Differential diagnosis of pancreatic serous cystadenoma and mucinous cystadenoma: utility of textural features in combination with morphological characteristics

Imaging of pancreatic serous cystadenoma and common imitators

Pancreatic cystic neoplasms are lesions comprised of cystic components that show different biological behaviors, epidemiology, clinical manifestations, imaging features, and malignant potential and management. Benign cystic neoplasms include serous cystic neoplasms (SCAs). Other pancreatic cystic lesions have malignant potential, such as intraductal papillary mucinous neoplasms and mucinous cystic neoplasms. SCAs can be divided into microcystic (classic appearance), honeycomb, oligocystic/macrocystic, and solid patterns based on imaging appearance. They are usually solitary but may be multiple in von Hippel-Lindau disease, which may depict disseminated involvement. The variable appearances of SCAs can mimic other types of pancreatic cystic lesions, and cross-sectional imaging plays an important role in their differential diagnosis. Endoscopic ultrasonography has helped in improving diagnostic accuracy of pancreatic cystic lesions by guiding tissue sampling (biopsy) or cyst fluid analysis. Immunohistochemistry and newer techniques such as radiomics have shown improved performance for preoperatively discriminating SCAs and their mimickers.

Utilization of texture features of volumetric ADC maps in differentiating between serous cystadenoma and intraductal papillary neoplasms

INTRODUCTION

The rising incidence of incidental detection of pancreatic cystic neoplasms has compelled radiologists to determine new diagnostic methods for the differentiation of various kinds of lesions. We aim to demonstrate the utility of texture features extracted from ADC maps in differentiating intraductal papillary mucinous neoplasms (IPMN) from serous cystadenomas (SCA).

METHODS

This retrospective study was performed on 136 patients (IPMN = 87, SCA = 49) split into testing and training datasets. A total of 851 radiomics features were extracted from volumetric contours drawn by an expert radiologist on ADC maps of the lesions. LASSO regression analysis was used to determine the most predictive set of features and a radiomics score was developed based on their respective coefficients. A hyper-optimized support vector machine was then utilized to classify the lesions based on their radiomics score.

RESULTS

A total of four Wavelet features (LHL/GLCM/LCM2, HLL/GLCM/LCM2, /LLL/First Order/90percent, /LLL/GLCM/MCC) were selected from all of the features to be included in our classifier. The classifier was optimized by altering hyperparameters and the trained model was applied to the validation dataset. The model achieved a sensitivity of 92.8, specificity of 90%, and an AUC of 0.97 in the training data set, and a sensitivity of 83.3%, specificity of 66.7%, and AUC of 0.90 in the testing dataset.

CONCLUSION

A support vector machine model trained and validated on volumetric texture features extracted from ADC maps showed the possible beneficence of these features in differentiating IPMNs from SCAs. These results are in line with previous regarding the role of ADC maps in classifying cystic lesions and offers new evidence regarding the role of texture features in differentiation of potentially neoplastic and benign lesions.

Radiomics advances in the evaluation of pancreatic cystic neoplasms

With the development of medical imaging, the detection rate of pancreatic cystic neoplasms (PCNs) has increased greatly. Serous cystic neoplasm, solid pseudopapillary neoplasm, intraductal papillary mucinous neoplasm and mucinous cystic neoplasm are the main subtypes of PCN, and their treatment options vary greatly due to the different biological behaviours of the tumours. Different from conventional qualitative imaging evaluation, radiomics is a promising noninvasive approach for the diagnosis, classification, and risk stratification of diseases involving high-throughput extraction of medical image features. We present a review of radiomics in the diagnosis of serous cystic neoplasm and mucinous cystic neoplasm, risk classification of intraductal papillary mucinous neoplasm and prediction of solid pseudopapillary neoplasm invasiveness compared to conventional imaging diagnosis. Radiomics is a promising tool in the field of medical imaging, providing a noninvasive, high-performance model for preoperative diagnosis and risk stratification of PCNs and improving prospects regarding management of these diseases. Further studies are warranted to investigate MRI image radiomics in connection with PCNs to improve the diagnosis and treatment strategies in the management of PCN patients.

Optimal peritoneal cancer index cutoff point for predicting surgical resectability of pseudomyxoma peritonei in treatment-naive patients

BACKGROUND

The peritoneal cancer index (PCI) has been used to predict surgical outcomes for pseudomyxoma peritonei (PMP). The present study aimed to establish the optimal cutoff point for PCI to predict surgical resectability of PMP.

METHODS

A total of 366 PMP patients were included. The patients were divided into low-grade and high-grade groups. Based on the completeness of the cytoreduction (CC) score, both low-grade and high-grade PMP patients were further divided into complete cytoreductive surgery (CRS) and maximal tumor debulking (MTD) subgroups. The ability to predict surgical resectability of total and selected PCI (regions 2 + 9 to 12) was analyzed through receiver operating characteristic (ROC) curves.

