Comparison contrast-enhanced CT with contrast-enhanced US in diagnosing combined hepatocellular-cholangiocarcinoma: a propensity score-matched study.

OBJECTIVES: To develop and compare noninvasive models for differentiating between combined hepatocellular-cholangiocarcinoma (cHCC-CCA) and HCC based on serum tumor markers, contrast-enhanced ultrasound (CEUS), and computed tomography (CECT). METHODS: From January 2010 to December 2021, patients with pathologically confirmed cHCC-CCA or HCC who underwent both preoperative CEUS and CECT were retrospectively enrolled. Propensity scores were calculated to match cHCC-CCA and HCC patients with a near-neighbor ratio of 1:2. Two predicted models, a CEUS-predominant (CEUS features plus tumor markers) and a CECT-predominant model (CECT features plus tumor markers), were constructed using logistic regression analyses. Model performance was evaluated by the area under the curve (AUC), sensitivity, specificity, and accuracy. RESULTS: A total of 135 patients (mean age, 51.3 years ± 10.9; 122 men) with 135 tumors (45 cHCC-CCA and 90 HCC) were included. By logistic regression analysis, unclear boundary in the intratumoral nonenhanced area, partial washout on CEUS, CA 19-9 > 100 U/mL, lack of cirrhosis, incomplete tumor capsule, and nonrim arterial phase hyperenhancement (APHE) volume < 50% on CECT were independent factors for a diagnosis of cHCC-CCA. The CECT-predominant model showed almost perfect sensitivity for cHCC-CCA, unlike the CEUS-predominant model (93.3% vs. 55.6%, p < 0.001). The CEUS-predominant model showed higher diagnostic specificity than the CECT-predominant model (80.0% vs. 63.3%; p = 0.020), especially in the ≤ 5 cm subgroup (92.0% vs. 70.0%; p = 0.013). CONCLUSIONS: The CECT-predominant model provides higher diagnostic sensitivity than the CEUS-predominant model for CHCC-CCA. Combining CECT features with serum CA 19-9 > 100 U/mL shows excellent sensitivity. CRITICAL RELEVANCE STATEMENT: Combining lack of cirrhosis, incomplete tumor capsule, and nonrim arterial phase hyperenhancement (APHE) volume < 50% on CECT with serum CA 19-9 > 100 U/mL shows excellent sensitivity in differentiating cHCC-CCA from HCC. KEY POINTS: 1. Accurate differentiation between cHCC-CCA and HCC is essential for treatment decisions. 2. The CECT-predominant model provides higher accuracy than the CEUS-predominant model for CHCC-CCA. 3. Combining CECT features and CA 19-9 levels shows a sensitivity of 93.3% in diagnosing cHCC-CCA.

Effectiveness of a socioecological model-guided, smart device-based, self-management-oriented lifestyle intervention in community residents: protocol for a cluster-randomized controlled trial.

BACKGROUND: Healthy lifestyles are crucial for preventing chronic diseases. Nonetheless, approximately 90% of Chinese community residents regularly engage in at least one unhealthy lifestyle. Mobile smart devices-based health interventions (mHealth) that incorporate theoretical frameworks regarding behavioral change in interaction with the environment may provide an appealing and cost-effective approach for promoting sustainable adaptations of healthier lifestyles. We designed a randomized controlled trial (RCT) to evaluate the effectiveness of a socioecological model-guided, smart device-based, and self-management-oriented lifestyles (3SLIFE) intervention, to promote healthy lifestyles among Chinese community residents. METHODS: This two-arm, parallel, cluster-RCT with a 6-month intervention and 6-month follow-up period foresees to randomize a total of 20 communities/villages from 4 townships in a 1:1 ratio to either intervention or control. Within these communities, a total of at least 256 community residents will be enrolled. The experimental group will receive a multi-level intervention based on the socioecological model supplemented with a multi-dimensional empowerment approach. The control group will receive information only. The primary outcome is the reduction of modifiable unhealthy lifestyles at six months, including smoking, excess alcohol consumption, physical inactivity, unbalanced diet, and overweight/obesity. A reduction by one unhealthy behavior measured with the Healthy Lifestyle Index Score (HLIS) will be considered favorable. Secondary outcomes include reduction of specific unhealthy lifestyles at 3 months, 9 months, and 12 months, and mental health outcomes such as depression measured with PHQ-9, social outcomes such as social support measured with the modified Multidimensional Scale of Perceived Social Support, clinical outcomes such as obesity, and biomedical outcomes such as the development of gut microbiota. Data will be analyzed with mixed effects generalized linear models with family and link function determined by outcome distribution and accounting for clustering of participants in communities. DISCUSSION: This study will provide evidence concerning the effect of a mHealth intervention that incorporates a behavioral change theoretical framework on cultivating and maintaining healthy lifestyles in community residents. The study will provide insights into research on and application of similar mHealth intervention strategies to promote healthy lifestyles in community populations and settings. TRIAL REGISTRATION NUMBER: ChiCTR2300070575. Date of registration: April 17, 2023. https://www.chictr.org.cn/index.aspx .

