Semiautomatic Segmentation and Radiomics for Dual-Energy CT: A Pilot Study to Differentiate Benign and Malignant Hepatic Lesions.

OBJECTIVE. This study assessed a machine learning-based dual-energy CT (DECT) tumor analysis prototype for semiautomatic segmentation and radiomic analysis of benign and malignant liver lesions seen on contrast-enhanced DECT. MATERIALS AND METHODS. This institutional review board-approved study included 103 adult patients (mean age, 65 ± 15 [SD] years; 53 men, 50 women) with benign (60/103) or malignant (43/103) hepatic lesions on contrast-enhanced dual-source DECT. Most malignant lesions were histologically proven; benign lesions were either stable on follow-up CT or had characteristic benign features on MRI. Low- and high-kilovoltage datasets were deidentified, exported offline, and processed with the DECT tumor analysis for semiautomatic segmentation of the volume and rim of each liver lesion. For each segmentation, contrast enhancement and iodine concentrations as well as radiomic features were derived for different DECT image series. Statistical analyses were performed to determine if DECT tumor analysis and radiomics can differentiate benign from malignant liver lesions. RESULTS. Normalized iodine concentration and mean iodine concentration in the benign and malignant lesions were significantly different (p < 0.0001-0.0084; AUC, 0.695-0.856). Iodine quantification and radiomic features from lesion rims (AUC, ≤ 0.877) had higher accuracy for differentiating liver lesions compared with the values from lesion volumes (AUC, ≤ 0.856). There was no difference in the accuracies of DECT iodine quantification (AUC, 0.91) and radiomics (AUC, 0.90) for characterizing liver lesions. CONCLUSION. DECT radiomics were more accurate than iodine quantification for differentiating solid benign and malignant hepatic lesions.

Can Dual-Energy Computed Tomography Quantitative Analysis and Radiomics Differentiate Normal Liver From Hepatic Steatosis and Cirrhosis?

OBJECTIVES: This study aimed to assess if dual-energy computed tomography (DECT) quantitative analysis and radiomics can differentiate normal liver, hepatic steatosis, and cirrhosis. MATERIALS AND METHODS: Our retrospective study included 75 adult patients (mean age, 54 ± 16 years) who underwent contrast-enhanced, dual-source DECT of the abdomen. We used Dual-Energy Tumor Analysis prototype for semiautomatic liver segmentation and DECT and radiomic features. The data were analyzed with multiple logistic regression and random forest classifier to determine area under the curve (AUC). RESULTS: Iodine quantification (AUC, 0.95) and radiomic features (AUC, 0.97) differentiate between healthy and abnormal liver. Combined fat ratio percent and mean mixed CT values (AUC, 0.99) were the strongest differentiators of healthy and steatotic liver. The most accurate differentiating parameters of normal liver and cirrhosis were a combination of first-order statistics (90th percentile), gray-level run length matrix (short-run low gray-level emphasis), and gray-level size zone matrix (gray-level nonuniformity normalized; AUC, 0.99). CONCLUSION: Dual-energy computed tomography iodine quantification and radiomics accurately differentiate normal liver from steatosis and cirrhosis from single-section analyses.

Computed Tomography-based Radiomics Evaluation of Postoperative Local Recurrence of Pancreatic Ductal Adenocarcinoma.

OBJECTIVE: To develop and validate an effective model for identifying patients with postoperative local disease recurrence of pancreatic ductal adenocarcinoma (PDAC). METHODS: A total of 153 patients who had undergone surgical resection of PDAC with regular postoperative follow-up were consecutively enrolled and randomly divided into training (n = 108) and validation (n = 45) cohorts. The postoperative soft-tissue biopsy results or clinical follow-up results served as the reference diagnostic criteria. Radiomics analysis of the postoperative soft-tissue was performed on a commercially available prototype software using portal vein phase image. Three models were built to characterize postoperative soft tissue: computed tomography (CT)-based radiomics, clinicoradiological, and their combination. The area under the receiver operating characteristic curves (AUC) was used to evaluate the differential diagnostic performance. A nomogram was used to select the final model with best performance. One radiologist's diagnostic choices that were made with and without the nomogram's assistance were evaluated. RESULTS: A seven-feature-combined radiomics signature was constructed as a predictor of postoperative local recurrence. The nomogram model combining the radiomics signature with postoperative CA 19-9 elevation showed the best performance (training cohort, AUC = 0.791 [95%CI: 0.707, 0.876]; validation cohort, AUC = 0.742 [95%CI: 0.590, 0.894]). In the validation cohort, the AUC for differential diagnosis was significantly improved for the combined model relative to that for postoperative CA 19-9 elevation (AUC = 0.742 vs. 0.533, p < 0.001). The calibration curve and decision curve analysis demonstrated the clinical usefulness of the proposed nomogram. The diagnostic performance of the radiologist was not significantly improve by using the proposed nomogram (AUC = 0.742 vs. 0.670, p = 0.17). CONCLUSION: The combined model using CT radiomic features and CA 19-9 elevation effectively characterized postoperative soft tissue and potentially may improve treatment strategies and facilitate personalized treatment for PDAC after surgical resection.

