REVIEW
Check for updates
A comprehensive approach to the CT detection and evaluation of large adrenal masses part 2: malignant adrenal lesions and future directions
Hajra Arshad1 . Satomi Kawamoto1 . Linda C. Chu1 . Elliot K. Fishman1
Received: 23 July 2025 / Revised: 4 September 2025 / Accepted: 23 September 2025 @ The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025
Abstract
Large adrenal tumors have traditionally been associated with high risk of malignancy; however, recent studies challenge this assumption, highlighting that a significant proportion of large adrenal lesions are benign. With increasing detection of incidental adrenal lesions, there remains a clinical dilemma in their appropriate management. Malignant adrenal lesions include adrenal cortical carcinoma, lymphoma, metastasis, and rare tumors such as adrenal sarcomas. These often exhibit overlapping imaging features with benign lesions, complicating treatment planning. Therefore, accurate radiologic charac- terization, supported by clinical and laboratory correlation, is essential to avoid unnecessary surgical interventions while ensuring timely identification of aggressive pathology. This part two of the two-part pictorial essay focuses on the CT evaluation of malignant adrenal lesions with an emphasis on key imaging features and differential diagnosis.
Keywords Adrenal gland neoplasm · Adrenocortical carcinoma · Pheochromocytoma . Lymphoma · Adrenal metastasis · Computed tomography
Introduction
With increased detection of adrenal incidentalomas on cross-sectional imaging, their management remains a clini- cal dilemma. The role of biopsy remains controversial in adrenal evaluation due to risk of needle track seeding and capsule rupture, and it is often non-discriminatory in dis- tinguishing between adrenal cortical adenoma (ACA) and adrenal cortical carcinoma (ACC) [1]. Hormonal evaluation can demonstrate clinical functionality but does not discrimi- nate between benign and malignant tumors effectively. This underscores the need for high diagnostic accuracy based
☒ Hajra Arshad harshad1@jh.edu
Satomi Kawamoto skawamo1@jhmi.edu
Linda C. Chu lchu1@jhmi.edu
Elliot K. Fishman efishman@jhmi.edu
1 Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, USA
on imaging alone, particularly with computed tomography (CT) scans, which remain the most widely used modality. Advanced imaging post-processing techniques including volume rendering (VR) and cinematic rendering (CR) have improved diagnostic accuracy on imaging.
A comprehensive imaging evaluation is essential for distinguishing “leave-alone” lesions from those warranting further evaluation [2]. Adrenal lesions greater than 4 cm are considered large adrenal tumors that were traditionally per- ceived more likely to be malignant [3]. However, emerging literature challenges this assumption, with a recent study reporting that only 31% of all large adrenal tumors were malignant - 13% ACC and 18% other malignant lesions. They also found that non-contrast CT attenuation above 10 HU identified all malignant adrenal lesions (100% sensi- tivity) but had a very low specificity of 46% [3]. Surgical resection is generally recommended for functional and large (>4 cm) adrenal masses [4]. However, some of these surger- ies for resection of benign masses can be potentially avoided if imaging could more accurately differentiate between the benign and malignant masses.
This second part of the two-part manuscript focuses on the CT features of malignant adrenal lesions and highlights future directions, including the use of AI and radiomics that could enhance diagnostic accuracy of adrenal lesions.
Figure 1 highlights the key imaging features of malignant adrenal lesions.
Pheochromocytoma
Pheochromocytoma is a rare neuroendocrine tumor aris- ing from the adrenal medulla. Most of the cases are benign, with only 10-15% being malignant [5]. They generally produce high amounts of catecholamines generating symp- toms of paroxysmal hypertension, headache and palpita- tions; however, 11-21% of patients are asymptomatic [6 They are often described using the 10% rule i.e. 10% are - malignant, bilateral, extra-adrenal, found in children, not associated with hypertension and contain calcifications. As biopsy is not advisable, imaging correlated with clinical and biochemical profile plays a key role in diagnosis. Elevated plasma and 24-hr urinary fractionated metanephrine levels are highly sensitive to the diagnosis. In a study on large adrenal tumors (>4 cm), pheochromocytoma was the sec- ond most common diagnosis after ACA, comprising 22% of the cohort with an average size of 5.2 cm (4-20 cm) and about half of them discovered incidentally [3].