RESULTS

Both total and selected PCI demonstrated excellent discriminative ability in predicting surgical resectability for low-grade PMP patients (n = 266), with the ROC-AUC of 0.940 (95% CI: 0.904-0.965) and 0.927 (95% CI: 0.889-0.955). The corresponding optimal cutoff point was 21 and 5, respectively. For high-grade PMP patients (n = 100), both total and selected PCI exhibited good performance in predicting surgical resectability, with the ROC-AUC of 0.894 (95% CI: 0.816-0.946) and 0.888 (95% CI: 0.810-0.943); correspondingly, the optimal cutoff point was 25 and 8, respectively. The discriminative ability between total and selected PCI in predicting surgical resectability did not show a statistical difference.

CONCLUSIONS

Both total and selected PCI exhibited good performance and similarity in predicting complete surgical resection for both low-grade and high-grade PMP patients. However, the selected PCI was simpler and time-saving in clinical practice. In the future, new imaging techniques or predictive models may be developed to better predict PCI preoperatively, which might assist in confirming whether complete surgical resection can be achieved.

Bland-Altman agreement analysis between CT predicted and surgical peritoneal cancer index in pseudomyxoma peritonei of appendiceal origin

Peritoneal cancer index (PCI) is the surgical variable most commonly used to quantify the extent of peritoneal metastases for pseudomyxoma peritonei (PMP) patients. The present study aimed to investigate the agreement between CT predicted and surgical PCI by the Bland-Altman method for PMP of appendiceal origin. A total of 167 PMP patients of appendiceal origin were included between 2016 and 2021. Bland-Altman analysis was performed for both total PCI and selected PCI (regions 2 + 9-12). After the Bland-Altman plot was drawn, the mean bias and its 95% limit of agreements (LoAs) was quantified. Besides, the correlation coefficients between CT-PCI and surgical PCI were also been calculated. The Bland-Altman plot showed the mean bias ± SD between total CT-PCI and surgical PCI as 0.431 ± 3.005, with the LoAs from - 5.459 to 6.321. There were nine points of difference in total PCI exceeded the 95% LoAs, with the rate of 5.39% (9/167). As for selected CT-PCI, Bland-Altman plot showed the mean bias ± SD between selected CT-PCI and surgical PCI as - 0.287 ± 1.955, with the LoAs from - 4.118 to 3.544. There were ten points of difference in selected PCI exceeded the 95% LoAs, with the rate of 5.99% (10/167). The Spearman's rank correlation coefficient between total CT-PCI and surgical PCI was 0.911, P < 0.001, as for selected CT-PCI and surgical PCI, the coefficient was 0.909, P < 0.001. Although there was a strong correlation for both total and selected CT-PCI with surgical PCI, however, the agreement is still not good in Bland-Altman analysis, which suggested that CT-PCI cannot predict surgical PCI accurately even in professional PMP treatment centers. In brief explanation, CT makes it difficult to distinguish the borderline between tumor tissue and mucus and to detect tumor lesions in the small intestine regions, which caused overestimation or underestimation by CT-PCI. In the future, a multiple linear regression model based on CT-PCI might accurately predict surgical PCI preoperatively.

Radiomics Based on Contrast-Enhanced Ultrasound Images for Diagnosis of Pancreatic Serous Cystadenoma

OBJECTIVE

The purpose of the study was to develop and validate a radiomics model by using contrast-enhanced ultrasound (CEUS) data for pre-operative differential diagnosis of pancreatic cystic neoplasms (PCNs), especially pancreatic serous cystadenoma (SCA).

METHODS

Patients with pathologically confirmed PCNs who underwent CEUS examination at Chinese PLA hospital from May 2015 to August 2022 were retrospectively collected. Radiomic features were extracted from the regions of interest, which were obtained based on CEUS images. A support vector machine algorithm was used to construct a radiomics model. Moreover, based on the CEUS image features, the CEUS and the combined models were constructed using logistic regression. The performance and clinical utility of the optimal model were evaluated by area under the receiver operating characteristic curve (AUC), sensitivity, specificity and decision curve analysis.

RESULTS

A total of 113 patients were randomly split into the training (n = 79) and test cohorts (n = 34). These patients were pathologically diagnosed with SCA, mucinous cystadenoma, intraductal papillary mucinous neoplasm and solid-pseudopapillary tumor. The radiomics model achieved an AUC of 0.875 and 0.862 in the training and test cohorts, respectively. The sensitivity and specificity of the radiomics model were 81.5% and 86.5% in the training cohort and 81.8% and 91.3% in the test cohort, respectively, which were higher than or comparable with that of the CEUS model and the combined model.

CONCLUSION

The radiomics model based on CEUS images had a favorable differential diagnostic performance in distinguishing SCA from other PCNs, which may be beneficial for the exploration of personalized management strategies.

