1
|
Huang R, Lin T, Chen M, Li X, Guo H. Diagnostic performance of magnetic resonance imaging features to differentiate adrenal pheochromocytoma from adrenal tumors with positive biochemical testing results. BMC Med Imaging 2024; 24:175. [PMID: 39026152 PMCID: PMC11264621 DOI: 10.1186/s12880-024-01350-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2023] [Accepted: 06/28/2024] [Indexed: 07/20/2024] Open
Abstract
BACKGROUND It is extremely essential to accurately differentiate pheochromocytoma from Adrenal incidentalomas (AIs) before operation, especially biochemical tests were inconclusive. We aimed to evaluate the value of magnetic resonance imaging (MRI) features to differentiate pheochromocytomas among adrenal tumors, among which the consequences of biochemical screening tests of catecholamines and/or catecholamine metabolites are positive. METHODS With institutional review board approval, this study retrospectively compared 35 pheochromocytoma (PHEO) patients with 27 non-pheochromocytoma(non-PHEO) patients between January 2022 to September 2023, among which the consequences of biochemical screening tests of catecholamines and/or catecholamine metabolites are positive. T test was used for the independent continuous data and the chi-square test was used for categorical variables. Univariate and multivariate logistic regression were applied to find the independent variate of the features to differentiate PHEO from non-PHEO and ROC analysis was applied to evaluate the diagnostic value of the independent variate. RESULTS We found that the T2-weighted (T2W) signal intensity in patients with pheochromocytoma was higher than other adrenal tumors, with greatly significant (p < 0.001). T2W signal intensity ratio (T2W nodule-to-muscle SI ratio) was an independent risk factor for the differential diagnosis of adrenal PHEOs from non-PHEOs. This feature alone had 91.4% sensitivity and 81.5% specificity to rule out pheochromocytoma based on optimal threshold, with an area under the receiver operating characteristics curve (AUC‑ROC) of 0.910(95% C I: 0.833-0.987). CONCLUSION Our study confirms that T2W signal intensity ratio can differentiate PHEO from non-PHEO, among which the consequences of biochemical screening tests of catecholamines and/or catecholamine metabolites are positive.
Collapse
Affiliation(s)
- Rukun Huang
- Department of Urology, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, China
- Institute of Urology, Nanjing University, Nanjing, China
| | - Tingsheng Lin
- Department of Urology, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, China
- Institute of Urology, Nanjing University, Nanjing, China
| | - Mengxia Chen
- Department of Urology, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, China
- Institute of Urology, Nanjing University, Nanjing, China
| | - Xiaogong Li
- Department of Urology, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, China.
- Institute of Urology, Nanjing University, Nanjing, China.
| | - Hongqian Guo
- Department of Urology, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, China.
- Institute of Urology, Nanjing University, Nanjing, China.
| |
Collapse
|
2
|
Tu W, Badawy M, Carney BW, Caoili EM, Corwin MT, Elsayes KM, Mayo-Smith W, Glazer DI, Bagga B, Petrocelli R, Taffel MT, Schieda N. Multicenter Validation of a T2-Weighted MRI Calculator to Differentiate Adrenal Adenoma From Adrenal Metastases. AJR Am J Roentgenol 2024; 222:e2329727. [PMID: 37556601 DOI: 10.2214/ajr.23.29727] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/11/2023]
Affiliation(s)
- Wendy Tu
- University of Alberta, Edmonton, AB, Canada
| | - Mohamed Badawy
- University of Texas MD Anderson Cancer Center, Houston, TX
| | | | | | | | | | | | | | - Barun Bagga
