Dataset Information

Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan.

ABSTRACT: New radioimaging techniques, exploiting the quantitative variables of imaging, permit to identify an hypothetical pathological tissue. We have applied this potential in a series of 72 adrenal incidentalomas (AIs) followed at our center, subdivided in functioning and non-functioning using laboratory findings. Each AI was studied in the preliminary non-contrast phase with a specific software (Mazda), surrounding a region of interest within each lesion. A total of 314 features were extrapolated. Mean and standard deviations of features were obtained and the difference in means between the two groups was statistically analyzed. Receiver Operating Characteristic (ROC) curves were used to identify an optimal cutoff for each variable and a prediction model was constructed via multivariate logistic regression with backward and stepwise selection. A 11-variable prediction model was constructed, and a ROC curve was used to differentiate patients with high probability of functioning AI. Using a threshold value of >-275.147, we obtained a sensitivity of 93.75% and a specificity of 100% in diagnosing functioning AI. On the basis of these results, computed tomography (CT) texture analysis appears a promising tool in the diagnostic definition of AIs.

SUBMITTER: Maggio R

PROVIDER: S-EPMC9248203 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan.

Maggio Roberta R Messina Filippo F D'Arrigo Benedetta B Maccagno Giacomo G Lardo Pina P Palmisano Claudia C Poggi Maurizio M Monti Salvatore S Matarazzo Iolanda I Laghi Andrea A Pugliese Giuseppe G Stigliano Antonio A

Frontiers in endocrinology 20220617

New radioimaging techniques, exploiting the quantitative variables of imaging, permit to identify an hypothetical pathological tissue. We have applied this potential in a series of 72 adrenal incidentalomas (AIs) followed at our center, subdivided in functioning and non-functioning using laboratory findings. Each AI was studied in the preliminary non-contrast phase with a specific software (Mazda), surrounding a region of interest within each lesion. A total of 314 features were extrapolated. Me ...[more]

PMID: 35784576

Similar Datasets

Project description:Purpose: To explore the application value of multiparametric computed tomography (CT) radiomics in non-invasive differentiation between aldosterone-producing and cortisol-producing functional adrenocortical adenomas. Methods: This retrospective review analyzed 83 patients including 41 patients with aldosterone-producing adenoma and 42 patients with cortisol-producing adenoma. The quantitative radiomics features were extracted from the complete unenhanced, arterial, and venous phase CT images. A comparative study of several frequently used machine learning models (linear discriminant analysis, logistic regression, random forest, and support vector machine) combined with different feature selection methods was implemented in order to determine which was most advantageous for differential diagnosis using radiomics features. Then, the integrated model using the combination of radiomic signature and clinic-radiological features was built, and the associated calibration curve was also presented. The diagnostic performance of these models was estimated and compared using the area under the receiver operating characteristic (ROC) curve (AUC). Result: In the radiomics-based machine learning model, logistic regression model with LASSO (least absolute shrinkage and selection operator) outperformed the other models, which yielded a sensitivity of 0.935, a specificity of 0.823, and an accuracy of 0.887 [AUC = 0.882, 95% confidence interval (CI) = 0.819-0.945]. Moreover, the nomogram representing the integrated model achieved good discrimination performances, which yielded a sensitivity of 0.915, a specificity of 0.928, and an accuracy of 0.922 (AUC = 0.902, 95% CI = 0.822-0.982), and it was better than that of the radiomics model alone. Conclusion: This study found that the combination of multiparametric radiomics signature and clinic-radiological features can non-invasively differentiate the subtypes of hormone-secreting functional adrenocortical adenomas, which may have good potential for facilitating the diagnosis and treatment in clinical practice.