On imaging, pheochromocytomas have a broad spectrum of appearances based on internal architecture, vascularity and size. Classically, they appear as round, hypervascular, heterogeneously enhancing masses. Due to the hypervascu- lar nature, the washout values often overlap with lipid-poor
Pheochromocytoma
· Mostly benign, 10% malignant. Hypervascular with central necrosis. ‘Ring sign’ in cystic pheo
Adrenal Cortical Carcinoma
· Heterogenous enhancement, retain IV contrast with absolute washout <60%
Lymphoma
· Bilateral in 70%. Well-defined, uniform, often with infiltrative pattern of growth
Adrenal Metastasis
· Commonly from lung, kidney, breast, colon, liver and melanoma. Often bilateral
Sarcoma and rare tumors
· Variable appearance based on subtype
adenomas, thus, washout analysis is not reliable to differen- tiate among the two, but venous phase attenuation of >130 HU and arterial phase attenuation of >110 HU strongly suggests pheochromocytoma [7]. As they grow larger, they tend to undergo ischemic and necrotic changes, resulting in central necrosis and heterogenous enhancement on CT, as seen in Fig. 2. Cystic pheochromocytoma is a relatively rare subtype, comprising one-third of all pheochromocytomas, that typically present with a thick wall and a ‘ring sign’ - a hyperenhancing rim of the tumor, helping to differentiate it from other cystic adrenal masses. Sometimes, they may have an infiltrative growth pattern invading the local struc- tures, however, infiltration does not correlate with malig- nancy [8 [8].
All pheochromocytomas are considered to have ‘meta- static potential’. Features suggestive of aggressiveness are large tumor size, extra-adrenal origin, and high levels of cat- echolamines in blood or urine [8]. Although no individual CT feature is specific for malignancy, the presence of distant metastases is the only definitive imaging finding diagnostic for malignant disease. ACC and pheochromocytoma both have heterogenous enhancement pattern, but trace amounts of intracellular lipids can be found in ACC, almost never occurring in pheochromocytomas. It is important to iden- tify and manage pheochromocytomas in a timely fashion to prevent life-threatening multisystem crisis that may occur due to intratumoral hemorrhage or rupture releasing large amounts of catecholamines in the blood [8]. In cases with equivocal imaging and biochemical results and high suspicion of pheochromocytoma, PET/CT with gallium 68- labeled somatostatin analogs (68 Ga-DOTA-NOC, 68 Ga-DOTA-TOC, and 68 Ga-DOTA-TATE) may be utilized for identification, assessment of lesion extent, metastasis and detect therapeutic molecular targets [9].
Adrenal cortical carcinoma
Adrenal Cortical Carcinoma (ACC) is a rare malignant tumor, with an estimated incidence of 0.5 to 2 cases per mil- lion people per year. At diagnosis, 22-35% of ACC patients have distant metastases, with stage IV disease carrying a poor prognosis with a 5-year survival rate of 6-13%, com- pared to 39-50% in stages I-III, highlighting the need for early diagnosis and treatment [10]. It has a bimodal age distribution with peak incidence observed in adults in their fourth to fifth decades of life [11]. Approximately 40-60% of ACCs are functional, most often presenting with Cush- ing’s syndrome, characterized by truncal obesity, diabetes, hypertension, easy bruising and menstrual irregularities. About 25% co-secrete glucocorticoids and androgens, while isolated androgen secretion occurs in roughly 10% of cases
A
B
C
A
[12]. While functional tumors maybe identified by hormonal symptoms, non-functional tumors are often discovered inci- dentally or present with local mass effect. Due to retroperi- toneal location, they tend to grow and present at large sizes, with median diameter of 10.9 cm (range: 4-24.4 cm) [3]. The prevalence of ACC increases significantly with adre- nal mass size. For tumors measuring 4-6 cm, reported ACC rates range from 2.4% to 4.8%, while for those larger than 6 cm, the prevalence rises substantially to 19.5-37.7% [9]. However, in the bigger picture, large size does not always indicate malignancy. A recent study of 705 large adrenal tumors (>4 cm) reported only 31% were malignant, and only 13% of the total cohort were ACC [3].
