scholarly journals An Approach Based on Mammographic Imaging and Radiomics for Distinguishing Male Benign and Malignant Lesions: A Preliminary Study

2021 ◽  
Vol 10 ◽  
Author(s):  
Yan Huang ◽  
Qin Xiao ◽  
Yiqun Sun ◽  
Zhe Wang ◽  
Qin Li ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Sensitivity And Specificity ◽  
Validation Cohort ◽  
Area Under The Curve ◽  
Region Of Interest ◽  
Imaging Features ◽  
Clinical Value ◽  
Oblique View ◽  
Imaging Model ◽  
Imaging Characteristics

PurposeTo develop and validate an imaging-radiomics model for the diagnosis of male benign and malignant breast lesions.MethodsNinety male patients who underwent preoperative mammography from January 2011 to December 2018 were enrolled in this study (63 in the training cohort and 27 in the validation cohort). The region of interest was segmented into a mediolateral oblique view, and 104 radiomics features were extracted. The minimum redundancy and maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) methods were used to exclude radiomics features to establish the radiomics score (rad-score). Mammographic features were evaluated by two radiologists. Univariate logistic regression was used to select for imaging features, and multivariate logistic regression was used to construct an imaging model. An imaging-radiomics model was eventually established, and a nomogram was developed based on the imaging-radiomics model. Area under the curve (AUC) and decision curve analysis (DCA) were applied to assess the clinical value.ResultsThe AUC based on the imaging model in the validation cohort was 0.760, the sensitivity was 0.750, and the specificity was 0.727. The AUC, sensitivity and specificity based on the radiomics in the validation cohort were 0.820, 0.750, and 0.867, respectively. The imaging-radiomics model was better than the imaging and radiomics models; the AUC, sensitivity, and specificity of the imaging-radiomics model in the validation cohort were 0.870, 0.824, and 0.900, respectively.ConclusionThe imaging-radiomics model created by the imaging characteristics and radiomics features exhibited a favorable discriminatory ability for male breast cancer.

Clot imaging characteristics predict first pass effect of aspiration—first approach to thrombectomy

2021 ◽  
pp. 159101992110191
Author(s):  
Muhammad Waqas ◽  
Weizhe Li ◽  
Tatsat R Patel ◽  
Felix Chin ◽  
Vincent M Tutino ◽  
...  
Keyword(s):  
Internal Carotid ◽  
Validation Cohort ◽  
Area Under The Curve ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
First Pass Effect ◽  
Imaging Characteristics ◽  
First Pass ◽  
Sensitivity Specificity ◽  
Youden’S Index

Background The value of clot imaging in patients with emergent large vessel occlusion (ELVO) treated with thrombectomy is unknown. Methods We performed retrospective analysis of clot imaging (clot density, perviousness, length, diameter, distance to the internal carotid artery (ICA) terminus and angle of interaction (AOI) between clot and the aspiration catheter) of consecutive cases of middle cerebral artery (MCA) occlusion and its association with first pass effect (FPE, TICI 2c-3 after a first attempt). Results Patients ( n = 90 total) with FPE had shorter clot length (9.9 ± 4.5 mm vs. 11.7 ± 4.6 mm, P = 0.07), shorter distance from ICA terminus (11.0 ± 7.1 mm vs. 14.7 ± 9.8 mm, P = 0.048), higher perviousness (39.39 ± 29.5 vs 25.43 ± 17.6, P = 0.006) and larger AOI (153.6 ± 17.6 vs 140.3 ± 23.5, P = 0.004) compared to no-FPE patients. In multivariate analysis, distance from ICA terminus to clot ≤13.5 mm (odds ratio (OR) 11.05, 95% confidence interval (CI) 2.65–46.15, P = 0.001), clot length ≤9.9 mm (OR 7.34; 95% CI 1.8–29.96, P = 0.005), perviousness ≥ 19.9 (OR 2.54, 95% CI 0.84–7.6, P = 0.09) and AOI ≥ 137°^ (OR 6.8, 95% CI 1.55–29.8, P = 0.011) were independent predictors of FPE. The optimal cut off derived using Youden’s index was 6.5. The area under the curve of a score predictive of FPE success was 0.816 (0.728–0.904, P < 0.001). In a validation cohort ( n = 30), sensitivity, specificity, positive and negative predictive value of a score of 6–10 were 72.7%, 73.6%, 61.5% and 82.3%. Conclusions Clot imaging predicts the likelihood of achieving FPE in patients with MCA ELVO treated with the aspiration-first approach.