Project description:Backgroundsignificance of incidental thyroid 2-deoxy-2-[18F]fluoro-D-glucose ([18F]FDG) uptake on positron emission tomography/computed tomography (PET/CT) scans remains controversial. We aimed to evaluate the ability of [18F]FDG-PET/CT texture analysis to predict final diagnosis in thyroid incidentaloma.MethodsWe retrospectively evaluated medical records of all patients who performed a [18F]FDG-PET/CT from January 2012 to October 2016. Those patients who presented a thyroid incidentaloma described in the medical records and performed a fine needle aspiration in our institution were considered for the analysis. Cytological and/or histological results were used as reference standard to define the final diagnosis. In case of negative cytology, the nodule was considered benign. In case of non-diagnostic or inconclusive results ultrasound, follow-up and further cytology/histology were used as final diagnosis. For suspected or positive cytological result, histology was used as reference standard. PET images were segmented using a General Electric AW workstation running PET VCAR software (GE Healthcare, Waukesha, WI, USA) settled with a threshold of 40% SUVmax. LifeX software (http://www.lifexsoft.org) was used to perform texture analysis. Statistical analysis was performed with R package (https://www.r-project.org).ResultsWe identified 55 patients with incidental thyroid [18F]FDG uptake. Five patients were excluded from the analysis because a final diagnosis was not available. Thirty-two out of 50 patients had benign nodules while in 18/50 cases a malignancy (primary thyroid cancer = 15, metastases = 3) was diagnosed. Conventional PET parameters and histogram-based features were calculated for all 50 patients, while other matrices-based features were available for 28/50 patients. SUVmax and skewness resulted significantly different in benign and malignant nodules (p = 0.01 and = 0.02, respectively). Using ROC analysis, seven features were identified as potential predictors. Among all the textural features tested, skewness showed the best area under the curve (= 0.66). SUV-based parameters resulted in the highest specificity while MTV, TLG, skewness and kurtosis, as well as correlationGLCM resulted better in sensitivity.Conclusions[18F]FDG-PET/CT texture analysis seems to be a promising approach to stratify the patients with thyroid incidentaloma identified on PET scans, with respect to the risk of the diagnosis of a malignant thyroid nodule and thus, could refine the selection of the patients to be referred for cytology.

Project description:PurposeTo evaluate the ability of texture features for distinguishing between benign and malignant testicular masses, and furthermore, for identifying primary testicular lymphoma in malignant tumors and identifying seminoma in testicular germ cell tumors, respectively.MethodsWe retrospectively collected 77 patients with an abdominal and pelvic enhanced computed tomography (CT) examination and a histopathologically confirmed testicular mass from a single center. The ROI of each mass was split into two parts by the largest cross-sectional slice and deemed to be two samples. After all processing steps, three-dimensional texture features were extracted from unenhanced and contrast-enhanced CT images. Excellent reproducibility of texture features was defined as intra-class correlation coefficient ≥0.8 (ICC ≥0.8). All the groups were balanced via the synthetic minority over-sampling technique (SMOTE) method. Dimension reduction was based on pearson correlation coefficient (PCC). Before model building, minimum-redundancy maximum-relevance (mRMR) selection and recursive feature elimination (RFE) were used for further feature selection. At last, three ML classifiers with the highest cross validation with 5-fold were selected: autoencoder (AE), support vector machine(SVM), linear discriminant analysis (LAD). Logistics regression (LR) and LR-LASSO were also constructed to compare with the ML classifiers.Results985 texture features with ICC ≥0.8 were extracted for further feature selection process. With the highest AUC of 0.946 (P <0.01), logistics regression was proved to be the best model for the identification of benign or malignant testicular masses. Besides, LR also had the best performance in identifying primary testicular lymphoma in malignant testicular tumors and in identifying seminoma in testicular germ cell tumors, with the AUC of 0.982 (P <0.01) and 0.928 (P <0.01), respectively.ConclusionUntil now, this is the first study that applied CT texture analysis (CTTA) to assess the heterogeneity of testicular tumors. LR model based on CTTA might be a promising non-invasive tool for the diagnosis and differentiation of testicular masses. The accurate diagnosis of testicular masses would assist urologists in correct preoperative and perioperative decision making.

Dataset Information

Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan.

Publications

Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets