience in prostate cancer (>10 years). After the segmentation, the texture features were extracted with LIFEx. Texture features were then tested with intraclass coefficient correlation (ICC) analysis to analyze the reliability of the segmentation.

RESULTS

Forty-four consecutive patients were included in the present analysis. In 26 patients (59.1%), the prostate biopsy confirmed the presence of prostate cancer, which was scored as Gleason 6 in 6 patients (13.6%), Gleason 3 + 4 in 8 patients (18.2%), and Gleason 4 + 3 in 12 patients (27.3%). The reliability analysis conversely showed poor reliability in the majority of the MRI acquisition (61% in T2, 89% in DWI50, 44% in DWI400, and 83% in DWI1,500), with ADC acquisition only showing better reliability (poor reliability in only 33% of the texture features).

CONCLUSIONS

The low ratio of reliability in a monoinstitutional homogeneous cohort represents a significant alarm bell for the application of MRI radiomics in the field of prostate cancer. More work is needed in a clinical setting to further study the potential of MRI radiomics in prostate cancer.

Radiomics as an emerging tool in the management of brain metastases

Brain metastases (BM) are associated with significant morbidity and mortality in patients with advanced cancer. Despite significant advances in surgical, radiation, and systemic therapy in recent years, the median overall survival of patients with BM is less than 1 year. The acquisition of medical images, such as computed tomography (CT) and magnetic resonance imaging (MRI), is critical for the diagnosis and stratification of patients to appropriate treatments. Radiomic analyses have the potential to improve the standard of care for patients with BM by applying artificial intelligence (AI) with already acquired medical images to predict clinical outcomes and direct the personalized care of BM patients. Herein, we outline the existing literature applying radiomics for the clinical management of BM. This includes predicting patient response to radiotherapy and identifying radiation necrosis, performing virtual biopsies to predict tumor mutation status, and determining the cancer of origin in brain tumors identified via imaging. With further development, radiomics has the potential to aid in BM patient stratification while circumventing the need for invasive tissue sampling, particularly for patients not eligible for surgical resection.

OUP accepted manuscript

Background

Materials and Methods

Results

Conclusion

Magnetic resonance imaging-based texture analysis for the prediction of postoperative clinical outcome in uterine cervical cancer

OBJECTIVES

Magnetic resonance imaging (MRI)-based texture analysis (MRTA) is a novel image analysis tool that offers objective information about the spatial arrangement of MRI signal intensity. We aimed to investigate the value of MRTA in predicting the postoperative clinical outcome of patients with uterine cervical cancer.

METHODS

This retrospective study included 115 patients with surgically proven cervical cancer who underwent preoperative pelvic 3T-MRI, and MRTA was performed on T2-weighted images (T2), apparent diffusion coefficient (ADC) maps, and contrast-enhanced T1-weighted images (CE-T1). Filtration histogram-based texture analysis was used to generate six first-order statistical parameters [mean intensity, standard deviation (SD), mean of positive pixels (MPP), entropy, skewness, and kurtosis] at five spatial scaling factors (SSFs, 2-6 mm) as well as from unfiltered images. Cox proportional hazard models and time-dependent receiver operating characteristic analyses were used to evaluate the associations between parameters and recurrence-free survival (RFS).

RESULTS

During a median follow-up of 36 months, tumor recurrence was found in 26 patients (22.6%). Multivariate analysis demonstrated that CE-T1 MPP and T2 kurtosis at SSF3-5, CE-T1 MPP at SSF6, and CE-T1 SD at unfiltered images were independent predictors of RFS (p < 0.05). Regarding the 2-year RFS for CE-T1 MPP and T2 kurtosis at SSF5, and CE-T1 MPP at SSF6, patients with > optimal cutoff values demonstrated significantly worse survival than those with ≤ optimal cutoff values (p < 0.05).

CONCLUSION

Preoperative MRTA may be useful for predicting postoperative outcome in patients with cervical cancer.

Prediction of Pancreatic Neuroendocrine Tumor Grading Risk Based on Quantitative Radiomic Analysis of MR

Background

Pancreatic neuroendocrine tumors (PNETs) grade is very important for treatment strategy of PNETs. The present study aimed to find the quantitative radiomic features for predicting grades of PNETs in MR images.

Materials and Methods

Totally 48 patients but 51 lesions with a pathological tumor grade were subdivided into low grade (G1) group and intermediate grade (G2) group. The ROI was manually segmented slice by slice in 3D-T1 weighted sequence with and without enhancement. Statistical differences of radiomic features between G1 and G2 groups were analyzed using the independent sample t-test. Logistic regression analysis was conducted to find better predictors in distinguishing G1 and G2 groups. Finally, receiver operating characteristic (ROC) was constructed to assess diagnostic performance of each model.

Results

No significant difference between G1 and G2 groups (P > 0.05) in non-enhanced 3D-T1 images was found. Significant differences in the arterial phase analysis between the G1 and the G2 groups appeared as follows: the maximum intensity feature (P = 0.021); the range feature (P = 0.039). Multiple logistic regression analysis based on univariable model showed the maximum intensity feature (P=0.023, OR = 0.621, 95% CI: 0.433-0.858) was an independent predictor of G1 compared with G2 group, and the area under the curve (AUC) was 0.695.

Conclusions

The maximum intensity feature of radiomic features in MR images can help to predict PNETs grade risk.

Assessment of Response to Chemotherapy in Pancreatic Cancer with Liver Metastasis: CT Texture as a Predictive Biomarker

In this paper, we assess changes in CT texture of metastatic liver lesions after treatment with chemotherapy in patients with pancreatic cancer and determine if texture parameters correlate with measured time to progression (TTP). This retrospective study included 110 patients with pancreatic cancer with liver metastasis, and mean, entropy, kurtosis, skewness, mean of positive pixels, and standard deviation (SD) values were extracted during texture analysis. Response assessment was also obtained by using RECIST 1.1, Choi and modified Choi criteria, respectively. The correlation of texture parameters and existing assessment criteria with TTP were evaluated using Kaplan-Meier and Cox regression analyses in the training cohort. Kaplan-Meier curves of the proportion of patients without disease progression were significantly different for several texture parameters, and were better than those for RECIST 1.1-, Choi-, and modified Choi-defined response (p < 0.05 vs. p = 0.398, p = 0.142, and p = 0.536, respectively). Cox regression analysis showed that percentage change in SD was an independent predictor of TTP (p = 0.016) and confirmed in the validation cohort (p = 0.019). In conclusion, CT texture parameters have the potential to become predictive imaging biomarkers for response evaluation in pancreatic cancer with liver metastasis.

Utility of diffusion MRI characteristics of cervical lymph nodes as disease classifier between patients with head and neck squamous cell carcinoma and healthy volunteers

Diffusion MRI characteristics assessed by apparent diffusion coefficient (ADC) histogram analysis in head and neck squamous cell carcinoma (HNSCC) have been reported as helpful in classifying tumours based on diffusion characteristics. There is little reported on HNSCC lymph nodes classification by diffusion characteristics. The aim of this study was to determine whether pretreatment nodal microstructural diffusion MRI characteristics can classify diseased nodes of patients with HNSCC from normal nodes of healthy volunteers. Seventy-nine patients with histologically confirmed HNSCC prior to chemoradiotherapy, and eight healthy volunteers, underwent diffusion-weighted (DW) MRI at a 1.5-T MR scanner. Two radiologists contoured lymph nodes on DW (b = 300 s/m² ) images. ADC, distributed diffusion coefficient (DDC) and alpha (α) values were calculated by monoexponential and stretched exponential models. Histogram analysis metrics of drawn volume were compared between patients and volunteers using a Mann-Whitney test. The classification performance of each metric between the normal and diseased nodes was determined by receiver operating characteristic (ROC) analysis. Intraclass correlation coefficients determined interobserver reproducibility of each metric based on differently drawn ROIs by two radiologists. Sixty cancerous and 40 normal nodes were analysed. ADC histogram analysis revealed significant differences between patients and volunteers (p ≤0.0001 to 0.0046), presenting ADC distributions that were more skewed (1.49 for patients, 1.03 for volunteers; p = 0.0114) and 'peaked' (6.82 for patients, 4.20 for volunteers; p = 0.0021) in patients. Maximum ADC values exhibited the highest area under the curve ([AUC] 0.892). Significant differences were revealed between patients and volunteers for DDC and α value histogram metrics (p ≤0.0001 to 0.0044); the highest AUC were exhibited by maximum DDC (0.772) and the 25th percentile α value (0.761). Interobserver repeatability was excellent for mean ADC (ICC = 0.88) and the 25th percentile α value (ICC = 0.78), but poor for all other metrics. These results suggest that pretreatment microstructural diffusion MRI characteristics in lymph nodes, assessed by ADC and α value histogram analysis, can identify nodal disease.