scholarly journals Computed Tomography Angiography under Deep Learning in the Treatment of Atherosclerosis with Rapamycin

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Fuguang Ji ◽  
Shuai Zhou ◽  
Zhangshuan Bi
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Computed Tomography Angiography ◽  
Atherosclerotic Lesion ◽  
Region Of Interest ◽  
Left Ventricular ◽  
Dice Similarity Coefficient ◽  
Imaging Features ◽  
Lesion Area ◽  
Imaging Characteristics

The clinical characteristics and vascular computed tomography (CT) imaging characteristics of patients were explored so as to assist clinicians in diagnosing patients with atherosclerosis. 316 patients with atherosclerosis who were hospitalized for emergency treatment were treated with rapamycin (RAPA) in the hospital. A group of manually delineated left ventricular myocardia (LVM) on the patient’s coronary computed tomography angiography (CCTA) were selected as the region of interest for imaging features extracted. The CCTA images of 80% of patients were randomly selected for training, and those of 20% of patients were used for verification. The correlation matrix method was used to remove redundant image omics features under different correlation thresholds. In the validation set, CCTA diagnostic parameters were about 40 times higher than the manually segmented data. The average dice similarity coefficient was 91.6%. The proposed method also produced a very small centroid distance (mean 1.058 mm, standard deviation 1.245 mm) and volume difference (mean 1.640), with a segmentation time of about 1.45 ± 0.51 s, compared to about 744.8 ± 117.49 s for physician manual segmentation. Therefore, the deep learning model effectively segmented the atherosclerotic lesion area, measured and assisted the diagnosis of future atherosclerosis clinical cases, improved medical efficiency, and accurately identified the patient’s lesion area. It had great application potential in helping diagnosis and curative effect analysis of atherosclerosis.

scholarly journals Lipoprotein-Associated Phospholipase A2 Is a Risk Factor for Patients With Parkinson’s Disease

2021 ◽  
Vol 15 ◽  
Author(s):  
Zubo Wu ◽  
Suyuan Wu ◽  
Tao Liang ◽  
Lin Wang
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Logistic Regression ◽  
Risk Factor ◽  
Phospholipase A2 ◽  
Area Under The Curve ◽  
Diagnostic Value ◽  
Multivariable Logistic Regression Analysis ◽  
Disease Course ◽  
Clinical Value

ObjectiveTo explore the association between lipoprotein-related phospholipase A2 (Lp-PLA2) and the risk of Parkinson’s disease (PD).MethodsA case-control study involving 58 hospitalized PD patients and 60 healthy controls was carried out. Serum Lp-PLA2 level was detected. According to the disease course and severity, PD patients were subdivided to analyze the clinical value of Lp-PLA2. Relationship between Lp-PLA2 and PD risk was analyzed by logistic regression. Diagnostic value of Lp-PLA2 in PD patients was investigated using receiver’s operator characteristic curves.ResultsLp-PLA2 level was significantly higher in the PD patients compared with the controls, and was significantly and positively correlated with the Hoehn-Yahr (H&amp;Y) stage. The serum Lp-PLA2 level and H&amp;Y stage of PD patients with a longer disease course were significantly higher than those with a shorter disease course. PD patients with milder conditions had significantly lower serum Lp-PLA2 levels than patients with severe conditions. Multivariable logistic regression analysis indicated higher Lp-PLA2 level was an independent risk factor of PD patients. Moreover, the area under the curve for Lp-PLA2 was 0.703, which was between those of homocysteine and serum amylase A.ConclusionTo our knowledge, this is the first study to show that increased level of Lp-PLA2 is associated with the risk of PD. Lp-PLA2 may be used for early detection of PD, and provides an effective intervention target for clinical treatment of PD.

