Differentiation of multiple adrenal adenoma subtypes based on a radiomics and clinico-radiological model: a dual-center study

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Background

The prevalence and detection rates of adrenal incidentalomas have been on the rise globally, with more than 90% of these lesions pathologically classified as adrenocortical adenomas. Among these, approximately 30% of patients present with hormone-secreting adenomas, leading to the deterioration of their health, with some requiring surgical resection. The available methods for adrenal function evaluation are invasive and costly. Moreover, their accuracy is influenced by numerous factors. Therefore, it is imperative to develop non-invasive and simplified preoperative diagnostic approach.

Methods

A retrospective study was performed on 169 patients from two tertiary medical centers. Subsequently, radiomics features were extracted after tumor margins were delineated layer-by-layer using a semi-automatic contouring approach. Feature selection was achieved in two cycles, with the first round utilizing a support vector machine (SVM) and the second round using a LASSO-based recursive feature elimination algorithm. Finally, logistic regression models were constructed using the clinico-radiological, radiomics, and a combination of both.

Results

After a comprehensive evaluation of the predictive indicators, the logistic regression classifier model based on the combined clinico-radiological and radiomic features had an AUC of (0.945, 0.927, 0.856) for aldosterone-producing adenoma (APA), (0.963, 0.889, 0.887) for cortisol-producing adenoma (CPA), and (0.940, 0.765, 0.816) for non-functioning adrenal adenoma (NAA) in the training set, validation set, and external test set, respectively. This model exhibited superior predictive performance in differentiating between the three adrenal adenoma subtypes.

Conclusions

A logistic regression model was constructed using radiomics and clinico-radiological features derived from multi-phase enhanced CT images and conducted external validation. The combined model showed good overall performance, highlighting the feasibility of applying the model for preoperative differentiation and prediction of various types of ACA.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-025-01556-w.

Related collections

Most cited references 22

Record: found
Abstract: found
Article: not found

Management of adrenal incidentalomas: European Society of Endocrinology Clinical Practice Guideline in collaboration with the European Network for the Study of Adrenal Tumors.

Martin Fassnacht, Wiebke Arlt, Irina Bancos … (2016)

: By definition, an adrenal incidentaloma is an asymptomatic adrenal mass detected on imaging not performed for suspected adrenal disease. In most cases, adrenal incidentalomas are nonfunctioning adrenocortical adenomas, but may also represent conditions requiring therapeutic intervention (e.g. adrenocortical carcinoma, pheochromocytoma, hormone-producing adenoma or metastasis). The purpose of this guideline is to provide clinicians with best possible evidence-based recommendations for clinical management of patients with adrenal incidentalomas based on the GRADE (Grading of Recommendations Assessment, Development and Evaluation) system. We predefined four main clinical questions crucial for the management of adrenal incidentaloma patients, addressing these four with systematic literature searches: (A) How to assess risk of malignancy?; (B) How to define and manage low-level autonomous cortisol secretion, formerly called 'subclinical' Cushing's syndrome?; (C) Who should have surgical treatment and how should it be performed?; (D) What follow-up is indicated if the adrenal incidentaloma is not surgically removed? SELECTED RECOMMENDATIONS: (i) At the time of initial detection of an adrenal mass establishing whether the mass is benign or malignant is an important aim to avoid cumbersome and expensive follow-up imaging in those with benign disease. (ii) To exclude cortisol excess, a 1mg overnight dexamethasone suppression test should be performed (applying a cut-off value of serum cortisol ≤50nmol/L (1.8µg/dL)). (iii) For patients without clinical signs of overt Cushing's syndrome but serum cortisol levels post 1mg dexamethasone >138nmol/L (>5µg/dL), we propose the term 'autonomous cortisol secretion'. (iv) All patients with '(possible) autonomous cortisol' secretion should be screened for hypertension and type 2 diabetes mellitus, to ensure these are appropriately treated. (v) Surgical treatment should be considered in an individualized approach in patients with 'autonomous cortisol secretion' who also have comorbidities that are potentially related to cortisol excess. (vi) In principle, the appropriateness of surgical intervention should be guided by the likelihood of malignancy, the presence and degree of hormone excess, age, general health and patient preference. (vii) Surgery is not usually indicated in patients with an asymptomatic, nonfunctioning unilateral adrenal mass and obvious benign features on imaging studies. We provide guidance on which surgical approach should be considered for adrenal masses with radiological findings suspicious of malignancy. Furthermore, we offer recommendations for the follow-up of patients with adrenal incidentaloma who do not undergo adrenal surgery, for those with bilateral incidentalomas, for patients with extra-adrenal malignancy and adrenal masses and for young and elderly patients with adrenal incidentalomas.

0 comments Cited 370 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

The incidental adrenal mass on CT: prevalence of adrenal disease in 1,049 consecutive adrenal masses in patients with no known malignancy.

George W Smith, Haowei Song, Abdul S. Chaudhry (2008)

The purpose of our study was to determine the nature and prevalence of adrenal lesions identified on CT in patients with no known malignancy. A computer search of abdominal CT reports using the term "adrenal" was performed in 65,231 consecutive patients with examinations performed from January 2000 to December 2003. An adrenal mass was identified in 3,307 (5%) patients. Patients with no known malignancy and no suspicion for a hyperfunctioning adrenal mass were further isolated. Nine hundred seventy-three patients with 1,049 adrenal masses fulfilled the study criteria. The nature of each lesion was determined by histopathology; imaging characterization with CT, MRI, or washout; a minimum of 1 year of stability on follow-up imaging; or clinical follow-up of at least 2 years. One thousand forty-nine adrenal masses were characterized with the following methods: histopathology (n = 12), imaging characterization (n = 909), imaging follow-up (n = 87), and clinical follow-up (n = 41). There were 788 adenomas constituting 75% of all lesions. There were 68 myelolipomas (6%), 47 hematomas (4%), and 13 cysts (1%). Three pheochromocytomas (0.3%) and one cortisol-producing adenoma (0.1%) were found incidentally. One hundred twenty-eight lesions (12%) were presumed to be benign by imaging or clinical stability. No malignant adrenal masses were found, even among the 14 patients who later developed malignancy elsewhere. In 973 consecutive patients with an incidental adrenal mass and no history of cancer, no malignant lesions were identified. Adenomas (75%) and myelolipomas (6%) were the most common lesions.

0 comments Cited 98 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: found

Is Open Access

European Society of Endocrinology Clinical Practice Guidelines on the management of adrenal incidentalomas, in collaboration with the European Network for the Study of Adrenal Tumors

Martin Fassnacht, Stylianos Tsagarakis, Massimo Terzolo … (2023)

Adrenal incidentalomas are adrenal masses detected on imaging performed for reasons other than suspected adrenal disease. In most cases, adrenal incidentalomas are non-functioning adrenocortical adenomas, but may also require therapeutic intervention including that for adrenocortical carcinoma, pheochromocytoma, hormone-producing adenoma or metastases. Here, we provide a revision of the first international, interdisciplinary guidelines on incidentalomas. We followed the GRADE (Grading of Recommendations Assessment, Development and Evaluation) system and updated systematic reviews on four predefined clinical questions crucial for the management of incidentalomas: A) How to assess risk of malignancy? ; B) How to define and manage mild autonomous cortisol secretion? ; C) Who should have surgical treatment and how should it be performed? ; D) What follow-up is indicated if the adrenal incidentaloma is not surgically removed? Selected Recommendations: 1) Each adrenal mass requires dedicated adrenal imaging. Recent advances now allow discrimination between risk categories: Homogeneous lesions with HU ≤ 10 on unenhanced CT are benign and do not require any additional imaging independent of size. All other patients should be discussed in a multidisciplinary expert meeting, but only lesions >4 cm that are inhomogeneous or have HU >20 have sufficiently high risk of malignancy that surgery will be the usual management of choice. 2) Every patient needs a thorough clinical and endocrine work-up to exclude hormone excess including the measurement of plasma or urinary metanephrines and a 1-mg overnight dexamethasone suppression test (applying a cutoff value of serum cortisol ≤50 nmol/l (≤1.8 µg/dl)). Recent studies have provided evidence that most patients without clinical signs of overt Cushing's syndrome but serum cortisol levels post dexamethasone >50 nmol/l (>1.8 µg/dl) harbor increased risk of morbidity and mortality. For this condition, we propose the term ‘mild autonomous cortisol secretion’ (MACS). 3) All patients with MACS should be screened for potential cortisol-related comorbidities that are potentially attributably to cortisol (e.g. hypertension and type 2 diabetes mellitus), to ensure these are appropriately treated. 4) In patients with MACS who also have relevant comorbidities surgical treatment should be considered in an individualized approach. 5) The appropriateness of surgical intervention should be guided by the likelihood of malignancy, the presence and degree of hormone excess, age, general health and patient preference. We provide guidance on which surgical approach should be considered for adrenal masses with radiological findings suspicious of malignancy. 6) Surgery is not usually indicated in patients with an asymptomatic, non-functioning unilateral adrenal mass and obvious benign features on imaging studies. Furthermore, we offer recommendations for the follow-up of non-operated patients, management of patients with bilateral incidentalomas, for patients with extra-adrenal malignancy and adrenal masses, and for young and elderly patients with adrenal incidentalomas. Finally, we suggest ten important research questions for the future.