A nomogram based on clinical factors and CT radiomics for predicting anti-MDA5+ DM complicated by RP-ILD.

OBJECTIVES: Anti-melanoma differentiation-associated gene 5 antibody-positive (anti-MDA5+) DM complicated by rapidly progressive interstitial lung disease (RP-ILD) has a high incidence and poor prognosis. The objective of this study was to establish a model for the prediction and early diagnosis of anti-MDA5+ DM-associated RP-ILD based on clinical manifestations and imaging features. METHODS: A total of 103 patients with anti-MDA5+ DM were included. The patients were randomly split into training and testing sets of 72 and 31 patients, respectively. After image analysis, we collected clinical, imaging and radiomics features from each patient. Feature selection was performed first with the minimum redundancy and maximum relevance algorithm and then with the best subset selection method. The final remaining features comprised the radscore. A clinical model and imaging model were then constructed with the selected independent risk factors for the prediction of non-RP-ILD and RP-ILD. We also combined these models in different ways and compared their predictive abilities. A nomogram was also established. The predictive performances of the models were assessed based on receiver operating characteristics curves, calibration curves, discriminability and clinical utility. RESULTS: The analyses showed that two clinical factors, dyspnoea (P = 0.000) and duration of illness in months (P = 0.001), and three radiomics features (P = 0.001, 0.044 and 0.008, separately) were independent predictors of non-RP-ILD and RP-ILD. However, no imaging features were significantly different between the two groups. The radiomics model built with the three radiomics features performed worse than the clinical model and showed areas under the curve (AUCs) of 0.805 and 0.754 in the training and test sets, respectively. The clinical model demonstrated a good predictive ability for RP-ILD in MDA5+ DM patients, with an AUC, sensitivity, specificity and accuracy of 0.954, 0.931, 0.837 and 0.847 in the training set and 0.890, 0.875, 0.800 and 0.774 in the testing set, respectively. The combination model built with clinical and radiomics features performed slightly better than the clinical model, with an AUC, sensitivity, specificity and accuracy of 0.994, 0.966, 0.977 and 0.931 in the training set and 0.890, 0.812, 1.000 and 0.839 in the testing set, respectively. The calibration curve and decision curve analyses showed satisfactory consistency and clinical utility of the nomogram. CONCLUSION: Our results suggest that the combination model built with clinical and radiomics features could reliably predict the occurrence of RP-ILD in MDA5+ DM patients.

Novel Computed-Tomography-Based Transformer Models for the Noninvasive Prediction of PD-1 in Pre-Operative Settings.

The expression status of programmed cell death protein 1 (PD-1) in patients with hepatocellular carcinoma (HCC) is associated with the checkpoint blockade treatment responses of PD-1/PD-L1. Thus, accurately and preoperatively identifying the status of PD-1 has great clinical implications for constructing personalized treatment strategies. To investigate the preoperative predictive value of the transformer-based model for identifying the status of PD-1 expression, 93 HCC patients with 75 training cohorts (2859 images) and 18 testing cohorts (670 images) were included. We propose a transformer-based network architecture, ResTransNet, that efficiently employs convolutional neural networks (CNNs) and self-attention mechanisms to automatically acquire a persuasive feature to obtain a prediction score using a nonlinear classifier. The area under the curve, receiver operating characteristic curve, and decision curves were applied to evaluate the prediction model's performance. Then, Kaplan-Meier survival analyses were applied to evaluate the overall survival (OS) and recurrence-free survival (RFS) in PD-1-positive and PD-1-negative patients. The proposed transformer-based model obtained an accuracy of 88.2% with a sensitivity of 88.5%, a specificity of 88.9%, and an area under the curve of 91.1% in the testing cohort.

Magnetic Resonance Imaging to Assess Body Composition Change in Adolescents With Obesity After Sleeve Gastrectomy.