Due to differences in prognosis and management, it is important to differentiate it from benign ACAs for timely surgical resection. Smaller ACCs are often difficult to dif- ferentiate from adenomas due to their homogenous appear- ance, but unlike adenomas, ACCs rarely have an attenuation of less than 20 HU [9]. As ACCs grow, they tend to undergo cystic, necrotic and hemorrhagic changes, reflecting a heterogeneously enhancing appearance on imaging. On non-contrast CT, they are inhomogeneous, while on con- trast-enhanced CT, heterogenous enhancement pattern with central non-enhancing region due to necrosis or hemorrhage is often seen, with a thin enhancing capsule visible in few cases [9, 13]. Calcification are also seen in 19-33% of cases
[14]. Data on washout kinetics is limited, but it often shows absolute percentage washout (APW)<60% and relative per- centage washout (RPW)<40%. Unfortunately, some ACCs may meet the washout criteria for ACAs. ACC may demon- strate irregular margin with direct extension (as seen in Fig. 3) or tumor thrombus in inferior vena cava and may metas- tasize to liver (most common), lung and lymph nodes [14]. Although ACCs do not have macroscopic or microscopic fat, the real challenge arises when differentiating them from lipid-poor ACAs. As adrenal biopsy is not recommended, high diagnostic confidence on imaging is necessary to guide management. Yalon et al. developed a nine-variable CT scoring system for differentiating ACC from lipid-poor ACA, with a 100% negative predictive value and an AUC of 0.974, including attenuation>10 HU, heterogeneity, size>4 cm, lymph node prominence, peritumoral fat infil- tration, necrosis, and a thick peripheral enhancement with central hypodensity. In contrast, peripheral septal enhance- ment and calcifications were associated with benign lesions. This combined approach demonstrated that, while no single feature or large size is definitive, their integration signifi- cantly improves preoperative differentiation between ACC and lipid-poor ACA [15].
-
11.82 cm
A
B
C
D
E
Primary adrenal lymphoma
Primary adrenal lymphoma (PAL) accounts for ~1% of all non-Hodgkin’s lymphomas with very few reported cases in the literature. PAL classically occurs bilaterally with only 30% unilateral presentation [16]. PAL typically presents with classic ‘B symptoms’ - fever, fatigue, night sweats, and weight loss, along with abdominal pain [17]. Adrenal insufficiency is observed in up to 61% of patients, particu- larly in cases with bilateral involvement. Unlike most adre- nal masses, PAL is rarely detected incidentally, with only 1-7% of cases identified without symptoms, reflecting its aggressive behavior and highly symptomatic nature [18]. It is generally a large tumor with reported median size of 8 cm (range: 5.7-10.7 cm) [18]. Generally, a large tumor
is presumed as ACC and rarer tumors like PAL are often not considered. However, clinical and imaging features that tend to favor PAL over ACC include B symptoms, bilater- ality, hepatosplenomegaly, lymphadenopathy, and Epstein- Barr virus (EBV) positivity, which is also observed in half of the patients.
Over the years, it has been seen that adrenal lymphoma can have a wide range of appearances on imaging. While secondary adrenal lymphoma appears as well-defined homogenous mass with soft tissue density and contrast enhancement, primary lymphoma in the adrenal gland has a variety of image appearances without specific features. These lesions may appear as complex cystic masses with internal fluid content or may be entirely homogenous. Clas- sically, PALs demonstrate mild to moderate enhancement
following contrast administration, but poorly enhancing lesions have also been seen [18, 19]. Although they demon- strate an infiltrative growth pattern, they typically preserve the gland’s characteristic ‘adreniform’ shape. In a retrospec- tive review of 28 patients with PAL, high FDG uptake was seen on PET/CT, with a median standardized uptake value (SUV) of 17.24 (range 9.5-48), which was higher in bilat- eral PAL (median SUV=19), compared to unilateral PAL (median SUV=9.5) [20]. Due to low diagnostic confidence on CT images, advanced visualization techniques using cin- ematic rendering have been shown to augment visualization of internal heterogeneity and cystic components [16]. Fig- ure 4 describes two cases of primary adrenal lymphoma. In summary, it is crucial to differentiate large PAL from ACC
on imaging, as biopsy is contraindicated and urgent surgery is required for ACC, whereas PAL requires and safely allows biopsy for diagnosis and prompt chemotherapy, avoiding unnecessary surgery.