0 comments Cited 96 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Contributors

Maolin Yang: 77052400@qq.com

Wei Li: lw13908701155@163.com

Junfeng Wang: 18987173605@qq.com

Journal

Journal ID (nlm-ta): BMC Med Imaging

Journal ID (iso-abbrev): BMC Med Imaging

Title: BMC Medical Imaging

Publisher: BioMed Central (London )

ISSN (Electronic): 1471-2342

Publication date (Electronic): 10 February 2025

Publication date PMC-release: 10 February 2025

Publication date Collection: 2025

Volume: 25

Electronic Location Identifier: 45

Affiliations

[1 ]Research Center of Digital Medicine, The First People’s Hospital of Yunnan Province, ( https://ror.org/00c099g34) Kunming, Yunnan 650032 China

[2 ]The Affiliated Hospital of Kunming University of Science and Technology, ( https://ror.org/00xyeez13) Kunming, Yunnan 650032 China

[3 ]Department of Urology, The First People’s Hospital of Yunnan Province, ( https://ror.org/00c099g34) Kunming, Yunnan 650032 China

[4 ]Medical School, Kunming University of Science and Technology, ( https://ror.org/00xyeez13) Kunming, Yunnan 650500 China

[5 ]GRID grid.517582.c, ISNI 0000 0004 7475 8949, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, ; Kunming, Yunnan 650118 China

[6 ]Second Affiliated Hospital of Kunming Medical University, ( https://ror.org/01kq6mv68) Kunming, Yunnan 650106 China

[7 ]Kunming Medical University, ( https://ror.org/038c3w259) Kunming, 650500 Yunnan China

[8 ]Department of Hepatobiliary Surgery, The First People’s Hospital of Yunnan Province, ( https://ror.org/00c099g34) Kunming, Yunnan 650032 China

[9 ]Department of Research & Development, Yizhun Medical AI Co. Ltd, Beijing, 100086 China

[10 ]School of Data Science, Fudan University, ( https://ror.org/013q1eq08) Shanghai, 200062 China

[11 ]School of Clinical Medicine, Dali University, ( https://ror.org/02y7rck89) Dali, 671003 Yunnan China

Article

Publisher ID: 1556

DOI: 10.1186/s12880-025-01556-w

PMC ID: 11812231

PubMed ID: 39930366

SO-VID: fa96bb87-d14b-477a-b145-3522b3213d23

License:

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

History

Date received : 1 November 2024

Date accepted : 8 January 2025

Funding

Funded by: Medical leading talents Project in Yunnan Province

Award ID: L-2019016

Funded by: Yunnan Province High-level personnel training support Program famous Medical Project

Award ID: YNWR-MY-2020-035

Custom metadata

ScienceOpen disciplines: Radiology & Imaging

Keywords: adrenocortical adenomas,radiomics,computed tomography,prediction model

Data availability:

ScienceOpen disciplines: Radiology & Imaging

Keywords: adrenocortical adenomas, radiomics, computed tomography, prediction model

Comments

Comment on this article

scite_

Smart Citations

Citing PublicationsSupportingMentioningContrasting

View Citations

See how this article has been cited at scite.ai

scite shows how a scientific paper has been cited by providing the context of the citation, a classification describing whether it supports, mentions, or contrasts the cited claim, and a label indicating in which section the citation was made.

Most referenced authors 308

See all reference authors

Differentiation of multiple adrenal adenoma subtypes based on a radiomics and clinico-radiological model: a dual-center study

Read this article at

Abstract

Background

Methods

Results

Conclusions

Supplementary Information

Related collections

Chinese Journal of Radiological Health

Most cited references 22

Management of adrenal incidentalomas: European Society of Endocrinology Clinical Practice Guideline in collaboration with the European Network for the Study of Adrenal Tumors.

The incidental adrenal mass on CT: prevalence of adrenal disease in 1,049 consecutive adrenal masses in patients with no known malignancy.

European Society of Endocrinology Clinical Practice Guidelines on the management of adrenal incidentalomas, in collaboration with the European Network for the Study of Adrenal Tumors

Author and article information

Contributors

Journal

Affiliations

Article

History

Funding

Categories

Custom metadata

Comments

Comment on this article

Similar content 128

Most referenced authors 308