Radiomic model for differentiating parotid pleomorphic adenoma from parotid adenolymphoma based on MRI images

Abstract Background: Distinguishing parotid pleomorphic adenoma (PPA) from parotid adenolymphoma (PA) is important for precision treatment, but there is a lack of readily available diagnostic methods. In this study, we aimed to explore the diagnostic value of radiomic signatures based on magnetic resonance imaging (MRI) for PPA and PA. Methods: The clinical characteristic and imaging data were retrospectively collected from 252 cases (126 cases in the training cohort and 76 patients in the validation cohort) in this study. Radiomic features were extracted from MRI scans, including T1-weighted imaging (T1WI) sequences and T2-weighted imaging (T2WI) sequences. The radiomic features from three sequences (T1WI, T2WI and T1WI combined with T2WI) were selected using univariate analysis, LASSO correlation and Spearman correlation. Then, we built six quantitative radiomic models using the selected features through two machine learning methods (multivariable logistic regression, MLR, and support vector machine, SVM). The performances of the six radiomic models were assessed and the diagnostic efficacies of the ideal T1-2WI radiomic model and the clinical model were compared.Results: The T1-2WI radiomic model using MLR showed optimal discriminatory ability (accuracy = 0.87 and 0.86, F-1 score = 0.88 and 0.86, sensitivity= 0.90 and 0.88, specificity=0.82 and 0.80, positive predictive value=0.86 and 0.84, negative predictive value=0.86 and 0.84 in the training and validation cohorts, respectively) and its calibration was observed to be good (p>0.05). The area under the curve (AUC) of the T1-2WI radiomic model was significantly better than that of the clinical model for both the training (0.95 vs. 0.67, p<0.001) and validation (0.90 vs. 0.68, p=0.001) cohorts.Conclusions: The T1-2WI radiomic model in our study is complementary to the current knowledge of differential diagnosis for PPA and PA.

Download Full-text

Radiomic model for differentiating parotid pleomorphic adenoma from parotid adenolymphoma based on MRI images

10.21203/rs.3.rs-43710/v2 ◽

2020 ◽

Author(s):

Le-le Song ◽

Shun-jun Chen ◽

Wang Chen ◽

Zhan Shi ◽

Xiao-dong Wang ◽

...

Keyword(s):

Pleomorphic Adenoma ◽

Predictive Value ◽

Current Knowledge ◽

Univariate Analysis ◽

Area Under The Curve ◽

Diagnostic Value ◽

Diagnostic Methods ◽

Support Vector ◽

Imaging Data ◽

Clinical Model

Abstract Background: Distinguishing parotid pleomorphic adenoma (PPA) from parotid adenolymphoma (PA) is important for precision treatment, but there is a lack of readily available diagnostic methods. In this study, we aimed to explore the diagnostic value of radiomic signatures based on magnetic resonance imaging (MRI) for PPA and PA. Methods: The clinical characteristic and imaging data were retrospectively collected from 252 cases (126 cases in the training cohort and 76 patients in the validation cohort) in this study. Radiomic features were extracted from MRI scans, including T1-weighted imaging (T1WI) sequences and T2-weighted imaging (T2WI) sequences. The radiomic features from three sequences (T1WI, T2WI and T1WI combined with T2WI) were selected using univariate analysis, LASSO correlation and Spearman correlation. Then, we built six quantitative radiomic models using the selected features through two machine learning methods (multivariable logistic regression, MLR, and support vector machine, SVM). The performances of the six radiomic models were assessed and the diagnostic efficacies of the ideal T1-2WI radiomic model and the clinical model were compared.Results: The T1-2WI radiomic model using MLR showed optimal discriminatory ability (accuracy = 0.87 and 0.86, F-1 score = 0.88 and 0.86, sensitivity= 0.90 and 0.88, specificity=0.82 and 0.80, positive predictive value=0.86 and 0.84, negative predictive value=0.86 and 0.84 in the training and validation cohorts, respectively) and its calibration was observed to be good (p>0.05). The area under the curve (AUC) of the T1-2WI radiomic model was significantly better than that of the clinical model for both the training (0.95 vs. 0.67, p=0.000) and validation (0.90 vs. 0.68, p=0.001) cohorts.Conclusions: The T1-2WI radiomic model in our study is complementary to the current knowledge of differential diagnosis for PPA and PA.

