Multi-Phase CT-Based Radiomics Nomogram for Discrimination Between Pancreatic Serous Cystic Neoplasm From Mucinous Cystic Neoplasm

PurposeThis study aimed to develop and verify a multi-phase (MP) computed tomography (CT)-based radiomics nomogram to differentiate pancreatic serous cystic neoplasms (SCNs) from mucinous cystic neoplasms (MCNs), and to compare the diagnostic efficacy of radiomics models for different phases of CT scans.Materials and MethodsA total of 170 patients who underwent surgical resection between January 2011 and December 2018, with pathologically confirmed pancreatic cystic neoplasms (SCN=115, MCN=55) were included in this single-center retrospective study. Radiomics features were extracted from plain scan (PS), arterial phase (AP), and venous phase (VP) CT scans. Algorithms were performed to identify the optimal features to build a radiomics signature (Radscore) for each phase. All features from these three phases were analyzed to develop the MP-Radscore. A combined model comprised the MP-Radscore and imaging features from which a nomogram was developed. The accuracy of the nomogram was evaluated using receiver operating characteristic (ROC) curves, calibration tests, and decision curve analysis.ResultsFor each scan phase, 1218 features were extracted, and the optimal ones were selected to construct the PS-Radscore (11 features), AP-Radscore (11 features), and VP-Radscore (12 features). The MP-Radscore (14 features) achieved better performance based on ROC curve analysis than any single phase did [area under the curve (AUC), training cohort: MP-Radscore 0.89, PS-Radscore 0.78, AP-Radscore 0.83, VP-Radscore 0.85; validation cohort: MP-Radscore 0.88, PS-Radscore 0.77, AP-Radscore 0.83, VP-Radscore 0.84]. The combination nomogram performance was excellent, surpassing those of all other nomograms in both the training cohort (AUC, 0.91) and validation cohort (AUC, 0.90). The nomogram also performed well in the calibration and decision curve analyses.ConclusionsRadiomics for arterial and venous single-phase models outperformed the plain scan model. The combination nomogram that incorporated the MP-Radscore, tumor location, and cystic number had the best discriminatory performance and showed excellent accuracy for differentiating SCN from MCN.

Download Full-text

Establishment and validation of prognosis model for patients with cerebral contusion

BMC Neurology ◽

10.1186/s12883-021-02482-4 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Yufeng Zhu ◽

Xiaoqing Jin ◽

Lulu Xu ◽

Pei Han ◽

Shengwu Lin ◽

...

Keyword(s):

Prediction Model ◽

Validation Cohort ◽

Characteristic Curve ◽

Third Ventricle ◽

Curve Analysis ◽

Imaging Features ◽

Lasso Regression ◽

Cerebral Contusion ◽

Decision Curve Analysis ◽

Training Cohort

Abstract Background And Objective Cerebral Contusion (CC) is one of the most serious injury types in patients with traumatic brain injury (TBI). In this study, the baseline data, imaging features and laboratory examinations of patients with CC were summarized and analyzed to develop and validate a prediction model of nomogram to evaluate the clinical outcomes of patients. Methods A total of 426 patients with cerebral contusion (CC) admitted to the People’s Hospital of Qinghai Province and Affiliated Hospital of Qingdao University from January 2018 to January 2021 were included in this study, We randomly divided the cohort into a training cohort (n = 284) and a validation cohort (n = 142) with a ratio of 2:1.At Least absolute shrinkage and selection operator (Lasso) regression were used for screening high-risk factors affecting patient prognosis and development of the predictive model. The identification ability and clinical application value of the prediction model were analyzed through the analysis of receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA). Results Twelve independent prognostic factors, including age, Glasgow Coma Score (GCS), Basal cistern status, Midline shift (MLS), Third ventricle status, intracranial pressure (ICP) and CT grade of cerebral edema,etc., were selected by Lasso regression analysis and included in the nomogram. The model showed good predictive performance, with a C index of (0.87, 95% CI, 0.026–0.952) in the training cohort and (0.93, 95% CI, 0.032–0.965) in the validation cohort. Clinical decision curve analysis (DCA) also showed that the model brought high clinical benefits to patients. Conclusion This study established a high accuracy of nomogram model to predict the prognosis of patients with CC, its low cost, easy to promote, is especially applicable in the acute environment, at the same time, CSF-glucose/lactate ratio(C-G/L), volume of contusion, and mean CT values of edema zone, which were included for the first time in this study, were independent predictors of poor prognosis in patients with CC. However, this model still has some limitations and deficiencies, which require large sample and multi-center prospective studies to verify and improve our results.

Download Full-text

Abstract WP406: Training and Validation of Deepmedic Machine Learning Tool for Automated Hematoma Segmentation and Volume Analysis on CT Using Multicenter Data

Stroke ◽

10.1161/str.51.suppl_1.wp406 ◽

2020 ◽

Vol 51 (Suppl_1) ◽

Author(s):

Sean Nurmsoo ◽

Alessandro Guida ◽

Alex Wong ◽

Richard I Aviv ◽

Andrew Demchuk ◽

...

Keyword(s):

Machine Learning ◽

Validation Cohort ◽

Learning Algorithm ◽

Intraclass Correlation ◽

Ct Scans ◽

Dice Similarity Coefficient ◽

Machine Learning Algorithm ◽

Manual Segmentation ◽

Training Cohort ◽

Volume Calculation

Introduction: We sought to train and validate an automated machine learning algorithm for ICH segmentation and volume calculation using multicenter data. Methods: An open-source 3D deep machine learning algorithm “DeepMedic” was trained using manually segmented ICH from 208 CT scans (129 patients) from the multicenter PREDICT study. The algorithm was then validated with 125 manually segmented CT scans (48 patients) from the SPOTLIGHT study. Manual segmentation was performed with Quantomo semi-automated software. ABC/2 was measured for all studies by two neuroradiologists. Accuracy of DeepMedic segmentation was assessed using the Dice similarity coefficient. Analysis was stratified by presence of IVH. Intraclass correlation (ICC) with 95% confidence intervals (CI) assessed agreement between manual vs. DeepMedic segmentation volume; and manual segmentation and ABC/2 volume. Bland-Altman charts were analyzed for ABC/2 and DeepMedic vs. manual segmentation volumes. Results: DeepMedic demonstrated high segmentation accuracy in the training cohort (median Dice 0.96; IQR 0.95 - 0.97) and in the validation cohort (median Dice 0.91; IQR 0.86 - 0.94). Dice coefficients were not significantly different between patients with IVH in the training cohort; however was significantly worse in the validation cohort in patients with IVH (Wilcoxon p<0.001). Agreement was significantly better between DeepMedic and manual segmentation (PREDICT: ICC 0.99 [95%CI 0.99 -1.00]; SPOTLIGHT: ICC 0.98 [95%CI 0.97 - 0.99]) than between ABC/2 and manual segmentation (PREDICT: ICC 0.92 [95%CI 0.89 - 0.95]; SPOTLIGHT: ICC 0.95 [95%CI 0.93-0.97]). Improved accuracy of DeepMedic was demonstrated in Bland-Altman charts (Fig 1). Conclusion: ICH machine learning segmentation with DeepMedic is feasible and accurate; and demonstrates greater agreement with manual segmentation compared to ABC/2 volumes. Accuracy of the machine learning algorithm however is limited in patients with IVH.

Download Full-text

Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images

Technology in Cancer Research & Treatment ◽

10.1177/1533033818824339 ◽

2019 ◽

Vol 18 ◽

pp. 153303381882433 ◽

Cited By ~ 11

Author(s):

Ran Wei ◽

Kanru Lin ◽

Wenjun Yan ◽

Yi Guo ◽

Yuanyuan Wang ◽

...