Association of Plasma Selenium and Its Untargeted Metabolomic Profiling with Cervical Cancer Prognosis

Selenium is an essential trace element that shows beneficial or adverse health effects depending on the dose. However, its role in the prognosis of cervical cancer (CC) has been less reported. We aimed to explore the association between selenium status and prognosis in CC patients with different prognoses and to elucidate the underlying mechanism of selenium in CC prognosis. This cross-sectional observational study had a case-control design at the Harbin Medical University Cancer Hospital and was conducted using 29 CC cases with poor prognosis and 29 CC cases with good prognosis. Plasma selenium levels were measured using an atomic fluorescence spectrometer. Untargeted metabolomics was used to identify metabolites. Plasma selenium levels of the poor prognosis group (49.90 ± 13.81 µg/L) were lower than that of the good prognosis group (59.38 ± 13.00 µg/L, t = 2.69, P = 0.009). In the logistic regression analysis, plasma selenium levels were associated with lower poor prognosis risk [odds ratio (OR) = 0.952, 95% CI: 0.909-0.998]. Receiver operating characteristic curve analysis revealed an optimal cut-off point of plasma selenium levels ≤ 47.68 µg/L for poor prognosis of CC. Based on the cut-off selenium levels, patients with different prognoses were divided into high and low selenium groups. Metabolomic analysis revealed six differential metabolites among different prognoses with low and high selenium levels, and the glycerophospholipid (GPL) metabolism was enriched. Plasma selenium levels were positively correlated with metabolite levels. Our findings provided evidence that low plasma selenium levels may associate with a poor prognosis of CC. Low plasma selenium levels might suppress GPL metabolism and influence the prognosis of CC. This finding requires confirmation in future prospective cohort studies.

Automated diagnosis of pancreatic mucinous and serous cystic neoplasms with modality-fusion deep neural network using multi-modality MRIs

Background

Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their sub-types, serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN), are often misclassified from each other. Because SCN is primarily benign and MCN has a high rate of malignant transformation. Distinguishing SCN and MCN is challenging and essential.

Purpose

MRIs have many different modalities, complete with SCN and MCN diagnosis information. With the help of an artificial intelligence-based algorithm, we aimed to propose a multi-modal hybrid deep learning network that can efficiently diagnose SCN and MCN using multi-modality MRIs.

Methods

A cross-modal feature fusion structure was innovatively designed, combining features of seven modalities to realize the classification of SCN and MCN. 69 Patients with multi-modalities of MRIs were included, and experiments showed performances of every modality.

Results

The proposed method with the optimized settings outperformed all other techniques and human radiologists with high accuracy of 75.07% and an AUC of 82.77%. Besides, the proposed disentanglement method outperformed other fusion methods, and delayed contrast-enhanced T1-weighted MRIs proved most valuable in diagnosing SCN and MCN.

Conclusions

Through the use of a contemporary artificial intelligence algorithm, physicians can attain high performance in the complex challenge of diagnosing SCN and MCN, surpassing human radiologists to a significant degree.

DEVELOPMENT OF A MACHINE LEARNING MODEL FOR PREDICTING 28-DAY MORTALITY OF SEPTIC PATIENTS WITH ATRIAL FIBRILLATION

ABSTRACT

Introduction: Septic patients with atrial fibrillation (AF) are common in the intensive care unit accompanied by high mortality. The early prediction of prognosis of these patients is critical for clinical intervention. This study aimed to develop a model by using machine learning (ML) algorithms to predict the risk of 28-day mortality in septic patients with AF. Methods: In this retrospective cohort study, we extracted septic patients with AF from the Medical Information Mart for Intensive Care III (MIMIC-III) and IV database. Afterward, only MIMIC-IV cohort was randomly divided into training or internal validation set. External validation set was mainly extracted from MIMIC-III database. Propensity score matching was used to reduce the imbalance between the external validation and internal validation data sets. The predictive factors for 28-day mortality were determined by using multivariate logistic regression. Then, we constructed models by using ML algorithms. Multiple metrics were used for evaluation of performance of the models, including the area under the receiver operating characteristic curve, sensitivity, specificity, recall, and accuracy. Results: A total of 5,317 septic patients with AF were enrolled, with 3,845 in the training set, 960 in the internal testing set, and 512 in the external testing set, respectively. Then, we established four prediction models by using ML algorithms. AdaBoost showed moderate performance and had a higher accuracy than the other three models. Compared with other severity scores, the AdaBoost obtained more net benefit. Conclusion: We established the first ML model for predicting the 28-day mortality of septic patients with AF. Compared with conventional scoring systems, the AdaBoost model performed moderately. The model established will have the potential to improve the level of clinical practice.