Download Full-text

Radiomic model for differentiating parotid pleomorphic adenoma from parotid adenolymphoma based on MRI images

BMC Medical Imaging ◽

10.1186/s12880-021-00581-9 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Le-le Song ◽

Shun-jun Chen ◽

Wang Chen ◽

Zhan Shi ◽

Xiao-dong Wang ◽

...

Keyword(s):

Pleomorphic Adenoma ◽

Predictive Value ◽

Current Knowledge ◽

Univariate Analysis ◽

Area Under The Curve ◽

Diagnostic Value ◽

Diagnostic Methods ◽

Support Vector ◽

Imaging Data ◽

Clinical Model

Abstract Background Distinguishing parotid pleomorphic adenoma (PPA) from parotid adenolymphoma (PA) is important for precision treatment, but there is a lack of readily available diagnostic methods. In this study, we aimed to explore the diagnostic value of radiomic signatures based on magnetic resonance imaging (MRI) for PPA and PA. Methods The clinical characteristic and imaging data were retrospectively collected from 252 cases (126 cases in the training cohort and 76 patients in the validation cohort) in this study. Radiomic features were extracted from MRI scans, including T1-weighted imaging (T1WI) sequences and T2-weighted imaging (T2WI) sequences. The radiomic features from three sequences (T1WI, T2WI and T1WI combined with T2WI) were selected using univariate analysis, LASSO correlation and Spearman correlation. Then, we built six quantitative radiomic models using the selected features through two machine learning methods (multivariable logistic regression, MLR, and support vector machine, SVM). The performances of the six radiomic models were assessed and the diagnostic efficacies of the ideal T1-2WI radiomic model and the clinical model were compared. Results The T1-2WI radiomic model using MLR showed optimal discriminatory ability (accuracy = 0.87 and 0.86, F-1 score = 0.88 and 0.86, sensitivity = 0.90 and 0.88, specificity = 0.82 and 0.80, positive predictive value = 0.86 and 0.84, negative predictive value = 0.86 and 0.84 in the training and validation cohorts, respectively) and its calibration was observed to be good (p > 0.05). The area under the curve (AUC) of the T1-2WI radiomic model was significantly better than that of the clinical model for both the training (0.95 vs. 0.67, p < 0.001) and validation (0.90 vs. 0.68, p = 0.001) cohorts. Conclusions The T1-2WI radiomic model in our study is complementary to the current knowledge of differential diagnosis for PPA and PA.

Download Full-text

Radiomic model for differentiating parotid pleomorphic adenoma from parotid adenolymphoma based on MRI images

10.21203/rs.3.rs-43710/v1 ◽

2020 ◽

Author(s):

Le-le Song ◽

Shun-jun Chen ◽

Wang Chen ◽

Zhan Shi ◽

Xiao-dong Wang ◽

...

Keyword(s):

Pleomorphic Adenoma ◽

Predictive Value ◽

Current Knowledge ◽

Characteristic Curve ◽

Univariate Analysis ◽

Diagnostic Value ◽

Support Vector ◽

Clinical Model ◽

Model Based ◽

Discriminatory Accuracy

Abstract Background: Magnetic resonance imaging (MRI) is used routinely in the clinical management, and we explored the diagnostic value of radiomic signatures based on MRI to distinguish parotid pleomorphic adenoma from parotid adenolymphoma. Methods: The clinical characteristics and images data were retrospectively collected from 252 cases (126 cases in training cohort and 76 patients in verification cohort) in this study. And 429 radiomic features of T1-weighted imaging (T1WI) sequence and 414 radiomic features of T2-weighted imaging (T2WI) were extracted from MRI images. We selected the radiomic features from three sequences (T1WI, T2WI and T1-2WI) by univariate analysis, lasso correlation and spearman correlation. Then we built six quantitative radiological models based on the selected radiomic features using two machine learning methods (multivariable logistic regression, MLR and support vector machine, SVM). We assessed the performance of the six radiomic models, and an ideal radiomic signature was chosen to compare its diagnosis efficacy with that of the clinical model. Results: The radiomic model based on features of T1-2WI sequence by MLR showed optimal discriminatory (accuracy = 0.87 and 0.86, F-1score = 0.88 and 0.86, Sensitivity= 0.90 and 0.88, Specificity=0.82 and 0.80 positive predictive value=0.86 and 0.84, negative predictive value=0.86 and 0.84 in training and validation cohorts, respectively) and its good calibration was also observed (p>0.05). The area under the receiver operating characteristic curve (AUC) of the T1-2WI radiomic model was significantly better than that of the clinical model for both the training (0.95 vs. 0.74, p=0.000) and validation (0.90 vs. 0.73, p=0.001) cohorts. Conclusions: The radiomic model based on MRI in our study is complementary to the current knowledge of differential diagnosis for parotid pleomorphic adenoma and parotid adenolymphoma.