- New York University Grossman School of Medicine, New York, NY
| | | | - Myles T Taffel
- New York University Grossman School of Medicine, New York, NY
| | | |
Collapse
|
3
|
Xiao DX, Zhong JP, Peng JD, Fan CG, Wang XC, Wen XL, Liao WW, Wang J, Yin XF. Machine learning for differentiation of lipid-poor adrenal adenoma and subclinical pheochromocytoma based on multiphase CT imaging radiomics. BMC Med Imaging 2023; 23:159. [PMID: 37845636 PMCID: PMC10580667 DOI: 10.1186/s12880-023-01106-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2023] [Accepted: 09/20/2023] [Indexed: 10/18/2023] Open
Abstract
BACKGROUND There is a paucity of research investigating the application of machine learning techniques for distinguishing between lipid-poor adrenal adenoma (LPA) and subclinical pheochromocytoma (sPHEO) based on radiomic features extracted from non-contrast and dynamic contrast-enhanced computed tomography (CT) scans of the abdomen. METHODS We conducted a retrospective analysis of multiphase spiral CT scans, including non-contrast, arterial, venous, and delayed phases, as well as thin- and thick-thickness images from 134 patients with surgically and pathologically confirmed. A total of 52 patients with LPA and 44 patients with sPHEO were randomly assigned to training/testing sets in a 7:3 ratio. Additionally, a validation set was comprised of 22 LPA cases and 16 sPHEO cases from two other hospitals. We used 3D Slicer and PyRadiomics to segment tumors and extract radiomic features, respectively. We then applied T-test and least absolute shrinkage and selection operator (LASSO) to select features. Six binary classifiers, including K-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP), were employed to differentiate LPA from sPHEO. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values were compared using DeLong's method. RESULTS All six classifiers showed good diagnostic performance for each phase and slice thickness, as well as for the entire CT data, with AUC values ranging from 0.706 to 1. Non-contrast CT densities of LPA were significantly lower than those of sPHEO (P < 0.001). However, using the optimal threshold for non-contrast CT density, sensitivity was only 0.743, specificity 0.744, and AUC 0.828. Delayed phase CT density yielded a sensitivity of 0.971, specificity of 0.641, and AUC of 0.814. In radiomics, AUC values for the testing set using non-contrast CT images were: KNN 0.919, LR 0.979, DT 0.835, RF 0.967, SVM 0.979, and MLP 0.981. In the validation set, AUC values were: KNN 0.891, LR 0.974, DT 0.891, RF 0.964, SVM 0.949, and MLP 0.979. CONCLUSIONS The machine learning model based on CT radiomics can accurately differentiate LPA from sPHEO, even using non-contrast CT data alone, making contrast-enhanced CT unnecessary for diagnosing LPA and sPHEO.
Collapse
Affiliation(s)
- Dao-Xiong Xiao
- Department of Medical Imaging, Ganzhou Hospital affiliated to Nanchang University, Ganzhou People's Hospital, Ganzhou, Jiangxi province, China.
| | - Jian-Ping Zhong
- Department of Medical Imaging, Ganzhou Hospital affiliated to Nanchang University, Ganzhou People's Hospital, Ganzhou, Jiangxi province, China
| | - Ji-Dong Peng
- Department of Medical Imaging, Ganzhou Hospital affiliated to Nanchang University, Ganzhou People's Hospital, Ganzhou, Jiangxi province, China
| | - Cun-Geng Fan
- Department of Medical Imaging, Ganzhou Hospital affiliated to Nanchang University, Ganzhou People's Hospital, Ganzhou, Jiangxi province, China
| | - Xiao-Chun Wang
- Department of Medical Imaging, Ganzhou Hospital affiliated to Nanchang University, Ganzhou People's Hospital, Ganzhou, Jiangxi province, China
| | - Xing-Lin Wen
- Department of Medical Imaging, Ganzhou Hospital affiliated to Nanchang University, Ganzhou People's Hospital, Ganzhou, Jiangxi province, China