OBJECTIVES: Metabolic and bariatric surgery is the most effective weight loss treatment for severe obesity. The number of adolescents undergoing sleeve gastrectomy is increasing. We investigated changes in body composition in adolescents undergoing sleeve gastrectomy 12-26 weeks post-operatively using whole-body magnetic resonance imaging (WB-MRI). METHODS: This prospective cohort study assessed changes in adipose tissue compartments (ie, visceral, subcutaneous, and intermuscular) and muscle in 18 obese adolescents, ages 14-19, 89% female, with body mass index z -score of 2.6 ± 0.25 (range 2.16-3.2). All underwent WB-MRI 1.5-17 weeks pre-operatively and 12-26 weeks post-operatively. RESULTS: Pre- and post-operative WB-MRI showed decreases in all adipose tissue compartments, as well as decreased skeletal muscle and liver fat fraction ( P < 0.0001). The post-operative percentage loss of adipose tissue in subcutaneous, visceral, and intermuscular compartments (89.0%, 5.8%, 5.2%, respectively) was similar to the pre-operative percentages of corresponding adipose tissue compartments (90.5%, 5.0%, 4.5%, respectively). Of note, participants with obstructive sleep apnea had significantly higher pre-operative volume of subcutaneous and intermuscular adipose tissue than participants without obstructive sleep apnea ( P = 0.003). CONCLUSIONS: We found, contrary to what is reported to occur in adults, that pre-operative percentage loss of adipose tissue in subcutaneous, visceral, and intermuscular compartments was similar to the post-operative percentage loss of corresponding adipose tissue compartments in adolescents 12-26 weeks after sleeve gastrectomy.

Radiomics signature: A potential biomarker for ß-arrestin1 phosphorylation prediction in hepatocellular carcinoma.

BACKGROUND: The phosphorylation status of ß-arrestin1 influences its function as a signal strongly related to sorafenib resistance. This retrospective study aimed to develop and validate radiomics-based models for predicting ß-arrestin1 phosphorylation in hepatocellular carcinoma (HCC) using whole-lesion radiomics and visual imaging features on preoperative contrast-enhanced computed tomography (CT) images. AIM: To develop and validate radiomics-based models for predicting ß-arrestin1 phosphorylation in HCC using radiomics with contrast-enhanced CT. METHODS: Ninety-nine HCC patients (training cohort: n = 69; validation cohort: n = 30) receiving systemic sorafenib treatment after surgery were enrolled in this retrospective study. Three-dimensional whole-lesion regions of interest were manually delineated along the tumor margins on portal venous CT images. Radiomics features were generated and selected to build a radiomics score using logistic regression analysis. Imaging features were evaluated by two radiologists independently. All these features were combined to establish clinico-radiological (CR) and clinico-radiological-radiomics (CRR) models by using multivariable logistic regression analysis. The diagnostic performance and clinical usefulness of the models were measured by receiver operating characteristic and decision curves, and the area under the curve (AUC) was determined. Their association with prognosis was evaluated using the Kaplan-Meier method. RESULTS: Four radiomics features were selected to construct the radiomics score. In the multivariate analysis, alanine aminotransferase level, tumor size and tumor margin on portal venous phase images were found to be significant independent factors for predicting ß-arrestin1 phosphorylation-positive HCC and were included in the CR model. The CRR model integrating the radiomics score with clinico-radiological risk factors showed better discriminative performance (AUC = 0.898, 95%CI, 0.820 to 0.977) than the CR model (AUC = 0.794, 95%CI, 0.686 to 0.901; P = 0.011), with increased clinical usefulness confirmed in both the training and validation cohorts using decision curve analysis. The risk of ß-arrestin1 phosphorylation predicted by the CRR model was significantly associated with overall survival in the training and validation cohorts (log-rank test, P < 0.05). CONCLUSION: The radiomics signature is a reliable tool for evaluating ß-arrestin1 phosphorylation which has prognostic significance for HCC patients, providing the potential to better identify patients who would benefit from sorafenib treatment.

Enhanced computed tomography features predict pancreatic neuroendocrine neoplasm with Ki-67 index less than 5.

BACKGROUND: Several studies have suggested that patients with pancreatic neuroendocrine neoplasm (pNEN) with the Ki-67 index of < 5% are more likely to show better prognosis after clinical intervention. Moreover, the Ki-67 index at 5% has also been suggested as a potential threshold by the 2016 European Neuroendocrine Tumor Society guidelines. OBJECTIVE: Based on preoperative enhanced computed tomography (CT), this study aimed to investigate imaging characteristics eligible to discriminate the ≤ 5% Ki-67 group from the > 5% Ki-67 group of patients with nonmetastatic pNEN. METHODS: Patients with pathologically diagnosed pNEN and preoperative multiphase CT were enrolled. Their Ki-67 index was calculated and grouped according to the 5% cutoff value. The following CT imaging characteristics and some serum biomarkers were assessed between the two groups: the diameter, location, tumor margin, calcification, pancreatic atrophy, distal pancreatic duct dilation, vessel involvement, and enhancement pattern characteristics of both arterial phase (AP) and portal vein phase (PVP). RESULTS: A total of 142 patients with pNEN were enrolled in this study, comprising 104 in the low (Ki-67, 1%-5%) and 38 in the high index group (Ki-67, >5%). Alpha fetoprotein and cancer antigen 125 were significantly different between the two groups (P-values, 0.030 and 0.049, respectively). The diameter (P < 0.0001), margin (P = 0.003), distal main ductal dilation (P = 0.021), vessel involvement (P = 0.002), AP hypoenhancement (P < 0.0001), PVP hypoenhancement (P = 0.003), AP ratio (P = 0.0001), and PVP ratio (P = 0.0003) were significantly different between the low and high index groups. The area under the curve of the multivariate logistic regression model was 0.853. CONCLUSION: Nonmetastatic pNENs with larger diameter, ill-defined margin, distal main ductal dilation, and tumor hypoenhancement in AP in preoperative enhanced CT tend to have a Ki-67 index of > 5%.The results of this study provide an alternative method to clinicians to decide whether surgery is appropriate.

A Bounding Box-Based Radiomics Model for Detecting Occult Peritoneal Metastasis in Advanced Gastric Cancer: A Multicenter Study.

PURPOSE: To develop a bounding box (BBOX)-based radiomics model for the preoperative diagnosis of occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC) patients. MATERIALS AND METHODS: 599 AGC patients from 3 centers were retrospectively enrolled and were divided into training, validation, and testing cohorts. The minimum circumscribed rectangle of the ROIs for the largest tumor area (R_BBOX), the nonoverlapping area between the tumor and R_BBOX (peritumoral area; PERI) and the smallest rectangle that could completely contain the tumor determined by a radiologist (M_BBOX) were used as inputs to extract radiomic features. Multivariate logistic regression was used to construct a radiomics model to estimate the preoperative probability of OPM in AGC patients. RESULTS: The M_BBOX model was not significantly different from R_BBOX in the validation cohort [AUC: M_BBOX model 0.871 (95% CI, 0.814-0.940) vs. R_BBOX model 0.873 (95% CI, 0.820-0.940); p = 0.937]. M_BBOX was selected as the final radiomics model because of its extremely low annotation cost and superior OPM discrimination performance (sensitivity of 85.7% and specificity of 82.8%) over the clinical model, and this radiomics model showed comparable diagnostic efficacy in the testing cohort. CONCLUSIONS: The BBOX-based radiomics could serve as a simpler reliable and powerful tool for the preoperative diagnosis of OPM in AGC patients. And M_BBOX-based radiomics is simpler and less time consuming.

Role of imaging in evaluating the response after neoadjuvant treatment for pancreatic ductal adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive malignancy. Despite the development of multimodality treatments, including surgical resection, radiotherapy, and chemotherapy, the long-term prognosis of patients with PDAC remains poor. Recently, the introduction of neoadjuvant treatment (NAT) has made more patients amenable to surgery, increasing the possibility of R0 resection, treatment of occult micro-metastasis, and prolongation of overall survival. Imaging plays a vital role in tumor response evaluation after NAT. However, conventional imaging modalities such as multidetector computed tomography have limited roles in the assessment of tumor resectability after NAT for PDAC because of the similar appearance of tissue fibrosis and tumor infiltration. Perfusion computed tomography, using blood perfusion as a biomarker, provides added value in predicting the histopathologic response of PDAC to NAT by reflecting the changes in tumor matrix and fibrosis content. Other imaging technologies, including diffusion-weighted imaging of magnetic resonance imaging and positron emission tomography, can reveal the tumor response by monitoring the structural changes in tumor cells and functional metabolic changes in tumors after NAT. In addition, with the renewed interest in data acquisition and analysis, texture analysis and radiomics have shown potential for the early evaluation of the response to NAT, thus improving patient stratification to achieve accurate and intensive treatment. In this review, we briefly introduce the application and value of NAT in resectable and unresectable PDAC. We also summarize the role of imaging in evaluating the response to NAT for PDAC, as well as the advantages, limitations, and future development directions of current imaging techniques.

Development and validation of MRI-based deep learning models for prediction of microsatellite instability in rectal cancer.

BACKGROUND: Microsatellite instability (MSI) predetermines responses to adjuvant 5-fluorouracil and immunotherapy in rectal cancer and serves as a prognostic biomarker for clinical outcomes. Our objective was to develop and validate a deep learning model that could preoperatively predict the MSI status of rectal cancer based on magnetic resonance images. METHODS: This single-center retrospective study included 491 rectal cancer patients with pathologically proven microsatellite status. Patients were randomly divided into the training/validation cohort (n = 395) and the testing cohort (n = 96). A clinical model using logistic regression was constructed to discriminate MSI status using only clinical factors. Based on a modified MobileNetV2 architecture, deep learning models were tested for the predictive ability of MSI status from magnetic resonance images, with or without integrating clinical factors. RESULTS: The clinical model correctly classified 37.5% of MSI status in the testing cohort, with an AUC value of 0.573 (95% confidence interval [CI], 0.468 ~ 0.674). The pure imaging-based model and the combined model correctly classified 75.0% and 85.4% of MSI status in the testing cohort, with AUC values of 0.820 (95% CI, 0.718 ~ 0.884) and 0.868 (95% CI, 0.784 ~ 0.929), respectively. Both deep learning models performed better than the clinical model (p < 0.05). There was no statistically significant difference between the deep learning models with or without integrating clinical factors. CONCLUSIONS: Deep learning based on high-resolution T2-weighted magnetic resonance images showed a good predictive performance for MSI status in rectal cancer patients. The proposed model may help to identify patients who would benefit from chemotherapy or immunotherapy and determine individualized therapeutic strategies for these patients.

Development and validation of magnetic resonance imaging-based radiomics models for preoperative prediction of microsatellite instability in rectal cancer.

BACKGROUND: Microsatellite instability (MSI) is a predictive biomarker for response to chemotherapy and a prognostic biomarker for clinical outcomes of rectal cancer. The purpose of this study was to develop and validate radiomics models for preoperative prediction of the MSI status of rectal cancer based on magnetic resonance (MR) images. METHODS: This study retrospectively recruited 491 rectal cancer patients with pathologically confirmed MSI status. Patients were randomly divided into a training cohort (n=327) and a validation cohort (n=164). The most predictive radiomics features were selected using intraclass correlation coefficient (ICC) analysis, the two-sample t test, and the least absolute shrinkage and selection operator (LASSO) method. XGBoost models were constructed in the training cohort to discriminate the MSI status using clinical factors, radiomics features, or a combined model incorporating both the radiomics signature and independent clinical characteristics. The diagnostic performance of these three models was evaluated in the validation cohort based on their area under the curve (AUC), sensitivity, specificity, and accuracy. RESULTS: Among the 491 rectal cancer patients, the prevalence of MSI was 10.39% (51/491). Following ICC analysis, two-sample t test, and LASSO regression, six radiomics features were selected for subsequent analysis. The combined model, which incorporated both the clinical factors and radiomics features achieved an AUC of 0.895 [95% confidence interval (CI), 0.838-0.938] in the validation cohort, and showed better performance in predicting MSI status than the other two models using either clinical factors (P=0.015) or radiomics features (P=0.204) alone. CONCLUSIONS: Radiomics features based on preoperative T2-weighted MR imaging (MRI) are associated with the MSI status of rectal cancer. Combinational analysis of clinical factors and radiomics features may improve predictive performance and potentially contribute to noninvasive personalized therapy selection.

A Novel Multiresolution-Statistical Texture Analysis Architecture: Radiomics-Aided Diagnosis of PDAC Based on Plain CT Images.

