Delayed Perforation After Endoscopic Resection of Upper Gastrointestinal Tumors: CT Findings to Identify Patients Requiring Surgery.

PURPOSE: To determine the clinical and imaging factors associated with surgical treatment in patients with delayed perforation after endoscopic resection of upper gastrointestinal tumors. METHODS: We retrospectively included patients with delayed perforation after endoscopic tumor resection for gastric or duodenal tumors between January 2007 and December 2021 in a tertiary hospital. We compared the clinical, endoscopic, and CT findings of the surgical and conservative treatment groups. Univariable and multivariable analyses were performed to identify significant factors associated with surgery. RESULTS: Among 10,423 patients who had undergone endoscopic tumor resection, 52 (0.50%) experienced delayed perforation, with 20 patients (35.5%) treated surgically and 32 patients (64.5%) treated conservatively. The CT findings of gross perforation (adjusted odds ratio [OR]=6.75, 95% confidence interval [CI], 1.04-43.89; P=0.045) and presence of peritonitis (OR=34.26, 95% CI, 5.52-212.50; P<0.001) were significantly associated with surgical treatment. Other clinical factors as well as CT-measured amount of pneumoperitoneum were not significant factors. CONCLUSIONS: CT findings of gross perforation and peritonitis are significant factors associated with surgery in delayed perforation after endoscopic tumor resection. These factors can aid in guiding the patients towards an appropriate treatment plan.

Prognostication of Hepatocellular Carcinoma Using Artificial Intelligence.

Hepatocellular carcinoma (HCC) is a biologically heterogeneous tumor characterized by varying degrees of aggressiveness. The current treatment strategy for HCC is predominantly determined by the overall tumor burden, and does not address the diverse prognoses of patients with HCC owing to its heterogeneity. Therefore, the prognostication of HCC using imaging data is crucial for optimizing patient management. Although some radiologic features have been demonstrated to be indicative of the biologic behavior of HCC, traditional radiologic methods for HCC prognostication are based on visually-assessed prognostic findings, and are limited by subjectivity and inter-observer variability. Consequently, artificial intelligence has emerged as a promising method for image-based prognostication of HCC. Unlike traditional radiologic image analysis, artificial intelligence based on radiomics or deep learning utilizes numerous image-derived quantitative features, potentially offering an objective, detailed, and comprehensive analysis of the tumor phenotypes. Artificial intelligence, particularly radiomics has displayed potential in a variety of applications, including the prediction of microvascular invasion, recurrence risk after locoregional treatment, and response to systemic therapy. This review highlights the potential value of artificial intelligence in the prognostication of HCC as well as its limitations and future prospects.

Prognostic value of CT-based radiomics in grade 1-2 pancreatic neuroendocrine tumors.

BACKGROUND: Surgically resected grade 1-2 (G1-2) pancreatic neuroendocrine tumors (PanNETs) exhibit diverse clinical outcomes, highlighting the need for reliable prognostic biomarkers. Our study aimed to develop and validate CT-based radiomics model for predicting postsurgical outcome in patients with G1-2 PanNETs, and to compare its performance with the current clinical staging system. METHODS: This multicenter retrospective study included patients who underwent dynamic CT and subsequent curative resection for G1-2 PanNETs. A radiomics-based model (R-score) for predicting recurrence-free survival (RFS) was developed from a development set (441 patients from one institution) using least absolute shrinkage and selection operator-Cox regression analysis. A clinical model (C-model) consisting of age and tumor stage according to the 8th American Joint Committee on Cancer staging system was built, and an integrative model combining the C-model and the R-score (CR-model) was developed using multivariable Cox regression analysis. Using an external test set (159 patients from another institution), the models' performance for predicting RFS and overall survival (OS) was evaluated using Harrell's C-index. The incremental value of adding the R-score to the C-model was evaluated using net reclassification improvement (NRI) and integrated discrimination improvement (IDI). RESULTS: The median follow-up periods were 68.3 and 59.7 months in the development and test sets, respectively. In the development set, 58 patients (13.2%) experienced recurrence and 35 (7.9%) died. In the test set, tumors recurred in 14 patients (8.8%) and 12 (7.5%) died. In the test set, the R-score had a C-index of 0.716 for RFS and 0.674 for OS. Compared with the C-model, the CR-model showed higher C-index (RFS, 0.734 vs. 0.662, p = 0.012; OS, 0.781 vs. 0.675, p = 0.043). CR-model also showed improved classification (NRI, 0.330, p < 0.001) and discrimination (IDI, 0.071, p < 0.001) for prediction of 3-year RFS. CONCLUSIONS: Our CR-model outperformed the current clinical staging system in prediction of the prognosis for G1-2 PanNETs and added incremental value for predicting postoperative recurrence. The CR-model enables precise identification of high-risk patients, guiding personalized treatment planning to improve outcomes in surgically resected grade 1-2 PanNETs.