Success of extracorporeal shock wave lithotripsy based on CT texture analysis

OBJECTIVE

The aims of the study were to evaluate whether computerised tomography texture analysis (CTTA) based on non-contrast computed tomography (NCCT) has predictive value for the success of extracorporeal-shockwave lithotripsy (ESWL) in upper urinary tract stones (UUTS).

METHODS

This study included 156 of 356 patients undergoing ESWL for UUTS sized 0.5-2 cm from 2015 to 2019. Patients with congenital kidney anomalies, radiolucent stones, multiple stones, treated for upper urinary tract stones previously and lower pole stones were excluded from study. The number of ESWL sessions of the patients was as follows: 78 (50%) patients had 1 session, 30 (19.2%) patients had 2 sessions and 48 (30.8%) patients had >2 sessions. First- and second-order CTTA properties of patients' UUTS were evaluated using texture analysis software (LIFEx Software). Other clinical features such as Hounsfield Unit (HU), initial stone size, body-mass index (BMI) and skin to stone distance (SSD) was recorded. The patients were divided into two groups according to ESWL success. Cases with residual stones larger than 4 mm were considered failed cases.

RESULTS

BMI, the standard deviation of HU, SSD, skewness, kurtosis, entropy and all second-order statistics were found to be statistically different between the two groups except for correlation (P < .05). Multivariate analysis showed longer SSD and four new parameters of CTTA (kurtosis, entropy, dissimilarity and energy by the distribution of pixel grey levels in the UUTS) to be significant predictors for unsuccessful ESWL outcomes. SSD and second-order CTTA properties (dissimilarity and energy) had an area under ROC curve of 0.802, 0.850 and 0.824 at a 95% confidence interval. ESWL success rate in all patients was 76.9%.

CONCLUSION

CTTA can help select patients who will undergo ESWL for upper urinary tract stones. Thus, we can reduce treatment costs and ESWL complications by preventing unnecessary ESWL applications.

CT texture analysis as a predictor of favorable response to anti-PD1 monoclonal antibodies in metastatic skin melanoma

PURPOSE

The purpose of this study was to determine whether texture analysis features on pretreatment contrast-enhanced computed tomography (CT) images and their evolution can predict treatment response of metastatic skin melanoma (SM) treated with anti-PD1 monoclonal antibodies.

MATERIALS AND METHODS

Sixty patients (29 men, 31 women; median age, 56 years; age range: 27-91 years) with metastatic SM treated with pembrolizumab (43/60; 72%) or nivolumab (17/60; 28%) were included. Texture analysis of SM metastases was performed on baseline and first post-treatment evaluation CT examinations. Mean gray-level, entropy, kurtosis, skewness, and standard deviation values were derived from the pixel distribution histogram before and after spatial filtration at different anatomic scales, ranging from fine to coarse. Lasso penalized Cox regression analyses were performed to identify independent variables associated with favorable response to treatment.

RESULTS

A total of 127 metastases were analyzed, with a median of two metastases per patient. Skewness at fine texture scale (spatial scale filtration [SSF] = 2; Hazard ratio [HR]: 3.51; 95% CI: 2.08-8.57; P = 0.010), skewness at medium texture scale (SSF = 3; HR: 0.56; 95% CI: 0.11-1.59; P = 0.014), variation of entropy at fine texture scale (SSF = 2; HR: 37.76; 95% CI: 3.48-496.22; P = 0.008) and LDH above the threshold of 248 UI/L (HR: 3.56; 95% CI: 1.78-21.35; P = 0.032] were independent predictors of response to treatment.

CONCLUSION

Pretreatment CT texture analysis-derived tumor skewness and variation of entropy between baseline and first control CT examination may be used as predictors of favorable response to anti-PD1 monoclonal antibodies in patients with metastatic SM.

Multi-level multi-modality (PET and CT) fusion radiomics: prognostic modeling for non-small cell lung carcinoma

We developed multi-modality radiomic models by integrating information extracted from¹⁸F-FDG PET and CT images using feature- and image-level fusions, toward improved prognosis for non-small cell lung carcinoma (NSCLC) patients. Two independent cohorts of NSCLC patients from two institutions (87 and 95 patients) were cycled as training and testing datasets. Fusion approaches were applied at two levels, namely feature- and image-levels. For feature-level fusion, radiomic features were extracted individually from CT and PET images and concatenated. Alternatively, radiomic features extracted separately from CT and PET images were averaged. For image-level fusion, wavelet fusion was utilized and tuned with two parameters, namely CT weight and Wavelet Band Pass Filtering Ratio. Clinical and combined clinical + radiomic models were developed. Gray level discretization was performed at 3 different levels (16, 32 and 64) and 225 radiomics features were extracted. Overall survival (OS) was considered as the endpoint. For feature reduction, correlated (redundant) features were excluded using Spearman's correlation, and best combination of top ten features with highest concordance-indices (via univariate Cox model) were selected in each model for further multivariate Cox model. Moreover, prognostic score's median, obtained from the training cohort, was used intact in the testing cohort as a threshold to classify patients into low- versus high-risk groups, and log-rank test was applied to assess differences between the Kaplan-Meier curves. Overall, while models based on feature-level fusion strategy showed limited superiority over single-modalities, image-level fusion strategy significantly outperformed both single-modality and feature-level fusion strategies. As such, the clinical model (C-index = 0.656) outperformed all models from single-modality and feature-level strategies, but was outperformed by certain models from image-level fusion strategy. Our findings indicated that image-level fusion multi-modality radiomics models outperformed single-modality, feature-level fusion, and clinical models for OS prediction of NSCLC patients.

Response prediction of neoadjuvant chemoradiation therapy in locally advanced rectal cancer using CT-based fractal dimension analysis

OBJECTIVES

There are individual variations in neo-adjuvant chemoradiation therapy (nCRT) in patients with locally advanced rectal cancer (LARC). No reliable modality currently exists that can predict the efficacy of nCRT. The purpose of this study is to assess if CT-based fractal dimension and filtration-histogram texture analysis can predict therapeutic response to nCRT in patients with LARC.

METHODS

In this retrospective study, 215 patients (average age: 57 years (18-87 years)) who received nCRT for LARC between June 2005 and December 2016 and underwent a staging diagnostic portal venous phase CT were identified. The patients were randomly divided into two datasets: a training set (n = 170), and a validation set (n = 45). Tumor heterogeneity was assessed on the CT images using fractal dimension (FD) and filtration-histogram texture analysis. In the training set, the patients with pCR and non-pCR were compared in univariate analysis. Logistic regression analysis was applied to identify the predictive value of efficacy of nCRT and receiver operating characteristic analysis determined optimal cutoff value. Subsequently, the most significant parameter was assessed in the validation set.

RESULTS

Out of the 215 patients evaluated, pCR was reached in 20.9% (n = 45/215) patients. In the training set, 7 out of 37 texture parameters showed significant difference comparing between the pCR and non-pCR groups and logistic multivariable regression analysis incorporating clinical and 7 texture parameters showed that only FD was associated with pCR (p = 0.001). The area under the curve of FD was 0.76. In the validation set, we applied FD for predicting pCR and sensitivity, specificity, and accuracy were 60%, 89%, and 82%, respectively.

CONCLUSION

FD on pretreatment CT is a promising parameter for predicting pCR to nCRT in patients with LARC and could be used to help make treatment decisions.

KEY POINTS

• Fractal dimension analysis on pretreatment CT was associated with response to neo-adjuvant chemoradiation in patients with locally advanced rectal cancer. • Fractal dimension is a promising biomarker for predicting pCR to nCRT and may potentially select patients for individualized therapy.

Radiomics in Oncology: A Practical Guide

Radiomics refers to the extraction of mineable data from medical imaging and has been applied within oncology to improve diagnosis, prognostication, and clinical decision support, with the goal of delivering precision medicine. The authors provide a practical approach for successfully implementing a radiomic workflow from planning and conceptualization through manuscript writing. Applications in oncology typically are either classification tasks that involve computing the probability of a sample belonging to a category, such as benign versus malignant, or prediction of clinical events with a time-to-event analysis, such as overall survival. The radiomic workflow is multidisciplinary, involving radiologists and data and imaging scientists, and follows a stepwise process involving tumor segmentation, image preprocessing, feature extraction, model development, and validation. Images are curated and processed before segmentation, which can be performed on tumors, tumor subregions, or peritumoral zones. Extracted features typically describe the distribution of signal intensities and spatial relationship of pixels within a region of interest. To improve model performance and reduce overfitting, redundant and nonreproducible features are removed. Validation is essential to estimate model performance in new data and can be performed iteratively on samples of the dataset (cross-validation) or on a separate hold-out dataset by using internal or external data. A variety of noncommercial and commercial radiomic software applications can be used. Guidelines and artificial intelligence checklists are useful when planning and writing up radiomic studies. Although interest in the field continues to grow, radiologists should be familiar with potential pitfalls to ensure that meaningful conclusions can be drawn.

Online supplemental material is available for this article.

Published under a CC BY 4.0 license.

Radiomics as a New Frontier of Imaging for Cancer Prognosis: A Narrative Review

The evaluation of the efficacy of different therapies is of paramount importance for the patients and the clinicians in oncology, and it is usually possible by performing imaging investigations that are interpreted, taking in consideration different response evaluation criteria. In the last decade, texture analysis (TA) has been developed in order to help the radiologist to quantify and identify parameters related to tumor heterogeneity, which cannot be appreciated by the naked eye, that can be correlated with different endpoints, including cancer prognosis. The aim of this work is to analyze the impact of texture in the prediction of response and in prognosis stratification in oncology, taking into consideration different pathologies (lung cancer, breast cancer, gastric cancer, hepatic cancer, rectal cancer). Key references were derived from a PubMed query. Hand searching and clinicaltrials.gov were also used. This paper contains a narrative report and a critical discussion of radiomics approaches related to cancer prognosis in different fields of diseases.

Differentiating prostate cancer from benign prostatic hyperplasia using whole-lesion histogram and texture analysis of diffusion- and T2-weighted imaging

Background

To explore the usefulness of analyzing histograms and textures of apparent diffusion coefficient (ADC) maps and T2-weighted (T2W) images to differentiate prostatic cancer (PCa) from benign prostatic hyperplasia (BPH) using histopathology as the reference.

Methods

Ninety patients with PCa and 112 patients with BPH were included in this retrospective study. Differences in whole-lesion histograms and texture parameters of ADC maps and T2W images between PCa and BPH patients were evaluated using the independent samples t-test. The diagnostic performance of ADC maps and T2W images in being able to differentiate PCa from BPH was assessed using receiver operating characteristic (ROC) curves.

Results 

The mean, median, 5^th, and 95^th percentiles of ADC values in images from PCa patients were significantly lower than those from BPH patients (p < 0.05). Significant differences were observed in the means, standard deviations, medians, kurtosis, skewness, and 5^th percentile values of T2W image between PCa and BPH patients (p < 0.05). The ADC_5th showed the largest AUC (0.906) with a sensitivity of 83.3 % and specificity of 89.3 %. The diagnostic performance of the T2W image histogram and texture analysis was moderate and had the largest AUC of 0.634 for T2W_Kurtosis with a sensitivity and specificity of 48.9% and 79.5 %, respectively. The diagnostic performance of the combined ADC_5th & T2W_Kurtosis parameters was also similar to that of the ADC_5th & ADC_{Diff−Variance}.

Conclusions

Histogram and texture parameters derived from the ADC maps and T2W images for entire prostatic lesions could be used as imaging biomarkers to differentiate PCa and BPH biologic characteristics, however, histogram parameters outperformed texture parameters in the diagnostic performance.

Prediction of serosal invasion in gastric cancer: development and validation of multivariate models integrating preoperative clinicopathological features and radiographic findings based on late arterial phase CT images

BACKGROUND

To develop and validate multivariate models integrating endoscopic biopsy, tumor markers, and CT findings based on late arterial phase (LAP) to predict serosal invasion in gastric cancer (GC).

METHODS

The preoperative differentiation degree, tumor markers, CT morphological characteristics, and CT value-related and texture parameters of 154 patients with GC were analyzed retrospectively. Multivariate models based on regression analysis and machine learning algorithms were performed to improve the diagnostic efficacy.

RESULTS

The differentiation degree, carbohydrate antigen (CA) 199, CA724, CA242, and multiple CT findings based on LAP differed significantly between T1-3 and T4 GCs in the primary cohort (all P < 0.05). Multivariate models based on regression analysis and random forest achieved AUCs of 0.849 and 0.865 in the primary cohort, respectively.

CONCLUSION

We developed and validated multivariate models integrating endoscopic biopsy, tumor markers, CT morphological characteristics, and CT value-related and texture parameters to predict serosal invasion in GCs and achieved favorable performance.

Radiomics and Digital Image Texture Analysis in Oncology (Review)

One of the most promising areas of diagnosis and prognosis of diseases is radiomics, a science combining radiology, mathematical modeling, and deep machine learning. The main concept of radiomics is image biomarkers (IBMs), the parameters characterizing various pathological changes and calculated based on the analysis of digital image texture. IBMs are used for quantitative assessment of digital imaging results (CT, MRI, ultrasound, PET). The use of IBMs in the form of “virtual biopsy” is of particular relevance in oncology.

The article provides the basic concepts of radiomics identifying the main stages of obtaining IBMs: data collection and preprocessing, tumor segmentation, data detection and extraction, modeling, statistical processing, and data validation. The authors have analyzed the possibilities of using IBMs in oncology, describing the currently known features and advantages of using radiomics and image texture analysis in the diagnosis and prognosis of cancer. The limitations and problems associated with the use of radiomics data are considered.

Although the novel effective tool for performing virtual biopsy of human tissue is at the development stage, quite a few projects have already been implemented, and medical software packages for radiomics analysis of digital images have been created.

Machine learning model development for quantitative analysis of CT heterogeneity in canine hepatic masses may predict histologic malignancy

Tumor heterogeneity is a well-established marker of biologically aggressive neoplastic processes and is associated with local recurrence and distant metastasis. Quantitative analysis of CT textural features is an indirect measure of tumor heterogeneity and therefore may help predict malignant disease. The purpose of this retrospective, secondary analysis study was to quantitatively evaluate CT heterogeneity in dogs with histologically confirmed liver masses to build a predictive model for malignancy. Forty dogs with liver tumors and corresponding histopathologic evaluation from a previous prospective study were included. Triphasic image acquisition was standardized across dogs and whole liver and liver mass were contoured on each precontrast and delayed postcontrast dataset. First-order and second-order indices were extracted from contoured regions. Univariate analysis identified potentially significant indices that were subsequently used for top-down model construction. Multiple quadratic discriminatory models were constructed and tested, including individual models using both postcontrast and precontrast whole liver or liver mass volumes. The best performing model utilized the CT features voxel volume and uniformity from postcontrast mass contours; this model had an accuracy of 0.90, sensitivity of 0.67, specificity of 1.0, positive predictive value of 1.0, negative predictive value of 0.88, and precision of 1.0. Heterogeneity indices extracted from delayed postcontrast CT hepatic mass contours were more informative about tumor type compared to indices from whole liver contours, or from precontrast hepatic mass and whole liver contours. Results demonstrate that CT radiomic feature analysis may hold clinical utility as a noninvasive method of predicting hepatic malignancy and may influence diagnostic or therapeutic approaches.

Computed tomography radiomic features hold prognostic utility for canine lung tumors: An analytical study

Quantitative analysis of computed tomography (CT) radiomic features is an indirect measure of tumor heterogeneity, which has been associated with prognosis in human lung carcinoma. Canine lung tumors share similar features to human lung tumors and serve as a model in which to investigate the utility of radiomic features in differentiating tumor type and prognostication. The purpose of this study was to correlate first-order radiomic features from canine pulmonary tumors to histopathologic characteristics and outcome. Disease-free survival, overall survival time and tumor-specific survival were calculated as days from the date of CT scan. Sixty-seven tumors from 65 dogs were evaluated. Fifty-six tumors were classified as primary pulmonary adenocarcinomas and 11 were non-adenocarcinomas. All dogs were treated with surgical resection; 14 dogs received adjuvant chemotherapy. Second opinion histopathology in 63 tumors confirmed the histologic diagnosis in all dogs and further characterized 53 adenocarcinomas. The median overall survival time was longer (p = 0.004) for adenocarcinomas (339d) compared to non-adenocarcinomas (55d). There was wide variation in first-order radiomic statistics across tumors. Mean Hounsfield units (HU) ratio (p = 0.042) and median mean HU ratio (p = 0.042) were higher in adenocarcinomas than in non-adenocarcinomas. For dogs with adenocarcinoma, completeness of excision was associated with overall survival (p<0.001) while higher mitotic index (p = 0.007) and histologic score (p = 0.037) were associated with shorter disease-free survival. CT-derived tumor variables prognostic for outcome included volume, maximum axial diameter, and four radiomic features: integral total, integral total mean ratio, total HU, and max mean HU ratio. Tumor volume was also significantly associated with tumor invasion (p = 0.044). Further study of radiomic features in canine lung tumors is warranted as a method to non-invasively interrogate CT images for potential predictive and prognostic utility.

Applying arterial enhancement fraction (AEF) texture features to predict the tumor response in hepatocellular carcinoma (HCC) treated with Transarterial chemoembolization (TACE)

Background

To evaluate the application of Arterial Enhancement Fraction (AEF) texture features in predicting the tumor response in Hepatocellular Carcinoma (HCC) treated with Transarterial Chemoembolization (TACE) by means of texture analysis.

Methods

HCC patients treated with TACE in Shengjing Hospital of China Medical University from June 2018 to December 2019 were retrospectively enrolled in this study. Pre-TACE Contrast Enhanced Computed Tomography (CECT) and imaging follow-up within 6 months were both acquired. The tumor responses were categorized according to the modified RECIST (mRECIST) criteria. Based on the CECT images, Region of Interest (ROI) of HCC lesion was drawn, the AEF calculation and texture analysis upon AEF values in the ROI were performed using CT-Kinetics (C.K., GE Healthcare, China). A total of 32 AEF texture features were extracted and compared between different tumor response groups. Multi-variate logistic regression was performed using certain AEF features to build the differential models to predict the tumor response. The Receiver Operator Characteristic (ROC) analysis was implemented to assess the discriminative performance of these models.

Results

Forty-five patients were finally enrolled in the study. Eight AEF texture features showed significant distinction between Improved and Un-improved patients (p < 0.05). In multi-variate logistic regression, 9 AEF texture features were applied into modeling to predict “Improved” outcome, and 4 AEF texture features were applied into modeling to predict “Un-worsened” outcome. The Area Under Curve (AUC), diagnostic accuracy, sensitivity, and specificity of the two models were 0.941, 0.911, 1.000, 0.826, and 0.824, 0.711, 0.581, 1.000, respectively.

Conclusions

Certain AEF heterogeneous features of HCC could possibly be utilized to predict the tumor response to TACE treatment.

Quantitative CT texture analysis in predicting PD-L1 expression in locally advanced or metastatic NSCLC patients

Purpose

The assessment of Programmed death-ligand 1 (PD-L1) expression has become a game changer in the treatment of patients with advanced non-small cell lung cancer (NSCLC). We aimed to investigate the ability of Radiomics applied to computed tomography (CT) in predicting PD-L1 expression in patients with advanced NSCLC.

Methods

By applying texture analysis, we retrospectively analyzed 72 patients with advanced NSCLC. The datasets were randomly split into a training cohort (2/3) and a validation cohort (1/3). Forty radiomic features were extracted by manually drawing tumor volumes of interest (VOIs) on baseline contrast-enhanced CT. After selecting features on the training cohort, two predictive models were created using binary logistic regression, one for PD-L1 values ≥ 50% and the other for values between 1 and 49%. The two models were analyzed with ROC curves and tested in the validation cohort.

Results

The Radiomic Score (Rad-Score) for PD-L1 values ≥ 50%, which consisted of Skewness and Low Gray-Level Zone Emphasis (GLZLM_LGZE), presented a cut-off value of − 0.745 with an area under the curve (AUC) of 0.811 and 0.789 in the training and validation cohort, respectively. The Rad-Score for PD-L1 values between 1 and 49% consisted of Sphericity, Skewness, Conv_Q3 and Gray Level Non-Uniformity (GLZLM_GLNU), showing a cut-off value of 0.111 with AUC of 0.763 and 0.806 in the two population, respectively.

Conclusion

Rad-Scores obtained from CT texture analysis could be useful for predicting PD-L1 expression and guiding the therapeutic choice in patients with advanced NSCLC.

Quantitative Histogram Analysis of T2-Weighted and Diffusion-Weighted Magnetic Resonance Images for Prediction of Malignant Thymic Epithelial Tumors

PURPOSE

To assess the value of histogram analysis for differentiating a high-risk thymic epithelial tumor (TET) from a low-risk TET using T2-weighted images and the apparent diffusion coefficient (ADC).

METHODS

Forty-nine patients with histopathologically proven TET after thymectomy were enrolled in this study and retrospectively classified as having low-risk TET (low-risk thymoma) or high-risk TET (high-risk thymoma or thymic carcinoma). Twelve parameters were obtained from the quantitative histogram analysis. The histogram parameters were compared using the Mann-Whitney U test. Diagnostic efficacy was estimated by receiver-operating characteristic curve analysis.

RESULTS

Twenty-five patients were classified as having low-risk TET and 24 as having high-risk TET. The mean ADC value showed diagnostic efficacy for differentiating high-risk TET from low-risk TET, with an area under the curve of 0.7, and was better than when using conventional methods alone.

CONCLUSION

The ADC-based histogram analysis could help to differentiate between high-risk and low-risk TETs.

Multiblock Discriminant Analysis of Integrative 18F-FDG-PET/CT Radiomics for Predicting Circulating Tumor Cells in Early-Stage Non-small Cell Lung Cancer Treated With Stereotactic Body Radiation Therapy

PURPOSE

The main objective of the present study was to integrate 18F-FDG-PET/CT radiomics with multiblock discriminant analysis for predicting circulating tumor cells (CTCs) in early-stage non-small cell lung cancer (ES-NSCLC) treated with stereotactic body radiation therapy (SBRT).

METHODS

Fifty-six patients with stage I NSCLC treated with SBRT underwent 18F-FDG-PET/CT imaging pre-SBRT and post-SBRT (median, 5 months; range, 3-10 months). CTCs were assessed via a telomerase-based assay before and within 3 months after SBRT and dichotomized at 5 and 1.3 CTCs/mL. Pre-SBRT, post-SBRT, and delta PET/CT radiomics features (n = 1548 × 3/1562 × 3) were extracted from gross tumor volume. Seven feature blocks were constructed including clinical parameters (n = 12). Multiblock data integration was performed using block sparse partial least squares-discriminant analysis (sPLS-DA) referred to as Data Integration Analysis for Biomarker Discovery Using Latent Components (DIABLO) for identifying key signatures by maximizing common information between different feature blocks while discriminating CTC levels. Optimal input blocks were identified using a pairwise combination method. DIABLO performance for predicting pre-SBRT and post-SBRT CTCs was evaluated using combined AUC (area under the curve, averaged across different blocks) analysis with 20 × 5-fold cross-validation (CV) and compared with that of concatenation-based sPLS-DA that consisted of combining all features into 1 block. CV prediction scores between 1 class versus the other were compared using the Wilcoxon rank sum test.

RESULTS

For predicting pre-SBRT CTCs, DIABLO achieved the best performance with combined pre-SBRT PET radiomics and clinical feature blocks, showing CV AUC of 0.875 (P = .009). For predicting post-SBRT CTCs, DIABLO achieved the best performance with combined post-SBRT CT and delta CT radiomics feature blocks, showing CV AUCs of 0.883 (P = .001). In contrast, all single-block sPLS-DA models could not attain CV AUCs higher than 0.7.

CONCLUSIONS

Multiblock integration with discriminant analysis of 18F-FDG-PET/CT radiomics has the potential for predicting pre-SBRT and post-SBRT CTCs. Radiomics and CTC analysis may complement and together help guide the subsequent management of patients with ES-NSCLC.