Early screening of PDAC (pancreatic ductal adenocarcinoma) based on plain CT (computed tomography) images is of great significance. Therefore, this work conducted a radiomics-aided diagnosis analysis of PDAC based on plain CT images. We explored a novel MSTA (multiresolution-statistical texture analysis) architecture to extract texture features and built machine learning models to classify PDACs and HPs (healthy pancreases). We also performed significance tests of differences to analyze the relationships between histopathological characteristics and texture features. The MSTA architecture originates from the analysis of histopathological characteristics and combines multiresolution analysis and statistical analysis to extract texture features. The MSTA architecture achieved better experimental results than the traditional architecture that scales the coefficient matrices of the multiresolution analysis. In the validation of the classifications, the MSTA architecture achieved an accuracy of 81.19% and an AUC (area under the ROC (receiver operating characteristic) curve) of 0.88 (95% confidence interval: 0.84-0.92). In the test of the classifications, it achieved an accuracy of 77.66% and an AUC of 0.79 (95% confidence interval: 0.71-0.87). Moreover, the significance tests of differences showed that the extracted texture features may be relevant to the histopathological characteristics. The MSTA architecture is beneficial for the radiomics-aided diagnosis of PDAC based on plain CT images. Its texture features can potentially enhance radiologists' imaging interpretation abilities.

Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer.

We aimed to develop a deep convolutional neural network (DCNN) model based on computed tomography (CT) images for the preoperative diagnosis of occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC). A total of 544 patients with AGC were retrospectively enrolled. Seventy-nine patients were confirmed with OPM during surgery or laparoscopy. CT images collected during the initial visit were randomly split into a training cohort and a testing cohort for DCNN model development and performance evaluation, respectively. A conventional clinical model using multivariable logistic regression was also developed to estimate the pretest probability of OPM in patients with gastric cancer. The DCNN model showed an AUC of 0.900 (95% CI: 0.851-0.953), outperforming the conventional clinical model (AUC = 0.670, 95% CI: 0.615-0.739; p < 0.001). The proposed DCNN model demonstrated the diagnostic detection of occult PM, with a sensitivity of 81.0% and specificity of 87.5% using the cutoff value according to the Youden index. Our study shows that the proposed deep learning algorithm, developed with CT images, may be used as an effective tool to preoperatively diagnose OPM in AGC.

A New Diagnostic Criterion with Gadoxetic Acid-Enhanced MRI May Improve the Diagnostic Performance for Hepatocellular Carcinoma.

BACKGROUND: To prospectively establish and validate new diagnostic criterion (DC) for liver-specific contrast agents and further compared the diagnostic sensitivity and specificity with conventional DC. METHODS: Institutional Review Board approved and written informed consent were obtained for this prospective study. Two board-certified reviewers established the reference standard as hepatocellular carcinoma (HCC), non-HCC lesions by using marks on all cross-sectional MR images. Another 2 abdominal radiologists independently performed the marked lesion observations using 5 different DCs, including DC-1: arterial phase hyperenhancement (APHE) and portal venous phase washout; DC-2: APHE and hepatobiliary phase (HBP) hypointensity; DC-3: APHE and diffusion-weighted imaging (DWI) hyperintensity; DC-4: HBP hypointensity and DWI hyperintensity; DC-5: HBP hypointensity, DWI hyperintensity and excluded these markedly T2 hyperintensity. Diagnostic performance of sensitivity, specificity, and accuracy for each imaging DC was calculated, per-lesion diagnostic sensitivity and specificity of imaging criteria were compared by using McNemars test. RESULTS: A total of 215 patients were included (mean age 53.82 ± 11.24 years; range 24-82 years) with 265 hepatic nodules (175 HCCs and 90 non-HCCs). The DC-4 (93.71%; 164/175) and DC-5 (92.57%; 162/175) yielded the highest diagnostic sensitivity and was better than DC-1 (72.57%; 127/175), DC-2 (82.86%; 145/175), and DC-3 (82.29%; 144/175) (all p < 0.001). The specificity of DC-1 (94.44%; 85/90) was significantly higher than that with DC-2 (83.33%; 75/90), DC-3 (84.44%; 76/90), DC-4 (74.44%; 67/90), and DC-5 (82.22%; 74/90) (all p < 0.05). Additionally, the DC-4 and DC-5 achieved the highest area under curve value of 0.841 (95% CI 0.783-0.899) and 0.874 (95% CI 0.822-0.925). CONCLUSIONS: The combined use of HBP hypointensity and DWI hyperintensity as a new DC for HCC enables a high diagnostic sensitivity and comparable specificity.

Development and validation of a radiomics model based on T2WI images for preoperative prediction of microsatellite instability status in rectal cancer: Study Protocol Clinical Trial (SPIRIT Compliant).

INTRODUCTION: Globally, colorectal cancer (CRC) is the third most commonly diagnosed cancer in males and the second in females. Rectal cancer (RC) accounts for about 28% of all newly diagnosed CRC cases. The treatment of choice for locally advanced RC is a combination of surgical resection and chemotherapy and/or radiotherapy. These patients can potentially be cured, but the clinical outcome depends on the tumor biology. Microsatellite instability (MSI) is an important biomarker in CRC, with crucial diagnostic, prognostic, and predictive implications. It is important to develop a noninvasive, repeatable, and reproducible method to reflect the microsatellite status. Magnetic resonance imaging (MRI) has been recommended as the preferred imaging examination for RC in clinical practice by both the National Comprehensive Cancer Network and the European Society for Medical Oncology guidelines. T2WI is the core sequence of MRI scanning protocol for RC. Radiomics, the high-throughput mining of quantitative image features from standard-of-care medical imaging that enables data to be extracted and applied within clinical-decision support systems to improve diagnostic, prognostic, and predictive accuracy, is gaining importance in cancer research.We proposed a hypothesis: A simple radiomics model based on only T2WI images can accurately evaluate the MSI status of RC preoperatively. OBJECTIVE: To develop a radiomics model based on T2WI images for accurate preoperative diagnosis the MSI status of RC. METHOD: All patients with RC were retrospectively enrolled. The dataset was randomly split into training cohort (70% of all patients) and testing cohort (30% of all patients). The radiomics features will be extracted from T2WI-MR images of the entire primary tumor region. Least absolute shrinkage and selection operator was used to select the most predictive radiomics features. Logistic regression models were constructed in the training/validation cohort to discriminate the MSI status using clinical factors, radiomics features, or their integration. The diagnostic performance of these 3 models was evaluated in the testing cohort based on their area under the curve, sensitivity, specificity, and accuracy. DISCUSSION: This study will help us know whether radiomics model based on T2WI images to preoperative identify MSI status of RC.

Differentiation combined hepatocellular and cholangiocarcinoma from intrahepatic cholangiocarcinoma based on radiomics machine learning.

BACKGROUND: Combined hepatocellular and cholangiocarcinoma (CHC) and intrahepatic cholangiocarcinoma (ICC) are hard to identify in clinical practice preoperatively. This study looked to develop and confirm a radiomics-based model for preoperative differentiation CHC from ICC. METHODS: The model was developed in 86 patients with ICC and 46 CHC, confirmed in 37 ICC and 20 CHC, and data were collected from January 2014 to December 2018. The radiomics scores (Radscores) were built from radiomics features of contrast-enhanced computed tomography in 12 regions of interest (ROI). The Radscore and clinical-radiologic factors were integrated into the combined model using multivariable logistic regression. The best-combined model constructed the radiomics-based nomogram, and the performance was assessed concerning its calibration, discrimination, and clinical usefulness. RESULTS: The radiomics features extracted from tumor ROI in the arterial phase (AP) with preprocessing were selected to build Radscore and yielded an area under the curve (AUC) of 0.800 and 0.789 in training and validation cohorts, respectively. The radiomics-based model contained Radscore and 4 clinical-radiologic factors showed the best performance (training cohort, AUC =0.942; validation cohort, AUC =0.942) and good calibration (training cohort, AUC =0.935; validation cohort, AUC =0.931). CONCLUSIONS: The proposed radiomics-based model may be used conveniently to the preoperatively differentiate CHC from ICC.

Retrospective imaging studies of gastric cancer: Study protocol clinical trial (SPIRIT Compliant).

INTRODUCTION: Peritoneal metastasis (PM) is a frequent condition in patients presenting with gastric cancer, especially in younger patients with advanced tumor stages. Computer tomography (CT) is the most common noninvasive modality for preoperative staging in gastric cancer. However, the challenges of limited CT soft tissue contrast result in poor CT depiction of small peritoneal tumors. The sensitivity for detecting PM remains low. About 16% of PM are undetected. Deep learning belongs to the category of artificial intelligence and has demonstrated amazing results in medical image analyses. So far, there has been no deep learning study based on CT images for the diagnosis of PM in gastric cancer. WE PROPOSED A HYPOTHESIS: CT images in the primary tumor region of gastric cancer had valuable information that could predict occult PM of gastric cancer, which could be extracted effectively through deep learning. OBJECTIVE: To develop a deep learning model for accurate preoperative diagnosis of PM in gastric cancer. METHOD: All patients with gastric cancer were retrospectively enrolled. All patients were initially diagnosed as PM negative by CT and later confirmed as positive through surgery or laparoscopy. The dataset was randomly split into training cohort (70% of all patients) and testing cohort (30% of all patients). To develop deep convolutional neural network (DCNN) models with high generalizability, 5-fold cross-validation and model ensemble were utilized. The area under the receiver operating characteristic curve, sensitivity and specificity were used to evaluate DCNN models on the testing cohort. DISCUSSION: This study will help us know whether deep learning can improve the performance of CT in diagnosing PM in gastric cancer.

Differential Diagnosis of Nonhypervascular Pancreatic Neuroendocrine Neoplasms From Pancreatic Ductal Adenocarcinomas, Based on Computed Tomography Radiological Features and Texture Analysis.

RATIONALE AND OBJECTIVES: To determine computed tomography (CT) radiological features and texture features that are rewarding in differentiating nonhypervascular pancreatic neuroendocrine neoplasms (PNENs) from pancreatic ductal adenocarcinomas (PDACs). MATERIALS AND METHODS: We compared patients to pathologically proven nonhypervascular PNENs and age-matched controls with pathologically proven PDACs in a 1:2 ratio. Preoperative CT images in the arterial phase (AP) and portal vein phase (PVP) were obtained. Two radiologists independently reviewed the morphological characteristics of each tumor. Three-dimensional regions of interest (ROIs), drawn using ITK-SNAP software, were input into AK software (Artificial Intelligent Kit, GE) to extract texture features from AP and PVP images. Differences between PNENs and PDACs were analyzed with the chi-squared test, least absolute shrinkage and selection operator, kappa statistics, and uni- and multivariate logistic regression analyses. RESULTS: In total, 40 nonhypervascular PNENs and 80 PDACs were evaluated. Maximum diameter on axial section, margin, calcification, vascularity in the tumor, and tumor heterogeneity were significantly different between PDACs and nonhypervascular PNENs. Multivariate analysis showed well-defined tumor margin (odds ratio: 21.0) and presence of calcification (odds ratio: 4.4) were significant predictors of nonhypervascular PNENs. The area under the receiver operating characteristic curve of the radiological feature model, AP texture model, and PVP texture model were 0.780, 0.855, and 0.929, respectively, based on logistic regression. CONCLUSION: A well-defined margin and calcification in the tumor were helpful in discriminating nonhypervascular PNENs from PDACs. Texture analysis of contrast-enhanced CT images could be beneficial in differentially diagnosing nonhypervascular PNENs and PDACs.

Grading of Clear Cell Renal Cell Carcinomas by Using Machine Learning Based on Artificial Neural Networks and Radiomic Signatures Extracted From Multidetector Computed Tomography Images.

RATIONALE AND OBJECTIVES: To evaluate the ability of artificial neural networks (ANN) fed with radiomic signatures (RSs) extracted from multidetector computed tomography images in differentiating the histopathological grades of clear cell renal cell carcinomas (ccRCCs). MATERIALS AND METHODS: The multidetector computed tomography images of 227 ccRCCs were retrospectively analyzed. For each ccRCC, 14 conventional image features (CIFs) were extracted manually by two radiologists, and 556 texture features (TFs) were extracted by a free software application, MaZda (version 4.6). The high-dimensional dataset of these RSs was reduced using the least absolute shrinkage and selection operator. Five minimum mean squared error models (minMSEMs) for predicting the ccRCC histopathological grades were constructed from the CIFs, the TFs of the corticomedullary phase images (CMP), and the TFs of the parenchyma phase (PP) images and their combinations, respectively abbreviated as CIF-minMSEM, CMP-minMSEM, PP-minMSEM, CIF+CMP-minMSEM, and CIF+PP-minMSEM. The RSs of each model were fed 30 times consecutively into an ANN for machine learning, and the predictive accuracy of each time ML was recorded for the statistical analysis. RESULTS: The five predictive models were constructed from 12, 19, and 10 features selected from the CIFs, the TFs of the CMP images, and that of PP images, respectively. On the basis of their accuracy across the whole cohort, the five models were ranked as follows: CIF+CMP-minMSEM (accuracy: 94.06% ± 1.14%), CIF + PP-minMSEM (accuracy: 93.32% ± 1.23%), CIF-minMSEM (accuracy: 92.26% ± 1.65%), CMP-minMSEM (accuracy: 91.76% ± 1.74%), and PP-minMSEM (accuracy: 90.89% ± 1.47%). CONCLUSION: Machine learning based on ANN helped establish an optimal predictive model, and TFs contributed to the development of high accuracy predictive models. The CIF+CMP-minMSEM showed the greatest accuracy for differentiating low- and high-grade ccRCCs.