Clinicoradiological Factors Predicting Lymph Node Metastasis in Patients with Nonfunctioning Pancreatic Neuroendocrine Neoplasms: A Systematic Review and Meta-Analysis.

INTRODUCTION: Lymph node metastasis of nonfunctioning pancreatic neuroendocrine neoplasms (pNENs) potentially leads to poor survival. Given the contradictory results in the literature regarding factors associated with lymph node metastasis of nonfunctioning pNENs, we conducted a systematic review and meta-analysis to determine the preoperative predictors of lymph node metastasis. METHODS: Original studies reporting factors associated with lymph node metastasis in patients with nonfunctioning pNENs were identified in PubMed, EMBASE, and Cochrane Library databases, and data from eligible studies were analyzed using random-effects meta-analysis to obtain pooled estimates of odds ratios (ORs) and their 95% confidence intervals (CIs). RESULTS: Eleven studies were included. Tumor size (>2 cm or >2.5 cm; OR, 5.80 [95% CI, 4.07-8.25]) and pancreatic head location (OR, 1.75 [95% CI, 1.05-2.94]) were significant preoperative predictors of lymph node metastasis. Old age (OR, 1.07 [95% CI, 0.68-1.68]) and male sex (OR, 1.12 [95% CI, 0.74-1.70]) were not significantly associated with lymph node metastasis. CONCLUSIONS: A large tumor size and pancreatic head location can be useful for planning optimal treatment in patients with nonfunctioning pNENs.

Does threshold growth benefit imaging criteria when used as a major diagnostic imaging feature for hepatocellular carcinoma?

PURPOSE: To evaluate the added value of threshold growth (TG) for imaging criteria for diagnosing hepatocellular carcinoma (HCC) on gadoxetic acid-enhanced MRI. METHODS: Patients who underwent preoperative gadoxetic acid-enhanced MRI because of absence of 'definite HCC' (Liver Imaging Reporting and Data System category 5) on prior CT or MRI between January 2016 and December 2020 were retrospectively analyzed. The sensitivity and specificity for 'definite HCC' according to the criteria of the European Association for the Study of the Liver [EASL], Asian Pacific Association for the Study of the Liver [APASL], and Korean Liver Cancer Association-National Cancer Center [KLCA-NCC] were separately calculated with and without TG as a major imaging feature. The results were compared using generalized estimating equations. RESULTS: Of 202 nodules in 154 patients, 19 % showed TG. When TG was used as a major imaging feature, the sensitivity of EASL were significantly higher than when it was not used (59.2 % vs. 51.4 %, p = 0.001), whereas the sensitivities of APASL and KLCA-NCC did not significantly differ. No significant difference was found in the specificities of the three imaging criteria when TG was used or not (p ≥ 0.16). Of 11 HCCs additionally detected when TG was added to EASL criteria, 9 showed transitional-phase or hepatobiliary-phase hypointensity without portal venous-phase washout. CONCLUSION: TG had added value for improving the sensitivity of EASL criteria for gadoxetic acid-enhanced MRI without extending washout to transitional-phase or hepatobiliary-phase images.

Proliferative hepatocellular carcinomas in cirrhosis: patient outcomes of LI-RADS category 4/5 and category M.

OBJECTIVES: We aimed to compare Liver Imaging Reporting and Data System (LI-RADS) category 4/5 and category M (LR-M) of proliferative hepatocellular carcinomas (HCCs) in cirrhotic patients and evaluate their impacts on prognosis. METHODS: This retrospective multi-reader study included cirrhotic patients with single treatment-naïve HCC ≤ 5.0 cm who underwent contrast-enhanced CT, MRI, and subsequent hepatic resection within 2 months. The percentages of CT/MRI LR-4/5 and LR-M in proliferative and non-proliferative HCCs were compared. Univariable and multivariable Cox proportional hazards regression analyses were performed to assess the association of LI-RADS categories (LR-4/5 vs. LR-M) and pathologic classification (proliferative vs. non-proliferative) with overall survival (OS) and recurrence-free survival (RFS). Subgroups of patients with proliferative and non-proliferative HCCs were analyzed to compare OS and RFS between LR-4/5 and LR-M. RESULTS: Of the 204 included patients, 38 were classified as having proliferative HCC. The percentages of LR-M were higher in proliferative than non-proliferative HCC on both CT (15.8% vs. 3.0%, p = 0.007) and MRI (26.3% vs. 9.6%, p = 0.016). Independent of pathologic classification, CT and MRI LR-M were significantly associated with poorer OS (hazard ratio (HR) = 4.58, p = 0.013, and HR = 6.45, p < 0.001) and RFS (HR = 3.66, p = 0.005, and HR = 6.44, p < 0.001) than LR-4/5. MRI LR-M was associated with significantly poorer OS (p ≤ 0.003) and RFS (p < 0.001) than MRI LR-4/5 in both proliferative and non-proliferative HCCs. CONCLUSIONS: This multi-reader study showed that the percentages of LR-M were significantly higher in proliferative than non-proliferative HCCs. CT/MRI LR-M was significantly associated with poor OS and RFS, independent of the pathologic classification of proliferative versus non-proliferative HCCs. CLINICAL RELEVANCE STATEMENT: CT and MRI LI-RADS category M can be clinically useful in predicting poor outcomes in patients with proliferative and non-proliferative hepatocellular carcinomas. KEY POINTS: • The percentages of LR-M tumors on both CT and MRI were significantly higher in proliferative than non-proliferative hepatocellular carcinomas. • Independent of pathologic classification, CT/MRI LR-M categories were correlated with poor overall survival and recurrence-free survival. • Patients with both proliferative and non-proliferative hepatocellular carcinomas categorized as MRI LR-M had significantly poorer overall survival and recurrence-free survival than those categorized as MRI LR-4/5.

Targetoid Primary Liver Malignancy in Chronic Liver Disease: Prediction of Postoperative Survival Using Preoperative MRI Findings and Clinical Factors.

OBJECTIVE: We aimed to assess and validate the radiologic and clinical factors that were associated with recurrence and survival after curative surgery for heterogeneous targetoid primary liver malignancies in patients with chronic liver disease and to develop scoring systems for risk stratification. MATERIALS AND METHODS: This multicenter retrospective study included 197 consecutive patients with chronic liver disease who had a single targetoid primary liver malignancy (142 hepatocellular carcinomas, 37 cholangiocarcinomas, 17 combined hepatocellular carcinoma-cholangiocarcinomas, and one neuroendocrine carcinoma) identified on preoperative gadoxetic acid-enhanced MRI and subsequently surgically removed between 2010 and 2017. Of these, 120 patients constituted the development cohort, and 77 patients from separate institution served as an external validation cohort. Factors associated with recurrence-free survival (RFS) and overall survival (OS) were identified using a Cox proportional hazards analysis, and risk scores were developed. The discriminatory power of the risk scores in the external validation cohort was evaluated using the Harrell C-index. The Kaplan-Meier curves were used to estimate RFS and OS for the different risk-score groups. RESULTS: In RFS model 1, which eliminated features exclusively accessible on the hepatobiliary phase (HBP), tumor size of 2-5 cm or > 5 cm, and thin-rim arterial phase hyperenhancement (APHE) were included. In RFS model 2, tumors with a size of > 5 cm, tumor in vein (TIV), and HBP hypointense nodules without APHE were included. The OS model included a tumor size of > 5 cm, thin-rim APHE, TIV, and tumor vascular involvement other than TIV. The risk scores of the models showed good discriminatory performance in the external validation set (C-index, 0.62-0.76). The scoring system categorized the patients into three risk groups: favorable, intermediate, and poor, each with a distinct survival outcome (all log-rank p < 0.05). CONCLUSION: Risk scores based on rim arterial enhancement pattern, tumor size, HBP findings, and radiologic vascular invasion status may help predict postoperative RFS and OS in patients with targetoid primary liver malignancies.