Keyword(s):

Validation Cohort ◽

Characteristic Curve ◽

Computer Aided Diagnosis ◽

Cystic Neoplasm ◽

Multidetector Row Computed Tomography ◽

Cystic Neoplasms ◽

Independent Validation ◽

Computer Aided ◽

Selection Operator ◽

Aided Diagnosis

Objective: Our aim was to propose a preoperative computer-aided diagnosis scheme to differentiate pancreatic serous cystic neoplasms from other pancreatic cystic neoplasms, providing supportive opinions for clinicians and avoiding overtreatment. Materials and Methods: In this retrospective study, 260 patients with pancreatic cystic neoplasm were included. Each patient underwent a multidetector row computed tomography scan and pancreatic resection. In all, 200 patients constituted a cross-validation cohort, and 60 patients formed an independent validation cohort. Demographic information, clinical information, and multidetector row computed tomography images were obtained from Picture Archiving and Communication Systems. The peripheral margin of each neoplasm was manually outlined by experienced radiologists. A radiomics system containing 24 guideline-based features and 385 radiomics high-throughput features was designed. After the feature extraction, least absolute shrinkage selection operator regression was used to select the most important features. A support vector machine classifier with 5-fold cross-validation was applied to build the diagnostic model. The independent validation cohort was used to validate the performance. Results: Only 31 of 102 serous cystic neoplasm cases in this study were recognized correctly by clinicians before the surgery. Twenty-two features were selected from the radiomics system after 100 bootstrapping repetitions of the least absolute shrinkage selection operator regression. The diagnostic scheme performed accurately and robustly, showing the area under the receiver operating characteristic curve = 0.767, sensitivity = 0.686, and specificity = 0.709. In the independent validation cohort, we acquired similar results with receiver operating characteristic curve = 0.837, sensitivity = 0.667, and specificity = 0.818. Conclusion: The proposed radiomics-based computer-aided diagnosis scheme could increase preoperative diagnostic accuracy and assist clinicians in making accurate management decisions.

Download Full-text

Prediction of 90-day mortality among sepsis patients based on a nomogram integrating diverse clinical indices

10.21203/rs.3.rs-596906/v1 ◽

2021 ◽

Author(s):

Qing-Bo Zeng ◽

Long-Ping He ◽

Nian-Qing Zhang ◽

Qing-Wei Lin ◽

Lin-Cui Zhong ◽

...

Keyword(s):

Risk Factors ◽

Intensive Care ◽

Validation Cohort ◽

International Normalized Ratio ◽

Curve Analysis ◽

Individual Risk ◽

Decision Curve Analysis ◽

Training Cohort ◽

Receiver Operating Characteristic Curves ◽

Individual Risk Factors

Abstract Background Sepsis is prevalent among intensive care units and is a frequent cause of death. Several studies have identified individual risk factors or potential predictors of sepsis-associated mortality, without defining an integrated predictive model. The present work aimed to define a nomogram for reliably predicting mortality. Methods We carried out a retrospective, single-center study based on 231 patients with sepsis who were admitted to our intensive care unit between May 2018 and October 2020. Patients were randomly split into training and validation cohorts. In the training cohort, multivariate logistic regression and a stepwise algorithm were performed to identify risk factors, which were then integrated into a predictive nomogram. Nomogram performance was assessed against the training and validation cohorts based on the area under receiver operating characteristic curves (AUC), calibration plots and decision curve analysis. Results Among the 161 patients in the training cohort and 70 patients in the validation cohort, 90-day mortality was 31.6%. Older age and higher values for the international normalized ratio, lactate level, and thrombomodulin level were associated with greater risk of 90-day mortality. The nomogram showed an AUC of 0.810 (95% CI 0.739 to 0.881) in the training cohort and 0.813 (95% CI 0.708 to 0.917) in the validation cohort. The nomogram also performed well based on the calibration curve and decision curve analysis. Conclusion This nomogram may help identify sepsis patients at elevated risk of 90-day mortality, which may help clinicians allocate resources appropriately to improve patient outcomes.

Download Full-text

Imaging features of hepatocellular carcinoma with bile duct tumor thrombus：a multicenter study

10.21203/rs.3.rs-40799/v2 ◽

2020 ◽

Author(s):

Li-Ming Huang ◽

Jun-Yi Wu ◽

Yan-Nan Bai ◽

Jia-Yi Wu ◽

Yong-Gang Wei ◽

...

