Dataset Information

Hepatocellular Carcinoma: Texture Analysis of Preoperative Computed Tomography Images Can Provide Markers of Tumor Grade and Disease-Free Survival.

ABSTRACT: OBJECTIVE:To investigate the usefulness of computed tomography (CT) texture analysis (CTTA) in estimating histologic tumor grade and in predicting disease-free survival (DFS) after surgical resection in patients with hepatocellular carcinoma (HCC). MATERIALS AND METHODS:Eighty-one patients with a single HCC who had undergone quadriphasic liver CT followed by surgical resection were enrolled. Texture analysis of tumors on preoperative CT images was performed using commercially available software. The mean, mean of positive pixels (MPP), entropy, kurtosis, skewness, and standard deviation (SD) of the pixel distribution histogram were derived with and without filtration. The texture features were then compared between groups classified according to histologic grade. Kaplan-Meier and Cox proportional hazards analyses were performed to determine the relationship between texture features and DFS. RESULTS:SD and MPP quantified from fine to coarse textures on arterial-phase CT images showed significant positive associations with the histologic grade of HCC (p < 0.05). Kaplan-Meier analysis identified most CT texture features across the different filters from fine to coarse texture scales as significant univariate markers of DFS. Cox proportional hazards analysis identified skewness on arterial-phase images (fine texture scale, spatial scaling factor [SSF] 2.0, p < 0.001; medium texture scale, SSF 3.0, p < 0.001), tumor size (p = 0.001), microscopic vascular invasion (p = 0.034), rim arterial enhancement (p = 0.024), and peritumoral parenchymal enhancement (p = 0.010) as independent predictors of DFS. CONCLUSION:CTTA was demonstrated to provide texture features significantly correlated with higher tumor grade as well as predictive markers of DFS after surgical resection of HCCs in addition to other valuable imaging and clinico-pathologic parameters.

SUBMITTER: Oh J

PROVIDER: S-EPMC6424831 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Hepatocellular Carcinoma: Texture Analysis of Preoperative Computed Tomography Images Can Provide Markers of Tumor Grade and Disease-Free Survival.

Oh Jiseon J Lee Jeong Min JM Park Junghoan J Joo Ijin I Yoon Jeong Hee JH Lee Dong Ho DH Ganeshan Balaji B Han Joon Koo JK

Korean journal of radiology 20190401 4

<h4>Objective</h4>To investigate the usefulness of computed tomography (CT) texture analysis (CTTA) in estimating histologic tumor grade and in predicting disease-free survival (DFS) after surgical resection in patients with hepatocellular carcinoma (HCC).<h4>Materials and methods</h4>Eighty-one patients with a single HCC who had undergone quadriphasic liver CT followed by surgical resection were enrolled. Texture analysis of tumors on preoperative CT images was performed using commercially avai ...[more]

PMID: 30887739

Similar Datasets

Project description:BackgroundGastric cancer is a highly prevalent and fatal disease. Accurate differentiation between early gastric cancer (EGC) and advanced gastric cancer (AGC) is essential for personalized treatment. Currently, the diagnostic accuracy of computerized tomography (CT) for gastric cancer staging is insufficient to meet clinical requirements. Many studies rely on manual marking of lesion areas, which is not suitable for clinical diagnosis.MethodsIn this study, we retrospectively collected data from 341 patients with gastric cancer at the First Affiliated Hospital of Wenzhou Medical University. The dataset was randomly divided into a training set (n=273) and a validation set (n=68) using an 8:2 ratio. We developed a two-stage deep learning model that enables fully automated EGC screening based on CT images. In the first stage, an unsupervised domain adaptive segmentation model was employed to automatically segment the stomach on unlabeled portal phase CT images. Subsequently, based on the results of the stomach segmentation model, the image was cropped out of the stomach area and scaled to a uniform size, and then the EGC and AGC classification models were built based on these images. The segmentation accuracy of the model was evaluated using the dice index, while the classification performance was assessed using metrics such as the area under the curve (AUC) of the receiver operating characteristic (ROC), accuracy, sensitivity, specificity, and F1 score.ResultsThe segmentation model achieved an average dice accuracy of 0.94 on the hand-segmented validation set. On the training set, the EGC screening model demonstrated an AUC, accuracy, sensitivity, specificity, and F1 score of 0.98, 0.93, 0.92, 0.92, and 0.93, respectively. On the validation set, these metrics were 0.96, 0.92, 0.90, 0.89, and 0.93, respectively. After three rounds of data regrouping, the model consistently achieved an AUC above 0.9 on both the validation set and the validation set.ConclusionThe results of this study demonstrate that the proposed method can effectively screen for EGC in portal venous CT images. Furthermore, the model exhibits stability and holds promise for future clinical applications.