Download Full-text

PEMERIKSAAN TINGKAT sdLDL SERUM SEBAGAI PETANDA DIAGNOSTIK STENOSIS KORONER (Serum sdLDL Level as A Diagnostic Marker of Coronary Stenosis)

INDONESIAN JOURNAL OF CLINICAL PATHOLOGY AND MEDICAL LABORATORY ◽

10.24293/ijcpml.v22i1.1215 ◽

2018 ◽

Vol 22 (1) ◽

pp. 9

Author(s):

Indranila K Samsuria ◽

Laily Adninta

Keyword(s):

Predictive Value ◽

Coronary Stenosis ◽

Area Under The Curve ◽

Clinical Pathology ◽

Diagnostic Value ◽

T Test ◽

Cross Sectional ◽

Increased Risk ◽

Test Kit ◽

Vascular Stenosis

Small dense LDL (sdLDL) is the LDL which particles are small and dense, it is pro-atherogenic. Increased levels of serum sdLDL areassociated with an increased risk of coronary stenosis. The aim of this study was to examine the diagnostic value of sd LDL in coronarystenosis. An analytical observational study with cross sectional approach was conducted at the Department of Clinical Pathology, MedicalFaculty of Diponegoro University/Dr. Kariadi Hospital and the Unit of Cardiac diseases during the period of March-October 2013. Thesubjects were 39 patients suspected of suffering a coronary stenosis. The diagnosis of coronary stenosis, degree of stenosis and numberof vascular stenosis was established at the time of cardiac catheterization. SdLDL assessment used a test kit. The statistical analysis usedwere unpaired t-test, Spearman correlation test, ROC analysis and diagnostic test. LDL levels in stenosis subjects, 35.4±9.01 mg/dL weresignificantly higher compared to levels in subjects that had no stenosis, 20.7±7.10 mg/dL (p<0.001; unpaired t-test). Correlation testresults showed a correlation between levels of serum sdLDL with severe degree of stenosis (correlation coefficient -0.64, p <0.001) and amoderate positive correlation between the number of vascular stenosis (Coefficient correlation 0.46; p=0.003; Spearman Correlation’sTest). The area under the curve of ROC was 0.9 (p <0.001). The cut off levels sdLDL were used to detect stenosis. The results showeda sensitivity of 85.2%, specificity of 75%, positive predictive value of 88.5%, negative predictive value of 69.2% and accuracy of 82%.Levels of serum sdLDL were associated with severe to extensive stenosis degree, and showed a good diagnostic value, thus, it can beused for screening to determine the presence of coronary stenosis.

Download Full-text

Immunocytochemistry Test of Protein BRAF Expression for Diagnosis of Well Differentiated Thyroid Carcinoma

Case Reports in Oncology ◽

10.1159/000495029 ◽

2018 ◽

Vol 11 (3) ◽

pp. 843-849 ◽

Cited By ~ 1

Author(s):

I. Wayan Sudarsa ◽

Elvis Deddy Kurniawan Pualillin ◽

Putu Anda Tusta Adiputra ◽

Ida Bagus Tjakra Wibawa Manuaba

Keyword(s):

Positive Predictive Value ◽

Thyroid Carcinoma ◽

Negative Predictive Value ◽

Diagnostic Test ◽

Predictive Value ◽

Preoperative Diagnosis ◽

Area Under The Curve ◽

Diagnostic Value ◽

Differentiated Thyroid Carcinoma ◽

Inclusion Criteria

Background: Thyroid carcinoma generally has a good prognosis. The main focus of current research on thyroid carcinoma is to increase the accuracy of preoperative diagnosis of thyroid nodules. When the result of fine needle aspiration biopsy (FNAB) is indeterminate, clinicians often have doubts in determining the surgical management. Objective: Protein BRAF expression analysis can help improve the accuracy of FNAB and optimize the management of differentiated thyroid carcinoma. Methods: This study is a diagnostic test performed from October 2016 at Sanglah General Hospital with 38 patients as subjects who fulfilled the inclusion criteria. Data is being presented in descriptive form before diagnostic test is done to determine sensitivity, specificity, positive predictive value, negative predictive value and the accuracy of immunocytochemistry test for BRAF on indeterminate thyroid nodule. Results: Thirty-eight samples met the inclusion criteria during the study period. Three samples were male (7.9%) and 35 samples (92.1%) were female. The mean age of the sample was 45.21 years (SD ±10.910 years) with ages ranging from 23 to 66 years. Of the 12 samples undergoing isthmolobectomy, 7 samples (58.4%) were determined to be malignant from histopathological results. The sensitivity value of BRAF immunocytochemistry test is 45.45% with a specificity value of 81.25%, a positive predictive value of 76.92%, a negative predictive value of 52% and an accuracy of 60.50%. Analysis of the receiver operator (ROC) curve shows the area under the curve (AUC) of 63.4% with a confidence interval of 45.5–81.2%. Conclusion: Immunocytochemistry BRAF test have a reliable diagnostic value and can be taken into consideration in the preoperative diagnosis of thyroid malignancies.

Download Full-text

Development of a bedside score to predict dengue severity

10.1101/2020.11.25.20238972 ◽

2020 ◽

Author(s):

Ingrid Marois ◽

Carole Forfait ◽

Catherine Inizan ◽

Elise Klement-Frutos ◽

Anabelle Valiame ◽

...

Keyword(s):

Predictive Value ◽

Hospital Admissions ◽

New Caledonia ◽

Univariate Analysis ◽

Dengue Infection ◽

Area Under The Curve ◽

Severe Dengue ◽

Health Practitioners ◽

Dengue Outbreaks ◽

Median Area

AbstractBackgroundIn 2017, New Caledonia experienced an outbreak of severe dengue causing high hospital burden (4,379 cases, 416 hospital admissions, 15 deaths). We decided to build a local operational model predictive of dengue severity, which was needed to ease the healthcare circuit.MethodsWe retrospectively analyzed clinical and biological parameters associated with severe dengue in the cohort of patients hospitalized at the Territorial Hospital between January and July 2017 with confirmed dengue, in order to elaborate a comprehensive patient’s score. Patients were compared in univariate and multivariate analyses. Predictive models for severity were built using a descending step-wise method.ResultsOut of 383 included patients, 130 (34%) developed severe dengue and 13 (3.4%) died. Major risk factors identified in univariate analysis were: age, comorbidities, presence of at least one alert sign, platelets count <30×109/L, prothrombin time <60%, AST and/or ALT >10N, and previous dengue infection. Severity was not influenced by the infecting dengue serotype nor by previous Zika infection. Two models to predict dengue severity were built according to sex. Best models for females and males had respectively a median Area Under the Curve = 0.80 and 0.88, a sensitivity = 84.5% and 84.5%, a specificity = 78.6% and 95.5%, a positive predictive value = 63.3% and 92.9%, a negative predictive value = 92.8% and 91.3%. Models were secondarily validated on 130 patients hospitalized for dengue in 2018.ConclusionWe built robust and efficient models to calculate a bedside score able to predict dengue severity in our setting. We propose the spreadsheet for dengue severity score calculations to health practitioners facing dengue outbreaks of enhanced severity in order to improve patients’ medical management and hospitalization flow.

Download Full-text

Stereotactic Body Radiotherapy for Hepatocellular Carcinoma: Current Evidence and the Feasibility of Radiomics-based Predictive Models

10.21203/rs.3.rs-17027/v1 ◽

2020 ◽

Author(s):

Yang-Hong Dai ◽

Po-Chien Shen ◽

Wei-Chou Chang ◽

Chen-Hsiang Lo ◽

Jen-Fu Yang ◽

...

Keyword(s):

Hepatocellular Carcinoma ◽

Local Control ◽

Predictive Models ◽

Stereotactic Body Radiotherapy ◽

Current Knowledge ◽

Area Under The Curve ◽

Current Evidence ◽

Support Vector ◽

Svm Classifier

Abstract Background : Stereotactic body radiotherapy (SBRT) is an effective but less focused alternative for treatment of hepatocellular carcinoma (HCC). To date, a personalized model for predicting therapeutic response is lacking. This study aimed to review current knowledge and to propose a radiomics-based machine-learning (ML) strategy for local response (LR) prediction. Methods : We searched the literature for studies conducted between January 1993 and August 2019 that used > 100 patients. Additionally, 172 HCC patients in our hospital were retrospectively analyzed between January 2007 and December 2016. In the radiomic analysis, 41 treated tumors were contoured and 46 radiomic features were extracted. Results : The 1-year local control was 85.4% in our patient cohort, comparable with current results (87-99%). The Support Vector Machine (SVM) classifier, based on computed tomography (CT) scans in the A phase processed by equal probability (Ep) quantization with 8 gray levels, showed the highest mean F1 score (0.7995) for favorable LR within 1 year (W1R), at the end of follow-up (EndR), and condition of in-field failure-free (IFFF). The area under the curve (AUC) for this model was 92.1%, 96.3%, and 99.2% for W1R, EndR, and IFFF, respectively. Conclusions : SBRT has high 1-year local control and our study sets the basis for constructing predictive models for HCC patients receiving SBRT.

Download Full-text

Identification and Validation of Novel Serum Autoantibodies Biomarkers for Staging Liver Fibrosis in Patients With Chronic Hepatitis B

Frontiers in Medicine ◽

10.3389/fmed.2021.807087 ◽

2022 ◽

Vol 8 ◽

Author(s):

Saiping Qi ◽

Jing Li ◽

Xiaomin He ◽

Jialing Zhou ◽

Zhibin Chen ◽

...

Keyword(s):

Chronic Hepatitis ◽

Liver Fibrosis ◽

Hepatitis B ◽

Chronic Hepatitis B ◽

Microarray Analysis ◽

Characteristic Curve ◽

Area Under The Curve ◽

Diagnostic Value ◽

Diagnostic Methods ◽

Pre Treatment

Aim: Liver fibrosis monitoring is essential in patients with chronic hepatitis B (CHB). However, less robust, noninvasive diagnostic methods for staging liver fibrosis, other than liver biopsy, are available. Our previous study demonstrated a panel of cellular proteins recognized by autoantibodies that may have potential value in discrimination of CHB and liver cirrhosis. We aim to assess the diagnostic value of these serum autoantibodies for staging liver fibrosis.Methods: Candidate autoantigens were screened and assessed by microarray analysis in 96 healthy controls and 227 CHB patients with pre-treatment biopsy-proven METAVIR fibrosis score, comprising 69, 115, and 43 cases with S0-1, S2-3, and S4 stages, respectively. Autoantibodies with potential diagnostic value for staging liver fibrosis were verified by enzyme-linked immunosorbent assays (ELISA). Receiver operating characteristic curve was conducted to evaluate autoantibody performance.Results: Microarray analysis identified autoantigens CENPF, ACY1, HSPA6, and ENO1 with potential diagnostic value for liver fibrosis staging, among which CENPF and ACY1 were validated using ELISA. CENPF and ACY1 autoantibodies had area under the curve values of 0.746 and 0.685, 58.14 and 74.42% sensitivity, and 88.41 and 60.87% specificity, respectively, for discriminating liver fibrosis stages S4 and S0-1. The prevalence of CENPF and ACY1 autoantibodies was not correlated with age, sex or level of inflammation.Conclusions: Autoimmune responses may be elicited during progression of liver fibrosis, and serum autoantibodies may be a valuable biomarker for staging liver fibrosis deserving of further study.

Download Full-text

Predictive value of qSOFA score for death in emergency department resuscitation room among adult trauma patients:a retrospective study

BMC Emergency Medicine ◽

10.1186/s12873-021-00498-0 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Wenjuan Huang ◽

Peng Yang ◽

Feng Xu ◽

Du Chen

Keyword(s):

Emergency Department ◽

Predictive Value ◽

Univariate Analysis ◽

Area Under The Curve ◽

Study Endpoint ◽

Trauma Patients ◽

Roc Curve Analysis ◽

Resuscitation Room ◽

Failure Assessment ◽

Qsofa Score

Abstract Background To explore the predictive value of the quick Sequential Organ Failure Assessment (qSOFA) score for death in the emergency department (ED) resuscitation room among adult trauma patients. Methods During the period November 1, 2016 to November 30, 2019, data was retrospectively collected of adult trauma patients triaged to the ED resuscitation room in the First Affiliated Hospital of Soochow University. Death occurring in the ED resuscitation room was the study endpoint. Univariate and multivariate analyses were performed to explore the association between qSOFA score and death. Receiver operating characteristic (ROC) curve analysis was also performed for death. Results A total of 1739 trauma victims were admitted, including 1695 survivors and 44 non-survivors. The death proportion raised with qSOFA score: 0.60% for qSOFA = 0, 3.28% for qSOFA = 1, 12.06% for qSOFA = 2, and 15.38% for qSOFA = 3, p < 0.001. Subgroup of qSOFA = 0 was used as a reference. In univariate analysis, crude OR for death with qSOFA = 1 was 5.65 [95% CI 2.25 to 14.24, p < 0.001], qSOFA = 2 was 22.85 [95% CI 8.84 to 59.04, p < 0.001], and qSOFA = 3 was 30.30 [95% CI 5.50 to 167.05, p < 0.001]. In multivariate analysis, with an adjusted OR (aOR) of 2.87 (95% CI 0.84 to 9.87, p = 0.094) for qSOFA = 1, aOR 6.80 (95% CI 1.79 to 25.90, p = 0.005) for qSOFA = 2, and aOR 24.42 (95% CI 3.67 to 162.27, p = 0.001) for qSOFA = 3. The Area Under the Curve (AUC) for predicting death in the ED resuscitation room among trauma patients was 0.78 [95% CI, 0.72–0.85]. Conclusions The qSOFA score can assess the severity of emergency trauma patients and has good predictive value for death in the ED resuscitation room.

Download Full-text

Diagnostic Value of the EZH2 Immunomarker in Malignant Effusion Cytology

Acta Cytologica ◽

10.1159/000501406 ◽

2019 ◽

Vol 64 (3) ◽

pp. 248-255

Author(s):

Piao Piao Ang ◽

Geok Chin Tan ◽

Norain Karim ◽

Yin Ping Wong

Keyword(s):

Cancer Progression ◽

Predictive Value ◽

Area Under The Curve ◽

Diagnostic Value ◽

Metastatic Carcinoma ◽

Mesothelial Cells ◽

Roc Curve Analysis ◽

Resource Limited ◽

Reactive N ◽

Economic Constraints

Background: Differentiating reactive mesothelial cells from metastatic carcinoma in effusion cytology is a challenging task. The application of at least 4 monoclonal antibodies including 2 epithelial markers (Ber-EP4, MOC-31, CEA, or B72.3) and 2 mesothelial markers (calretinin, WT-1, CK5/6, or HBME-1) are often useful in this distinction; however, it is not readily available in many resource-limited developing countries. Aberrant immunoexpression of enhancer of zeste homolog 2 (EZH2), a transcriptional repressor involved in cancer progression, is observed widely in various malignancy. In this study, we evaluate the diagnostic value of EZH2 as a single reliable immunomarker for malignancy in effusion samples. Methods: A total of 108 pleural, peritoneal, and pericardial effusions/washings diagnosed as unequivocally reactive (n = 41) and metastatic carcinoma (n = 67) by cytomorphology over 18 months were reviewed. Among the metastatic carcinoma cases, 54 were adenocarcinoma and others were squamous cell carcinoma (n = 1), carcinosarcoma (n = 1), and carcinoma of undefined histological subtypes (n = 11). Cell block sections were immunostained by EZH2 (Cell Marque, USA). The percentages of EZH2-immunolabeled cells over the total cells of interest were calculated. Receiver operating characteristic (ROC) curve analysis was performed to determine the optimal cut-off score to define EZH2 immunopositivity. Results: A threshold of 8% EZH2-immunolabeled cells allows distinction between malignant and reactive mesothelial cells, with 95.5% sensitivity, 100% specificity, 100% positive predictive value, and 93.2% negative predictive value (p < 0.0001). The area under the curve was 0.988. Conclusion: EZH2 is a promising diagnostic biomarker for malignancy in effusion cytology which is inexpensive yet trustworthy and could potentially be used routinely in countries under considerable economic constraints.

Download Full-text