Predicting the prognosis of hepatocellular carcinoma with the treatment of transcatheter arterial chemoembolization combined with microwave ablation using pretreatment MR imaging texture features

OBJECTIVE

To investigate the prognostic value of baseline magnetic resonance imaging (MRI) texture analysis of hepatocellular carcinoma (HCC) treated with transcatheter arterial chemoembolization (TACE) and microwave ablation (MWA).

METHODS

MRI was performed on 102 patients with HCC before receiving TACE combined with MWA in this retrospective study. The best 10 texture features were screened as a feature group for each MRI sequence by MaZda software using mutual information coefficient (MI), nonlinear discriminant analysis (NDA) and other methods. The optimal feature group with the lowest misdiagnosis rate was achieved on one MRI sequence between two groups dichotomized by 3-year survival, which was used to optimize the significant texture features with the optimal cutoff values. The Cox proportional hazards model was generated for the significant texture features and clinical variables to determine the independent predictors of overall survival (OS). The predictive performance of the model was further evaluated by the area under the ROC curve (AUC). Kaplan-Meier and log-rank tests were performed for disease-free survival (DFS) and Local recurrence-free survival (LRFS).

RESULTS

The optimal feature group with the lowest misdiagnosis rate of 8.82% was obtained on T2WI using MI combined with NDA feature analysis. For Cox proportional hazards regression models, the independent prognostic factors associated with OS were albumin (P = 0.047), BCLC stage (P = 0.001), Correlat_{(1,- 1)T2} (P = 0.01) and SumEntrp_(3,0)T2 (P = 0.015), and the prediction efficiency of multivariate model is AUC = 0.876, 95%CI = 0.803-0.949. Kaplan-Meier analyses further demonstrated that BCLC (P < 0.001), Correlat_{(1,- 1)T2} (P = 0.023) and SumEntrp_(3,0)T2 (P < 0.001) were associated with DFS, and BCLC (P = 0.007) related to LRFS.

CONCLUSIONS

MR imaging texture features may be used to predict the prognosis of HCC treated with TACE combined with MWA.

Radiomics and functional imaging in lung cancer: the importance of radiological heterogeneity beyond FDG PET/CT and lung biopsy

PURPOSE

[¹⁸F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET/CT) has a central role in the lung nodules' characterization even if, with SUV < 2.5, percutaneous CT-guided Lung Biopsy (CTLB) is needed to assess nodule nature. In that scenario, CT Texture Analysis (CTTA) could be a non-invasive imaging biomarker. Our purpose is to test CTTA ability in differentiating malignant from benign nodules.

METHOD

Patients that underwent FDG PET/CT followed by CTLB between January 2013 and December 2018 were retrospectively enrolled. Were included patients with lung nodule SUV < 2.5 and histological diagnosis.

EXCLUSION CRITERIA

nodules SUV > 2.5, patients who refused CTLB or received oncological treatment before CTLB, indeterminate pathology report, CT motion artifacts. Two radiologists in consensus performed CTTA, drawing a volumetric Region of Interest of nodule with a dedicated first order TA software with and without spatial scaling filters, on preliminary CT performed for CTLB. Statistics included a comparison between malignant and benign neoplasms distribution (2-tailed T-test or Mann-Whitney test according to normal/non-normal data distribution), P-values < 0.05 were considered statistically significant. CTTA accuracy was tested with Receiver Operating Characteristics (ROC) curve.

RESULTS

Form an initial population of 1178, 46 patients encountered inclusion criteria. Pathologist reported 27/46 (59%) malignant and 19/46 (41%) benign nodules. In malignant lesions CTTA showed lower Kurtosis' and higher Skewness' values (all P ≤ 0.0013 and all filtered TA P < 0.024, respectively). ROC curve showed significant Area Under the Curve for Kurtosis and Skewness (0.654 and 0.642, P < 0.001) at medium filtration.

CONCLUSIONS

CTTA is a promising radiological tool to characterize benign and malignant lung nodules, even in those cases without an altered glucose metabolism.

Volumetric CT Texture Analysis of Intrahepatic Mass-Forming Cholangiocarcinoma for the Prediction of Postoperative Outcomes: Fully Automatic Tumor Segmentation Versus Semi-Automatic Segmentation

Objective

To determine whether volumetric CT texture analysis (CTTA) using fully automatic tumor segmentation can help predict recurrence-free survival (RFS) in patients with intrahepatic mass-forming cholangiocarcinomas (IMCCs) after surgical resection.

Materials and Methods

This retrospective study analyzed the preoperative CT scans of 89 patients with IMCCs (64 male; 25 female; mean age, 62.1 years; range, 38–78 years) who underwent surgical resection between January 2005 and December 2016. Volumetric CTTA of IMCCs was performed in late arterial phase images using both fully automatic and semi-automatic liver tumor segmentation techniques. The time spent on segmentation and texture analysis was compared, and the first-order and second-order texture parameters and shape features were extracted. The reliability of CTTA parameters between the techniques was evaluated using intraclass correlation coefficients (ICCs). Intra- and interobserver reproducibility of volumetric CTTAs were also obtained using ICCs. Cox proportional hazard regression were used to predict RFS using CTTA parameters and clinicopathological parameters.

Results

The time spent on fully automatic tumor segmentation and CTTA was significantly shorter than that for semi-automatic segmentation: mean ± standard deviation of 1 minutes 37 seconds ± 50 seconds vs. 10 minutes 48 seconds ± 13 minutes 44 seconds (p < 0.001). ICCs of the texture features between the two techniques ranged from 0.215 to 0.980. ICCs for the intraobserver and interobserver reproducibility using fully automatic segmentation were 0.601–0.997 and 0.177–0.984, respectively. Multivariable analysis identified lower first-order mean (hazard ratio [HR], 0.982; p = 0.010), larger pathologic tumor size (HR, 1.171; p < 0.001), and positive lymph node involvement (HR, 2.193; p = 0.014) as significant parameters for shorter RFS using fully automatic segmentation.

Conclusion

Volumetric CTTA parameters obtained using fully automatic segmentation could be utilized as prognostic markers in patients with IMCC, with comparable reproducibility in significantly less time compared with semi-automatic segmentation.

Limitations and Pitfalls of FDG-PET/CT in Infection and Inflammation

White blood cells activated by either a pathogen or as part of a systemic inflammatory disease are characterized by high energy consumption and are therefore taking up the glucose analogue PET tracer FDG avidly. It is therefore not surprising that a steadily growing body of research and clinical reports now supports the use of FDG PET/CT to diagnose a wide range of patients with non-oncological diseases. However, using FDG PET/CT in patients with infectious or inflammatory diseases has some limitations and potential pitfalls that are not necessarily as pronounced in oncology FDG PET/CT. Some of these limitations are of a general nature and related to the laborious acquisition of PET images in patients that are often acutely ill, whereas others are more disease-specific and related to the particular metabolism in some of the organs most commonly affected by infections or inflammatory disease. Both inflammatory and infectious diseases are characterized by a more diffuse and less pathognomonic pattern of FDG uptake than oncology FDG PET/CT and the affected organs also typically have some physiological FDG uptake. In addition, patients referred to PET/CT with suspected infection or inflammation are rarely treatment naïve and may have received varying doses of antibiotics, corticosteroids or other immune-modulating drugs at the time of their examination. Combined, this results in a higher rate of false positive FDG findings and also in some cases a lower sensitivity to detect active disease. In this review, we therefore discuss the limitations and pitfalls of FDG PET/CT to diagnose infections and inflammation taking these issues into consideration. Our review encompasses the most commonly encountered inflammatory and infectious diseases in head and neck, in the cardiovascular system, in the abdominal organs and in the musculoskeletal system. Finally, new developments in the field of PET/CT that may help overcome some of these limitations are briefly highlighted.

Computed tomography radiomics to predict EBER positivity in Epstein-Barr virus-associated gastric adenocarcinomas: a retrospective study

BACKGROUND

The relevance of Epstein-Barr virus (EBV) in gastric carcinoma has been represented by the existence of EBV-encoded small RNA (EBER) in the tumor cells and has prognostic significance in gastric cancer, while gastric adenocarcinoma represents the most frequently occurring gastric malignancy.

PURPOSE

To observe the capacity of radiomic features extracted from contrast-enhanced computed tomography (CE-CT) images to differentiate EBER-positive gastric adenocarcinoma from EBER-negative ones.

MATERIAL AND METHODS

A total of 54 patients with gastric adenocarcinoma (EBER-positive: 27, EBER-negative: 27) were retrospectively examined. Radiomic imaging features were extracted from all regions of interest (ROI) delineated by two experienced radiologists on late arterial phase CT images. We distinguished related radiomic features through the two-tailed t test and applied them to construct a decision tree model to evaluate whether EBER in situ hybridization positive had appeared.

RESULTS

Nine radiomics features were significantly related to EBER in situ hybridization status (P < 0.05), four of which were used to build the decision tree through backward elimination: Correlation_ AllDirection_offset7, Correlation_ angle135_offset7, RunLengthNonuniformity_ AllDirection_offset1_SD, and HighGreyLevelRunEmphasis_ AllDiretion_offset1_SD. The decision tree model consisted of seven decision nodes and six terminal nodes, three of which demonstrated positive EBER in situ hybridization. The specificity, sensitivity, and accuracy of the model were 84%, 80%, and 81.7%, respectively. The area under the curve of the decision tree model was 0.87.

CONCLUSION

Radiomics based on CE-CT could be applied to predict EBER in situ hybridization status preoperatively in patients with gastric adenocarcinoma.

A Novel Radiomics Nomogram for the Prediction of Secondary Loss of Response to Infliximab in Crohn's Disease

Purpose

The prediction of the loss of response (LOR) to infliximab (IFX) is crucial for optimizing treatment strategies and shifting biologics. However, a secondary LOR is difficult to predict by endoscopy due to the intestinal stricture, perforation, and fistulas. This study aimed to develop and validate a radiomic nomogram for the prediction of secondary LOR to IFX in patients with Crohn’s disease (CD).

Patients and Methods

A total of 186 biologic-naive patients diagnosed with CD between September 2016 and June 2019 were enrolled. Secondary LOR was determined during week 54. Computed tomography enterography (CTE) texture analysis (TA) features were extracted from lesions and analyzed using LIFEx software. Feature selection was performed by least absolute shrinkage and selection operator (LASSO) and ten-fold cross validation. A nomogram was constructed using multivariable logistic regression, and the internal validation was approached by ten-fold cross validation.

Results

Predictors contained in the radiomics nomogram included three first-order and five second-order signatures. The prediction model presented significant discrimination (AUC, 0.880; 95% CI, 0.816–0.944) and high calibration (mean absolute error of = 0.028). Decision curve analysis (DCA) indicated that the nomogram provided clinical net benefit. Ten-fold cross validation assessed the stability of the nomogram with an AUC of 0.817 and an accuracy of 0.819.

Conclusion

This novel radiomics nomogram provides a predictive tool to assess secondary LOR to IFX in patients with Crohn’s disease. This tool will help physicians decide when to switch therapy.

Delta-radiomics and response to neoadjuvant treatment in locally advanced gastric cancer-a multicenter study of GIRCG (Italian Research Group for Gastric Cancer)

Background

To predict response to neoadjuvant chemotherapy (NAC) of gastric cancer (GC), prior to surgery, would be pivotal to customize patient treatment. The aim of this study is to investigate the reliability of computed tomography (CT) texture analysis (TA) in predicting the histo-pathological response to NAC in patients with resectable locally advanced gastric cancer (AGC).

Methods

Seventy (40 male, mean age 63.3 years) patients with resectable locally AGC, treated with NAC and radical surgery, were included in this retrospective study from 5 centers of the Italian Research Group for Gastric Cancer (GIRCG). Population was divided into two groups: 29 patients from one center (internal cohort for model development and internal validation) and 41 from other four centers (external cohort for independent external validation). Gross tumor volume (GTV) was segmented on each pre- and post-NAC multidetector CT (MDCT) image by using a dedicated software (RayStation), and 14 TA parameters were then extrapolated. Correlation between TA parameters and complete pathological response (tumor regression grade, TRG1), was initially investigated for the internal cohort. The univariate significant variables were tested on the external cohort and multivariate logistic analysis was performed.

Results

In multivariate logistic regression the only significant TA variable was delta gray-level co-occurrence matrix (GLCM) contrast (P=0.001, Nagelkerke R²: 0.546 for the internal cohort and P=0.014, Nagelkerke R²: 0.435 for the external cohort). Receiver operating characteristic (ROC) curves, generated from the logistic regression of all the patients, showed an area under the curve (AUC) of 0.763.

Conclusions

Post-NAC GLCM contrast and dissimilarity and delta GLCM contrast TA parameters seem to be reliable for identifying patients with locally AGC responder to NAC.

Influence of Adaptive Statistical Iterative Reconstructions on CT Radiomic Features in Oncologic Patients

Iterative reconstructions (IR) might alter radiomic features extraction. We aim to evaluate the influence of Adaptive Statistical Iterative Reconstruction-V (ASIR-V) on CT radiomic features. Patients who underwent unenhanced abdominal CT (Revolution Evo, GE Healthcare, USA) were retrospectively enrolled. Raw data of filtered-back projection (FBP) were reconstructed with 10 levels of ASIR-V (10–100%). CT texture analysis (CTTA) of liver, kidney, spleen and paravertebral muscle for all datasets was performed. Six radiomic features (mean intensity, standard deviation (SD), entropy, mean of positive pixel (MPP), skewness, kurtosis) were extracted and compared between FBP and all ASIR-V levels, with and without altering the spatial scale filter (SSF). CTTA of all organs revealed significant differences between FBP and all ASIR-V reconstructions for mean intensity, SD, entropy and MPP (all p < 0.0001), while no significant differences were observed for skewness and kurtosis between FBP and all ASIR-V reconstructions (all p > 0.05). A per-filter analysis was also performed comparing FBP with all ASIR-V reconstructions for all six SSF separately (SSF0-SSF6). Results showed significant differences between FBP and all ASIR-V reconstruction levels for mean intensity, SD, and MPP (all filters p < 0.0315). Skewness and kurtosis showed no differences for all comparisons performed (all p > 0.05). The application of incremental ASIR-V levels affects CTTA across various filters. Skewness and kurtosis are not affected by IR and may be reliable quantitative parameters for radiomic analysis.

Texture Analysis of Fractional Water Content Images Acquired during PET/MRI: Initial Evidence for an Association with Total Lesion Glycolysis, Survival and Gene Mutation Profile in Primary Colorectal Cancer

To assess the capability of fractional water content (FWC) texture analysis (TA) to generate biologically relevant information from routine PET/MRI acquisitions for colorectal cancer (CRC) patients. Thirty consecutive primary CRC patients (mean age 63.9, range 42-83 years) prospectively underwent FDG-PET/MRI. FWC tumor parametric images generated from Dixon MR sequences underwent TA using commercially available research software (TexRAD). Data analysis comprised (1) identification of functional imaging correlates for texture features (TF) with low inter-observer variability (intraclass correlation coefficient: ICC > 0.75), (2) evaluation of prognostic performance for FWC-TF, and (3) correlation of prognostic imaging signatures with gene mutation (GM) profile. Of 32 FWC-TF with ICC > 0.75, 18 correlated with total lesion glycolysis (TLG, highest: rs = -0.547, p = 0.002). Using optimized cut-off values, five MR FWC-TF identified a good prognostic group with zero mortality (lowest: p = 0.017). For the most statistically significant prognostic marker, favorable prognosis was significantly associated with a higher number of GM per patient (medians: 7 vs. 1.5, p = 0.009). FWC-TA derived from routine PET/MRI Dixon acquisitions shows good inter-operator agreement, generates biological relevant information related to TLG, GM count, and provides prognostic information that can unlock new clinical applications for CRC patients.

Comparison of Different Machine Models Based on Contrast-Enhanced Computed Tomography Radiomic Features to Differentiate High From Low Grade Clear Cell Renal Cell Carcinomas

Purpose

This study was to investigate the role of different radiomics models with enhanced computed tomography (CT) scan in differentiating low from high grade renal clear cell carcinomas.

Materials and Methods

CT data of 190 cases with pathologically confirmed renal cell carcinomas were collected and divided into the training set and testing set according to different time periods, with 122 cases in the training set and 68 cases in the testing set. The region of interest (ROI) was delineated layer by layer.

Results

A total of 402 radiomics features were extracted for analysis. Six of the radiomic parameters were deemed very valuable by univariate analysis, rank sum test, LASSO cross validation and correlation analysis. From these six features, multivariate logistic regression model, support vector machine (SVM), and decision tree model were established for analysis. The performance of each model was evaluated by AUC value on the ROC curve and decision curve analysis (DCA). Among the three prediction models, the SVM model showed a high predictive efficiency. The AUC values of the training set and the testing set were 0.84 and 0.83, respectively, which were significantly higher than those of the decision tree model and the multivariate logistic regression model. The DCA revealed a better predictive performance in the SVM model that possessed the highest degree of coincidence.

Conclusion

Radiomics analysis using the SVM radiomics model has highly efficiency in discriminating high- and low-grade clear cell renal cell carcinomas.

Computed tomography-based radiomic model at node level for the prediction of normal-sized lymph node metastasis in cervical cancer

•

The metastatic status of lymph nodes in cervical cancer patients can be predicted.

•

Computed tomography-based radiomic model can identify the status of the normal-sized lymph node singly.

•

The model may help doctors to make staging and clinical decision, and realize individualized treatment.

Purpose

Radiomic models have been demonstrated to have acceptable discrimination capability for detecting lymph node metastasis (LNM). We aimed to develop a computed tomography–based radiomic model and validate its usefulness in the prediction of normal-sized LNM at node level in cervical cancer.

Methods

A total of 273 LNs of 219 patients from 10 centers were evaluated in this study. We randomly divided the LNs from the 2 centers with the largest number of LNs into the training and internal validation cohorts, and the rest as the external validation cohort. Radiomic features were extracted from the arterial and venous phase images. We trained an artificial neural network (ANN) to develop two single-phase models. A radiomic model reflecting the features of two-phase images was also built for directly predicting LNM in cervical cancer. Moreover, four state-of-the-art methods were used for comparison. The performance of all models was assessed using the area under the receiver operating characteristic curve (AUC).

Results

Among the models we built, the models combining the features of two phases surpassed the single-phase models, and the models generated by ANN had better performance than the others. We found that the radiomic model achieved the highest AUCs of 0.912 and 0.859 in the training and internal validation cohorts, respectively. In the external validation cohort, the AUC of the radiomic model was 0.800.

Conclusion

We constructed a radiomic model that exhibited great ability in the prediction of LNM. The application of the model could optimize clinical staging and decision-making.

Differentiating low and high grade mucoepidermoid carcinoma of the salivary glands using CT radiomics

Background

The purpose of this study is to determine if Haralick texture analysis on CT imaging of mucoepidermoid carcinomas (MEC) can differentiate low-grade and high-grade tumors.

Methods

A retrospective review of 18 patients with MEC of the salivary glands, corresponding CT imaging and pathology report was performed. Tumors were manually segmented and image analysis was performed to calculate radiomic features. Radiomic features were compared between low-grade and high-grade MEC. A multivariable logistic regression model and receiver operating characteristic analysis was performed.

Results

A total of 18 patients (mean age, 51, range 9-83 years, 8 men and 10 women) were included. Nine patients had low-grade pathology and nine patients had high-grade pathology. Of the 18 cases, 7 (39%) occurred in the parotid gland and 11 (61%) occurred in minor salivary glands. No individual feature was significantly different between low-grade and high-grade MEC. A logistic regression model including surface regularity, energy and information measure II of correlation was performed and was able to predict high-grade MEC accurately (sensitivity 89%, specificity 68%). The area under the receiver operating characteristic curve was 0.802.

Conclusions

High-grade MEC tend to have a low energy, high correlation texture as well as surface irregularity. Together, these three features may comprise a tumor phenotype that is able to predict high-grade pathology in MECs.

Utility of first order MRI-Texture analysis parameters in the prediction of histologic grade and muscle invasion in urinary bladder cancer: a preliminary study

OBJECTIVE

To explore the utility of first-order MRI-texture analysis (TA) parameters in predicting histologic grade and muscle invasion in urinary bladder cancer (UBC).

METHODS

After ethical clearance, 40 patients with UBC, who were imaged on a 3.0-Tesla scanner, were retrospectively included. Using the TexRAD^TM platform, two readers placed freehand ROI on the sections demonstrating the largest dimension of the tumor, evaluating only one tumor per patient. Interobserver reproducibility was assessed using the intraclass correlation coefficient (ICC). Mann-Whitney U test and ROC curve analysis were used to identify statistical significance and select parameters with high class separation capacity (AUC >0.8), respectively. Pearson's test was used to identify redundancy in the results.

RESULTS

All texture parameters showed excellent ICC. The best parameters in differentiating high and low-grade tumors were mean/ mean of positive pixels (MPP) at SSF 0 (AUC: 0.897) and kurtosis at SSF 5 (AUC: 0.828) on the ADC images. In differentiating muscle invasive from non-muscle invasive tumors, mean/ MPP at SSF 0 on the ADC images showed AUC >0.8; however, this finding resulted from the confounding effect of high-grade histology on the ADC values of muscle invasive tumors.

CONCLUSION

MRI-TA generated few parameters which were reproducible and useful in predicting histologic grade. No independent parameters predicted muscle invasion.

ADVANCES IN KNOWLEDGE

There is lacuna in the literature concerning the role of MRI-TA in the prediction of histologic grade and muscle invasion in UBC. Our study generated a few first-order parameters which were useful in predicting high-grade histology.

Global evolution of research on pulmonary nodules: a bibliometric analysis

Aim: To provide a historical and global picture of research concerning lung nodules, compare the contributions of major countries and explore research trends over the past 10 years. Methods: A bibliometric analysis of publications from Scopus (1970-2020) and Web of Science (2011-2020). Results: Publications about pulmonary nodules showed an enormous growth trend from 1970 to 2020. There is a high level of collaboration among the 20 most productive countries and regions, with the USA located at the center of the collaboration network. The keywords 'deep learning', 'artificial intelligence' and 'machine learning' are current hotspots. Conclusions: Abundant research has focused on pulmonary nodules. Deep learning is emerging as a promising tool for lung cancer diagnosis and management.

Prediction of tumor response via a pretreatment MRI radiomics-based nomogram in HCC treated with TACE

Objectives

To develop and validate a pre-transcatheter arterial chemoembolization (TACE) MRI-based radiomics model for predicting tumor response in intermediate-advanced hepatocellular carcinoma (HCC) patients.

Materials

Ninety-nine intermediate-advanced HCC patients (69 for training, 30 for validation) treated with TACE were enrolled. MRI examinations were performed before TACE, and the efficacy was evaluated according to the mRECIST criterion 3 months after TACE. A total of 396 radiomics features were extracted from T2-weighted pre-TACE images, and least absolute shrinkage and selection operator (LASSO) regression was applied to feature selection and model construction. The performance of the model was evaluated by receiver operating characteristic (ROC) curves, calibration curves, and decision curves.

Results

The AFP value, Child-Pugh score, and BCLC stage showed a significant difference between the TACE response (TR) and non-TACE response (nTR) patients. Six radiomics features were selected by LASSO and the radiomics score (Rad-score) was calculated as the sum of each feature multiplied by the non-zero coefficient from LASSO. The AUCs of the ROC curve based on Rad-score were 0.812 and 0.866 in the training and validation cohorts, respectively. To improve the diagnostic efficiency, the Rad-score was further integrated with the above clinical indicators to form a novel predictive nomogram. Results suggested that the AUC increased to 0.861 and 0.884 in the training and validation cohorts, respectively. Decision curve analysis showed that the radiomics nomogram was clinically useful.

Conclusion

The radiomics and clinical indicator-based predictive nomogram can well predict TR in intermediate-advanced HCC and can further be applied for auxiliary diagnosis of clinical prognosis.

Key Points

• The therapeutic outcome of TACE varies greatly even for patients with the same clinicopathologic features.

• Radiomics showed excellent performance in predicting the TACE response.

• Decision curves demonstrated that the novel predictive model based on the radiomics signature and clinical indicators has great clinical utility.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-07910-0.

