Utility of Combined Use of Imaging Features From Abdominopelvic CT and CA 125 to Identify Presence of CT Occult Peritoneal Metastases in Advanced Gastric Cancer.

OBJECTIVE: The purpose of this study is to identify the presence of occult peritoneal metastasis (OPM) in patients with advanced gastric cancer (AGC) by using clinical characteristics and abdominopelvic computed tomography (CT) features. METHODS: This retrospective study included 66 patients with OPM and 111 patients without peritoneal metastasis (non-PM [NPM]) who underwent preoperative contrast-enhanced CT between January 2020 and December 2021. Occult PMs means PMs that are missed by CT but later diagnosed by laparoscopy or laparotomy. Patients with NPM means patients have neither PM nor other distant metastases, indicating there is no evidence of distant metastases in patients with AGC. Patients' clinical characteristics and CT features such as tumor marker, Borrmann IV, enhancement patterns, and pelvic ascites were observed by 2 experienced radiologists. Computed tomography features and clinical characteristics were combined to construct an indicator for identifying the presence of OPM in patients with AGC based on a logistic regression model. Receiver operating characteristic curves and the area under the receiver operating characteristic curve (AUC) were generated to assess the diagnostic performance of the combined indicator. RESULTS: Four independent predictors (Borrmann IV, pelvic ascites, carbohydrate antigen 125, and normalized arterial CT value) differed significantly between OPM and NPM and performed outstandingly in distinguishing patients with OPM from those without PM (AUC = 0.643-0.696). The combined indicator showed a higher AUC value than the independent risk factors (0.820 vs 0.643-0.696). CONCLUSIONS: The combined indicator based on abdominopelvic CT features and carbohydrate antigen 125 may assist clinicians in identifying the presence of CT OPMs in patients with AGC.

Dual-energy CT quantitative parameters to evaluate occult peritoneal metastasis in advanced gastric cancer preoperatively.

PURPOSE: To explore whether dual-energy CT (DECT) quantitative parameters could provide analytic value for the diagnosis of patients with occult peritoneal metastasis (OPM) in advanced gastric cancer preoperatively. MATERIALS AND METHODS: This retrospective study included 219 patients with advanced gastric cancer and DECT scans. The patient's clinical data and DECT related iodine concentration (IC) parameters and effective atomic number (Zeff) were collated and analyzed among noun-peritoneal metastasis (NPM), OPM and radiologically peritoneal metastasis (RPM) groups. The predictive performance of the DECT parameters was compared with that of the conventional CT features and clinical characteristics through evaluating area under curve of the precision-recall (AUC-PR), F1 score, balanced accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). RESULTS: Borrmann IV type diagnosed on CT and serum tumor indicator CA125 index were statistically different between the NPM and OPM groups. DECT parameters included IC, normalized IC (NIC), and Zeff of PM group were lower than the NPM group. The DECT predictive nomogram combined three independent DECT parameters produced a better diagnostic performance than the conventional CT feature Borrmann IV type and serum CA125 index in AUC-PR with 0.884 vs 0.368 vs 0.189, but similar to the combined indicator which was based on the DECT parameters, the conventional CT feature, and serum CA125 index in AUC-PR with 0.884 vs 0.918. CONCLUSION: The lower quantitative NIC, IC ratio, and Zeff on DECT was associated with peritoneal metastasis in advanced gastric cancer and was promising to identify patients with OPM noninvasively.

Deep learning-accelerated T2WI: image quality, efficiency, and staging performance against BLADE T2WI for gastric cancer.

PURPOSE: The purpose of our study is to investigate image quality, efficiency, and diagnostic performance of a deep learning-accelerated single-shot breath-hold (DLSB) against BLADE for T2-weighted MR imaging (T2WI) for gastric cancer (GC). METHODS: 112 patients with GCs undergoing gastric MRI were prospectively enrolled between Aug 2022 and Dec 2022. Axial DLSB-T2WI and BLADE-T2WI of stomach were scanned with same spatial resolution. Three radiologists independently evaluated the image qualities using a 5-scale Likert scales (IQS) in terms of lesion delineation, gastric wall boundary conspicuity, and overall image quality. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated in measurable lesions. T staging was conducted based on the results of both sequences for GC patients with gastrectomy. Pairwise comparisons between DLSB-T2WI and BLADE-T2WI were performed using the Wilcoxon signed-rank test, paired t-test, and chi-squared test. Kendall's W, Fleiss' Kappa, and intraclass correlation coefficient values were used to determine inter-reader reliability. RESULTS: Against BLADE, DLSB reduced total acquisition time of T2WI from 495 min (mean 4:42 per patient) to 33.6 min (18 s per patient), with better overall image quality that produced 9.43-fold, 8.00-fold, and 18.31-fold IQS upgrading against BALDE, respectively, in three readers. In 69 measurable lesions, DLSB-T2WI had higher mean SNR and higher CNR than BLADE-T2WI. Among 71 patients with gastrectomy, DLSB-T2WI resulted in comparable accuracy to BLADE-T2WI in staging GCs (P > 0.05). CONCLUSIONS: DLSB-T2WI demonstrated shorter acquisition time, better image quality, and comparable staging accuracy, which could be an alternative to BLADE-T2WI for gastric cancer imaging.

SurvivalCNN: A deep learning-based method for gastric cancer survival prediction using radiological imaging data and clinicopathological variables.

Radiological images have shown promising effects in patient prognostication. Deep learning provides a powerful approach for in-depth analysis of imaging data and integration of multi-modal data for modeling. In this work, we propose SurvivalCNN, a deep learning structure for cancer patient survival prediction using CT imaging data and non-imaging clinical data. In SurvivalCNN, a supervised convolutional neural network is designed to extract volumetric image features, and radiomics features are also integrated to provide potentially different imaging information. Within SurvivalCNN, a novel multi-thread multi-layer perceptron module, namely, SurvivalMLP, is proposed to perform survival prediction from censored survival data. We evaluate the proposed SurvivalCNN framework on a large clinical dataset of 1061 gastric cancer patients for both overall survival (OS) and progression-free survival (PFS) prediction. We compare SurvivalCNN to three different modeling methods and examine the effects of various sets of data/features when used individually or in combination. With five-fold cross validation, our experimental results show that SurvivalCNN achieves averaged concordance index 0.849 and 0.783 for predicting OS and PFS, respectively, outperforming the compared state-of-the-art methods and the clinical model. After future validation, the proposed SurvivalCNN model may serve as a clinical tool to improve gastric cancer patient survival estimation and prognosis analysis.

LiSNet: An artificial intelligence -based tool for liver imaging staging of hepatocellular carcinoma aggressiveness.

BACKGROUND: Presurgical assessment of hepatocellular carcinoma (HCC) aggressiveness can benefit patients' treatment options and prognosis. PURPOSE: To develop an artificial intelligence (AI) tool, namely, LiSNet, in the task of scoring and interpreting HCC aggressiveness with computed tomography (CT) imaging. METHODS: A total of 358 patients with HCC undergoing curative liver resection were retrospectively included. Three subspecialists were recruited to pixel-wise annotate and grade tumor aggressiveness based on CT imaging. LiSNet was trained and validated in 193 and 61 patients with a deep neural network to emulate the diagnostic acumen of subspecialists for staging HCC. The test set comprised 104 independent patients. We subsequently compared LiSNet with an experience-based binary diagnosis scheme and human-AI partnership that combined binary diagnosis and LiSNet for assessing tumor aggressiveness. We also assessed the efficiency of LiSNet for predicting survival outcomes. RESULTS: At the pixel-wise level, the agreement rate of LiSNet with subspecialists was 0.658 (95% confidence interval [CI]: 0.490-0.779), 0.595 (95% CI: 0.406-0.734), and 0.369 (95% CI: 0.134-0.566), for scoring HCC aggressiveness grades I, II, and III, respectively. Additionally, LiSNet was comparable to subspecialists for predicting histopathological microvascular invasion (area under the curve: LiSNet: 0.668 [95% CI: 0.559-0.776] versus subspecialists: 0.699 [95% CI: 0.591-0.806], p > 0.05). In a human-AI partnered diagnosis, combining LiSNet and experience-based binary diagnosis can achieve the best predictive ability for microvascular invasion (area under the curve: 0.705 [95% CI: 0.589-0.820]). Furthermore, LiSNet was able to indicate overall survival after surgery. CONCLUSION: The designed LiSNet tool warrants evaluation as an alternative tool for radiologists to conduct automatic staging of HCC aggressiveness at the pixel-wise level with CT imaging. Its prognostic value might benefit patients' treatment options and survival prediction.

Development and validation of a dual-energy CT-based model to estimate the malignant probability of distal gastric wall thickening.

Background: This study developed and validated a viable model for the preoperative diagnosis of malignant distal gastric wall thickening based on dual-energy spectral computed tomography (DEsCT). Methods: The imaging data of 208 patients who were diagnosed with distal gastric wall thickening using DEsCT were retrospectively collected and divided into a training cohort (n=151) and a testing cohort (n=57). The patient's clinical data and pathological information were collated. The multivariable logistic regression model was built using 5 selected features, and subsequently, a 10-fold cross-validation was performed to identify the optimal model. A nomogram was established based on the training cohort. Finally, the diagnostic performance of the best model was compared to the existing conventional CT scheme through evaluating the discrimination ability in the testing cohort in terms of the receiver operating characteristic curve (ROC), calibration, and clinical usefulness. Results: Stepwise regression analysis identified 5 candidate variables with the smallest Akaike information criteria (AIC), namely, the venous phase spectral curve [VP_ SC; odds ratio (OR) 8.419], focal enhancement (OR 3.741), arterial phase mixed (OR 1.030), tumor site (OR 0.573), and diphasic shape change (DP_shape change; OR 2.746). The best regression model with 10-fold cross-validation consisting of VP_SC and focal enhancement was built using the 5 candidate variables. The average area under the ROC curve (AUC) of the model from the 10-fold cross-validation was 0.803 (sensitivity of 69.2%, specificity of 94.1%, and accuracy of 74.8%). In the testing cohort, the DEsCT model identified using the regression model performed better (AUC 0.905, sensitivity 81.3%, specificity 85.4%, and accuracy 84.2%) than did the conventional CT scheme (AUC 0.852, sensitivity 80.0%, specificity 76.6%, and accuracy 77.2%). The nomogram based on the DEsCT model showed good calibration and provided a better net benefit for predicting malignancy of distal gastric wall thickening. Conclusions: Comprehensive assessment with the DEsCT-based model can be used to facilitate the individualized diagnosis of malignancy risk in patients presenting with distal gastric wall thickening.

Comparison of Computed Tomography Features of Gastric and Small Bowel Gastrointestinal Stromal Tumors With Different Risk Grades.

OBJECTIVE: This study aimed to compare the computed tomography (CT) features of gastric and small bowel gastrointestinal stromal tumors (GISTs) and further identify the predictors for risk stratification of them, respectively. METHODS: According to the modified National Institutes of Health criteria, patients were classified into low-malignant potential group and high-malignant potential group. Two experienced radiologists reviewed the CT features including the difference of CT values between arterial phase and portal venous phase (PVPMAP) by consensus. The CT features of gastric and small bowel GISTs were compared, and the association of CT features with risk grades was analyzed, respectively. Determinant CT features were used to construct corresponding models. RESULTS: Univariate analysis showed that small bowel GISTs tended to present with irregular contour, mixed growth pattern, ill-defined margin, severe necrosis, ulceration, tumor vessels, heterogeneous enhancement, larger size, and marked enhancement compared with gastric GISTs. According to multivariate analysis, tumor size (P < 0.001; odds ratio [OR], 3.279), necrosis (P = 0.008; OR, 2.104) and PVPMAP (P = 0.045; OR, 0.958) were the independent influencing factors for risk stratification of gastric GISTs. In terms of small bowel GISTs, the independent predictors were tumor size (P < 0.001; OR, 3.797) and ulceration (P = 0.031; OR, 4.027). Receiver operating characteristic curve indicated that the CT models for risk stratification of gastric and small bowel GISTs both achieved the best predictive performance. CONCLUSIONS: Computed tomography features of gastric and small bowel GISTs are different. Furthermore, the qualitative and quantitative CT features of GISTs may be favorable for preoperative risk stratification.

Prognostic aspects of lymphovascular invasion in localized gastric cancer: new insights into the radiomics and deep transfer learning from contrast-enhanced CT imaging.

OBJECTIVES: Lymphovascular invasion (LVI) is a factor significantly impacting treatment and outcome of patients with gastric cancer (GC). We aimed to investigate prognostic aspects of a preoperative LVI prediction in GC using radiomics and deep transfer learning (DTL) from contrast-enhanced CT (CECT) imaging. METHODS: A total of 1062 GC patients (728 training and 334 testing) between Jan 2014 and Dec 2018 undergoing gastrectomy were retrospectively included. Based on CECT imaging, we built two gastric imaging (GI) markers, GI-marker-1 from radiomics and GI-marker-2 from DTL features, to decode LVI status. We then integrated demographics, clinical data, GI markers, radiologic interpretation, and biopsies into a Gastric Cancer Risk (GRISK) model for predicting LVI. The performance of GRISK model was tested and applied to predict survival outcomes in GC patients. Furthermore, the prognosis between LVI (+) and LVI (-) patients was compared in chemotherapy and non-chemotherapy cohorts, respectively. RESULTS: GI-marker-1 and GI-marker-2 yield similar performance in predicting LVI in training and testing dataset. The GRISK model yields the diagnostic performance with AUC of 0.755 (95% CI 0.719-0.790) and 0.725 (95% CI 0.669-0.781) in training and testing dataset. Patients with LVI (+) trend toward lower progression-free survival (PFS) and overall survival (OS). The difference of prognosis between LVI (+) and LVI (-) was more noticeable in non-chemotherapy than that in chemotherapy group. CONCLUSION: Radiomics and deep transfer learning features on CECT demonstrate potential power for predicting LVI in GC patients. Prospective use of a GRISK model can help to optimize individualized treatment decisions and predict survival outcomes.

Radiomics analysis of pretreatment MRI in predicting tumor response and outcome in hepatocellular carcinoma with transarterial chemoembolization: a two-center collaborative study.

BACKGROUND AND OBJECTIVE: To develop a machine-learning model by integrating clinical and imaging modalities for predicting tumor response and survival of hepatocellular carcinoma (HCC) with transarterial chemoembolization (TACE). METHODS: 140 HCC patients with TACE were retrospectively included from two centers. Tumor response were evaluated using modified Response Evaluation Criteria in Solid Tumors (mRECIST) criteria. Response-related radiomics scores (Rad-scores) were constructed on T2-weighted images (T2WI) and dynamic contrast-enhanced (DCE) imaging separately, and then integrated with conventional clinic-radiological variables into a logistic regression (LR) model for predicting tumor response. LR model was trained in 94 patients in center 1 and independently tested in 46 patients in center 2. RESULTS: Among 4 MRI sequences, T2WI achieved better performance than DCE (area under the curve [AUC] 0.754 vs 0.602 to 0.752). LR model by combining Rad-score on T2WI with Barcelona Clinic Liver Cancer (BCLC) stage and albumin-bilirubin (ALBI) grade resulted in an AUC of 0.813 in training and 0.781 in test for predicting tumor response. In survival analysis, progression-free survival (PFS) and overall survival (OS) presented significant difference between LR-predicted responders and non-responders. The ALBI grade and BCLC stage were independent predictors of PFS; and LR-predicted response, ALBI grade, satellite node, and BCLC stage were independent predictors of OS. The resulting Cox model produced concordance-indexes of 0.705 and 0.736 for predicting PFS and OS, respectively. CONCLUSIONS: The model combined MRI radiomics with clinical factors demonstrated favorable performance for predicting tumor response and clinical outcomes, thus may help personalized clinical management.

Identifying Prognostic Markers From Clinical, Radiomics, and Deep Learning Imaging Features for Gastric Cancer Survival Prediction.

BACKGROUND: Gastric cancer is one of the leading causes of cancer death in the world. Improving gastric cancer survival prediction can enhance patient prognostication and treatment planning. METHODS: In this study, we performed gastric cancer survival prediction using machine learning and multi-modal data of 1061 patients, including 743 for model learning and 318 independent patients for evaluation. A Cox proportional-hazard model was trained to integrate clinical variables and CT imaging features (extracted by radiomics and deep learning) for overall and progression-free survival prediction. We further analyzed the prediction effects of clinical, radiomics, and deep learning features. Concordance index (c-index) was used as the model performance metric, and the predictive effects of multi-modal features were measured by hazard ratios (HRs) at pre- and post-operative settings. RESULTS: Among 318 patients in the independent testing group, the hazard predicted by Cox from multi-modal features is associated with their survival. The highest c-index was 0.783 (95% CI, 0.782-0.783) and 0.770 (95% CI, 0.769-0.771) for overall and progression-free survival prediction, respectively. The post-operative variables are significantly (p<0.001) more predictive than the pre-operative variables. Pathological tumor stage (HR=1.336 [overall survival]/1.768 [progression-free survival], p<0.005), pathological lymph node stage (HR=1.665/1.433, p<0.005), carcinoembryonic antigen (CEA) (HR=1.632/1.522, p=0.02), chemotherapy treatment (HR=0.254/0.287, p<0.005), radiomics signature [HR=1.540/1.310, p<0.005], and deep learning signature [HR=1.950/1.420, p<0.005]) are significant survival predictors. CONCLUSION: Our study showed that CT radiomics and deep learning imaging features are significant pre-operative predictors, providing additional prognostic information to the pathological staging markers. Lower CEA levels and chemotherapy treatments also increase survival chances. These findings can enhance gastric cancer patient prognostication and inform treatment planning.

Prediction of prognostic risk factors in hepatocellular carcinoma with transarterial chemoembolization using multi-modal multi-task deep learning.

BACKGROUND: Due to heterogeneity of hepatocellular carcinoma (HCC), outcome assessment of HCC with transarterial chemoembolization (TACE) is challenging. METHODS: We built histologic-related scores to determine microvascular invasion (MVI) and Edmondson-Steiner grade by training CT radiomics features using machine learning classifiers in a cohort of 494 HCCs with hepatic resection. Meanwhile, we developed a deep learning (DL)-score for disease-specific survival by training CT imaging using DL networks in a cohort of 243 HCCs with TACE. Then, three newly built imaging hallmarks with clinicoradiologic factors were analyzed with a Cox-Proportional Hazard (Cox-PH) model. FINDINGS: In HCCs with hepatic resection, two imaging hallmarks resulted in areas under the curve (AUCs) of 0.79 (95% confidence interval [CI]: 0.71-0.85) and 0.72 (95% CI: 0.64-0.79) for predicting MVI and Edmondson-Steiner grade, respectively, using test data. In HCCs with TACE, higher DL-score (hazard ratio [HR]: 3.01; 95% CI: 2.02-4.50), American Joint Committee on Cancer (AJCC) stage III+IV (HR: 1.71; 95% CI: 1.12-2.61), Response Evaluation Criteria in Solid Tumors (RECIST) with stable disease + progressive disease (HR: 2.72; 95% CI: 1.84-4.01), and TACE-course > 3 (HR: 0.65; 95% CI: 0.45-0.76) were independent prognostic factors. Using these factors via a Cox-PH model resulted in a concordance index of 0.73 (95% CI: 0.71-0.76) for predicting overall survival and AUCs of 0.85 (95% CI: 0.81-0.89), 0.90 (95% CI: 0.86-0.94), and 0.89 (95% CI: 0.84-0.92), respectively, for predicting 3-year, 5-year, and 10-year survival. INTERPRETATION: Our study offers a DL-based, noninvasive imaging hallmark to predict outcome of HCCs with TACE. FUNDING: This work was supported by the key research and development program of Jiangsu Province (Grant number: BE2017756).

Quantitative assessment of diffusion kurtosis imaging depicting deep myometrial invasion: a comparative analysis with diffusion-weighted imaging.

PURPOSE: We aimed to investigate histogram analysis of diffusion kurtosis imaging (DKI) and conventional diffusion-weighted imaging (DWI) to distinguish between deep myometrial invasion and superficial myometrial invasion in endometrial carcinoma (EC). METHODS: A total of 118 pathologically confirmed EC patients with preoperative DWI were included. The data were postprocessed with a DKI (b value of 0, 700, 1400, and 2000 s/mm2) model for quantitation of apparent diffusion values (D) and apparent kurtosis coefficient values (K) for non-Gaussian distribution. The apparent diffusion coefficient (ADC) was postprocessed with a conventional DWI model (b values of 0 and 800 s/mm2). A whole-tumor analysis approach was used. Comparisons of the histogram parameters of D, K, and ADC were carried out for the deep myometrial invasion and superficial myometrial invasion subgroups. Diagnostic performance of the imaging parameters was assessed. RESULTS: The Dmean, D10th, and D90th in deep myometrial invasion group were significantly lower than those in superficial invasion group (P < 0.001, P < 0.001, and P = 0.023, respectively), as well as the ADCmean, ADC10th, and ADC90th (P = 0.001, P = 0.001, and P = 0.042, respectively). The Kmean and K90th were significantly higher in deep invasion group than those in superficial myometrial invasion group (P = 0.002 and P = 0.026, respectively). The D10th, Kmean, and ADC10th had a relatively higher area under the curve (AUC) (0.72, 0.66, and 0.71, respectively) than other parameters for distinguishing deep myometrial invasion of EC. D10th showed a relatively higher AUC than ADC10th for the differentiation of lesions with deep myometrial invasion from those with superficial myometrial invasion (0.72 vs. 0.71), but the variation was not statistically significant (P = 0.35). CONCLUSION: Distribution of DKI and conventional DWI parameters characterized by histogram analysis may represent an indicator for deep myometrial invasion in EC. Both DKI and DWI models showed relatively equivalent effectiveness.

Direct Comparison of Four Presurgical Stratifying Schemes for Prediction of Microvascular Invasion in Hepatocellular Carcinoma by Gadoxetic Acid-Enhanced MRI.

BACKGROUND: Microvascular invasion (MVI) is implicated in the poor prognosis of hepatocellular carcinoma (HCC). Presurgical stratifying schemes have been proposed for HCC-MVI but lack external validation. PURPOSE: To perform external validation and comparison of four presurgical stratifying schemes for the prediction of MVI using gadoxetic acid-based MRI in a cohort of HCC patients. STUDY TYPE: Retrospective. SUBJECTS: Included were 183 surgically resected HCCs from patients who underwent pretreatment MRI. FIELD STRENGTH/SEQUENCE: This includes 1.5-3.0 T with T2 , T1 , diffusion-weighted imaging (DWI), and dynamic gadoxetic acid contrast-enhancement imaging sequences. ASSESSMENT: A two-trait predictor of venous invasion (TTPVI), Lei model, Lee model, and Xu model were compared. We relied on preoperative characteristics and imaging findings via four independent radiologists who were blinded to histologic results, as required by the tested tools. STATISTICAL TEST: Tests of accuracy between predicted and observed HCC-MVI rates using receiver operating characteristic (ROC) curve and decision curve analysis. The intraclass correlation coefficient (ICC) and Cronbach's alpha statistics were used to evaluate reproducibility. RESULTS: HCC-MVI was identified in 52 patients (28.4%). The average ROC curves (AUCs) for HCC-MVI predictions were 0.709-0.880, 0.714-0.828, and 0.588-0.750 for the Xu model, Lei model, and Lee model, respectively. The rates of accuracy were 60.7-81.4%, 69.9-75.9%, and 65.6-73.8%, respectively. Decision curve analyses indicated a higher benefit for the Xu and Lei models compared to the Lee model. The ICC and Cronbach's alpha index were highest in the Lei model (0.896/0.943), followed by the Xu model (0.882/0.804), and the Lee model (0.769/0.715). The TTPVI resulted in a Cronbach's alpha index of 0.606 with a sensitivity of 34.6-61.5% and a specificity of 76.3-91.6%. DATA CONCLUSION: Stratifying schemes relying on gadoxetic acid-enhanced MRI provide an additional insight into the presence of preoperative MVI. The Xu model outperformed the other models in terms of accuracy when performed by an experienced radiologist. Conversely, the Lei model outperformed the other models in terms of reproducibility. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2 J. Magn. Reson. Imaging 2020;52:433-447.

Histogram analysis of DCE-MRI for chemoradiotherapy response evaluation in locally advanced esophageal squamous cell carcinoma.

AIMS: The aim of the study was to predict and assess treatment response by histogram analysis of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to patients with locally advanced esophageal squamous cell carcinoma receiving chemoradiotherapy (CRT). MATERIALS AND METHODS: Seventy-two patients with locally advanced esophageal squamous cell carcinoma who underwent DCE-MRI before and after chemoradiotherapy were enrolled and divided into the complete response (CR) group and the non-CR group based on RECIST. The histogram parameters (10th percentile, 90th percentile, median, mean, standard deviation, skewness, and kurtosis) of pre-CRT and post-CRT were compared using a paired Student's t test in the CR and non-CR groups, respectively. The histogram parameter differences between the CR and the non-CR groups were compared using an unpaired Student's t test. A receiver operating characteristic (ROC) analysis was performed to evaluate the diagnostic performance. RESULTS: The histogram parameters of Ktrans values were observed to have significantly decreased after chemoradiotherapy in the CR group. The CR responders showed significantly higher median, mean, and 10th and 90th percentile of pre-Ktrans values than those of the non-CR group. The histogram analysis indicated the decreased heterogeneity in the CR group after CRT. Esophageal cancer with higher pre-Ktrans and lower post-Ktrans values indicated a good treatment response to CRT. Pre-Ktrans-10th showed the best diagnostic performance in predicting the chemoradiotherapy response. CONCLUSIONS: The histogram parameters of Ktrans are useful in the assessment and prediction of the chemoradiotherapy response in patients with advanced esophageal squamous cell carcinoma. DCE-MRI could serve as an adjunctive imaging technique for treatment planning.

RNA-binding protein Musashi2 stabilizing androgen receptor drives prostate cancer progression.

The androgen receptor (AR) pathway is critical for prostate cancer carcinogenesis and development; however, after 18-24 months of AR blocking therapy, patients invariably progress to castration-resistant prostate cancer (CRPC), which remains an urgent problem to be solved. Therefore, finding key molecules that interact with AR as novel strategies to treat prostate cancer and even CRPC is desperately needed. In the current study, we focused on the regulation of RNA-binding proteins (RBPs) associated with AR and determined that the mRNA and protein levels of AR were highly correlated with Musashi2 (MSI2) levels. MSI2 was upregulated in prostate cancer specimens and significantly correlated with advanced tumor grades. Downregulation of MSI2 in both androgen sensitive and insensitive prostate cancer cells inhibited tumor formation in vivo and decreased cell growth in vitro, which could be reversed by AR overexpression. Mechanistically, MSI2 directly bound to the 3'-untranslated region (UTR) of AR mRNA to increase its stability and, thus, enhanced its transcriptional activity. Our findings illustrate a previously unknown regulatory mechanism in prostate cancer cell proliferation regulated by the MSI2-AR axis and provide novel evidence towards a strategy against prostate cancer.

Machine Learning-Based Computational Models Derived From Large-Scale Radiographic-Radiomic Images Can Help Predict Adverse Histopathological Status of Gastric Cancer.

INTRODUCTION: Adverse histopathological status (AHS) decreases outcomes of gastric cancer (GC). With the lack of a single factor with great reliability to preoperatively predict AHS, we developed a computational approach by integrating large-scale imaging factors, especially radiomic features at contrast-enhanced computed tomography, to predict AHS and clinical outcomes of patients with GC. METHODS: Five hundred fifty-four patients with GC (370 training and 184 test) undergoing gastrectomy were retrospectively included. Six radiomic scores (R-scores) related to pT stage, pN stage, Lauren & Borrmann (L&B) classification, World Health Organization grade, lymphatic vascular infiltration, and an overall histopathologic score (H-score) were, respectively, built from 7,000+ radiomic features. R-scores and radiographic factors were then integrated into prediction models to assess AHS. The developed AHS-based Cox model was compared with the American Joint Committee on Cancer (AJCC) eighth stage model for predicting survival outcomes. RESULTS: Radiomics related to tumor gray-level intensity, size, and inhomogeneity were top-ranked features for AHS. R-scores constructed from those features reflected significant difference between AHS-absent and AHS-present groups (P < 0.001). Regression analysis identified 5 independent predictors for pT and pN stages, 2 predictors for Lauren & Borrmann classification, World Health Organization grade, and lymphatic vascular infiltration, and 3 predictors for H-score, respectively. Area under the curve of models using those predictors was training/test 0.93/0.94, 0.85/0.83, 0.63/0.59, 0.66/0.63, 0.71/0.69, and 0.84/0.77, respectively. The AHS-based Cox model produced higher area under the curve than the eighth AJCC staging model for predicting survival outcomes. Furthermore, adding AHS-based scores to the eighth AJCC staging model enabled better net benefits for disease outcome stratification. DISCUSSION: The developed computational approach demonstrates good performance for successfully decoding AHS of GC and preoperatively predicting disease clinical outcomes.

Performance of a machine learning-based decision model to help clinicians decide the extent of lymphadenectomy (D1 vs. D2) in gastric cancer before surgical resection.

BACKGROUND: Controversy still exists on the optimal surgical resection for potentially curable gastric cancer (GC). Use of radiologic evaluation and machine learning algorithms might predict extent of lymphadenectomy to limit unnecessary surgical treatment. We purposed to design a machine learning-based clinical decision-support model for predicting extent of lymphadenectomy (D1 vs. D2) in local advanced GC. METHODS: Clinicoradiologic features available from routine clinical assignments in 557 patients with GCs were retrospectively interpreted by an expert panel blinded to all histopathologic information. All patients underwent surgery using standard D2 resection. Decision models were developed with a logistic regression (LR), support vector machine (SVM) and auto-encoder (AE) algorithm in 371 training and tested in 186 test data, respectively. The primary end point was to measure diagnostic performance of decision model and a Japanese gastric cancer treatment guideline version 4th (JPN 4th) criteria for discriminate D1 (pT1 + pN0) versus D2 (≥ pT1 + ≥ pN1) lymphadenectomy. RESULTS: The decision model with AE analysis produced highest area under ROC curve (train: 0.965, 95% confidence interval (CI) 0.948-0.978; test: 0.946, 95% CI 0.925-0.978), followed by SVM (train: 0.925, 95% CI 0.902-0.944; test: 0.942, 95% CI 0.922-0.973) and LR (train: 0.886, 95% CI 0.858-0.910; test: 0.891, 95% CI 0.891-0.952). By this improvement, overtreatment was reduced from 21.7% (121/557) by treat-all pattern, to 15.1% (84/557) by JPN 4th criteria, and to 0.7-0.9% (4-5/557) by the new approach. CONCLUSIONS: The decision model with machine learning analysis demonstrates high accuracy for identifying patients who are candidates for D1 versus D2 resection. Its approximate 14-20% improvements in overtreatment compared to treat-all pattern and JPN 4th criteria potentially increase the number of patients with local advanced GCs who can safely avoid unnecessary lymphadenectomy.

A radiomics approach to predict lymph node metastasis and clinical outcome of intrahepatic cholangiocarcinoma.

OBJECTIVES: This study was conducted in order to establish and validate a radiomics model for predicting lymph node (LN) metastasis of intrahepatic cholangiocarcinoma (IHC) and to determine its prognostic value. METHODS: For this retrospective study, a radiomics model was developed in a primary cohort of 103 IHC patients who underwent curative-intent resection and lymphadenectomy. Radiomics features were extracted from arterial phase computed tomography (CT) scans. A radiomics signature was built based on highly reproducible features using the least absolute shrinkage and selection operator (LASSO) method. Multivariate logistic regression analysis was adopted to establish a radiomics model incorporating radiomics signature and other independent predictors. Model performance was determined by its discrimination, calibration, and clinical usefulness. The model was internally validated in 52 consecutive patients. RESULTS: The radiomics signature comprised eight LN-status-related features and showed significant association with LN metastasis in both cohorts (p < 0.001). A radiomics nomogram that incorporates radiomics signature and CA 19-9 level showed good calibration and discrimination in the primary cohort (AUC 0.8462) and validation cohort (AUC 0.8921). Promisingly, the radiomics nomogram yielded an AUC of 0.9224 in the CT-reported LN-negative subgroup. Decision curve analysis confirmed the clinical utility of this nomogram. High risk for metastasis portended significantly lower overall and recurrence-free survival than low risk for metastasis (both p < 0.001). The radiomics nomogram was an independent preoperative predictor of overall and recurrence-free survival. CONCLUSIONS: Our radiomics model provided a robust diagnostic tool for prediction of LN metastasis, especially in CT-reported LN-negative IHC patients, that may facilitate clinical decision-making. KEY POINTS: • The radiomics nomogram showed good performance for prediction of LN metastasis in IHC patients, particularly in the CT-reported LN-negative subgroup. • Prognosis of high-risk patients remains dismal after curative-intent resection. • The radiomics model may facilitate clinical decision-making and define patient subsets benefiting most from surgery.

Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma.

BACKGROUND & AIMS: Microvascular invasion (MVI) impairs surgical outcomes in patients with hepatocellular carcinoma (HCC). As there is no single highly reliable factor to preoperatively predict MVI, we developed a computational approach integrating large-scale clinical and imaging modalities, especially radiomic features from contrast-enhanced CT, to predict MVI and clinical outcomes in patients with HCC. METHODS: In total, 495 surgically resected patients were retrospectively included. MVI-related radiomic scores (R-scores) were built from 7,260 radiomic features in 6 target volumes. Six R-scores, 15 clinical factors, and 12 radiographic scores were integrated into a predictive model, the radiographic-radiomic (RR) model, with multivariate logistic regression. RESULTS: Radiomics related to tumor size and intratumoral heterogeneity were the top-ranked MVI predicting features. The related R-scores showed significant differences according to MVI status (p <0.001). Regression analysis identified 8 MVI risk factors, including 5 radiographic features and an R-score. The R-score (odds ratio [OR] 2.34) was less important than tumor capsule (OR 5.12), tumor margin (OR4.20), and peritumoral enhancement (OR 3.03). The RR model using these predictors achieved an area under the curve (AUC) of 0.909 in training/validation and 0.889 in the test set. Progression-free survival (PFS) and overall survival (OS) were significantly different between the RR-predicted MVI-absent and MVI-present groups (median PFS: 49.5 vs. 12.9 months; median OS: 76.3 vs. 47.3 months). RR-computed MVI probability, histologic MVI, tumor size, and Edmondson-Steiner grade were independently associated with disease-specific recurrence and mortality. CONCLUSIONS: The computational approach, integrating large-scale clinico-radiologic and radiomic features, demonstrates good performance for predicting MVI and clinical outcomes. However, radiomics with current CT imaging analysis protocols do not provide statistically significant added value to radiographic scores. LAY SUMMARY: The most effective treatment for hepatocellular carcinoma (HCC) is surgical removal of the tumor but often recurrence occurs, partly due to the presence of microvascular invasion (MVI). Lacking a single highly reliable factor able to preoperatively predict MVI, we developed a computational approach to predict MVI and the long-term clinical outcome of patients with HCC. In particular, the added value of radiomics, a newly emerging form of radiography, was comprehensively investigated. This computational method can enhance the communication with the patient about the likely success of the treatment and guide clinical management, with the aim of finding drugs that reduce the risk of recurrence.

An Intelligent Clinical Decision Support System for Preoperative Prediction of Lymph Node Metastasis in Gastric Cancer.

PURPOSE: The aim of this study was to develop and validate a computational clinical decision support system (DSS) on the basis of CT radiomics features for the prediction of lymph node (LN) metastasis in gastric cancer (GC) using machine learning-based analysis. METHODS: Clinicopathologic and CT imaging data were retrospectively collected from 490 patients who were diagnosed with GC between January 2002 and December 2016. Radiomics features were extracted from venous-phase CT images. Relevant features were selected, ranked, and modeled using a support vector machine classifier in 326 training and validation data sets. A model test was performed independently in a test set (n = 164). Finally, a head-to-head comparison of the diagnostic performance of the DSS and that of the conventional staging criterion was performed. RESULTS: Two hundred ninety-seven of the 490 patients examined had histopathologic evidence of LN metastasis, yielding a 60.6% metastatic rate. The area under the curve for predicting LN+ was 0.824 (95% confidence interval, 0.804-0.847) for the DSS in the training and validation data and 0.764 (95% confidence interval, 0.699-0.833) in the test data. The calibration plots showed good concordance between the predicted and observed probability of LN+ using the DSS approach. The DSS was better able to predict LN metastasis than the conventional staging criterion in the training and validation data (accuracy 76.4% versus 63.5%) and in the test data (accuracy 71.3% versus 63.2%) CONCLUSIONS: A DSS based on 13 "worrisome" radiomics features appears to be a promising tool for the preoperative prediction of LN status in patients with GC.