BACKGROUND:The mutation status of rat sarcoma viral oncogene homolog (RAS) has prognostic significance and serves as a key predictive biomarker for the effectiveness of antiepidermal growth factor receptor (EGFR) therapy. However, there remains a lack of effective models for predicting RAS mutation status in colorectal liver metastases (CRLMs). This study aimed to construct and validate a diagnostic model for predicting RAS mutation status among patients undergoing hepatic resection for CRLMs.METHODS:A diagnostic multivariate prediction model was developed and validated in patients with CRLMs who had undergone hepatectomy between 2014 and 2020. Patients from Institution A were assigned to the model development group (i.e., Development Cohort), while patients from Institutions B and C were assigned to the external validation groups (i.e., Validation Cohort_1 and Validation Cohort_2). The presence of CRLMs was determined by examination of surgical specimens. RAS mutation status was determined by genetic testing. The final predictors, identified by a group of oncologists and radiologists, included several key clinical, demographic, and radiographic characteristics derived from magnetic resonance images. Multiple imputation was performed to estimate the values of missing non-outcome data. A penalized logistic regression model using the adaptive least absolute shrinkage and selection operator penalty was implemented to select appropriate variables for the development of the model. A single nomogram was constructed from the model. The performance of the prediction model, discrimination, and calibration were estimated and reported by the area under the receiver operating characteristic curve (AUC) and calibration plots. Internal validation with a bootstrapping procedure and external validation of the nomogram were assessed. Finally, decision curve analyses were used to characterize the clinical outcomes of the Development and Validation Cohorts.RESULTS:A total of 173 patients were enrolled in this study between January 2014 and May 2020. Of the 173 patients, 117 patients from Institution A were assigned to the Model Development group, while 56 patients (33 from Institution B and 23 from Institution C) were assigned to the Model Validation groups. Forty-six (39.3%) patients harbored RAS mutations in the Development Cohort compared to 14 (42.4%) in Validation Cohort_1 and 8 (34.8%) in Validation Cohort_2. The final model contained the following predictor variables: time of occurrence of CRLMs, location of primary lesion, type of intratumoral necrosis, and early enhancement of liver parenchyma. The diagnostic model based on clinical and MRI data demonstrated satisfactory predictive performance in distinguishing between mutated and wild-type RAS, with AUCs of 0.742 (95% confidence interval [CI]: 0.651─0.834), 0.741 (95% CI: 0.649─0.836), 0.703 (95% CI: 0.514─0.892), and 0.708 (95% CI: 0.452─0.964) in the Development Cohort, bootstrapping internal validation, external Validation Cohort_1 and Validation Cohort_2, respectively. The Hosmer-Lemeshow goodness-of-fit values for the Development Cohort, Validation Cohort_1 and Validation Cohort_2 were 2.868 (p = 0.942), 4.616 (p = 0.465), and 6.297 (p = 0.391), respectively.CONCLUSIONS:Integrating clinical, demographic, and radiographic modalities with a magnetic resonance imaging-based approach may accurately predict the RAS mutation status of CRLMs, thereby aiding in triage and possibly reducing the time taken to perform diagnostic and life-saving procedures. Our diagnostic multivariate prediction model may serve as a foundation for prognostic stratification and therapeutic decision-making.

Background Persistent organ failure (POF) is the leading cause of death in patients with acute necrotizing pancreatitis (ANP). Although several risk factors have been identified, there remains a lack of efficient instruments to accurately predict the incidence of POF in ANP. Methods Retrospectively, the clinical and imaging data of 178 patients with ANP were collected from our database, and the patients were divided into training (n = 125) and validation (n = 53) cohorts. Through computed tomography image acquisition, the volume of interest segmentation, and feature extraction and selection, a pure radiomics model in terms of POF prediction was established. Then, a clinic-radiomics model integrating the pure radiomics model and clinical risk factors was constructed. Both primary and secondary endpoints were compared between the high- and low-risk groups stratified by the clinic-radiomics model. Results According to the 547 selected radiomics features, four models were derived from features. A clinic-radiomics model in the training and validation sets showed better predictive performance than pure radiomics and clinical models. The clinic-radiomics model was evaluated by the ratios of intervention and mechanical ventilation, intensive care unit (ICU) stays, and hospital stays. The results showed that the high-risk group had significantly higher intervention rates, ICU stays, and hospital stays than the low-risk group, with the confidence interval of 90% (p < 0.1 for all). Conclusions This clinic-radiomics model is a useful instrument for clinicians to evaluate the incidence of POF, facilitating patients' and their families' understanding of the ANP prognosis.