| | - Wei-Wei Liao
- Department of Medical Imaging, Ganzhou Hospital affiliated to Nanchang University, Ganzhou People's Hospital, Ganzhou, Jiangxi province, China
| | - Jun Wang
- Department of Medical Imaging, the First Affiliated Hospital of Gannan Medical University, Ganzhou, Jiangxi province, China
| | - Xiao-Feng Yin
- Department of Medical Imaging, Nankang District People's Hospital, Nankang District, Ganzhou, Jiangxi province, China
| |
Collapse
|
4
|
Araujo-Castro M, García Sanz I, Mínguez Ojeda C, Calatayud M, Hanzu FA, Mora M, Vicente Delgado A, Carrera CB, de Miguel Novoa P, Del Carmen López García M, Manjón-Miguélez L, Rodríguez de Vera Gómez P, Del Castillo Tous M, Barahona San Millán R, Recansens M, Fernández-Ladreda MT, Valdés N, Gracia Gimeno P, Robles Lazaro C, Michalopoulou T, Gómez Dos Santos V, Alvarez-Escola C, García Centeno R, Lamas C, Herrera-Martínez A. An Integrated CT and MRI Imaging Model to Differentiate between Adrenal Adenomas and Pheochromocytomas. Cancers (Basel) 2023; 15:3736. [PMID: 37509397 PMCID: PMC10378495 DOI: 10.3390/cancers15143736] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2023] [Revised: 07/05/2023] [Accepted: 07/19/2023] [Indexed: 07/30/2023] Open
Abstract
PURPOSE to perform an external validation of our predictive model to rule out pheochromocytoma (PHEO) based on unenhanced CT in a cohort of patients with PHEOs and adenomas who underwent adrenalectomy. METHODS The predictive model was previously developed in a retrospective cohort of 1131 patients presenting with adrenal lesions. In the present study, we performed an external validation of the model in another cohort of 214 patients with available histopathological results. RESULTS For the external validation, 115 patients with PHEOs and 99 with adenomas were included. Our previously described predictive model combining the variables of high lipid content and tumor size in unenhanced CT (AUC-ROC: 0.961) had a lower diagnostic accuracy in our current study population for the prediction of PHEO (AUC: 0.750). However, when we excluded atypical adenomas (with Hounsfield units (HU) > 10, n = 39), the diagnostic accuracy increased to 87.4%. In addition, in the whole cohort (including atypical adenomas), when MRI information was included in the model, the diagnostic accuracy increased to up to 85% when the variables tumor size, high lipid content in an unenhanced CT scan, and hyperintensity in the T2 sequence in MRI were included. The probability of PHEO was <0.3% for adrenal lesions <20 mm with >10 HU and without hyperintensity in T2. CONCLUSION Our study confirms that our predictive model combining tumor size and lipid content has high reliability for the prediction of PHEO when atypical adrenal lesions are excluded. However, for atypical adrenal lesions with >10 HU in an unenhanced CT scan, MRI information is necessary for a proper exclusion of the PHEO diagnosis.
Collapse
Affiliation(s)
- Marta Araujo-Castro
- Endocrinology & Nutrition Department, Hospital Universitario Ramón y Cajal, Instituto de Investigación Biomédica Ramón y Cajal (IRYCIS), 28034 Madrid, Spain
- Medicine Departmen, University of Alcalá, 28801 Madrid, Spain
| | - Iñigo García Sanz
- General & Digestive Surgery Department, Hospital Universitario de La Princesa, 28006 Madrid, Spain
| | - César Mínguez Ojeda
- Urology Department, Hospital Universitario Ramón y Cajal, 28034 Madrid, Spain
| | - María Calatayud
- Endocrinology & Nutrition Department, Hospital Universitario Doce de Octubre, 28041 Madrid, Spain
| | - Felicia A Hanzu
- Endocrinology & Nutrition Department, Hospital Clinic, 08036 Barcelona, Spain
| | - Mireia Mora
- Endocrinology & Nutrition Department, Hospital Clinic, 08036 Barcelona, Spain
