High-dimensional imaging features extracted from diagnostic imaging, called radiomics, are increasingly reported for diagnosis, prognosis, and response to therapy. Establishing the sensitivity of radiomic features to variation in scan protocols is necessary because acquisition and reconstruction parameters can vary widely across and within institutions. Our objective was to assess the reproducibility of radiomic features derived from computed tomography (CT) images by varying tube current (mA), noise index, and reconstruction [adaptive statistical iterative reconstruction (ASiR)], parameters increasingly varied by institutions seeking to reduce radiation dose in their patients. We extracted radiomic features from CT images of a uniform water phantom, anthropomorphic phantom, and a human scan. Scans were acquired from the phantoms with six tube currents (50, 100, 200, 300, 400, and 500 mA) and five noise index levels (12, 14, 16, 18, and 20), respectively. Scans of the phantoms and patient were reconstructed from 0% ASiR (i.e., filtered back projection) to 100% ASiR in increments of 10%. Two hundred and forty-eight well-known radiomic features were extracted from all scans. The concordance correlation coefficient was used to assess agreement of features. Our analysis suggests that image acquisition parameters (tube current, noise index) as well as the reconstruction technique strongly influence radiomic feature reproducibility and demonstrate a subset of reproducible features potentially usable in clinical practice.

After portal vein embolization (PVE), the future liver remnant (FLR) hypertrophies for several weeks. An early marker that predicts a low risk of post-hepatectomy liver failure can reduce the delay to surgery. Liver volumes of 153 patients who underwent a major hepatectomy (>3 segments) after PVE for primary or secondary liver malignancy between September 1999 and November 2012 were retrospectively evaluated with computerized volumetry. Pre- and post-PVE FLR volume and functional liver volume were measured. Degree of hypertrophy (DH = post-FLR/post-functional liver volume - pre-FLR/pre-functional liver volume) and growth rate (GR = DH/weeks since PVE) were calculated. Postoperative complications and liver failure were correlated with DH, measured GR, and estimated GR derived from a formula based on body surface area. Eligible patients underwent 93 right hepatectomies, 51 extended right hepatectomies, 4 left hepatectomies, and 5 extended left hepatectomies. Major complications occurred in 44 patients (28.7%) and liver failure in 6 patients (3.9%). Nonparametric regression showed that post-embolization FLR percent correlated poorly with liver failure. Receiver operating characteristic curves showed that DH and GR were good predictors of liver failure (area under the curve [AUC] = 0.80; p = 0.011 and AUC = 0.79; p = 0.015) and modest predictors of major complications (AUC = 0.66; p = 0.002 and AUC = 0.61; p = 0.032). No patient with GR >2.66% per week had liver failure develop. The predictive value of measured GR was superior to estimated GR for liver failure (AUC = 0.79 vs 0.58; p = 0.046). Both DH and GR after PVE are strong predictors of post-hepatectomy liver failure. Growth rate might be a better guide for the optimum timing of liver resection than static volumetric measurements. Measured volumetrics correlated with outcomes better than estimated volumetrics.

Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers in the United States with a five-year survival rate of 7.2% for all stages. Although surgical resection is the only curative treatment, currently we are unable to differentiate between resectable patients with occult metastatic disease from those with potentially curable disease. Identification of patients with poor prognosis via early classification would help in initial management including the use of neoadjuvant chemotherapy or radiation, or in the choice of postoperative adjuvant therapy. PDAC ranges in appearance from homogeneously isoattenuating masses to heterogeneously hypovascular tumors on CT images; hence, we hypothesize that heterogeneity reflects underlying differences at the histologic or genetic level and will therefore correlate with patient outcome. We quantify heterogeneity of PDAC with texture analysis to predict 2-year survival. Using fuzzy minimum-redundancy maximum-relevance feature selection and a naive Bayes classifier, the proposed features achieve an area under receiver operating characteristic curve (AUC) of 0.90 and accuracy (Ac) of 82.86% with the leave-one-image-out technique and an AUC of 0.80 and Ac of 75.0% with three-fold cross-validation. We conclude that texture analysis can be used to quantify heterogeneity in CT images to accurately predict 2-year survival in patients with pancreatic cancer. From these data, we infer differences in the biological evolution of pancreatic cancer subtypes measurable in imaging and identify opportunities for optimized patient selection for therapy.

Microvascular invasion (MVI) is a significant risk factor for early recurrence after resection or transplantation for hepatocellular carcinoma (HCC). Knowledge of MVI status would help guide treatment recommendations, but is generally identified after operation. This study aims to predict MVI preoperatively using quantitative image analysis. One hundred and twenty patients from 2 institutions underwent resection of HCC from 2003 to 2015 were included. The largest tumor from preoperative CT was subjected to quantitative image analysis, which uses an automated computer algorithm to capture regional variation in CT enhancement patterns. Quantitative imaging features by automatic analysis, qualitative radiographic descriptors by 2 radiologists, and preoperative clinical variables were included in multivariate analysis to predict histologic MVI. Histologic MVI was identified in 19 (37%) patients with tumors ≤5 cm and 34 (49%) patients with tumors >5 cm. Among patients with tumors ≤5 cm, none of the clinical findings or radiographic descriptors were associated with MVI; however, quantitative features based on angle co-occurrence matrix predicted MVI with an area under curve of 0.80, positive predictive value of 63%, and negative predictive value of 85%. In patients with tumors >5 cm, higher α-fetoprotein level, larger tumor size, and viral hepatitis history were associated with MVI, and radiographic descriptors were not. However, a multivariate model combining α-fetoprotein, tumor size, hepatitis status, and quantitative feature based on local binary pattern predicted MVI with area under curve of 0.88, positive predictive value of 72%, and negative predictive value of 96%. This study reveals the potential importance of quantitative image analysis as a predictor of MVI.