Development and Validation of a Prognostic Model to Predict Hearing Recovery for Patients With Chronic Otitis Media

2021 ◽  
pp. 014556132110655
Author(s):  
Fengyang Xie ◽  
Xiaoyue Zhen ◽  
Haiyuan Zhu ◽  
Yan Kou ◽  
Changle Li ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Otitis Media ◽  
Validation Cohort ◽  
Area Under The Curve ◽  
Chronic Otitis Media ◽  
Ossicular Chain ◽  
Multivariable Logistic Regression Analysis ◽  
Canal Wall ◽  
Multivariable Logistic Regression ◽  
Hearing Recovery

Objective To explore the factors affecting postoperative hearing recovery in chronic otitis media (COM) patients, establish a clinical prediction model for hearing recovery, and verify the accuracy of the model. Methods Data of patients with COM who were admitted to our hospital between January 1, 2012 and September 30, 2020 were retrospectively analyzed. We collected data on relevant clinicopathological characteristics of patients. The patients were randomly divided into the development cohort and validation cohorts. A postoperative air-bone gap (ABG) ≤20 dB was defined as successful hearing recovery. Univariate and multivariable logistic regression analyses were used to investigate the association of several prognostic factors with hearing recovery. These factors were then used to establish a nomogram. The model was subjected to bootstrap internal validation and performance evaluation in terms of discrimination, calibration, and clinical validity. Results This study included 2146 patients with COM: the development cohort comprised 1610 patients (mean [standard deviation; SD] age, 44.1 [14.7] years; 733 men [45.5%]) and the validation cohort included 536 patients (mean [SD] age, 42.9 [14.4] years; 234 men [43.7%]). Multivariable logistic regression analysis showed that age, duration of onset, styles of surgery (tympanoplasty, canal wall up-CWU, or canal wall down-CWD), ossicular prosthesis, granulation or calcified blocks around the ossicular chain, ossicular chain integrity, duration of drilling, eustachian tube dysfunction, mixed hearing loss, semicircular canal fistula, and second surgery were associated with hearing recovery. A nomogram based on these variables was constructed. The area under the curve was 0.797 (95% confidence interval [CI], 0.778–0.812) in the development cohort and 0.798 (95% CI, 0.7605–0.8355) in the validation cohort. Conclusions This study demonstrated the various clinical factors correlated with hearing recovery in patients with COM. The nomogram developed with these data could provide personalized risk estimates of hearing recovery to enhance preoperative counseling and help to set realistic expectations in patients.

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

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.

scholarly journals Intermediate Likelihood of Choledocholithiasis: Do All Need EUS or MRCP?

2021 ◽  
Vol 12 (01) ◽  
pp. 019-023
Author(s):  
Nitin Jagtap ◽  
Arun Karyampudi ◽  
HS Yashavanth ◽  
Mohan Ramchandani ◽  
Sundeep Lakhtakia ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Sensitivity And Specificity ◽  
Logistic Regression Analysis ◽  
Validation Cohort ◽  
Magnetic Resonance Cholangiopancreatography ◽  
Composite Score ◽  
Published Data ◽  
Derivation Cohort ◽  
Intermediate Likelihood

Abstract Background Recently updated guidelines for choledocholithiasis stratify suspected patients into high, intermediate, and low likelihood, with the aim to reduce risk of diagnostic endoscopic retrograde cholangiopancreatography. This approach has increased proportion of patients in intermediate likelihood making it heterogenous. We aim to substratify intermediate group so that diagnostic tests (endoscopic ultrasound/magnetic resonance cholangiopancreatography) are judicially used. Methods This is a single-center retrospective analysis of prospectively maintained data. We used subset of patients who met intermediate likelihood of American Society of Gastrointestinal Endoscopy (ASGE) criteria from previously published data (PMID:32106321) as derivation cohort. Binominal logistic regression analysis was used to define independent predictors of choledocholithiasis. A composite score was derived by allotting 1 point for presence of each independent predictor. The diagnostic performance of a composite score of ≥ 1 was evaluated in validation cohort. Results A total of 678 (mean age [standard deviation]: 47.0 [15.9] years; 48.1% men) and 162 (mean age 47.8 [14.8] years; 47.4% men) patients in ASGE intermediate-likelihood group were included as derivation cohort and validation cohort, respectively. Binominal logistic regression analysis showed that male gender (p = 0.024; odds ratio [OR] = 1.92), raised bilirubin (p = 0.001; OR = 2.40), and acute calculus cholecystitis (p = 0.010; OR = 2.04) were independent predictors for choledocholithiasis. A composite score was derived by allotting 1 point for presence of independent predictors Using ≥ 1 as cutoff, sensitivity and specificity for detection of choledocholithiasis were 80% (95% confidence interval [CI]: 68.2–88.9) and 36.2% (95% CI: 32.2–40.0), respectively, in derivation cohort. Applying composite score in independent validation cohort showed sensitivity and specificity of 73.3% (95% CI: 44.9–92.2) and 40.1% (95% CI: 30.1–48.5), respectively. Conclusion Substratification of intermediate-likelihood group of ASGE criteria is feasible. It may be useful in deciding in whom confirmatory tests should be performed with priority and in whom watchful waiting may be sufficient.

scholarly journals Do gliosarcomas have distinct imaging features on routine MRI?

2021 ◽  
pp. 197140092110123
Author(s):  
Christoph J Maurer ◽  
Irina Mader ◽  
Felix Joachimski ◽  
Ori Staszewski ◽  
Bruno Märkl ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Multivariate Analysis ◽  
Regression Model ◽  
Logistic Regression Model ◽  
External Validation ◽  
Area Under The Curve ◽  
Training Dataset ◽  
Validation Dataset ◽  
Imaging Features ◽  
Age And Sex

Purpose The aim of this study was the development and external validation of a logistic regression model to differentiate gliosarcoma (GSC) and glioblastoma multiforme (GBM) on standard MR imaging. Methods A univariate and multivariate analysis was carried out of a logistic regression model to discriminate patients histologically diagnosed with primary GSC and an age and sex-matched group of patients with primary GBM on presurgical MRI with external validation. Results In total, 56 patients with GSC and 56 patients with GBM were included. Evidence of haemorrhage suggested the diagnosis of GSC, whereas cystic components and pial as well as ependymal invasion were more commonly observed in GBM patients. The logistic regression model yielded a mean area under the curve (AUC) of 0.919 on the training dataset and of 0.746 on the validation dataset. The accuracy in the validation dataset was 0.67 with a sensitivity of 0.85 and a specificity of 0.5. Conclusions Although some imaging criteria suggest the diagnosis of GSC or GBM, differentiation between these two tumour entities on standard MRI alone is not feasible.

scholarly journals Differentiation between Germinoma and Craniopharyngioma Using Radiomics-Based Machine Learning

2022 ◽  
Vol 12 (1) ◽  
pp. 45
Author(s):  
Boran Chen ◽  
Chaoyue Chen ◽  
Yang Zhang ◽  
Zhouyang Huang ◽  
Haoran Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Validation Cohort ◽  
Characteristic Curve ◽  
Clinical Manifestations ◽  
Treatment Strategies ◽  
Region Of Interest ◽  
Imaging Features ◽  
Contrast Enhanced ◽  
Accurate Preoperative Diagnosis ◽  
The Difference

For the tumors located in the anterior skull base, germinoma and craniopharyngioma (CP) are unusual types with similar clinical manifestations and imaging features. The difference in treatment strategies and outcomes of patients highlights the importance of making an accurate preoperative diagnosis. This retrospective study enrolled 107 patients diagnosed with germinoma (n = 44) and CP (n = 63). The region of interest (ROI) was drawn independently by two researchers. Radiomic features were extracted from contrast-enhanced T1WI and T2WI sequences. Here, we established the diagnosis models with a combination of three selection methods, as well as three classifiers. After training the models, their performances were evaluated on the independent validation cohort and compared based on the index of the area under the receiver operating characteristic curve (AUC) in the validation cohort. Nine models were established and compared to find the optimal one defined with the highest AUC in the validation cohort. For the models applied in the contrast-enhanced T1WI images, RFS + RFC and LASSO + LDA were observed to be the optimal models with AUCs of 0.91. For the models applied in the T2WI images, DC + LDA and LASSO + LDA were observed to be the optimal models with AUCs of 0.88. The evidence of this study indicated that radiomics-based machine learning could be potentially considered as the radiological method in the presurgical differential diagnosis of germinoma and CP with a reliable diagnostic performance.

scholarly journals Radiomics Study for Discriminating Second Primary Lung Cancers From Pulmonary Metastases in Pulmonary Solid Lesions

2022 ◽  
Vol 11 ◽  
Author(s):  
Feiyang Zhong ◽  
Zhenxing Liu ◽  
Wenting An ◽  
Binchen Wang ◽  
Hanfei Zhang ◽  
...  
Keyword(s):  
Clinical Data ◽  
Pulmonary Metastases ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Pulmonary Nodules ◽  
Second Primary ◽  
Imaging Features ◽  
Clinical Value ◽  
Discriminative Ability ◽  
Lung Cancers

BackgroundThe objective of this study was to assess the value of quantitative radiomics features in discriminating second primary lung cancers (SPLCs) from pulmonary metastases (PMs).MethodsThis retrospective study enrolled 252 malignant pulmonary nodules with histopathologically confirmed SPLCs or PMs and randomly assigned them to a training or validation cohort. Clinical data were collected from the electronic medical records system. The imaging and radiomics features of each nodule were extracted from CT images.ResultsA rad-score was generated from the training cohort using the least absolute shrinkage and selection operator regression. A clinical and radiographic model was constructed using the clinical and imaging features selected by univariate and multivariate regression. A nomogram composed of clinical-radiographic factors and a rad-score were developed to validate the discriminative ability. The rad-scores differed significantly between the SPLC and PM groups. Sixteen radiomics features and four clinical-radiographic features were selected to build the final model to differentiate between SPLCs and PMs. The comprehensive clinical radiographic–radiomics model demonstrated good discriminative capacity with an area under the curve of the receiver operating characteristic curve of 0.9421 and 0.9041 in the respective training and validation cohorts. The decision curve analysis demonstrated that the comprehensive model showed a higher clinical value than the model without the rad-score.ConclusionThe proposed model based on clinical data, imaging features, and radiomics features could accurately discriminate SPLCs from PMs. The model thus has the potential to support clinicians in improving decision-making in a noninvasive manner.

scholarly journals S100A1 as a potential biomarker for the diagnosis of patients with acute aortic dissection

2021 ◽  
Vol 49 (4) ◽  
pp. 030006052110045
Author(s):  
Chenjun Han ◽  
Qiang Liu ◽  
Yuanmin Li ◽  
Wangfu Zang ◽  
Jian Zhou
Keyword(s):  
Logistic Regression ◽  
Aortic Dissection ◽  
Roc Curve ◽  
Acute Aortic Dissection ◽  
Troponin T ◽  
Area Under The Curve ◽  
Hospital Death ◽  
Clinical Value ◽  
Roc Curve Analysis ◽  
Potential Biomarker

Objective Acute aortic dissection (AAD) is a common life-threatening cardiovascular disease. This retrospective study was conducted to analyze the plasma concentration of S100A1 and its diagnostic value for AAD through receiver operating characteristic (ROC) curve and logistic regression analyses. Methods Seventy-eight patients with AAD and 77 healthy controls were included, and the relevant clinical data for each group were collected. According to the Stanford classification, the AAD patients were divided into types A and B. The plasma levels of S100A1, D-dimer, hypersensitive C-reactive protein, and cardiac troponin T were detected by enzyme-linked immunosorbent assays. Results The S100A1 concentrations in the healthy control, Stanford A, and Stanford B groups were 0.7 ± 0.6, 4.9 ± 2.6, and 3.5 ± 2.2 ng/mL, respectively. The concentration of S100A1 was increased in patients with AAD complicated with aortic regurgitation, pericardial effusion, or in-hospital death. ROC curve analysis showed that the area under the curve was 0.89. Logistic regression analysis revealed that the S100A1 level was an important risk factor for the development of AAD. Conclusion Plasma S100A1 is significantly elevated in patients with AAD, and its concentration has potential clinical value for diagnosing AAD.

Sign in / Sign up

Export Citation Format

Share Document