Project description:BackgroundIf the bony region indicating the ilioischial line is established on the preoperative axial computed tomography (CT) image, the distance between the simulated cup and the ilioischial line can be measured on this image so that the surgeon can use these data to define a more accurate preoperative two-dimensional (2D) template of total hip arthroplasty (THA). This study aimed to verify the hypothesis that on the CT axial image, the cortical bone area, indicated by the superimposition of a line (line α) with a perspective projection angle to the ilioischial line on radiography and tangent to the medial acetabular wall, is the cortical bone that represents the ilioischial line on radiography.MethodsStudy 1: If the two measured distances (distance A' and distance B) are sufficiently equal, then the hypothesis can be supported. Distance A' was calculated by multiplying the distance A, between the ilioischial line and the medial margin of the metal cup after THA measured at the level of the hip joint center on the pelvic radiograph, by 0.91 to correct for radiographic magnification. Distance B was defined as the distance between the medial margin of the metal cup and line α on the axial CT image at the level of the hip joint center. These two distances were measured for all 51 hip joints included in the study. Study 2: The difference between distance A and distance A# (distance A on the 2D template) was compared between the group containing 59 primary THAs in which distance B' was measured (distance B in the simulation) and the control group containing 59 primary THAs.ResultsStudy 1: The average distance for A' was 4.5 ± 2 mm, and the average distance for B was 4.7 ± 2.1 mm. The difference between distances A and B was 0.2 ± 0.2 mm. Study 2: The mean difference between distance A and distance A# for the measurement and control groups was 1.8 ± 1.3 mm and 3.7 ± 2.4 mm, respectively (P < 0.001).ConclusionsThe ilioischial line is located in the bony region where line α intersects the medial acetabular wall with a maximum overlap on axial CT images.

Project description:BACKGROUND:To investigate the potential value of volumetric iodine quantification using preoperative dual-energy computed tomography (DECT) for predicting microvascular invasion (MVI) of hepatocellular carcinoma (HCC). METHODS:This retrospective study included patients with single HCC treated through surgical resection who underwent preoperative DECT. Quantitative DECT features, including normalized iodine concentration (NIC) to the aorta and mixed-energy CT attenuation value in the arterial phase, were three-dimensionally measured for peritumoral and intratumoral regions: (i) layer-by-layer analysis for peritumoral layers (outer layers 1 and 2; numbered in close order from the tumor boundary) and intratumoral layers (inner layers 1 and 2) with 2-mm layer thickness and (ii) volume of interest (VOI)-based analysis with different volume coverage (tumor itself; VOIO1, tumor plus outer layer 1; VOIO2, tumor plus outer layers 1 and 2; VOII1, tumor minus inner layer 1; VOII2, tumor minus inner layers 1 and 2). In addition, qualitative CT features, including peritumoral enhancement and tumor margin, were assessed. Qualitative and quantitative CT features were compared between HCC patients with and without MVI. Diagnostic performance of DECT parameters of layers and VOIs was assessed using receiver operating characteristic curve analysis. RESULTS:A total of 36 patients (24 men, mean age 59.9 ± 8.5 years) with MVI (n = 14) and without MVI (n = 22) were included. HCCs with MVI showed significantly higher NICs of outer layer 1, outer layer 2, VOIO1, and VOIO2 than those without MVI (P = 0.01, 0.04, 0.02, 0.02, respectively). Among the NICs of layers and VOIs, the highest area under the curve was obtained in outer layer 1 (0.747). Qualitative features, including peritumoral enhancement and tumor margin, and the mean CT attenuation of each layer and each VOI were not significantly different between HCCs with and without MVI (both P > 0.05). CONCLUSIONS:Volumetric iodine quantification of peritumoral and intratumoral regions in arterial phase using DECT may help predict the MVI of HCC.

Dataset Information

Hepatocellular Carcinoma: Texture Analysis of Preoperative Computed Tomography Images Can Provide Markers of Tumor Grade and Disease-Free Survival.

Publications

Hepatocellular Carcinoma: Texture Analysis of Preoperative Computed Tomography Images Can Provide Markers of Tumor Grade and Disease-Free Survival.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets