Development and multicenter validation of deep convolutional neural network-based detection of colorectal cancer on abdominal CT.

OBJECTIVES: This study aims to develop computer-aided detection (CAD) for colorectal cancer (CRC) using abdominal CT based on a deep convolutional neural network. METHODS: This retrospective study included consecutive patients with colorectal adenocarcinoma who underwent abdominal CT before CRC resection surgery (training set = 379, test set = 103). We customized the 3D U-Net of nnU-Net (CUNET) for CRC detection, which was trained with fivefold cross-validation using annotated CT images. CUNET was validated using datasets covering various clinical situations and institutions: an internal test set (n = 103), internal patients with CRC first determined by CT (n = 54) and asymptomatic CRC (n = 51), and an external validation set from two institutions (n = 60). During each validation, data from the healthy population were added (internal = 60; external = 130). CUNET was compared with other deep CNNs: residual U-Net and EfficientDet. The CAD performances were evaluated using per-CRC sensitivity (true positive/all CRCs), free-response receiver operating characteristic (FROC), and jackknife alternative FROC (JAFROC) curves. RESULTS: CUNET showed a higher maximum per-CRC sensitivity than residual U-Net and EfficientDet (internal test set 91.3% vs. 61.2%, and 64.1%). The per-CRC sensitivity of CUNET at false-positive rates of 3.0 was as follows: internal CRC determined by CT, 89.3%; internal asymptomatic CRC, 87.3%; and external validation, 89.6%. CUNET detected 69.2% (9/13) of CRCs missed by radiologists and 89.7% (252/281) of CRCs from all validation sets. CONCLUSIONS: CUNET can detect CRC on abdominal CT in patients with various clinical situations and from external institutions. KEY POINTS: • Customized 3D U-Net of nnU-Net (CUNET) can be applied to the opportunistic detection of colorectal cancer (CRC) in abdominal CT, helping radiologists detect unexpected CRC. • CUNET showed the best performance at false-positive rates ≥ 3.0, and 30.1% of false-positives were in the colorectum. CUNET detected 69.2% (9/13) of CRCs missed by radiologists and 87.3% (48/55) of asymptomatic CRCs. • CUNET detected CRCs in multiple validation sets composed of varying clinical situations and from different institutions, and CUNET detected 89.7% (252/281) of CRCs from all validation sets.

Machine Learning-Based Magnetic Resonance Radiomics Analysis for Predicting Low- and High-Grade Clear Cell Renal Cell Carcinoma.

PURPOSE: To explore whether high- and low-grade clear cell renal cell carcinomas (ccRCC) can be distinguished using radiomics features extracted from magnetic resonance imaging. METHODS: In this retrospective study, 154 patients with pathologically proven clear ccRCC underwent contrast-enhanced 3 T magnetic resonance imaging and were assigned to the development (n = 122) and test (n = 32) cohorts in a temporal-split setup. A total of 834 radiomics features were extracted from whole-tumor volumes using 3 sequences: T2-weighted imaging (T2WI), diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging. A random forest regressor was used to extract important radiomics features that were subsequently used for model development using the random forest algorithm. Tumor size, apparent diffusion coefficient value, and percentage of tumor-to-renal parenchymal signal intensity drop in the tumors were recorded by 2 radiologists for quantitative analysis. The area under the receiver operating characteristic curve (AUC) was generated to predict ccRCC grade. RESULTS: In the development cohort, the T2WI-based radiomics model demonstrated the highest performance (AUC, 0.82). The T2WI-based radiomics and radiologic feature hybrid model showed AUCs of 0.79 and 0.83, respectively. In the test cohort, the T2WI-based radiomics model achieved an AUC of 0.82. The range of AUCs of the hybrid model of T2WI-based radiomics and radiologic features was 0.73 to 0.80. CONCLUSION: Magnetic resonance imaging-based classifier models using radiomics features and machine learning showed satisfactory diagnostic performance in distinguishing between high- and low-grade ccRCC, thereby serving as a helpful noninvasive tool for predicting ccRCC grade.

Diagnostic Feasibility of Magnetic Resonance Elastography Radiomics Analysis for the Assessment of Hepatic Fibrosis in Patients With Nonalcoholic Fatty Liver Disease.

OBJECTIVE: The aim of the study was to investigate the diagnostic feasibility of radiomics analysis using magnetic resonance elastography (MRE) to assess hepatic fibrosis in patients with nonalcoholic fatty liver disease (NAFLD). METHODS: One hundred patients with suspected NAFLD were retrospectively enrolled. All patients underwent a liver parenchymal biopsy. Magnetic resonance elastography was performed using a 3.0-T scanner. After multislice segmentation of MRE images, 834 radiomic features were analyzed using a commercial program. Radiologic features, such as median and mean values of the regions of interest and variable clinical features, were analyzed. A random forest regressor was used to extract important radiomic, radiological, and clinical features. A random forest classifier model was trained to use these features to classify the fibrosis stage. The area under the receiver operating characteristic curve was evaluated using a classifier for fibrosis stage diagnosis. RESULTS: The pathological hepatic fibrosis stage was classified as low-grade fibrosis (stages F0-F1, n = 82) or clinically significant fibrosis (stages F2-F4, n = 18). Eight important features were extracted from radiomics analysis, with the 2 most important being wavelet-high high low gray level dependence matrix dependence nonuniformity-normalized and wavelet-high high low gray level dependence matrix dependence entropy. The median value of the multiple small regions of interest was identified as the most important radiologic feature. Platelet count has been identified as an important clinical feature. The area under the receiver operating characteristic curve of the classifier using radiomics was comparable with that of radiologic measures (0.97 ± 0.07 and 0.96 ± 0.06, respectively). CONCLUSIONS: Magnetic resonance elastography radiomics analysis provides diagnostic performance comparable with conventional MRE analysis for the assessment of clinically significant hepatic fibrosis in patients with NAFLD.

Radiomics Analysis of Magnetic Resonance Proton Density Fat Fraction for the Diagnosis of Hepatic Steatosis in Patients With Suspected Non-Alcoholic Fatty Liver Disease.

BACKGROUND: This study aimed to assess the diagnostic feasibility of radiomics analysis based on magnetic resonance (MR)-proton density fat fraction (PDFF) for grading hepatic steatosis in patients with suspected non-alcoholic fatty liver disease (NAFLD). METHODS: This retrospective study included 106 patients with suspected NAFLD who underwent a hepatic parenchymal biopsy. MR-PDFF and MR spectroscopy were performed on all patients using a 3.0-T scanner. Following whole-volume segmentation of the MR-PDFF images, 833 radiomic features were analyzed using a commercial program. Radiologic features were analyzed, including median and mean values of the multiple regions of interest and variable clinical features. A random forest regressor was used to extract the important radiomic, radiologic, and clinical features. The model was trained using 20 repeated 10-fold cross-validations to classify the NAFLD steatosis grade. The area under the receiver operating characteristic curve (AUROC) was evaluated using a classifier to diagnose steatosis grades. RESULTS: The levels of pathological hepatic steatosis were classified as low-grade steatosis (grade, 0-1; n = 82) and high-grade steatosis (grade, 2-3; n = 24). Fifteen important features were extracted from the radiomic analysis, with the three most important being wavelet-LLL neighboring gray tone difference matrix coarseness, original first-order mean, and 90th percentile. The MR spectroscopy mean value was extracted as a more important feature than the MR-PDFF mean or median in radiologic measures. Alanine aminotransferase has been identified as the most important clinical feature. The AUROC of the classifier using radiomics was comparable to that of radiologic measures (0.94 ± 0.09 and 0.96 ± 0.08, respectively). CONCLUSION: MR-PDFF-derived radiomics may provide a comparable alternative for grading hepatic steatosis in patients with suspected NAFLD.

Active Learning for Efficient Segmentation of Liver with Convolutional Neural Network-Corrected Labeling in Magnetic Resonance Imaging-Derived Proton Density Fat Fraction.