Metastasis to the adrenal gland
A wide range of malignancies metastasize to the adrenal glands commonly including basal cell carcinoma, lung cancer, breast cancer, cervical cancer, pancreato-biliary tumors, gastrointestinal tumors (Fig. 5), contralateral ACC, renal cell carcinoma, etc. [21]. They pose a diagnostic chal- lenge when identified incidentally in a patient with a known
A
B
A
C
D
E
F
A
B
A
B
primary malignancy. It is one of the few scenarios where tis- sue sampling is considered appropriate to evaluate the adre- nal lesion, however, metabolic workup should be performed before biopsy to identify any functional activity from the lesion, and to avoid a catecholamine crisis in cases such as pheochromocytoma [21]. Adrenal metastasis is bilateral in 49% of the cases [22]. It is important to recognize anatomi- cal variations of the normal adrenal gland, such as hyper- trophied or nodular limbs, which may correlate with patient age, to avoid misinterpreting them as metastatic lesions, particularly in patients with known primary malignancies [14]. On imaging, they may be hyper- or hypo- vascular depending on the primary tumor. They usually demon- strate a lower washout on delayed imaging (APW<60% and RPW<40%) as compared to adenoma [14]. However, hypervascular metastases particularly from renal cell carci- noma and hepatocellular carcinoma may fulfill washout cri- teria for ACA, representing a potential diagnostic pitfall. In suspected cases of metastasis, it is essential to review prior imaging studies to compare adrenal shape and lesions and assess their timeline of onset and growth.
Rare malignant adrenal tumors
Rare malignant tumors include epithelioid angiosarcoma, pleomorphic sarcoma, leiomyosarcoma, primary malignant melanoma and adrenal cortical carcinosarcoma. For these rare tumors, definitive diagnosis requires histological con- firmation via surgical resection, which is both diagnostic and therapeutic. Sarcomas of the adrenal gland are exceed- ingly rare with limited published literature. Among adult soft-tissue sarcomas, the most common histological sub- types include undifferentiated pleomorphic sarcoma, lipo- sarcoma and leiomyosarcoma. Imaging features vary based on the composition of fat, soft tissue and myxoid elements within the tumor [23]. Figure 6 shows a case of a rare epi- thelioid angiosarcoma with a heterogeneously enhancing appearance and internal vascularity.
Future directions
Artificial intelligence (AI) and radiomics have been explored for adrenal lesion detection, segmentation, charac- terization and predicting treatment response [24]. Utilizing CT based radiomics features, several studies have reported promising results in lipid-poor ACA characterization and differentiation from pheochromocytoma, malignant lesion
and metastasis from lung cancer [25-28]. However, there is limited literature on its utility for ACCs [24]. Although cur- rent research is still in the preliminary stages, AI holds great potential to help clinicians in characterization and treatment planning for adrenal lesions. It may play a valuable role in addressing the rising detection of adrenal incidentalomas and the associated clinical challenges in their management. Combining CT-based imaging features with clinical and laboratory data to build explainable AI models could be a promising direction for future research for adrenal lesion characterization and prognostication. The efficacy of AI extends beyond images, as AI-based automatic detection of adrenal incidentalomas on radiology reports has shown an AUC of 0.95 [29]. Natural language processing (NLP) based approaches have also shown to improve guideline- based management in incidental adrenal lesions [30].
Conclusion
Large adrenal lesions (>4 cm) are not always malignant, as tumor size alone does not reliably predict malignancy and benign etiologies must be considered. A multidisciplinary evaluation integrating imaging characteristics, clinical assessment and laboratory values is required for accurately distinguishing between benign and malignant adrenal lesions. This facilitates timely resection for malignant adre- nal lesions and surveillance decision on benign lesions. However, there is a need for standardized guidelines to bridge the gap between increased detection of adrenal inci- dentalomas and management planning. In the future, AI and radiomics hold the potential for assisting clinicians with adrenal lesion characterization, treatment planning and prognostication.
Author contributions H.A .: conceptualization, writing-original draft, reviewing and editing. E.F .: conceptualization, writing- review- ing and editing, supervision. S.K .: conceptualization, writing-re- viewing and editing. L.C .: conceptualization, writing- reviewing and editing.
Data availability No datasets were generated or analysed during the current study.
Declarations
Competing interests The authors declare no competing interests.
References
1. Bancos I, Tamhane S, Shah M, Delivanis DA, Alahdab F, Arlt W, et al. DIAGNOSIS OF ENDOCRINE DISEASE: The diag- nostic performance of adrenal biopsy: a systematic review and
meta-analysis. Eur J Endocrinol. 2016;175(2):R65-80. doi: https ://doi.org/10.1530/EJE-16-0297.
2. Johnson PT, Horton KM, Fishman EK. Adrenal imaging with MDCT: Nonneoplastic disease. AJR Am J Roentgenol. 2009;193(4):1128-35. doi: https://doi.org/10.2214/AJR.09.2551.
3. Iniguez-Ariza NM, Kohlenberg JD, Delivanis DA, Hartman RP, Dean DS, Thomas MA, et al. Clinical, Biochemical, and Radio- logical Characteristics of a Single-Center Retrospective Cohort of 705 Large Adrenal Tumors. Mayo Clin Proc Innov Qual Out- comes. 2018;2(1):30-9. doi: https://doi.org/10.1016/j.mayocpiqo .2017.11.002.
4. Owei L, Wachtel H. The Landmark Series: Evaluation and Man- agement of Adrenal Incidentalomas. Ann Surg Oncol. 2025. doi: https://doi.org/10.1245/s10434-025-17296-8.
5. Reisch N, Peczkowska M, Januszewicz A, Neumann HP. Pheo- chromocytoma: presentation, diagnosis and treatment. J Hyper- tens. 2006;24(12):2331-9. doi: https://doi.org/10.1097/01.hjh.00 00251887.01885.54.
6. Kopetschke R, Slisko M, Kilisli A, Tuschy U, Wallaschofski H, Fassnacht M, et al. Frequent incidental discovery of phaeochro- mocytoma: data from a German cohort of 201 phaeochromocy- toma. Eur J Endocrinol. 2009;161(2):355-61. doi: https://doi.org /10.1530/EJE-09-0384.
7. Northcutt BG, Raman SP, Long C, Oshmyansky AR, Siegelman SS, Fishman EK, et al. MDCT of adrenal masses: Can dual-phase enhancement patterns be used to differentiate adenoma and pheo- chromocytoma? AJR Am J Roentgenol. 2013;201(4):834-9. doi: https://doi.org/10.2214/AJR.12.9753.
8. Berry R, Busireddy K, Chu LC, Johnson PT, Fishman EK. The good, the bad, and the ugly: uncommon CT appearances of pheo- chromocytoma. Abdom Radiol (NY). 2022;47(4):1406-13. doi: h ttps://doi.org/10.1007/s00261-022-03447-y.
9. Chung R, Garratt J, Remer EM, Navin P, Blake MA, Taffel MT, et al. Adrenal Neoplasms: Lessons from Adrenal Multidisciplinary Tumor Boards. Radiographics. 2023;43(7):e220191. doi: https:// doi.org/10.1148/rg.220191.
10. Yip L, Duh QY, Wachtel H, Jimenez C, Sturgeon C, Lee C, et al. American Association of Endocrine Surgeons Guide- lines for Adrenalectomy: Executive Summary. JAMA Surg. 2022;157(10):870-7. doi: https://doi.org/10.1001/jamasurg.2022 .3544.
11. Bharwani N, Rockall AG, Sahdev A, Gueorguiev M, Drake W, Grossman AB, et al. Adrenocortical carcinoma: the range of appearances on CT and MRI. AJR Am J Roentgenol. 2011;196(6):W706-14. doi: https://doi.org/10.2214/AJR.10.554 0.
12. Sherlock M, Scarsbrook A, Abbas A, Fraser S, Limumporn- petch P, Dineen R, et al. Adrenal Incidentaloma. Endocr Rev. 2020;41(6):775-820. doi: https://doi.org/10.1210/endrev/bnaa00 8.
13. Fishman EK, Deutch BM, Hartman DS, Goldman SM, Zer- houni EA, Siegelman SS. Primary adrenocortical carcinoma: CT evaluation with clinical correlation. AJR Am J Roentgenol. 1987;148(3):531-5. doi: https://doi.org/10.2214/ajr.148.3.531.
14. Johnson PT, Horton KM, Fishman EK. Adrenal mass imaging with multidetector CT: pathologic conditions, pearls, and pitfalls. Radiographics. 2009;29(5):1333-51. doi: https://doi.org/10.1148 /rg.295095027.
15. Yalon T, Yalon M, Assaf D, Lenartowicz K, Foster T, Lyden M, et al. Differentiating between adrenocortical carcinoma and lipid- poor cortical adenoma: A novel cross-sectional imaging-based score. Surgery. 2023;173(1):35-42. doi: https://doi.org/10.1016/ j.surg.2022.07.029.
16. Ahmed TM, Fishman EK, Morris-Wiseman LF, Baraban E, Chu LC. Cinematic rendering of primary adrenal lymphoma. Curr
Probl Diagn Radiol. 2024;53(5):641-7. doi: https://doi.org/10.1 067/j.cpradiol.2024.05.005.