The molecular, immune features, and risk score construction of intraductal papillary mucinous neoplasm patients

Intraductal papillary mucinous neoplasm (IPMN) is a common pancreatic precancerous lesion, with increasing incidence in recent years. However, the mechanisms of IPMN progression into invasive cancer remain unclear. The mRNA expression data of IPMN/PAAD patients were extracted from the TCGA and GEO databases. First, based on GSE19650, we analyzed the molecular alterations, tumor stemness, immune landscape, and transcriptional regulation of IPMN progression. The results indicated that gene expression changed dramatically, specifically at the intraductal papillary-mucinous adenoma (IPMA) stage. Gene ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Kyoto Encyclopedia of Genes and Genomes (GSEA) pathway analyses showed that glycoprotein-related, cell cycle, and P53 pathways displayed the most significant changes during progression. With IPMN progression, tumor stemness increased continuously, and KRAS, ERBB3, RUNX1, and ELF3 are essential driver genes affecting tumor stemness. Motif analysis suggested that KLF4 may be a specific transcription factor that regulates gene expression in the IPMA stage, while MYB and MYBL1 control gene expression in the IPMC and invasive stages, respectively. Then, GSE19650 and GSE71729 transcriptome data were combined to perform the least absolute shrinkage and selection operator (LASSO) method and Cox regression analysis to develop an 11-gene prediction model (KCNK1, FHL2, LAMC2, CDCA7, GPX3, C7, VIP, HBA1, BTG2, MT1E, and LYVE1) to predict the prognosis of pancreatic cancer patients. The reliability of the model was validated in the GSE71729 and TCGA databases. Finally, 11 additional IPMN patients treated in our hospital were included, and the immune microenvironment changes during IPMN progression were analyzed by immunohistochemistry (IHC). IHC results suggest that Myeloid-derived suppressor cells (MDSCs) and macrophages may be key in the formation of immunosuppressive microenvironment of IPMN progression. Our study deepens our understanding of IPMN progression, especially the changes in the immune microenvironment. The findings of this work may contribute to the development of new therapeutic strategies for IPMN.

Artificial Intelligence Applied to Pancreatic Imaging: A Narrative Review

The diagnosis, evaluation, and treatment planning of pancreatic pathologies usually require the combined use of different imaging modalities, mainly, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). Artificial intelligence (AI) has the potential to transform the clinical practice of medical imaging and has been applied to various radiological techniques for different purposes, such as segmentation, lesion detection, characterization, risk stratification, or prediction of response to treatments. The aim of the present narrative review is to assess the available literature on the role of AI applied to pancreatic imaging. Up to now, the use of computer-aided diagnosis (CAD) and radiomics in pancreatic imaging has proven to be useful for both non-oncological and oncological purposes and represents a promising tool for personalized approaches to patients. Although great developments have occurred in recent years, it is important to address the obstacles that still need to be overcome before these technologies can be implemented into our clinical routine, mainly considering the heterogeneity among studies.

Can granulysin provide prognostic value in primary breast cancer?

BACKGROUND

Granulysin (GNLY) is a cytolytic and proinflammatory molecule which also acts as an immune alarmin. The multifunctional nature of this molecule has made it challenging to define its full potential as a biomarker in breast cancer.

AIM

To evaluate the prognostic value of intratumoral GNLY in primary breast cancer patients and its association with established clinicopathological parameters.

PATIENTS AND METHODS

The study included 69 node-negative breast cancer patients with known clinicopathological parameters, all of whom had not received any prior hormonal or chemotherapeutic systemic therapy that would interfere with the course of disease. The median follow-up period was 144 months. Steroid hormone receptor status was determined by ligand-binding assay and HER2 status by chromogenic in situ hybridisation (CISH). Intratumoral GNLY mRNA levels were determined by RT-qPCR. Prognostic performance was evaluated by the receiver operating characteristic (ROC), Cox proportional hazards regression and Kaplan-Meier analysis. Classification of patients into GNLY^low and GNLY^high subgroups was performed by the use of the outcome-oriented cut-off point categorisation approach.

RESULTS

There was a significant difference between GNLY values of patients without any recurrences and those with local or distant recurrences (Mann-Whitney test, p = 0.05 and p = 0.02, respectively). None of the tested parameters showed prognostic significance for local and distant recurrences when combined. When distant metastases and local recurrences were separated as events, the best prognostic performance was observed for GNLY as compared with any clinicopathological parameter (AUC=0.24 and p = 0.04 for local events; AUC=0.71 and p = 0.03 for distant events). Local recurrence incidence was 0% for the GNLY^high subgroup and 19% for the GNLY^low subgroup; however distant recurrence incidence was 24% for the GNLY^high subgroup but only 3% for the GNLY^low subgroup (Kaplan-Meier analysis). A significant positive correlation was found between intratumoral ER and GNLY levels, and a significant negative correlation between tumour grade and GNLY levels.

CONCLUSION

High levels of granulysin prognosticate low risk of local recurrence but a high risk of distant metastasis in primary, untreated, breast cancer patients.

The prognostic significance of serum interferon-gamma (IFN-γ) in hormonally dependent breast cancer

BACKGROUND

Interferon-γ (IFN-γ) is a pleiotropic immunomodulatory cytokine. Because of its contradictory and even dualistic roles in malignancies, its potential as a biomarker remains to be unraveled.

AIM

To evaluate the prognostic significance of serum IFN-γ in hormonally treated breast cancer patients.

MATERIAL AND METHODS

The study included 72 premenopausal breast cancer patients with known clinicopathological characteristics. All patients received adjuvant hormonal therapy based on hormone receptor-positivity. The median follow-up period was 93 months. IFN-γ serum protein levels were determined by quantitative ELISA. Prognostic performance was evaluated by the receiver operating characteristic (ROC), Cox proportional hazards regression and Kaplan-Meier analyses. Classification of patients into IFN-γ^low and IFN-γ^high subgroups was performed by the use of the outcome-oriented cut-off point categorization approach.

RESULTS

The best prognostic performance was achieved by IFN-γ (AUC = 0.24 and p = 0.01 for distant events, AUC = 0.29 and p = 0.01 for local and distant events combined). Age and IFN-γ were prognostically significant in instances of all types of outcomes and IFN-γ was the independent prognostic parameter (Cox regression). There was a significant difference between IFN-γ values of patients without any events and those with distant metastases (Mann-Whitney test, p = 0.007). IFN-γ levels correlated significantly with nodal status and tumor stage (Spearman's rank order, r = -0.283 and r = -0.238, respectively). Distant recurrence incidence was 4% for the IFN-γ^high subgroup and 33% for the IFN-γ^low subgroup (Kaplan-Meier analysis).

CONCLUSIONS

Raised serum IFN-γ levels associate independently with favorable disease outcome in hormonally dependent breast cancer.

Recent advances in the diagnostic evaluation of pancreatic cystic lesions

Pancreatic cystic lesions (PCLs) are becoming more prevalent due to more frequent abdominal imaging and the increasing age of the general population. It has become crucial to identify these PCLs and subsequently risk stratify them to guide management. Given the high morbidity associated with pancreatic surgery, only those PCLs at high risk for malignancy should undergo such treatment. However, current diagnostic testing is suboptimal at accurately diagnosing and risk stratifying PCLs. Therefore, research has focused on developing new techniques for differentiating mucinous from non-mucinous PCLs and identifying high risk lesions for malignancy. Cross sectional imaging radiomics can potentially improve the predictive accuracy of primary risk stratification of PCLs at the time of detection to guide invasive testing. While cyst fluid glucose has reemerged as a potential biomarker, cyst fluid molecular markers have improved accuracy for identifying specific types of PCLs. Endoscopic ultrasound guided approaches such as confocal laser endomicroscopy and through the needle microforceps biopsy have shown a good correlation with histopathological findings and are evolving techniques for identifying and risk stratifying PCLs. While most of these recent diagnostics are only practiced at selective tertiary care centers, they hold a promise that management of PCLs will only get better in the future.

Retrospective Analysis of the Value of Enhanced CT Radiomics Analysis in the Differential Diagnosis Between Pancreatic Cancer and Chronic Pancreatitis

Purpose

To investigate the feasibility of enhanced computed tomography (CT) radiomics analysis to differentiate between pancreatic cancer (PC) and chronic pancreatitis.

Methods and materials

The CT images of 151 PCs and 24 chronic pancreatitis were retrospectively analyzed in the three-dimensional regions of interest on arterial phase (AP) and venous phase (VP) and segmented by MITK software. A multivariable logistic regression model was established based on the selected radiomics features. The radiomics score was calculated, and the nomogram was established. The discrimination of each model was analyzed by the receiver operating characteristic curve (ROC). Decision curve analysis (DCA) was used to evaluate clinical utility. The precision recall curve (PRC) was used to evaluate whether the model is affected by data imbalance. The Delong test was adopted to compare the diagnostic efficiency of each model.

Results

Significant differences were observed in the distribution of gender (P = 0.034), carbohydrate antigen 19-9 (P < 0.001), and carcinoembryonic antigen (P < 0.001) in patients with PC and chronic pancreatitis. The area under the ROC curve (AUC) value of AP multivariate regression model, VP multivariate regression model, AP combined with VP features model (Radiomics), clinical feature model, and radiomics combined with clinical feature model (COMB) was 0.905, 0.941, 0.941, 0.822, and 0.980, respectively. The sensitivity and specificity of the COMB model were 0.947 and 0.917, respectively. The results of DCA showed that the COMB model exhibited net clinical benefits and PRC shows that COMB model have good precision and recall (sensitivity).

Conclusion

The COMB model could be a potential tool to distinguish PC from chronic pancreatitis and aid in clinical decisions.

Pancreatic Serous Cystic Neoplasms and Mucinous Cystic Neoplasms: Differential Diagnosis by Combining Imaging Features and Enhanced CT Texture Analysis

Objective

To establish a diagnostic model by combining imaging features with enhanced CT texture analysis to differentiate pancreatic serous cystadenomas (SCNs) from pancreatic mucinous cystadenomas (MCNs).

Materials and Methods

Fifty-seven and 43 patients with pathology-confirmed SCNs and MCNs, respectively, from one center were analyzed and divided into a training cohort (n = 72) and an internal validation cohort (n = 28). An external validation cohort (n = 28) from another center was allocated. Demographic and radiological information were collected. The least absolute shrinkage and selection operator (LASSO) and recursive feature elimination linear support vector machine (RFE_LinearSVC) were implemented to select significant features. Multivariable logistic regression algorithms were conducted for model construction. Receiver operating characteristic (ROC) curves for the models were evaluated, and their prediction efficiency was quantified by the area under the curve (AUC), 95% confidence interval (95% CI), sensitivity and specificity.

Results

Following multivariable logistic regression analysis, the AUC was 0.932 and 0.887, the sensitivity was 87.5% and 90%, and the specificity was 82.4% and 84.6% with the training and validation cohorts, respectively, for the model combining radiological features and CT texture features. For the model based on radiological features alone, the AUC was 0.84 and 0.91, the sensitivity was 75% and 66.7%, and the specificity was 82.4% and 77% with the training and validation cohorts, respectively.

Conclusion

This study showed that a logistic model combining radiological features and CT texture features is more effective in distinguishing SCNs from MCNs of the pancreas than a model based on radiological features alone.

Factors Influencing Hypertrophic Scarring after Thyroidectomy

OBJECTIVE

To identify the risk factors of hypertrophic scarring (HS) after thyroidectomy and construct a risk prediction model.

METHODS

From November 2018 to March 2019, the clinical data of patients undergoing thyroidectomy were collected for retrospective analysis. According to the occurrence of HS, the patients were divided into an HS group and a non-HS group. Univariate analysis and binary logistic regression analysis were conducted to explore the independent risk factors for HS. Receiver operating characteristic analysis was also carried out.

RESULTS

In this sample, 121 of 385 patients developed HS, an incidence of 31.4%. Univariate analysis showed significant differences in sex, age, postoperative infection, history of abnormal wound healing, history of pathologic scar, family history of pathologic scar, and scar prevention measures between the two groups (P < .05). Binary logistic regression analysis indicated that age 45 years or younger (odds ratio [OR], 1.815), history of abnormal wound healing (OR, 4.247), history of pathologic scarring (OR, 9.840), family history of pathologic scarring (OR, 5.708), and absence of preventive scar measures (OR, 5.566) were independent factors for HS after thyroidectomy. The area under the receiver operating characteristic curve was 0.837. When the optimal diagnostic cutoff value was 0.206, the sensitivity was 0.661, and the specificity was 0.932.

CONCLUSIONS

The development of HS after thyroidectomy is related to many factors, and the proposed risk prediction model based on the combined risk factors shows a good predictive value for postoperative HS. When researchers consider the prevention and treatment of scarring in patients at risk, the incidence of HS in different populations can provide theoretical support for clinical decision-making.

Correlation between bispectral index and prognosis of patients with acute cerebral infarction

INTRODUCTION

This study aimed to investigate the clinical value of bispectral index (BIS) monitoring in assessing the consciousness and prognosis of acute cerebral infarction (ACI) patients.

METHODS

In total, 64 patients who suffered from ACI with consciousness disturbance were enrolled in this study. Glasgow Coma Scale (GCS) was performed to evaluate the consciousness level of ACI patients, and BIS was used to monitor the depth of anesthesia and sedation. Then, patients were divided into good prognosis, poor prognosis and death groups according to modified Rankin score (mRS). Discrimination analysis of BIS values and GCS score for the prediction of prognosis was performed using the receiver operator characteristic (ROC) curve.

RESULTS

GCS score and BIS values showed statistically significant differences among the three groups. Spearman rank correlation analysis revealed a significant positive correlation between BIS values and GCS score, while BIS values was negatively related with mRS. The ROC curve of prognosis prediction showed strong prognostic power, with area under the curves (AUCs) between 0.830 and 0.917. Moreover, the AUC of BISmean score was higher than that of BISmax, BISmin and GCS, and BISmean of 74 was the best cut-off point for good prognosis.

CONCLUSION

BIS directly reflects the degree of consciousness disturbance in ACI patients, and thus accurately predicts the prognosis, indicating potential application values of BIS in clinical practice.

A nomogram for predicting pancreatic mucinous cystic neoplasm and serous cystic neoplasm

OBJECTIVES

To develop and validate a nomogram for the preoperative prediction of pancreatic serous cystic neoplasm (SCN) and mucinous cystic neoplasm (MCN) based on multidetector computed tomography (MDCT).