This study aimed to propose an efficient method for self-automated segmentation of the liver using magnetic resonance imaging-derived proton density fat fraction (MRI-PDFF) through deep active learning. We developed an active learning framework for liver segmentation using labeled and unlabeled data in MRI-PDFF. A total of 77 liver samples on MRI-PDFF were obtained from patients with nonalcoholic fatty liver disease. For the training, tuning, and testing of the liver segmentation, the ground truth of 71 (internal) and 6 (external) MRI-PDFF scans for training and testing were verified by an expert reviewer. For 100 randomly selected slices, manual and deep learning (DL) segmentations for visual assessments were classified, ranging from very accurate to mostly accurate. The dice similarity coefficients for each step were 0.69 ± 0.21, 0.85 ± 0.12, and 0.94 ± 0.01, respectively (p-value = 0.1389 between the first step and the second step or p-value = 0.0144 between the first step and the third step for paired t-test), indicating that active learning provides superior performance compared with non-active learning. The biases in the Bland-Altman plots for each step were - 24.22% (from - 82.76 to - 2.70), - 21.29% (from - 59.52 to 3.06), and - 0.67% (from - 10.43 to 4.06). Additionally, there was a fivefold reduction in the required annotation time after the application of active learning (2 min with, and 13 min without, active learning in the first step). The number of very accurate slices for DL (46 slices) was greater than that for manual segmentations (6 slices). Deep active learning enables efficient learning for liver segmentation on a limited MRI-PDFF.

Predicting cannulation difficulty in endoscopic retrograde cholangiopancreatography using CT image findings: a decision-tree analysis.

BACKGROUND: Difficult cannulation during endoscopic retrograde cholangiopancreatography (ERCP) is associated with increased complications; therefore, its prediction is important. PURPOSE: To identify radiologic risk factors of difficult cannulation during ERCP based on computed tomography (CT) findings and to develop a predictive model for a difficult cannulation. MATERIAL AND METHODS: A total of 171 patients with native papilla who underwent both enhanced CT and ERCP were recruited. Two radiologists independently measured the distal common bile duct (CBD) diameter and choledochoduodenal (CD) angle and analyzed CT images for presence of CBD stone and papilla bulging, size and type of periampullary diverticulum (PAD), and duodenal segment in which major papilla was located. Multivariate logistic regression analysis and decision-tree analysis were performed to identify risk factors for difficult cannulation. RESULTS: Thirty-nine patients underwent a difficult cannulation. The multivariate logistic regression analysis revealed that a smaller CBD diameter, presence of papilla bulging, location of the major papilla other than the descending duodenum, a smaller CD angle, and a higher worrisome PAD score were statistically relevant factors for difficult cannulation (P < 0.049). In the decision-tree analysis, a higher worrisome PAD score was the strongest predictor of difficult cannulation, followed by the presence of papilla bulging, smaller CD angle, and a smaller CBD diameter. The predictive model had an 82.5% overall predictive accuracy. CONCLUSION: The CT findings-based decision-tree analysis model showed a high accuracy in predicting cannulation difficulty and may be helpful for making pre-ERCP strategy.

Predicting the Development of Surgically Induced Chronic Kidney Disease After Total Nephrectomy Using Body Surface Area-Adjusted Renal Cortical Volume on CT Angiography.

OBJECTIVE: The purpose of this study was to predict the probability of surgically induced chronic kidney disease (CKD) developing in patients who underwent total nephrectomy by measuring the body surface area (BSA)-adjusted renal cortical volume (RCV) with preoperative CT angiography (CTA). MATERIALS AND METHODS: A total of 105 patients with a normal preoperative estimated glomerular filtration rate (eGFR) who underwent preoperative CTA and subsequent total nephrectomy for kidney donation (n = 67) or a renal tumor (n = 38) were included in this retrospective study. Patients were divided into group A (patients without surgically induced CKD; n = 61) and group B (patients with surgically induced CKD; n = 44) according to postoperative renal function. The preoperative and postoperative eGFR and other laboratory findings were collected, and the BSA-adjusted postnephrectomy RCV was measured using a semiautomated segmentation technique on CTA. Multiple logistic regression analysis was used to determine the formula for predicting the probability of development of surgically induced CKD; external validation was conducted using the validation dataset (n = 28). RESULTS: The estimated probability of surgically induced CKD developing can be calculated using the following formula: logit (probability of surgically induced CKD developing) = [1.431 × I (reason for operation was renal tumor)] + (-0.097 × preoperative eGFR) + (-0.033 × BSA-adjusted postnephrectomy RCV) + 10.937, where I denotes an indicator function (I = 1, reason for operation was renal tumor; I = 0, reason for operation was kidney donation). The optimal cutoff value derived from 10,000 bootstrapped samples was 0.444 (95% CI, 0.298-0.681). The formula was determined to be a good tool for prediction of surgically induced CKD on external validation (AUC value, 0.894). CONCLUSION: The probability of CKD developing in patients who undergo total nephrectomy may be predicted using a BSA-adjusted postnephrectomy RCV volume measured on preoperative CTA.

Hepatic Parenchymal Heterogeneity as a Marker for Oxaliplatin-Induced Sinusoidal Obstruction Syndrome: Correlation With Treatment Response of Colorectal Cancer Liver Metastases.

OBJECTIVE: The objective of our study was to evaluate the influence of oxaliplatin-based chemotherapy (OBC)-induced hepatic parenchymal heterogeneity detected on contrast-enhanced CT scans on response of liver metastasis. We chose to study hepatic parenchymal heterogeneity on the basis of the assumption that hepatic parenchymal heterogeneity may indicate the presence of chemotherapy-induced sinusoidal obstruction syndrome (SOS). MATERIALS AND METHODS: For this retrospective study, 104 patients with hepatic metastases from colorectal cancer (male-female ratio, 66:38; age range, 20-80 years) who had undergone OBC and serial CT studies were consecutively registered. Two blinded imagers independently scored CT images using a 5-point scale to determine the severity of newly developed hepatic parenchymal heterogeneity after OBC. Subsequently, two radiologists evaluated tumor response to OBC using a 4-point ordinal scale. We performed generalized estimating equation (GEE) analysis using cumulative logits to account for the effect of hepatic parenchymal heterogeneity severity on the cumulative tumor response probability. RESULTS: The interobserver agreements for the severity of hepatic parenchymal heterogeneity were excellent (κ = 0.825). GEE analyses showed that the severity of post-OBC hepatic parenchymal heterogeneity, number of chemotherapy sessions, and presence of other organ metastases were significant predictors of tumor response; these three factors also showed significance in the final GEE model (p < 0.0001 for severity of hepatic parenchymal heterogeneity for both readers; p = 0.011 and 0.010 for the number of chemotherapy sessions for readers 1 and 2; p = 0.046 and 0.012 for the presence of other organ metastases for readers 1 and 2). CONCLUSION: Hepatic parenchymal heterogeneity detected on contrast-enhanced CT of patients with hepatic metastases from colorectal cancer who have undergone OBC may indicate the presence of SOS, and the more severe the SOS, the worse the tumor response of hepatic metastasis to oxaliplatin is expected to be.

Magnetic Resonance Imaging-Based Prostate-Specific Antigen Density for Prediction of Gleason Score Upgrade in Patients With Low-Risk Prostate Cancer on Initial Biopsy.

OBJECTIVE: The aim of this study was to assess the utility of prostate-specific antigen density (PSAD) calculated using magnetic resonance imaging for predicting Gleason score (GS) upgrade in patients with low-risk prostate cancer on biopsy. METHODS: Seventy-three patients were divided into 2 groups according to the concordance between biopsy and prostatectomy GS: group 1 (6/6) and group 2 (6/≥7). Magnetic resonance imaging-based PSAD, prostate volume, prostate-specific antigen (PSA), and age were compared between the 2 groups. Logistic regression and receiver operating characteristic curve analysis were performed. RESULTS: Gleason score was upgraded in 40 patients. Patients in group 2 had significantly higher PSAD and PSA values and smaller prostate volume than did those in group 1. Prostate-specific antigen density of 0.26 ng/mL per cm or higher, PSA of 7.63 ng/mL or higher, and prostate volume of 25.1 cm or less were related to GS upgrade, with area-under-the-curve values of 0.765, 0.721, and 0.639, respectively. CONCLUSIONS: Magnetic resonance imaging-based PSAD could help in predicting postoperative GS upgrade in patients with low-risk prostate cancer.

Correlation of CT imaging features and tumor size with Fuhrman grade of clear cell renal cell carcinoma.

Background Identification of clinical features to determine the aggressive potential of tumors is highly warranted to stratify patients for adequate treatment. Computed tomography (CT) imaging features of clear cell renal cell carcinoma (ccRCC) may contribute to personalized risk assessment. Purpose To assess the correlation between CT imaging features and Fuhrman grade of ccRCC, and to identify the predictors of high Fuhrman grade in conjunction with tumor size. Material and Methods CT scans of 169 patients with 173 pathologically proven ccRCCs were retrospectively reviewed in consensus by two radiologists for the presence of intratumoral necrosis and intratumoral cyst and tumor size. Histologic grade was classified as either low (Fuhrman grade I or II) or high (Fuhrman grade III or IV). Statistical significance was evaluated by using univariate, multivariate regression, receiver operating characteristic (ROC) curve, and Spearman correlation analyses. Results On CT, 20 of the 173 tumors had intratumoral cysts, 60 had intratumoral necrosis, and 93 showed entirely solid tumors. The odds of high grade were higher with intratumoral necrosis and entirely solid tumor than with intratumoral cyst ( P < 0.03). Intratumoral necrosis showed a significantly high odds ratio of 25.73 for high Fuhrman grade. The ROC curve showed a threshold tumor size of 36 mm to predict high Fuhrman grade for overall tumors (area under the ROC curve, 0.70). In ccRCCs with intratumoral necrosis or cyst, tumor size did not significantly correlate with Fuhrman grade. Conclusion Intratumoral necrosis on CT was a strong and independent predictor of biologically aggressive ccRCCs, irrespective of tumor size.

Hepatic Parenchymal Heterogeneity on Contrast-enhanced CT Scans Following Oxaliplatin-based Chemotherapy: Natural History and Association with Clinical Evidence of Sinusoidal Obstruction Syndrome.

PURPOSE: To evaluate the natural history and contrast material-enhanced computed tomographic (CT) features of postoxaliplatin heterogeneity of liver parenchyma (POHL) and to investigate the association of POHL with clinical factors and biomarkers of sinusoidal obstruction syndrome (SOS). MATERIALS AND METHODS: The retrospective study was approved by the institutional review board, and informed consent was waived. Two hundred seventy patients (159 men, 111 women; age range, 31-92 years) who underwent oxaliplatin-based chemotherapy (OBC) and serial contrast-enhanced CT were consecutively registered. POHL severity was independently scored by two abdominal imagers, who were blinded to the clinical data, using a six-point scale (POHL presence, ≥4), followed by a consensus review. Complete radiologic remission was determined by consensus on the disappearance of heterogeneity on CT images. The association of POHL severity score with CT-based quantitative (ie, change in spleen size and blood-free hepatic parenchymal attenuation) and laboratory values (ie, aspartate aminotransferase, alanine transaminase, and platelet count), as well as time to complete radiologic remission, were evaluated with the Spearman rank test. Multivariate analysis was performed to determine the association between clinical factors of SOS (ie, age, sex, number of OBC sessions, chemotherapy regimen, bevacizumab use, and presence of concomitant hepatic metastasis) and POHL development. RESULTS Interobserver agreement was excellent (κ = 0.90). POHL was present in 167 (61.9%) of 270 patients, and the number of OBC sessions was significantly associated with POHL development (odds ratio, 1.138; 95% confidence interval: 1.039, 1.245; P = .005). POHL severity score was correlated with quantitative CT and laboratory values (P < .05 for all statistical analysis). Peripheral distribution (103 of 167, 61.7%) and right lobar predominance (103 of 165, 62.4%) were the most common POHL features. The mean time to complete radiologic remission, which was correlated with POHL severity score, was 82.5 days ± 68.8 after OBC discontinuation. CONCLUSION: POHL development is associated with increased number of OBC sessions, and POHL severity was correlated with various biomarkers of SOS.