| | | | - Concepción Blanco Carrera
- Endocrinology & Nutrition Department, Hospital Universitario Príncipe de Asturias, 28805 Madrid, Spain
| | - Paz de Miguel Novoa
- Endocrinology & Nutrition Department, Hospital Clínico San Carlos, 28040 Madrid, Spain
| | | | - Laura Manjón-Miguélez
- Endocrinology & Nutrition Department, Hospital Universitario Central de Asturias, Instituto de Investigación Sanitaria del Principado de Asturias (ISPA), 33011 Oviedo, Spain
| | | | - María Del Castillo Tous
- Endocrinology & Nutrition Department, Hospital Universitario Virgen de la Macarena, 41009 Sevilla, Spain
| | | | - Mónica Recansens
- Endocrinology & Nutrition Department, Institut Català de la Salut Girona, 17001 Girona, Spain
| | | | - Nuria Valdés
- Endocrinology & Nutrition Department, Hospital Universitario de Cabueñes, 33394 Asturias, Spain
| | - Paola Gracia Gimeno
- Endocrinology & Nutrition Department, Hospital Royo Villanova, 50015 Zaragoza, Spain
| | - Cristina Robles Lazaro
- Endocrinology & Nutrition Department, Hospital Universitario de Salamanca, 37007 Salamanca, Spain
| | - Theodora Michalopoulou
- Department of Endocrinology and Nutrition, Joan XXIII University Hospital, 43005 Tarragona, Spain
| | | | | | - Rogelio García Centeno
- Endocrinology & Nutrition Department, Hospital Universitario Gregorio Marañón, 28029 Madrid, Spain
| | - Cristina Lamas
- Endocrinology & Nutrition Department, Hospital Universitario de Albacete, 02008 Albacete, Spain
| | - Aura Herrera-Martínez
- Department of Endocrinology and Nutrition, Reina Sofía Hospital, 31500 Córdoba, Spain
| |
Collapse
|
5
|
Inter-individual comparison of diagnostic accuracy of adrenal washout CT compared to chemical shift MRI plus the T2-weighted (T2W) adrenal MRI calculator in indeterminate adrenal masses: a retrospective non-inferiority study. Abdom Radiol (NY) 2022; 47:2453-2461. [PMID: 35536326 DOI: 10.1007/s00261-022-03533-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2022] [Revised: 04/12/2022] [Accepted: 04/13/2022] [Indexed: 11/01/2022]
Abstract
OBJECTIVE To compare diagnostic accuracy of washout (WO)-CT to chemical shift (CS)-MRI + T2W adrenal MRI Calculator (T2W-Calculator) to diagnose adrenal adenoma in indeterminate adrenal masses. METHODS This retrospective, cross-sectional, non-inferiority study evaluated 40 consecutive indeterminate adrenal masses; each with WO-CT and MRI. Two blinded radiologists independently evaluated in mixed order: pre-contrast attenuation (Hounsfield Units, HU) and absolute WO ([Peak.HU-Delay.HU]/[Peak.HU-Pre.HU] × 100%), Chemical Shift Signal Intensity (CS-SI) Index, T2W SI ratio, and Entropy (which were imputed into the T2W-Calculator). Diagnostic accuracy for adrenal adenoma was tabulated using 2 × 2 tables. True -positive diagnoses of adenoma were CT = Pre-HU < 10 or absolute WO ≥ 60%, MRI = SI index ≥ 16.5% or T2W-Calculator < 0.631. RESULTS There were 73% (29/40) adenomas and 27% (11/40) other masses (5 pheochromocytoma, 3 solitary fibrous tumor, 1 metastasis, 1 cavernous hemangioma, and 1 adrenocortical carcinoma). Sensitivity, specificity, and accuracy for diagnosis of adenoma using CT-WO were 78% (95% confidence intervals [CI] 56-93%), 35% (14-62%), and 57% (42-71%) Reader 1 and 72% (53-87%), 46% (17-77%), and 59% (41-76%) Reader 2. Sensitivity, specificity, and accuracy for diagnosis of adenoma using MRI were 100% (88-100%), 64% (34-90%), and 82% (67-97%) Reader 1 and 86% (68-96%), 73% (39-94%), and 80% (64-95%) Reader 2. MRI had higher overall accuracy (p = 0.02 Reader 1, 0.05 Reader 2) compared to CT-WO. CONCLUSION Chemical shift MRI combined with the T2W adrenal MRI calculator is not inferior to CT Washout for diagnosis of adrenal adenoma among indeterminate adrenal masses.
Collapse
|