Background:Limited literature is available on new-onset diabetes mellitus (NODM) after distal pancreatectomy. This study aimed to investigate the correlation between surgery-related factors and the incidence of NODM after distal pancreatectomy. Methods:Patients were divided into the NODM-positive or NODM-negative group according to the diagnosis of NODM. After propensity score matching, the correlation between operation-related factors and the incidence of NODM was analyzed. The diagnostic threshold for predicting NODM was determined using the receiver operating characteristic (ROC) curve and the Youden index. Results:No significant correlation was observed between the NODM incidence after distal pancreatectomy and operative blood loss, spleen preservation, surgical method (open or laparoscopy), postoperative ALB and HB (first day after surgery), and postoperative pathology. However, a significant correlation was found between the NODM incidence and the postoperative pancreatic volume or the resected pancreatic volume ratio. Resected pancreatic volume ratio was identified as a predictive risk factor for NODM. Youden index of the ROC curve was 0.548, with a cut off value of 32.05% for resected pancreatic volume ratio. The sensitivity and specificity of the cut off values were 0.952 and 0.595, respectively. Conclusions:This study demonstrated that the volume ratio of pancreatic resection is a risk factor for the incidence of NODM after distal pancreatectomy. This can be used to predict the incidence of NODM and may have further clinical applications.

Objectives The purpose of this study was to establish a risk prediction model for differential diagnosis of pheochromocytomas (PCCs) from lipid-poor adenomas (LPAs) using a grouping method based on tri-phasic CT image features. Methods In this retrospective study, we enrolled patients that were assigned to a training set (136 PCCs and 183 LPAs) from two medical centers, along with an external independent validation set (30 PCCs and 54 LPAs) from another center. According to the attenuation values in unenhanced CT (CTu), the lesions were divided into three groups: group 1, 10 HU < CTu ≤ 25 HU; group 2, 25 HU < CTu ≤ 40 HU; and group 3, CTu > 40 HU. Quantitative and qualitative CT imaging features were calculated and evaluated. Univariate, ROC, and binary logistic regression analyses were applied to compare these features. Results Cystic degeneration, CTu, and the peak value of enhancement in the arterial and venous phase (DEpeak) were independent risk factors for differential diagnosis of adrenal PCCs from LPAs. In all subjects (groups 1, 2, and 3), the model formula for the differentiation of PCCs was as follows: Y = -7.709 + 3.617*(cystic degeneration) + 0.175*(CTu ≥ 35.55 HU) + 0.068*(DEpeak ≥ 51.35 HU). ROC curves were drawn with an AUC of 0.95 (95% CI: 0.927–0.973) in the training set and 0.91 (95% CI: 0.860–0.929) in the external validation set. Conclusion A reliable and practical prediction model for differential diagnosis of adrenal PCCs and LPAs was established using a grouping method.

BACKGROUND AND AIMS:The detection rate for early gastric cancer (EGC) is unsatisfactory, and mastering the diagnostic skills of magnifying endoscopy with narrow-band imaging (ME-NBI) requires rich expertise and experience. We aimed to develop an EGC captioning model (EGCCap) to automatically describe the visual characteristics of ME-NBI images for endoscopists. METHODS:ME-NBI images (n = 1886) from 294 cases were enrolled from multiple centers, and corresponding 5658 text data were designed following the simple EGC diagnostic algorithm. An EGCCap was developed using the multiscale meshed-memory transformer. We conducted comprehensive evaluations for EGCCap including the quantitative and quality of performance, generalization, robustness, interpretability, and assistant value analyses. The commonly used metrics were BLEUs, CIDEr, METEOR, ROUGE, SPICE, accuracy, sensitivity, and specificity. Two-sided statistical tests were conducted, and statistical significance was determined when P < .05. RESULTS:EGCCap acquired satisfying captioning performance by outputting correctly and coherently clinically meaningful sentences in the internal test cohort (BLEU1 = 52.434, CIDEr = 36.734, METEOR = 27.823, ROUGE = 49.949, SPICE = 35.548) and maintained over 80% performance when applied to other centers or corrupted data. The diagnostic ability of endoscopists improved with the assistance of EGCCap, which was especially significant (P < .05) for junior endoscopists. Endoscopists gave EGCCap an average remarkable score of 7.182, showing acceptance of EGCCap. CONCLUSIONS:EGCCap exhibited promising captioning performance and was proven with satisfying generalization, robustness, and interpretability. Our study showed potential value in aiding and improving the diagnosis of EGC and facilitating the development of automated reporting in the future.

Gastroscopic biopsy provides the only effective method for gastric cancer diagnosis, but the gold standard histopathology is time-consuming and incompatible with gastroscopy. Conventional stimulated Raman scattering (SRS) microscopy has shown promise in label-free diagnosis on human tissues, yet it requires the tuning of picosecond lasers to achieve chemical specificity at the cost of time and complexity. Here, we demonstrate that single-shot femtosecond SRS (femto-SRS) reaches the maximum speed and sensitivity with preserved chemical resolution by integrating with U-Net. Fresh gastroscopic biopsy is imaged in <60 s, revealing essential histoarchitectural hallmarks perfectly agreed with standard histopathology. Moreover, a diagnostic neural network (CNN) is constructed based on images from 279 patients that predicts gastric cancer with accuracy >96%. We further demonstrate semantic segmentation of intratumor heterogeneity and evaluation of resection margins of endoscopic submucosal dissection (ESD) tissues to simulate rapid and automated intraoperative diagnosis. Our method holds potential for synchronizing gastroscopy and histopathological diagnosis.

Purpose The aim of this study is to investigate radiomics features extracted from the optimal peritumoral region and the intratumoral area on the early phase of dynamic contrast-enhanced MRI (DCE-MRI) for predicting molecular subtypes of invasive ductal breast carcinoma (IDBC). Methods A total of 422 IDBC patients with immunohistochemical and fluorescence in situ hybridization results from two hospitals (Center 1: 327 cases, Center 2: 95 cases) who underwent preoperative DCE-MRI were retrospectively enrolled. After image preprocessing, radiomic features were extracted from the intratumoral area and four peritumoral regions on DCE-MRI from two centers, and selected the optimal peritumoral region. Based on the intratumoral, peritumoral radiomics features, and clinical–radiological characteristics, five radiomics models were constructed through support vector machine (SVM) in multiple classification tasks related to molecular subtypes and visualized by nomogram. The performance of radiomics models was evaluated by receiver operating characteristic curves, confusion matrix, calibration curves, and decision curve analysis. Results A 6-mm peritumoral size was defined the optimal peritumoral region in classification tasks of hormone receptor (HR)-positive vs others, triple-negative breast cancer (TNBC) vs others, and HR-positive vs human epidermal growth factor receptor 2 (HER2)-enriched vs TNBC, and 8 mm was applied in HER2-enriched vs others. The combined clinical–radiological and radiomics models in three binary classification tasks (HR-positive vs others, HER2-enriched vs others, TNBC vs others) obtained optimal performance with AUCs of 0.838, 0.848, and 0.930 in the training cohort, respectively; 0.827, 0.813, and 0.879 in the internal test cohort, respectively; and 0.791, 0.707, and 0.852 in the external test cohort, respectively. Conclusion Radiomics features in the intratumoral and peritumoral regions of IDBC on DCE-MRI had a potential to predict the HR-positive, HER2-enriched, and TNBC molecular subtypes preoperatively.

Methods:We studied 51 abdominal PGL patients at the First Affiliated Hospital of Bengbu Medical College, Tongde Hospital, and Sir Run Shaw Hospital, Hangzhou, Zhejiang Province, China, from June 2009 to May 2019. Thereafter, the clinical research data, tumor biomarkers, and CT features were compared between the aggressive PGLs and the nonaggressive PGLs using independent-samples t-tests and chi-square tests.Results:Of the 51 cases, 43 were benign and 8 had malignant tendencies. Postoperative recurrence and metastasis were more likely to occur when the tumor diameter was >8 cm or/and the enhancement degree was not obvious. Clinical symptoms, tumor markers, sex, age, and CT image characteristics including morphology, presence of cystic degeneration, "pointed peach" sign, calcification, hemorrhage, enlarged lymph nodes, and peritumor and intratumor blood vessels were not significantly different between the two groups (p > 0.05).Conclusion:Our findings suggest that CT features, including size >8 cm and enhancement degree, could provide important evidence to assess risk factors for aggressive PGLs.

RATIONALE:Hemangioblastomas in the kidney are rare. Although a few cases of renal hemangioblastoma (RH) have been reported, the content of these articles mainly focused on clinical and pathological research, with minimal descriptions of radiologic findings. Moreover, there are no descriptions of magnetic resonance imaging (MRI) with enhancement of this condition. Herein, we report 2 cases of RH with computed tomography (CT) and MRI findings.PATIENT CONCERNS:Two patients presented to our institution because of dull pain in the left abdomen, and a mass in the left kidney was found by ultrasound examination in each case. The patient had no special family history. Physical examination revealed no obvious tenderness or percussion pain in the renal and ureteral walking areas, and there was no obvious mass. Routine blood and urine tests were normal, and the serum tumor markers were negative. No obvious lesions were found on imaging of the other body parts.DIAGNOSIS:Similar radiologic findings were observed in both cases and mimicked those of cavernous hemangiomas of the liver, including peripheral nodular enhancement in the corticomedullary phase, progressive centripetal enhancement in the nephrographic and delayed phases, and occasional complete "filling in" in the delayed phase. We made a radiologic diagnosis of renal clear cell carcinoma for patient 1 and suspected renal clear cell carcinoma for patient 2, but the pathological results showed RH.INTERVENTIONS:Given the suspicion of renal cell carcinoma, both patients underwent partial nephrectomy.OUTCOME:The recovery of the two patients was uneventful, and there was no evidence of local recurrence or metastasis many years after surgery.LESSONS:RH is a rare benign tumor that can be easily misdiagnosed as clear cell carcinoma. Characteristic CT and MRI manifestations may improve preoperative diagnostic accuracy to avoid surgery or indicate nephron-sparing surgery.

OBJECTIVES:This study explored the early predictive value of volume and mean CT density of necrosis for adverse outcomes in patients with acute necrotising pancreatitis (ANP).METHODS:A total of 155 patients with ANP who underwent CECT within 7 days of symptom onset were included. The necrosis volume, mean CT density, and modified CT severity index (mCTSI) were calculated. C-reactive protein (CRP) and blood urea nitrogen (BUN) levels both 48 h after symptom onset were reviewed. Adverse outcomes were recorded. The predictive value of each indicator was assessed using ROC curve analysis.RESULTS:There were significant associations between necrosis volume and mean CT density and organ failure (OF), persistent OF (POF), and need for intervention (p < 0.001 for all). For predicting OF, the area under the curve (AUC) was significantly higher for necrosis volume than for mCTSI and BUN (AUC: 0.84 vs 0.67, p = 0.0011; 0.84 vs 0.71, p = 0.0193, respectively). For predicting POF and need for intervention, the AUCs for necrosis volume were significantly higher than those for mCTSI (AUC: 0.79 vs 0.66, p = 0.0045; 0.77 vs 0.61, p = 0.0019, respectively), but did not significantly differ from those for CRP and BUN. For predicting OF, a significantly better predictive value was achieved with mean CT density than with mCTSI (AUC: 0.79 vs 0.67, p = 0.0163). There were no significant differences in predictive value between mean CT density, CRP, and BUN.CONCLUSIONS:The volume and mean CT density of necrosis based on CECT can provide early prediction of OF, POF, and need for intervention.KEY POINTS:• Compared to mCTSI, necrosis volume might be used to more accurately diagnose organ failure and persistent organ failure and might be better associated with the need for intervention. • Necrosis volume and mean CT density based on CECT are reliable quantitative predictors for organ failure, persistent organ failure, and intervention in acute pancreatitis.

We aimed to build radiomics models based on triple-phase CT images combining clinical features to predict the risk rating of gastrointestinal stromal tumors (GISTs). A total of 231 patients with pathologically diagnosed GISTs from July 2012 to July 2020 were categorized into a training data set (82 patients with high risk, 80 patients with low risk) and a validation data set (35 patients with high risk, 34 patients with low risk) with a ratio of 7:3. Four diagnostic models were constructed by assessing 20 clinical characteristics and 18 radiomic features that were extracted from a lesion mask based on triple-phase CT images. The receiver operating characteristic (ROC) curves were applied to calculate the diagnostic performance of these models, and ROC curves of these models were compared using Delong test in different data sets. The results of ROC analyses showed that areas under ROC curves (AUC) of model 4 [Clinic + CT value of unenhanced (CTU) + CT value of arterial phase (CTA) + value of venous phase (CTV)], model 1 (Clinic + CTU), model 2 (Clinic + CTA), and model 3 (Clinic + CTV) were 0.925, 0.894, 0.909, and 0.914 in the training set and 0.897, 0.866, 0,892, and 0.892 in the validation set, respectively. Model 4, model 1, model 2, and model 3 yielded an accuracy of 88.3%, 85.8%, 86.4%, and 84.6%, a sensitivity of 85.4%, 84.2%, 76.8%, and 78.0%, and a specificity of 91.2%, 87.5%, 96.2%, and 91.2% in the training set and an accuracy of 88.4%, 84.1%, 82.6%, and 82.6%, a sensitivity of 88.6%, 77.1%, 74.3%, and 85.7%, and a specificity of 88.2%, 91.2%, 91.2%, and 79.4% in the validation set, respectively. There was a significant difference between model 4 and model 1 in discriminating the risk rating in gastrointestinal stromal tumors in the training data set (Delong test, p < 0.05). The radiomic models based on clinical features and triple-phase CT images manifested excellent accuracy for the discrimination of risk rating of GISTs.

The purpose of this study was to investigate the predictive value of combined clinical and imaging features, compared with the clinical or radiological risk factors only. Moreover, the expected results aimed to improve the identification of severe acute respiratory syndrome coronavirus-2 (SARS-COV-2) patients who may have critical outcomes. This retrospective study included laboratory-confirmed SARS-COV-2 cases between January 18, 2020, and February 16, 2020. The patients were divided into 2 groups with noncritical illness and critical illness regarding severity status within the hospitalization. Univariable and multivariable logistic regression models were used to explore the risk factors associated with clinical and radiological outcomes in patients with SARS-COV-2. The ROC curves were performed to compare the prediction performance of different factors. A total of 180 adult patients in this study included 20 critical patients and 160 noncritical patients. In univariate logistic regression analysis, 15 risk factors were significantly associated with critical outcomes. Of importance, C-reactive protein (1.051, 95% confidence interval 1.024-1.078), D-dimer (1.911, 95% CI, 1.050-3.478), and CT score (1.29, 95% CI, 1.053-1.529) on admission were independent risk factors in multivariate analysis. The combined model achieved a better performance in disease severity prediction (P = .05). CRP, D-dimer, and CT score on admission were independent risk factors for critical illness in adults with SARS-COV-2. The combined clinical and radiological model achieved better predictive performance than clinical or radiological factors alone.