17. Majidi F, Martino S, Kondakci M, Antke C, Haase M, Chortis V, et al. Clinical spectrum of primary adrenal lymphoma: results of a multicenter cohort study. Eur J Endocrinol. 2020;183(4):453-62. doi: https://doi.org/10.1530/EJE-19-0506.
18. Rashidi A, Fisher SI. Primary adrenal lymphoma: a systematic review. Ann Hematol. 2013;92(12):1583-93. doi: https://doi.org/ 10.1007/s00277-013-1812-3.
19. Wang Y, Ren Y, Ma L, Li J, Zhu Y, Zhao L, et al. Clinical Features of 50 Patients With Primary Adrenal Lymphoma. Front Endocri- nol (Lausanne). 2020;11:595. doi: https://doi.org/10.3389/fendo. 2020.00595.
20. Laurent C, Casasnovas O, Martin L, Chauchet A, Ghesquieres H, Aussedat G, et al. Adrenal lymphoma: presentation, management and prognosis. QJM. 2017;110(2):103-9. doi: https://doi.org/10. 1093/qjmed/hcw174.
21. Leonard S, Smaldone MC. Rare Adrenal Tumors and Adrenal Metastasis. Urol Clin North Am. 2025;52(2):287-96. doi: https:// doi.org/10.1016/j.ucl.2025.01.010.
22. Lam KY, Lo CY. Metastatic tumours of the adrenal glands: a 30-year experience in a teaching hospital. Clin Endocrinol (Oxf). 2002;56(1):95-101. doi: https://doi.org/10.1046/j.0300-0664.200 1.01435.x.
23. Ahmed TM, Rowe SP, Fishman EK, Soyer P, Chu LC. Three- dimensional CT cinematic rendering of adrenal masses: Role in tumor analysis and management. Diagn Interv Imaging. 2024;105(1):5-14. doi: https://doi.org/10.1016/j.diii.2023.09.00 4.
24. Barat M, Gaillard M, Cottereau AS, Fishman EK, Assie G, Jouinot A, et al. Artificial intelligence in adrenal imaging: A critical review of current applications. Diagn Interv Imaging. 2023;104(1):37-42. doi: https://doi.org/10.1016/j.diii.2022.09.0 03.
25. Jhaveri KS, Lad SV, Haider MA. Computed tomographic histo- gram analysis in the diagnosis of lipid-poor adenomas: compari- son to adrenal washout computed tomography. J Comput Assist
Tomogr. 2007;31(4):513-8. doi: https://doi.org/10.1097/01.rct.00 00250105.93423.a2.
26. Yi X, Guan X, Chen C, Zhang Y, Zhang Z, Li M, et al. Adrenal incidentaloma: machine learning-based quantitative texture anal- ysis of unenhanced CT can effectively differentiate sPHEO from lipid-poor adrenal adenoma. J Cancer. 2018;9(19):3577-82. doi: https://doi.org/10.7150/jca.26356.
27. Ho LM, Samei E, Mazurowski MA, Zheng Y, Allen BC, Nelson RC, et al. Can Texture Analysis Be Used to Distinguish Benign From Malignant Adrenal Nodules on Unenhanced CT, Contrast- Enhanced CT, or In-Phase and Opposed-Phase MRI? AJR Am J Roentgenol. 2019;212(3):554-61. doi: https://doi.org/10.2214/A JR. 18.20097.
28. Tu W, Verma R, Krishna S, McInnes MDF, Flood TA, Schieda N. Can Adrenal Adenomas Be Differentiated From Adrenal Metas- tases at Single-Phase Contrast-Enhanced CT? AJR Am J Roent- genol. 2018;211(5):1044-50. doi: https://doi.org/10.2214/AJR.1 7.19276.
29. Canton SP, Dadashzadeh E, Yip L, Forsythe R, Handzel R. Auto- matic Detection of Thyroid and Adrenal Incidentals Using Radiol- ogy Reports and Deep Learning. J Surg Res. 2021;266:192-200. doi: https://doi.org/10.1016/j.jss.2021.03.060.
30. Frye CC, Akhund R, Murcy M, Veazey LG, McLeod MC, Osborne JD, et al. A natural language processing-informed adre- nal gland incidentaloma clinic improves guideline-based care. World J Surg. 2024;48(12):2907-17. doi: https://doi.org/10.100 2/wjs.12346.
Publisher’s note Springer Nature remains neutral with regard to juris- dictional claims in published maps and institutional affiliations.
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.