Value of contrast-enhanced CT texture analysis in predicting IDH mutation status of intrahepatic cholangiocarcinoma

To explore the value of contrast-enhanced CT texture analysis in predicting isocitrate dehydrogenase (IDH) mutation status of intrahepatic cholangiocarcinomas (ICCs). Institutional review board approved this study. Contrast-enhanced CT images of 138 ICC patients (21 with IDH mutation and 117 without IDH mutation) were retrospectively reviewed. Texture analysis was performed for each lesion and compared between ICCs with and without IDH mutation. All textural features in each phase and combinations of textural features (p < 0.05) by Mann–Whitney U tests were separately used to train multiple support vector machine (SVM) classifiers. The classification generalizability and performance were evaluated using a tenfold cross-validation scheme. Among plain, arterial phase (AP), portal venous phase (VP), equilibrium phase (EP) and Sig classifiers, VP classifier showed the highest accuracy of 0.863 (sensitivity, 0.727; specificity, 0.885), with a mean area under the receiver operating characteristic curve of 0.813 in predicting IDH mutation in validation cohort. Texture features of CT images in portal venous phase could predict IDH mutation status of ICCs with SVM classifier preoperatively.

Radiomic Model Predicts Lymph Node Response to Induction Chemotherapy in Locally Advanced Head and Neck Cancer

This study developed a pretreatment CT-based radiomic model of lymph node response to induction chemotherapy in locally advanced head and neck squamous cell carcinoma (HNSCC) patients. This was a single-center retrospective study of patients with locally advanced HPV+ HNSCC. Forty-one enlarged lymph nodes were found from 27 patients on pretreatment CT and were split into 3:1 training and testing cohorts. Ninety-three radiomic features were extracted. A radiomic model and a combined radiomic-clinical model predicting lymph node response to induction chemotherapy were developed using multivariable logistic regression. Median age was 57 years old, and 93% of patients were male. Post-treatment evaluation was 32 days after treatment, with a median reduction in lymph node volume of 66%. A three-feature radiomic model (minimum, skewness, and low gray level run emphasis) and a combined radiomic-clinical model were developed. The combined model performed the best, with AUC = 0.85 on the training cohort and AUC = 0.75 on the testing cohort. A pretreatment CT-based lymph node radiomic signature combined with clinical parameters was able to predict nodal response to induction chemotherapy for patients with locally advanced HNSCC.

Primary Gastro-Intestinal Lymphoma and Gastro-Intestinal Adenocarcinoma: An Initial Study of CT Texture Analysis as Quantitative Biomarkers for Differentiation

BACKGROUND

To explore the potential role of computed tomography (CT) texture analysis and an imaging biomarker in differentiating primary gastro-intestinal lymphoma (PGIL) from gastro-intestinal adenocarcinoma (GIAC).

METHODS

A total of 131 patients with surgical pathologically PGIL and GIAC were enrolled in this study. Histogram parameters of arterial and venous phases extracted from contrast enhanced modified discrete cosine transform (MDCT) images were compared between PGIL and GIAC by Mann-Whitney U tests. The optimal parameters for differentiating these two groups were obtained through receiver operating characteristic (ROC) curves and the area under the curve (AUC) was calculated.

RESULTS

Compared with GIAC, in arterial phase, PGIL had statistically higher 5th, 10th percentiles (p = 0.003 and 0.011) and statistically lower entropy (p = 0.001). In the venous phase, PGIL had statistically lower mean, median, 75th, 90th, 95th percentiles, and entropy (p = 0.036, 0.029, 0.007, 0.001 and 0.001, respectively). For differentiating PGIL from GIAC, V-median + A-5th percentile was an optimal parameter for combined diagnosis (AUC = 0.746, p < 0.0001), and the corresponding sensitivity and specificity were 81.7 and 64.8%, respectively.

CONCLUSION

CT texture analysis could be useful for differential diagnosis of PGIL and GIAC.

Non-contrast CT-based radiomic signature for screening thoracic aortic dissections: a multicenter study

OBJECTIVE

To develop a non-contrast CT-based radiomic signature to effectively screen for thoracic aortic dissections (ADs).

METHODS

We retrospectively enrolled 378 patients who underwent non-contrast chest CT scans along with CT angiography or MRI from 4 medical centers. The training and validation sets were from 3 centers, while the external test set was from a 4th center. Radiomic features were extracted from non-contrast CT images. The radiomic signature was created on the basis of selected features by a logistic regression algorithm. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were conducted to assess the predictive ability of radiomic signature.

RESULTS

The radiomic signature demonstrated AUCs of 0.91 (95% confidence interval [CI], 0.86-0.95) in the training set, 0.92 (95% CI, 0.86-0.98) in the validation set, and 0.90 (95% CI, 0.82-0.98) in the external test set. The predicted diagnosis was in good agreement with the probability of thoracic AD. In the external test group, the diagnostic accuracy, sensitivity, specificity, PPV, and NPV were 90.5%, 85.7%, 91.7%, 70.6%, and 96.5%, respectively.

CONCLUSIONS

A radiomic signature based on non-contrast CT images can effectively predict thoracic ADs. This method may serve as a potential screening tool for thoracic ADs.

KEY POINTS

• The non-contrast CT-based radiomic signature can effectively predict the thoracic aortic dissections. • This radiomic signature shows better predictive performance compared to the current clinical model. • This prediction method may be a potential tool for screening thoracic aortic dissections.

Differentiation of benign and malignant regions in paraffin embedded tissue blocks of pulmonary adenocarcinoma using micro CT scanning of paraffin tissue blocks: a pilot study for method validation

PURPOSE

Micro computed tomography (micro-CT) can provide detailed information about the internal structure of materials. This study aimed to demonstrate the diagnostic value of micro-CT in formalin fixed paraffin embedded pulmonary adenocarcinomas by correlating the micro-CT findings of tumoral and non-tumoral areas with hematoxylin and eosin (HE) sections.

METHODS

Paraffin blocks obtained from three adenocarcinomas were scanned with micro-CT. Ten regions of interest (ROIs) from adenocarcinoma and 11 ROIs from pulmonary parenchyma (ROI-C and ROI-N, respectively) areas were compared regarding the various structural parameters.

RESULTS

All parameters were significantly different regarding the tumoral and non-tumoral ROIs. The percent object volume, structure thickness, structure linear density, connectivity and connectivity density were higher in ROI-Cs (p < 0.000, p < 0.000, p = 0.001, p < 0.000, and p < 0.000 respectively); whereas intersection surface and structure model index were higher in ROI-Ns (p < 0.000 and p < 0.000). The open porosity percentage was higher in ROI-Ns (68.86 + 2.96 vs 48.29 + 5.11, p < 0.000) and the closed porosity percentage was higher in ROI-Cs (2.29 + 0.55 vs 0.57 + 0.17 p < 0.000).

CONCLUSIONS

The tumoral and non-tumoral areas in paraffin blocks can be distinguished from each other, using the quantitative and qualitative information obtained by micro-CT. Making this distinction with quantitative data obtained from micro-CT can therefore be the basis of creating artificial intelligence algorithms in the future.

CT-Based Radiomics Signatures for Predicting the Risk Categorization of Thymic Epithelial Tumors

Objectives

This study aims to assess the performance of radiomics approaches based on 3D computed tomography (CT), clinical and semantic features in predicting the pathological classification of thymic epithelial tumors (TETs).

Methods

A total of 190 patients who underwent surgical resection and had pathologically confirmed TETs were enrolled in this retrospective study. All patients underwent non-contrast-enhanced CT (NECT) scans and contrast-enhanced CT (CECT) scans before treatment. A total of 396 hand-crafted radiomics features of each patient were extracted from the volume of interest in NECT and CECT images. We compared three clinical features and six semantic features (observed radiological traits) between patients with TETs. Two triple-classification radiomics models (RMs), two corresponding clinical RMs, and two corresponding clinical-semantic RMs were built to identify the types of the TETs. The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) were useful to evaluate the different models.

Results

Of the 190 patients, 83 had low-risk thymoma, 58 had high-risk thymoma, and 49 had thymic carcinoma. Clinical features (Age) and semantic features (mediastinal fat infiltration, mediastinal lymph node enlargement, and pleural effusion) were significantly different among the groups(P < 0.001). In the validation set, the NECT-based clinical RM (AUC = 0.770 for low-risk thymoma, 0.689 for high-risk thymoma, and 0.783 for thymic carcinoma; ACC = 0.569) performed better than the CECT-based clinical-semantic RM (AUC = 0.785 for low-risk thymoma, 0.576 for high-risk thymoma, and 0.774 for thymic carcinoma; ACC = 0.483).

Conclusions

NECT-based and CECT-based RMs may provide a non-invasive method to distinguish low-risk thymoma, high-risk thymoma, and thymic carcinoma, and NECT-based RMs performed better.

Advances in Knowledge

Radiomics models may be used for the preoperative prediction of the pathological classification of TETs.