Keyword(s):

Hepatocellular Carcinoma ◽

Bile Duct ◽

Ct Scans ◽

Arterial Phase ◽

Imaging Features ◽

Portal Venous Phase ◽

Bile Duct Tumor ◽

Hepatic Arterial Phase ◽

Mri Scans ◽

Venous Phase

Abstract Background: There are still difficult and challenging problems in diagnosis of hepatocellular carcinoma (HCC) with bile duct tumor thrombus (BDTT) before operation. This study aimed to analyze the imaging features of HCC with B1-B3 BDTT. Methods: The clinicopathological data and imaging findings of 30 HCC patients with B1-B3 BDTT from three high-volume institutions were retrospectively reviewed. Eighteen patients underwent computed tomography (CT) scans and twelve patients underwent magnetic resonance imaging (MRI) scans before operation, respectively. The diagnosis of HCC with BDTT was conﬁrmed by postoperative pathologic examination.Results: According to Japanese classification, 5 patients were classified as B1 BDTT, 12 B2, 13 B3, and 82 B4, respectively. The HCC lesions were detected in all patients, and the localized bile duct dilation were detected in 28 (93.3%) patients. The BDTT was observed in all B3 patients and 3 B2 patients, but it was not observed in all B1 patients on CT or MRI. The BDTT showed relatively hypoattenuation on plain CT scans and T1W images, relatively hyperattenuation signals on T2W. The BDTT showed hyperattenuation at hepatic arterial phase with washout at portal venous phase. The localized biliary dilation showed no enhancement at hepatic arterial phase and no progressively delayed enhancement at portal venous phase, but it was more obvious at portal venous phase on CT.Conclusions: The HCC lesions and the localized bile duct dilatation on CT or MRI scans are imaging features of HCC with BDTT, which might facilitate the early diagnosis for B1-B3 BDTT.

Download Full-text

A Systemic Inflammation Response Score for Prognostic Prediction of Breast Cancer Patients Undergoing Surgery

Journal of Personalized Medicine ◽

10.3390/jpm11050413 ◽

2021 ◽

Vol 11 (5) ◽

pp. 413

Author(s):

Kaiming Zhang ◽

Liqin Ping ◽

Xueqi Ou ◽

Meiheban Bazhabayi ◽

Xiangsheng Xiao

Keyword(s):

Breast Cancer ◽

Receiver Operating Characteristic ◽

Cancer Patients ◽

Clinical Features ◽

Operating Characteristic ◽

Validation Cohort ◽

Curve Analysis ◽

Breast Cancer Patients ◽

Training Cohort ◽

Response Score

Background: Systemic inflammatory response is related to the occurrence, progression, and prognosis of cancers. In this research, a novel systemic inflammation response score (SIRS) was calculated, and its prognostic value for postoperative stage I-III breast cancer (BC) patients was analyzed. Methods: 1583 BC patients were included in this research. Patients were randomly divided into a training cohort (n = 1187) and validation cohort (n = 396). SIRS was established in the training cohort based on independent prognostic hematological indicator, its relationship between prognosis and clinical features was analyzed. Then, a nomogram consisted of SIRS and clinical features was established, its performance was examined by calibration plots and receiver operating characteristic curve analysis. Results: The SIRS was an independent prognostic indicator for BC patients, and a high-SIRS was related to multifocality, advanced N stage, and worse prognosis. Incorporating SIRS into a nomogram could accurately predict the prognosis of BC patients, the results of receiver operating characteristic (ROC) curve analysis showed that the area under the curve (AUC) of nomogram was up to 0.806 in training cohort and 0.905 in the validation cohort. Conclusion: SIRS was associated with the prognosis of patients with breast cancer. Nomogram based on SIRS can accurately predict the prognosis of breast cancer patients.

Download Full-text

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

Frontiers in Oncology ◽

10.3389/fonc.2021.745001 ◽

2021 ◽

Vol 11 ◽

Author(s):

Hai-Yan Chen ◽

Xue-Ying Deng ◽

Yao Pan ◽

Jie-Yu Chen ◽

Yun-Ying Liu ◽

...