Correlation of Radiomics with Treatment Response in Liver Metastases.

RATIONALE AND OBJECTIVES: To assess differences in radiomics derived from semi-automatic segmentation of liver metastases for stable disease (SD), partial response (PR), and progressive disease (PD) based on RECIST1.1 and to assess if radiomics alone at baseline can predict response. MATERIALS AND METHODS: Our IRB-approved study included 203 women (mean age 54 ± 11 years) with metastatic liver disease from breast cancer. All patients underwent contrast abdomen-pelvis CT in the portal venous phase at two points: baseline (pre-treatment) and follow-up (between 3 and 12 months following treatment). Patients were subcategorized into three subgroups based on RECIST 1.1 criteria (Response Evaluation Criteria in Solid Tumors version 1.1): 66 with SD, 69 with PR, and 68 with PD on follow-up CT. The deidentified baseline and follow-up CT images were exported to the radiomics prototype. The prototype enabled semi-automatic segmentation of the target liver lesions for the extraction of first and high order radiomics. Statistical analyses with logistic regression and random forest classifiers were performed to differentiate SD from PD and PR. RESULTS: There was no significant difference between the radiomics on the baseline and follow-up CT images of patients with SD (area under the curve (AUC): 0.3). Random forest classifier differentiated patients with PR with an AUC of 0.845. The most relevant feature was the large dependence emphasis's high and low pass wavelet filter (derived gray level dependence matrix features). Random forest classifier differentiated PD with an AUC of 0.731, with the most relevant feature being the surface-to-volume ratio. There was no difference in radiomics among the three groups at baseline; therefore, a response could not be predicted. CONCLUSION: Radiomics of liver metastases with semi-automatic segmentation demonstrate differences between SD from PR and PD. SUMMARY STATEMENT: Semiautomatic segmentation and radiomics of metastatic liver disease demonstrate differences in SD from the PR and progressive metastatic on the baseline and follow-up CT. Despite substantial variations in the scanners, acquisition, and reconstruction parameters, radiomics had an AUC of 0.84-0.89 for differentiating stable hepatic metastases from decreasing and increasing metastatic disease.

Differentiation of adrenal adenomas from adrenal metastases in single-phased staging dual-energy CT and radiomics.

PURPOSE Differentiation of incidental adrenal lesions remains a challenge in diagnostic imaging, especially on single-phase portal venous computed tomography (CT) in the oncological setting. The aim of the study was to explore the ability of dual-energy CT (DECT)-based iodine quantification and virtual non-contrast (VNC) imaging and advanced radiomic analysis of DECT for differentiation of adrenal adenomas from metastases. METHODS A total of 46 patients with 49 adrenal lesions underwent clinically indicated staging DECT and magnetic resonance imaging. Median values of quantitative parameters such as VNC, fat frac- tion, and iodine density in DECT images were collected and compared between adenomas and metastases using non-parametric tests. Magnetic resonance imaging, washout CT, and clinical follow-up were used as a reference standard. Diagnostic accuracy was assessed by calculat- ing receiver operating characteristics. A DECT tumor analysis prototype software was used for semiautomatic segmentation of adrenal lesions and extraction of radiomic features. A radiomics prototype was used to analyze the data with multiple logistic regression and random forest clas- sification to determine the area under the curve (AUC). RESULTS The study cohort (60.87% women; mean age: 66.91 ± 12.93 years) consisted of 32 adenomas and 17 metastases. DECT-based VNC imaging (AUC=0.89) and fat quantification (AUC=0.86) differentiate between adrenal adenomas and metastases with high diagnostic accuracy (P < .001). Analysis of radiomic features revealed that DECT features such as VNC imaging and fat fraction (AUC = 0.87-0.89; < .001) and radiomic features such as 90th percentile and total energy (AUC = 0.88-0.93; P < .001) differentiate with high diagnostic accuracy between adrenal adeno- mas and metastases. Random forest classification revealed an AUC of 0.83 for separating adrenal adenomas from metastases. CONCLUSION Virtual non-contrast imaging and fat quantification as well as extraction of radiomic features accurately differentiate between adrenal adenomas and metastases on single-phase oncologic staging DECT.

Characterization of Benign and Malignant Pancreatic Lesions with DECT Quantitative Metrics and Radiomics.

RATIONALE AND OBJECTIVES: To compare dual energy CT (DECT) quantitative metrics and radiomics for differentiating benign and malignant pancreatic lesions on contrast enhanced abdomen CT. MATERIALS AND METHODS: Our study included 103 patients who underwent contrast-enhanced DECT for assessing focal pancreatic lesions at one of the two hospitals (Site A: age 68 ± 12 yrs; malignant = 41, benign = 18; Site B: age 46 ± 2 yrs; malignant = 23, benign = 21). All malignant lesions had histologic confirmation, and benign lesions were stable on follow up CT (>12 months) or had characteristic benign features on MRI. Arterial-phase, low- and high-kV DICOM images were processed with the DECT Tumor Analysis (DETA) to obtain DECT quantitative metrics such as HU, iodine and water content from a region of interest (ROI) over focal pancreatic lesions. Separately, we obtained DECT radiomics from the same ROI. Data were analyzed with multiple logistic regression and receiver operating characteristics to generate area under the curve (AUC) for best predictive variables. RESULTS: DECT quantitative metrics and radiomics had AUCs of 0.98-0.99 at site A and 0.89-0.94 at site B data for classifying benign and malignant pancreatic lesions. There was no significant difference in the AUCs and accuracies of DECT quantitative metrics and radiomics from lesion rims and volumes among patients at both sites (p > 0.05). Supervised learning-based model with data from the two sites demonstrated best AUCs of 0.94 (DECT radiomics) and 0.90 (DECT quantitative metrics) for characterizing pancreatic lesions as benign or malignant. CONCLUSION: Compared to complex DECT radiomics, quantitative DECT information provide a simpler but accurate method of differentiating benign and malignant pancreatic lesions.

Use of radiomics to differentiate left atrial appendage thrombi and mixing artifacts on single-phase CT angiography.

To assess if radiomics can differentiate left atrial appendage (LAA) contrast-mixing artifacts and thrombi on early-phase CT angiography without the need for late-phase images. Our study included 111 patients who underwent early- and late-phase, contrast-enhanced cardiac CT. Of these, 79 patients had LAA filling defects from thrombus (n = 46, mean age: 72  ±  12 years, M:F 26:20) or contrast-mixing artifact (n = 33, mean age: 71  ±  13 years, M:F 21:12) on early-contrast-enhanced phase. The remaining 32 patients (mean age: 66  ±  10 years, M:F 19:13) had homogeneous LAA opacification without filling defects. The entire LAA volume on early-phase CT images was manually segmented to obtain radiomic features (Frontier, Siemens). A radiologist assessed for the presence of LAA filling defects and recorded the size and mean CT attenuation (HU) of filling defects and normal LAA. The data were analyzed using multiple logistic regression with receiver operating characteristics area under the curve (AUC) as an output. The radiologist correctly identified all 32 patients without LAA filling defects, 42/46 LAA with thrombi, and 23/33 contrast mixing artifacts. Although HU of LAA thrombi and contrast mixing artifacts was significantly different, with the lowest AUC (0.66), it was inferior to both radiologist assessment and radiomics (p = 0.05). Combination of radiologist assessment and radiomics (AUC 0.92) was superior to HU (0.66), radiomics (0.85), and radiologist (0.80) alone (p < 0.008). Radiomics can differentiate between LAA filling defects from thrombi and contrast mixing artifacts on early-phase contrast-enhanced CT images without the need for late-phase CT.

Publisher Correction: The Technome - A Predictive Internal Calibration Approach for Quantitative Imaging Biomarker Research.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

The Technome - A Predictive Internal Calibration Approach for Quantitative Imaging Biomarker Research.

The goal of radiomics is to convert medical images into a minable data space by extraction of quantitative imaging features for clinically relevant analyses, e.g. survival time prediction of a patient. One problem of radiomics from computed tomography is the impact of technical variation such as reconstruction kernel variation within a study. Additionally, what is often neglected is the impact of inter-patient technical variation, resulting from patient characteristics, even when scan and reconstruction parameters are constant. In our approach, measurements within 3D regions-of-interests (ROI) are calibrated by further ROIs such as air, adipose tissue, liver, etc. that are used as control regions (CR). Our goal is to derive general rules for an automated internal calibration that enhance prediction, based on the analysed features and a set of CRs. We define qualification criteria motivated by status-quo radiomics stability analysis techniques to only collect information from the CRs which is relevant given a respective task. These criteria are used in an optimisation to automatically derive a suitable internal calibration for prediction tasks based on the CRs. Our calibration enhanced the performance for centrilobular emphysema prediction in a COPD study and prediction of patients' one-year-survival in an oncological study.