MATERIALS AND METHODS

In this retrospective study, the data of 227 patients with SCN and MCN were analyzed. Each patient underwent MDCT and surgical resection. A multivariable logistic regression model was developed using a training set consisting of 129 patients with SCN and 38 patients with MCN who were admitted between October 2012 and April 2019. The model was validated in 60 consecutive patients, 44 of whom had SCN and 16 of whom had MCN, admitted between May 2019 and April 2020. The regression model was adopted to establish a nomogram. Nomogram performance was determined by its discriminative ability and clinical utility.

RESULT

The multivariable logistic regression model included sex, size, location, shape, cyst characteristic, and cystic wall thickening. The individualized prediction nomogram showed good discrimination in the training sample (AUC 0.89; 95% CI 0.83-0.95) and in the validation sample (AUC 0.81; 95% CI 0.70-0.94). If the threshold probability is between 0.03 and 0.9, and > 0.93 in the prediction model, using the nomogram to predict SCN and MCN is more beneficial than the treat-all-patients as SCN scheme or the treat-all-patients as MCN scheme. The prediction model showed better discrimination than the radiologists' diagnosis (AUC = 0.68).

CONCLUSION

The nomogram could predict SCN and MCN preoperatively and may aid clinical decision-making.

A novel strategy to identify candidate diagnostic and prognostic biomarkers for gastric cancer

Background

Gastric cancer (GC) is one of the most common cancer worldwide. It is essential to identify non-invasive diagnostic and prognostic biomarkers of GC. The aim of the present study was to screen candidate biomarkers associated with the pathogenesis and prognosis of GC by a novel strategy.

Methods

The expression level of gene higher in cancer than in adjacent non-cancer tissue was defined as “positive”, and the top 5% genes with “positive rate” were filtered out as candidate diagnostic biomarkers in three Gene Expression Omnibus (GEO) datasets. Further, a prognostic risk model was constructed by multivariate Cox regression analysis in GEO dataset and validated in The Cancer Genome Atlas (TCGA). The expression level of candidate biomarkers was determined in serum and serum-derived exosomes of GC patients. Moreover, the effect of biomarkers in exosomes on migration of GC cells was analyzed by transwell assay.

Results

Ten candidate biomarkers (AGT, SERPINH1, WNT2, LIPG, PLAU, COL1A1, MMP7, MXRA5, CXCL1 and COL11A1) were identified with efficient diagnostic value in GC. A prognostic gene signature consisted of AGT, SERPINH1 and MMP7 was constructed and showed a good performance in predicting overall survivals in TCGA. Consistently, serum levels of the three biomarkers also showed high sensitivity and specificity in distinguishing GC patients from controls. In addition, the expression level of the three biomarkers were associated with malignant degree and decreased after surgery in GC patients. Moreover, the expression level of AGT and MMP7 in exosomes correlated positively with serum level. The exosomes derived from serum of GC patients can promote migration of SGC‐7901 cells. After neutralized the expression level of three proteins in exosomes with antibodies, the migration of GC cells was obviously suppressed.

Conclusions

Our findings provided a novel strategy to identify diagnostic biomarkers based on public datasets, and suggested that the three-gene signature was a candidate diagnostic and prognostic biomarker for patients with GC.

CT-Based Radiomics Analysis for Preoperative Diagnosis of Pancreatic Mucinous Cystic Neoplasm and Atypical Serous Cystadenomas

Objectives

To investigate the value of CT-based radiomics analysis in preoperatively discriminating pancreatic mucinous cystic neoplasms (MCN) and atypical serous cystadenomas (ASCN).

Methods

A total of 103 MCN and 113 ASCN patients who underwent surgery were retrospectively enrolled. A total of 764 radiomics features were extracted from preoperative CT images. The optimal features were selected by Mann-Whitney U test and minimum redundancy and maximum relevance method. The radiomics score (Rad-score) was then built using random forest algorithm. Radiological/clinical features were also assessed for each patient. Multivariable logistic regression was used to construct a radiological model. The performance of the Rad-score and the radiological model was evaluated using 10-fold cross-validation for area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy.

Results

Ten screened optimal features were identified and the Rad-score was then built based on them. The radiological model was built based on four radiological/clinical factors. In the 10-fold cross-validation, the Rad-score was proved to be robust and reliable (average AUC: 0.784, sensitivity: 0.847, specificity: 0.745, PPV: 0.767, NPV: 0.849, accuracy: 0.793). The radiological model performed slightly less well in classification (average AUC: average AUC: 0.734 sensitivity: 0.748, specificity: 0.705, PPV: 0.732, NPV: 0.798, accuracy: 0.728.

Conclusions

The CT-based radiomics analysis provided promising performance for preoperatively discriminating MCN from ASCN and showed good potential in improving diagnostic power, which may serve as a novel tool for guiding clinical decision-making for these patients.

Incidental Pancreatic Cysts on Cross-Sectional Imaging

Incidental pancreatic cysts are commonly encountered in radiology practice. Although some of these are benign, mucinous varieties have a potential to undergo malignant transformation. Characterization of some incidental pancreatic cysts based on imaging alone is limited, and given that some pancreatic cysts have a malignant potential, various societies have created guidelines for the management and follow-up of incidental pancreatic cysts. This article reviews the imaging findings and work-up of pancreatic cysts and gives an overview of the societal guidelines for the management and follow-up of incidental pancreatic cysts.

Key Experimental Factors of Machine Learning-Based Identification of Surgery Cancellations

This study aimed to provide effective methods for the identification of surgeries with high cancellation risk based on machine learning models and analyze the key factors that affect the identification performance. The data covered the period from January 1, 2013, to December 31, 2014, at West China Hospital in China, which focus on elective urologic surgeries. All surgeries were scheduled one day in advance, and all cancellations were of institutional resource- and capacity-related types. Feature selection strategies, machine learning models, and sampling methods are the most discussed topic in general machine learning researches and have a direct impact on the performance of machine learning models. Hence, they were considered to systematically generate complete schemes in machine learning-based identification of surgery cancellations. The results proved the feasibility and robustness of identifying surgeries with high cancellation risk, with the considerable maximum of area under the curve (AUC) (0.7199) for random forest model with original sampling using backward selection strategy. In addition, one-side Delong test and sum of square error analysis were conducted to measure the effects of feature selection strategy, machine learning model, and sampling method on the identification of surgeries with high cancellation risk, and the selection of machine learning model was identified as the key factors that affect the identification of surgeries with high cancellation risk. This study offers methodology and insights for identifying the key experimental factors for identifying surgery cancellations, and it is helpful to further research on machine learning-based identification of surgeries with high cancellation risk.

Discrimination of serous cystadenoma from mucinous cystic neoplasm and branch duct intraductal papillary mucinous neoplasm in the pancreas with CT

PURPOSE

The imaging features of serous cystadenomas (SCAs) overlap with those of mucinous cystic neoplasms (MCNs) and branch duct intraductal papillary mucinous neoplasms (BD-IPMNs), and an accurate preoperative diagnosis is important for clinical treatment due to their different biological behaviors. The aim of this study was to provide a computed tomographic (CT) feature for the diagnosis of SCAs and estimate whether the "circumvascular sign" can contribute to the discrimination of SCAs from MCNs and BD-IPMNs.

METHODS

From August 2011 through December 2019, a total of 71 patients (30 patients with 30 SCAs, 21 patients with 21 MCNs and 20 patients with 22 BP-IPMNs) were enrolled in this study. All patients underwent CT examination and were confirmed by surgical pathology. In addition to patient clinical information, CT features (e.g., location, shape) were evaluated via CT.

RESULTS

Central scarring, central calcification and the circumvascular sign were found to be specific CT features for the diagnosis of SCAs and their differential diagnosis from MCNs and BD-IPMNs. All three CT features had high specificity, and both central scarring and central calcification had low sensitivity. When any one of these two features was combined with the circumvascular sign, the sensitivity increased to 83.3%.

CONCLUSION

Pancreatic cystic neoplasms that show central scarring, central calcification or the circumvascular sign on CT could be diagnosed as SCAs. When either of the first two features is combined with the circumvascular sign, the diagnostic sensitivity could be increased.

[Quality of indications in cystic lesions of the pancreas]

Cystic tumors of the pancreas (PCN) have increasingly gained importance in the clinical routine as they are frequently diagnosed as an incidental finding due to the continuous improvement in cross-sectional imaging. A differentiation is made between non-neoplastic and neoplastic cysts, whereby the latter has a tendency to malignant transformation to a varying extent. Therefore, they can be considered as precursor lesions of pancreatic cancer (PDAC). In addition to a detailed patient history and examination, imaging modalities, such as computed tomography (CT), magnetic resonance imaging (MRI) and endoscopic ultrasound (EUS) with fine needle aspiration (FNA) are used for the differential diagnosis. The indications for surgical resection of these lesions are based on the current European guidelines from 2018; however, the content is not evidence-based but relies on knowledge and recommendations from experts. According to these consensus recommendations asymptomatic serous cystic neoplasms (SCN) are serous lesions with a low tendency for malignant transformation and can be monitored. In contrast resection is warranted for all mucinous cystic neoplasms (MCN) >4 cm and all solid pseudopapillary neoplasms (SPN). Intraductal papillary mucinous neoplasms (IPMN), which are differentiated into main duct (MD-IPMN) and branch duct type (BD-IPMN) IPMN based on the position in the pancreatic duct system, should be resected as MD-IPMN and mixed type (MT)-IPMN. The risk of malignant transformation in BD-IPMN is variable and depends on risk factors, which are defined clinically and by imaging morphology. The treatment management is therefore carried out on an individual basis following risk estimation. In order to quantify the quality of indications in PCN and thereby also contributing to optimized medical care, prospective long-term studies are urgently needed.