Immunoglobulin G4-related paratesticular fibrous pseudotumor and retroperitoneal fibrosis: a case report.

A 46-year-old man with a past history of retroperitoneal fibrosis was admitted with an enlarged, hard right testis. The paratesticular lesion showed heterogeneous hypoechogenicity on ultrasonography, low signal intensity on T1- and T2-weighted magnetic resonance imaging (MRI), and lack of diffusion restriction on diffusion-weighted MRI. Following steroid treatment, the paratesticular mass was decreased in size on follow-up computed tomography. The radiologic and clinical features are recognized as a manifestation of immunoglobulin G4-related sclerosing disease involving the paratesticular region and retroperitoneum.

Chemotherapy-induced focal hepatopathy in patients with gastrointestinal malignancy: gadoxetic acid--enhanced and diffusion-weighted MR imaging with clinical-pathologic correlation.

PURPOSE: To retrospectively evaluate findings of chemotherapy-induced focal hepatopathy (CIFH) on gadoxetic acid-enhanced magnetic resonance (MR) and diffusion-weighted (DW) images and to determine imaging features that are most helpful in differentiating CIFH from metastasis. MATERIALS AND METHODS: This retrospective study was approved by the institutional review board, and informed consent was waived. MR images, including DW images and gadoxetic acid-enhanced images, from 12 patients (four men, eight women; age range, 25-64 years) with 15 CIFHs were reviewed independently and in consensus by two radiologists and were compared with those obtained in 20 control patients (12 men, eight women; age range, 32-84 years) with 30 hepatic metastasis who were matched for tumor size, primary organ, and chemotherapy regimen. Interobserver agreement was assessed with κ statistics, and univariate analysis was performed for comparisons. For quantitative analyses, apparent diffusion coefficients (ADCs) and lesion-to-liver contrast ratios (CRs) were measured. Histopathologic examinations were performed for CIFHs. RESULTS: Histopathologic examination revealed that the development of CIFHs was attributable to accentuated manifestations of sinusoidal obstruction syndrome. Interobserver agreement was excellent (κ > 0.85). An ill-defined margin on hepatobiliary phase (HBP) images was the most discriminating independent variable in the differentiation of CIFH from metastasis (odds ratio, 16; P = .009). ADC and CR values in CIFH group were significantly higher than those in metastasis group (P < .001 and P = .041). CONCLUSION: CIFH should be considered a mimicker of metastasis in patients with gastrointestinal malignancy during chemotherapy. CIFH can be differentiated from metastasis on the basis of gadoxetic acid-enhanced MR and DW imaging findings; an ill-defined margin on HBP images was especially characteristic.

Imaging features of growing teratoma syndrome following a malignant ovarian germ cell tumor.

OBJECTIVE: To access imaging findings of growing teratoma syndrome (GTS), which is a rare complication of malignant ovarian germ cell tumor (GCT) after chemotherapy. METHODS: Five patients met the criteria for GTS. Computed tomography and magnetic resonance images were retrospectively reviewed by 2 radiologists in consensus for margin, attenuation, and the presence of gross fat or calcification of GTS lesions, which were compared with primary GCTs regarding tumor composition. RESULTS: Growing teratoma syndrome lesions were characterized as follows: poorly circumscribed, diffuse peritoneal masses in 2 patients; well-circumscribed, localized peritoneal masses in 1 patient, and ovarian masses in 2 patients. Features more noticeable in GTS lesions were more prominent fatty components in 4 patients and purely cystic lesion in 1 patient. CONCLUSIONS: Growing teratoma syndrome can be manifested as intraperitoneal masses with an increased fatty or cystic component. Radiologists should consider GTS when there are such masses on follow-up imaging studies in patients with malignant ovarian GCT.

Imaging of complications associated with port access of abdominal laparoscopic surgery.

Advanced techniques and equipment in laparoscopic surgery offer advantages over open surgery, expanding the application of this minimally invasive procedure to a wide range of abdominal operations that used to be performed as an open procedure. Laparoscopic surgery is performed in the closed abdominal cavity in which the space is limited. To create a working space in the abdominal cavity, an artificial pneumoperitoneum is established and multiple ports are placed for the introduction of various laparoscopic instruments. Unlike open surgery in which the incision is made just above the target organ, laparoscopic access is made away from the area of dissection, with the instruments triangulated around the target organ within the abdomen. This fundamental difference in approach between the open and laparoscopic procedures may lead to peculiar postoperative complications after laparoscopic surgery, which may be present away from the target organ or in the abdominal wall, and be easily missed on postoperative imaging studies. These complications include port-related direct organ injuries, such as abdominal organ or vascular injury; abdominal wall complications related to laparoscopic port insertion such as vascular injury, infection, and hernia; abdominal wall complications related to specimen removal, such as port site tumor seeding and endometriosis; and complications related to gas insufflation. The radiologist plays an important role in the diagnosis of complications after laparoscopic surgery, and therefore should be familiar with the features of such complications on imaging scans in the era of laparoscopic surgeries.

Modified fusion imaging combining CT gastrography and CT angiography: an initial experience of preoperative mapping prior to laparoscopic exogastric wedge resection of small (<3 cm) gastric submucosal lesions.

PURPOSE: To evaluate the feasibility of modified fusion imaging (MFI) combining CT gastrography (CTG) and CT angiography (CTA) in the preoperative mapping and intraoperative localization of small (<3 cm) submucosal lesions (SMLs) during laparoscopic exogastric wedge resection. METHODS: Thirty consecutive patients scheduled for laparoscopic wedge resection of small SMLs (<3 cm) were enrolled. MFI was reconstructed using a volume rendering of the arterial phase CT data acquired after gastric distension. With MFI, the possibility of preoperative mapping and feasibility for successful intraoperative localization was evaluated using intraoperative findings as the reference standard. RESULTS: In 21 of 30 patients (70%), preoperative mapping was possible. Preoperative mapping was feasible for successful intraoperative localization in 13 of 14 patients (93%) who underwent exogastric resection. CONCLUSIONS: MFI combining CTG and CTA is a feasible method for developing preoperative and intraoperative "road maps" for performing laparoscopic exogastric wedge resection of small SMLs.

Development and validation of CT­based radiomics model of PET-negative residual CT masses: a potential biomarker for predicting relapse­free survival in non-Hodgkin lymphoma patients showing complete metabolic response.

PURPOSE: PET-negative residual CT masses (PnRCMs) are usually dismissed as nonviable post-treatment lesions in non-Hodgkin lymphoma (NHL) patients showing complete metabolic response (CMR). We aimed to develop and validate computed tomography (CT)-based radiomics model of PET-negative residual CT mass (PnRCM) for predicting relapse-free survival (RFS) in NHL patients showing CMR. METHODS: A total of 224 patients who showed CMR after completing first-line chemotherapy for PET-avid NHL were recruited for model development. Patients with PnRCM were selected in accordance with the Lugano classification. Three-dimensional segmentation was done by two readers. Radiomic scores (RS) were constructed using features extracted using the Least-absolute shrinkage and selection operator analysis among radiomics features of PnRCMs showing more than substantial interobserver agreement (> 0.6). Cox regression analysis was performed with clinical and radiologic features. The performance of the model was evaluated using area under the curve (AUC). For validation, 153 patients from an outside hospital were recruited and analyzed in the same way. RESULTS: In the model development cohort, 68 (30.4%) patients had PnRCM. Kaplan-Meier analysis showed that patients with PnRCM had significantly (p = 0.005) shorter RFS than those without PnRCM. In Kaplan-Meier analysis, the high RS group showed significantly (p = 0.038) shorter RFS than the low-scoring group. Multivariate Cox regression analysis showed that high IPI score [hazard ratio (HR) 2.46; p = 0.02], treatment without rituximab (HR 3.821; p = 0.019) were factors associated with shorter RFS. In estimating RFS, combined model in both development and validation cohort showed AUC values of 0.81. CONCLUSION: The combined model that incorporated both clinical parameters and CT-based RS showed good performance in predicting relapse in NHL patients with PnRCM.

Hepatocellular carcinoma pathologic grade prediction using radiomics and machine learning models of gadoxetic acid-enhanced MRI: a two-center study.

PURPOSE: To develop a radiomics-based hepatocellular carcinoma (HCC) grade classifier model based on data from gadoxetic acid-enhanced MRI. METHODS: This retrospective study included 137 patients who underwent hepatectomy for a single HCC and gadoxetic acid-enhanced MRI within 60 days before surgery. HCC grade was categorized as low or high (modified Edmondson-Steiner grade I-II vs. III-IV). We used the hepatobiliary phase (HBP), portal venous phase, T2-weighted image(T2WI), and T1-weighted image(T1WI). From the volume of interest in HCC, 833 radiomic features were extracted. Radiomic and clinical features were selected using a random forest regressor, and the classification model was trained and validated using a random forest classifier and tenfold stratified cross-validation. Eight models were developed using the radiomic features alone or by combining the radiomic and clinical features. Models were validated with internal enrolled data (internal validation) and a dataset (28 patients) at a separate institution (external validation). The area under the curve (AUC) of the validation results was compared using the DeLong test. RESULTS: In internal and external validation, the HBP radiomics-only model showed the highest AUC (internal 0.80 ± 0.09, external 0.70 ± 0.09). In external validation, all models showed lower AUC than those for internal validation, while the T2WI and T1WI models failed to predict the HCC grade (AUC 0.30-0.58) in contrast to the internal validation results (AUC 0.67-0.78). CONCLUSION: The radiomics-based machine learning model from gadoxetic acid-enhanced liver MRI could distinguish between low- and high-grade HCCs. The radiomics-only HBP model showed the best AUC among the eight models, good performance in internal validation, and fair performance in external validation.

Accuracy of MRI for predicting anterior peritoneal reflection involvement in locally advanced rectal cancer: a comparison with operative findings.

PURPOSE: To assess the diagnostic accuracy of preoperative rectal MRI for anterior peritoneal reflection (APR) involvement in rectal cancer through comparison with the surgeon's operative findings. METHODS: This retrospective study was approved by the institutional review board; informed consent was waived. We enrolled 55 consecutive patients with suspected locally advanced mid-to-upper rectal cancer. All patients underwent rectal MRI using a 3T system. APR involvement in rectal cancer was assessed radiologically using a 5-point scale by two independent board-certified abdominal radiologists. The surgeon's evaluation during surgery was regarded as the gold standard for APR involvement. The accuracy of rectal MRI in predicting APR involvement was obtained. RESULTS: Rectal MRI showed good APR identification (rater 1, 92.7%; rater 2, 94.7%). On preoperative rectal MRI, rater 1 diagnosed 19 (34.5%) patients as having APR involvement and rater 2 diagnosed 28 (50.9%) as having APR involvement. There was moderate agreement (κ = 0.602, p < 0.001) between the two raters with regard to the evaluation of APR involvement. During surgery, the surgeon confirmed APR involvement in 13 (23.6%) patients. The sensitivity, specificity, PPV, and NPV of preoperative MRI for APR involvement were 69.2%, 76.2%, 47.4%, and 88.9%, respectively. The diagnostic accuracy of MRI for predicting APR involvement was 74.6%. CONCLUSION: Preoperative rectal MRI provides accurate anatomical information regarding APR involvement with high conspicuity. However, MRI has relatively low sensitivity (< 70%) and a low PPV (< 50%) with regard to the assessment of APR involvement in rectal tumors. Both rater 1 and rater 2 evaluated these images as positive involvement of APR. The patient underwent laparoscopic low anterior resection after preoperative evaluation. However, during surgery, the surgeon evaluated APR involvement as negative, and the final pathologic staging was confirmed as T3.