Keyword(s):

Logistic Regression ◽

Texture Analysis ◽

Validation Cohort ◽

Texture Features ◽

Imaging Features ◽

Cystic Neoplasms ◽

Radiological Features ◽

Model Combining ◽

Enhanced Ct ◽

Ct Texture Analysis

ObjectiveTo 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 MethodsFifty-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.ResultsFollowing 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.ConclusionThis 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.

Download Full-text

Prediction of 90-Day Mortality among Sepsis Patients Based on a Nomogram Integrating Diverse Clinical Indices

BioMed Research International ◽

10.1155/2021/1023513 ◽

2021 ◽

Vol 2021 ◽

pp. 1-7

Author(s):

Qingbo Zeng ◽

Longping He ◽

Nianqing Zhang ◽

Qingwei Lin ◽

Lincui Zhong ◽

...

Keyword(s):

Risk Factors ◽

Intensive Care ◽

Validation Cohort ◽

International Normalized Ratio ◽

Curve Analysis ◽

Individual Risk ◽

Decision Curve Analysis ◽

Training Cohort ◽

Receiver Operating Characteristic Curves ◽

Individual Risk Factors

Background. Sepsis is prevalent among intensive care units and is a frequent cause of death. Several studies have identified individual risk factors or potential predictors of sepsis-associated mortality, without defining an integrated predictive model. The present work was aimed at defining a nomogram for reliably predicting mortality. Methods. We carried out a retrospective, single-center study based on 231 patients with sepsis who were admitted to our intensive care unit between May 2018 and October 2020. Patients were randomly split into training and validation cohorts. In the training cohort, multivariate logistic regression and a stepwise algorithm were performed to identify risk factors, which were then integrated into a predictive nomogram. Nomogram performance was assessed against the training and validation cohorts based on the area under receiver operating characteristic curves (AUC), calibration plots, and decision curve analysis. Results. Among the 161 patients in the training cohort and 70 patients in the validation cohort, 90-day mortality was 31.6%. Older age and higher values for the international normalized ratio, lactate level, and thrombomodulin level were associated with greater risk of 90-day mortality. The nomogram showed an AUC of 0.810 (95% CI 0.739 to 0.881) in the training cohort and 0.813 (95% CI 0.708 to 0.917) in the validation cohort. The nomogram also performed well based on the calibration curve and decision curve analysis. Conclusion. This nomogram may help identify sepsis patients at elevated risk of 90-day mortality, which may help clinicians allocate resources appropriately to improve patient outcomes.

Download Full-text

Single phase computed tomography is equivalent to dual phase method for localizing hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism: A retrospective review

10.7287/peerj.preprints.3058v1 ◽

2017 ◽

Author(s):

Fanny Moron ◽

Alfred Delumpa ◽

Justin Chetta ◽

Danielle Guffey ◽

David Dunaway

Keyword(s):

Primary Hyperparathyroidism ◽

Single Phase ◽

Parathyroid Glands ◽

Ct Scans ◽

Arterial Phase ◽

Phase Method ◽

Dual Phase ◽

Parathyroid Adenomas ◽

Multiphase Ct ◽

Parathyroid Imaging

Objective: This study aims to compare the sensitivity of dual phase (non-contrast and arterial) versus single phase (arterial) CT for detection of hyper-functioning parathyroid glands in patients with primary hyperparathyroidism. Methods: The CT scans of thirty-two patients who have biochemical evidence of primary hyperparathyroidism, pathologically proven parathyroid adenomas, and pre-operative multiphase parathyroid imaging were evaluated retrospectively in order to compare the adequacy of single phase vs. dual phase CT scans for the detection of parathyroid adenomas. Results: The parathyroid adenomas were localized in 83% of cases on single arterial phase CT and 80% of cases on dual phase CT. The specificity for localization of parathyroid tumor was 96% for single phase CT and 97% for dual phase CT. The results were not significantly different (p=0.695). These results are similar to those found in the literature for multiphase CT of 55-94%. Conclusions: Our study supports the use of a single arterial phase CT for the detection of hyperfunctioning parathyroid adenomas. Advances in knowledge: A single arterial phase CT has similar sensitivity for localizing parathyroid adenomas as dual phase CT and significantly reduces radiation dose to the patient.

Download Full-text