Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan
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...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-06-01
|
| Series: | Frontiers in Endocrinology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fendo.2022.873189/full |
| _version_ | 1818555729222565888 |
|---|---|
| author | Roberta Maggio Filippo Messina Benedetta D’Arrigo Giacomo Maccagno Pina Lardo Claudia Palmisano Maurizio Poggi Salvatore Monti Iolanda Matarazzo Andrea Laghi Giuseppe Pugliese Antonio Stigliano |
| author_facet | Roberta Maggio Filippo Messina Benedetta D’Arrigo Giacomo Maccagno Pina Lardo Claudia Palmisano Maurizio Poggi Salvatore Monti Iolanda Matarazzo Andrea Laghi Giuseppe Pugliese Antonio Stigliano |
| author_sort | Roberta Maggio |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-12T09:57:24Z |
| format | Article |
| id | doaj.art-25293b45db714a1381419cb0d822c728 |
| institution | Directory Open Access Journal |
| issn | 1664-2392 |
| language | English |
| last_indexed | 2024-12-12T09:57:24Z |
| publishDate | 2022-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Endocrinology |
| spelling | doaj.art-25293b45db714a1381419cb0d822c7282022-12-22T00:28:05ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922022-06-011310.3389/fendo.2022.873189873189Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT ScanRoberta Maggio0Filippo Messina1Benedetta D’Arrigo2Giacomo Maccagno3Pina Lardo4Claudia Palmisano5Maurizio Poggi6Salvatore Monti7Iolanda Matarazzo8Andrea Laghi9Giuseppe Pugliese10Antonio Stigliano11Endocrinology, Department of Clinical and Molecular Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyDepartment of Surgical and Medical Sciences and Translational Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyDepartment of Surgical and Medical Sciences and Translational Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyDepartment of Surgical and Medical Sciences and Translational Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyEndocrinology, Department of Clinical and Molecular Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyDepartment of Surgical and Medical Sciences and Translational Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyEndocrinology, Department of Clinical and Molecular Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyEndocrinology, Department of Clinical and Molecular Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyDepartment of Surgical and Medical Sciences and Translational Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyDepartment of Surgical and Medical Sciences and Translational Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyEndocrinology, Department of Clinical and Molecular Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyEndocrinology, Department of Clinical and Molecular Medicine, Sant’Andrea University Hospital, Sapienza University of Rome, Rome, ItalyNew 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.https://www.frontiersin.org/articles/10.3389/fendo.2022.873189/fulladrenal incidentalomasdifferential diagnosis of adrenal masssubclinical hypercortisolismcortisol secreting adrenal massnon-secreting adrenal massradiomics |
| spellingShingle | Roberta Maggio Filippo Messina Benedetta D’Arrigo Giacomo Maccagno Pina Lardo Claudia Palmisano Maurizio Poggi Salvatore Monti Iolanda Matarazzo Andrea Laghi Giuseppe Pugliese Antonio Stigliano Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan Frontiers in Endocrinology adrenal incidentalomas differential diagnosis of adrenal mass subclinical hypercortisolism cortisol secreting adrenal mass non-secreting adrenal mass radiomics |
| title | Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan |
| title_full | Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan |
| title_fullStr | Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan |
| title_full_unstemmed | Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan |
| title_short | Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan |
| title_sort | machine learning based texture analysis in the characterization of cortisol secreting vs non secreting adrenocortical incidentalomas in ct scan |
| topic | adrenal incidentalomas differential diagnosis of adrenal mass subclinical hypercortisolism cortisol secreting adrenal mass non-secreting adrenal mass radiomics |
| url | https://www.frontiersin.org/articles/10.3389/fendo.2022.873189/full |
| work_keys_str_mv | AT robertamaggio machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT filippomessina machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT benedettadarrigo machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT giacomomaccagno machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT pinalardo machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT claudiapalmisano machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT mauriziopoggi machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT salvatoremonti machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT iolandamatarazzo machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT andrealaghi machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT giuseppepugliese machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan AT antoniostigliano machinelearningbasedtextureanalysisinthecharacterizationofcortisolsecretingvsnonsecretingadrenocorticalincidentalomasinctscan |