Visualization Score of Gadoxetic Acid-Enhanced Magnetic Resonance Imaging: The Effect on the Diagnostic Accuracy for Hepatocellular Carcinoma.

BACKGROUND: The visualization score of hepatobiliary-phase (HBP) images has been introduced as an image quality index for gadoxetic acid-enhanced MRI. It may be associated with hepatic function and could have an implication on the diagnostic accuracy for hepatocellular carcinoma (HCC). PURPOSE: To investigate the association between the visualization score of gadoxetic acid-enhanced MRI and clinical factors and to evaluate its effect on the diagnostic accuracy for HCC ≤ 3.0 cm. STUDY TYPE: Retrospective. POPULATION: A total of 493 focal lesions from 397 patients. FIELD STRENGTH/SEQUENCE: A 5-T or 3.0 -T with pre/postcontrast T1-weighted 3D gradient echo sequence, and T2-weighted fast spin-echo sequence ASSESSMENT: Child-Pugh classification and albumin-bilirubin (ALBI) score were assessed. Three readers evaluated the visualization score of each MRI examination (A, no or minimal; B, moderate; and C, severe limitations), and major features (arterial-phase hyperenhancement, washout, enhancing capsule, threshold growth) and ancillary features of each focal lesion. STATISTICAL TESTS: Univariable and multivariable logistic regression analyses were performed to determine significant clinical factors associated with a suboptimal visualization score (B or C). Generalized estimating equations were used to compare the sensitivity and specificity for diagnosing HCC between the two group (visualization score A vs. B or C). A P value < 0.05 was considered statistically significant. RESULTS: Of the 397 MRI examinations, the incidence of suboptimal visualization score was 13%. A suboptimal visualization score was significantly associated with Child-Pugh classification B or C (adjusted odds ratio [OR] = 15.2) and ALBI grade 2 or 3 (OR = 4.7). Compared with the visualization score A group, the suboptimal visualization score group showed significantly lower sensitivity (56.8% vs. 75.2%) and less frequent washout in HCC (62.2% vs. 84.0%). DATA CONCLUSION: The visualization score on gadoxetic acid-enhanced MRI can be an important image quality index and the diagnostic accuracy for HCC ≤ 3.0 cm may not be sufficient in the suboptimal visualization score group. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 3.

Prediction of Decompensation and Death in Advanced Chronic Liver Disease Using Deep Learning Analysis of Gadoxetic Acid-Enhanced MRI.

OBJECTIVE: This study aimed to evaluate the usefulness of quantitative indices obtained from deep learning analysis of gadoxetic acid-enhanced hepatobiliary phase (HBP) MRI and their longitudinal changes in predicting decompensation and death in patients with advanced chronic liver disease (ACLD). MATERIALS AND METHODS: We included patients who underwent baseline and 1-year follow-up MRI from a prospective cohort that underwent gadoxetic acid-enhanced MRI for hepatocellular carcinoma surveillance between November 2011 and August 2012 at a tertiary medical center. Baseline liver condition was categorized as non-ACLD, compensated ACLD, and decompensated ACLD. The liver-to-spleen signal intensity ratio (LS-SIR) and liver-to-spleen volume ratio (LS-VR) were automatically measured on the HBP images using a deep learning algorithm, and their percentage changes at the 1-year follow-up (ΔLS-SIR and ΔLS-VR) were calculated. The associations of the MRI indices with hepatic decompensation and a composite endpoint of liver-related death or transplantation were evaluated using a competing risk analysis with multivariable Fine and Gray regression models, including baseline parameters alone and both baseline and follow-up parameters. RESULTS: Our study included 280 patients (153 male; mean age ± standard deviation, 57 ± 7.95 years) with non-ACLD, compensated ACLD, and decompensated ACLD in 32, 186, and 62 patients, respectively. Patients were followed for 11-117 months (median, 104 months). In patients with compensated ACLD, baseline LS-SIR (sub-distribution hazard ratio [sHR], 0.81; p = 0.034) and LS-VR (sHR, 0.71; p = 0.01) were independently associated with hepatic decompensation. The ΔLS-VR (sHR, 0.54; p = 0.002) was predictive of hepatic decompensation after adjusting for baseline variables. ΔLS-VR was an independent predictor of liver-related death or transplantation in patients with compensated ACLD (sHR, 0.46; p = 0.026) and decompensated ACLD (sHR, 0.61; p = 0.023). CONCLUSION: MRI indices automatically derived from the deep learning analysis of gadoxetic acid-enhanced HBP MRI can be used as prognostic markers in patients with ACLD.

Application of deep learning to the diagnosis of cervical lymph node metastasis from thyroid cancer with CT: external validation and clinical utility for resident training.

PURPOSE: This study aimed to validate a deep learning model's diagnostic performance in using computed tomography (CT) to diagnose cervical lymph node metastasis (LNM) from thyroid cancer in a large clinical cohort and to evaluate the model's clinical utility for resident training. METHODS: The performance of eight deep learning models was validated using 3838 axial CT images from 698 consecutive patients with thyroid cancer who underwent preoperative CT imaging between January and August 2018 (3606 and 232 images from benign and malignant lymph nodes, respectively). Six trainees viewed the same patient images (n = 242), and their diagnostic performance and confidence level (5-point scale) were assessed before and after computer-aided diagnosis (CAD) was included. RESULTS: The overall area under the receiver operating characteristics (AUROC) of the eight deep learning algorithms was 0.846 (range 0.784-0.884). The best performing model was Xception, with an AUROC of 0.884. The diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of Xception were 82.8%, 80.2%, 83.0%, 83.0%, and 80.2%, respectively. After introducing the CAD system, underperforming trainees received more help from artificial intelligence than the higher performing trainees (p = 0.046), and overall confidence levels significantly increased from 3.90 to 4.30 (p < 0.001). CONCLUSION: The deep learning-based CAD system used in this study for CT diagnosis of cervical LNM from thyroid cancer was clinically validated with an AUROC of 0.884. This approach may serve as a training tool to help resident physicians to gain confidence in diagnosis. KEY POINTS: • A deep learning-based CAD system for CT diagnosis of cervical LNM from thyroid cancer was validated using data from a clinical cohort. The AUROC for the eight tested algorithms ranged from 0.784 to 0.884. • Of the eight models, the Xception algorithm was the best performing model for the external validation dataset with 0.884 AUROC. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were 82.8%, 80.2%, 83.0%, 83.0%, and 80.2%, respectively. • The CAD system exhibited potential to improve diagnostic specificity and accuracy in underperforming trainees (3 of 6 trainees, 50.0%). This approach may have clinical utility as a training tool to help trainees to gain confidence in diagnoses.

Sigmoid volvulus: identifying patients requiring emergency surgery with the dark torsion knot sign.

OBJECTIVES: To determine which clinical or CT imaging factors can help accurately identify complicated sigmoid volvulus (SV), defined as irreversible bowel ischaemia or necrosis requiring emergent surgery in patients with SV. METHODS: We performed a retrospective study of 51 patients admitted consecutively to the emergency department for SV. All patients attempted endoscopic detorsion as the first treatment. Clinical and contrast-enhanced CT factors were analysed. A newly described dark torsion knot sign (sudden loss of mucosal enhancement in the volvulus torsion knot) was included as a CT factor. Patients were diagnosed with complicated versus simple SV based on either surgery or follow-up endoscopic findings. Univariate and multivariate analyses were used to identify predictors of complicated SV. RESULTS: Of 51 study patients, 9 patients (17.6%) had complicated SV. Univariate analysis revealed that three clinical factors (sepsis, elevated C-reactive protein, and elevated lactic acid levels) and four CT factors (reduced bowel wall enhancement, increased bowel wall thickness, dark torsion knot sign, and diffuse omental infiltration) were significantly associated with complicated SV. Multivariate analysis identified only dark torsion knot sign (odds ratio = 104.40; p = 0.002) and sepsis (odds ratio = 16.85; p = 0.043) as independent predictive factors of complicated SV. CONCLUSION: A newly defined CT imaging factor of dark torsion knot sign and a clinical factor of sepsis can predict complicated SV necessitating emergent surgery instead of colonoscopic detorsion as a primary treatment of choice. KEY POINTS: • A newly defined CT imaging factor of dark torsion knot sign and a clinical factor of sepsis can be helpful for predicting complicated SV necessitating emergent surgery instead of endoscopic detorsion.