Objective:This study aimed to evaluate the performance of breast magnetic resonance imaging (MRI) abbreviated protocol (AP) in diagnosing breast neoplasms.Methods:We retrospectively analyzed the data of 86 patients who had undergone breast MRI examinations and compared the images using an AP and full diagnostic protocol (FDP). The AP consisted of axial T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and four-phase dynamic enhancement sequences. The FDP consisted of sagittal T2WI, axial T2WI, T1-weighted imaging, DWI, and seven-phase dynamic enhancement sequences. All the images were analyzed using the Breast Imaging Reporting and Data System (BI-RADS). The consistencies between the different protocols were then calculated. With the pathological diagnosis as the gold standard, the diagnostic capabilities of the two protocols were compared.Result:Two radiologists analyzed the AP and FDP images. The consistencies in the BI-RADS between the different protocols were 0.856 and 0.900, and those in time-signal intensity curves (TICs) were 0.822 and 0.922. Within the same protocol, the consistencies in the BI-RADS between different radiologists were 0.744 and 0.822, and those in TICs were 0.889 and 0.878. No significant differences were found ( P>0.05). In terms of diagnosing malignant neoplasms using the BI-RADS, the sensitivities of the AP and FDP were 89.8% (95 %CI: 0.785-0.958) and 91.5% (95 %CI: 0.806-0.968), respectively; their specificities were 71.0% (95 %CI: 0.518-0.851) and 77.4% (95 %CI: 0.585-0.897), respectively; and the areas under the curves (AUCs) were 0.804 (95 %CI: 0.698-0.910) and 0.845 (95 %CI: 0.748-0.941), respectively. Diagnosing malignant neoplasms using TICs, the sensitivities of the AP and FDP were 86.4% (95 %CI: 0.745-0.936) and 89.8% (95 %CI: 0.785-0.958), respectively; their specificities were 61.3% (95 %CI: 0.423-0.776) and 67.7% (95 %CI: 0.485-0.827), respectively, and the AUCs were 0.739 (95 %CI: 0.623-0.855) and 0.788 (95 %CI: 0.679-0.897), respectively. There was no significant difference between the AP and FDP ( P>0.05). The MRI acquisition times of the AP and FDP were 11.97±0.94 min and 21.25±1.12 min, respectively, with a significant difference ( P<0.001). The average reading time was reduced by 13.5% using the AP compared with that using the FDP. Conclusion:Compared with the FDP, the AP reduced the acquisition time and maintained the diagnostic accuracy, which can be used as an improved pattern for MRI screening in high-risk populations of breast neoplasms.

Diagnosis of breast invasive micropapillary carcinoma (IMPC) before surgery is of great value for determining the optimal treatment strategy. The aim of the present study was to investigate the magnetic resonance imaging (MRI) and pathological features of IMPC. MRI features of IMPC were characterized in relation to the patients' clinicopathological features. Clinical manifestations, mammography results and/or MRI findings of patients with IMPC were retrospectively analyzed. Parameters included morphology, plain T2-weighted imaging (T2WI) signal intensity, the apparent diffusion coefficient (ADC), the internal enhancement mode, early enhancement rates and time-intensity curve (TIC) types during dynamic enhanced scanning. A total of 10 lesions were detected by MRI in eight patients, with one case having three lesions with the mean diameter of 34.44 mm. In plain T2WI scanning, the lesions appeared inhomogeneous with a moderate or high signal intensity. When the b value was 800 sec/mm(2), the average ADC value was 0.823 +/- 0.12x10(-3)mm(2)/sec. A total of four cases exhibited mass-like enhancement, including an oval rim in one case (three lesions), irregular inhomogeneous enhancement in two cases and irregular uniform enhancement in one case. The margins were clear in one case (three lesions), irregular in two cases and spiculate in one case. Among the four cases with non-mass enhancement, the distribution was focal in two cases, linear in one case and regional in one case, and the internal enhancement mode was cluster-like in one case, heterogeneous in one case and uniform in two cases. The average early enhancement rate was 116.96 +/- 45.26%. TICs of type III were observed in all cases. In conclusion, MRI of IMPC demonstrated typical features of malignant tumors and lymphatic vessel infiltration, suggesting that MRI may exhibit guiding significance for the diagnosis and treatment planning of IMPC.

Cholangiocarcinoma is a most lethal malignancy frequently resistant to chemotherapy. Herpes simplex virus thymidine kinase/Ganciclovir (HSV-TK/GCV) suicide gene therapy is a promising approach to treat different cancers, including cholangiocarcinoma. However drawbacks including low therapeutic gene expression and lack of precise targeted gene delivery limit the wide clinical utilization of the suicide gene therapy. We attempted to overcome these obstacles. We established the "proof-of-principle" of this concept via serial in-vitro experiments using human cholangiocarcinoma cells and then validated the new interventional oncology technique in vivo using mice harboring the same patient derived cholangiocarcinomas. Curative effects were evaluated by magnetic resonance imaging and confirmed by pathology and laboratory examinations. Intratumoral radiofrequency hyperthermia (RFH) significantly elevated the targeted expression of HSV-TK gene and further enhanced the therapeutic effects of direct intratumoral HSV-TK/GCV gene therapy, evident as the least number of survival tumor cells, smallest tumor size, and the highest apoptosis index in the combination treatment of HSV-TK plus RFH, compared to other control treatments. The novel combination of image-guided interventional oncology, RFH technology, and direct gene therapy may be valuable for the effective treatment of cholangiocarcinoma.