18F-FDG-PET/CT-based machine learning model evaluates indeterminate adrenal nodules in patients with extra-adrenal malignancies

BACKGROUND

To assess the value of an 18F-FDG-positron emission tomography/computed tomography (PET/CT)-based machine learning model for distinguishing between adrenal benign nodules (ABNs) and adrenal metastases (AMs) in patients with indeterminate adrenal nodules and extra-adrenal malignancies.

METHODS

A total of 303 patients who underwent 18F-FDG-PET/CT with indeterminate adrenal nodules and extra-adrenal malignancies from March 2015 to June 2021 were included in this retrospective study (training dataset (n = 182): AMs (n = 97), ABNs (n = 85); testing dataset (n = 121): AMs (n = 68), ABNs (n = 55)). The clinical and PET/CT imaging features of the two groups were analyzed. The predictive model and simplified scoring system for distinguishing between AMs and ABNs were built based on clinical and PET/CT risk factors using multivariable logistic regression in the training cohort. The performances of the predictive model and simplified scoring system in both the training and testing cohorts were evaluated by the areas under the receiver operating characteristic curves (AUCs) and calibration curves. The comparison of AUCs was evaluated by the DeLong test.

RESULTS

The predictive model included four risk factors: sex, the ratio of the maximum standardized uptake value (SUVmax) of adrenal lesions to the mean liver standardized uptake value, the value on unenhanced CT (CTU), and the clinical stage of extra-adrenal malignancies. The model achieved an AUC of 0.936 with a specificity, sensitivity and accuracy of 0.918, 0.835, and 0.874 in the training dataset, respectively, while it yielded an AUC of 0.931 with a specificity, sensitivity, and accuracy of 1.00, 0.735, and 0.851 in the testing dataset, respectively. The simplified scoring system had comparable diagnostic value to the predictive model in both the training (AUC 0.938, sensitivity: 0.825, specificity 0.953, accuracy 0.885; P = 0.5733) and testing (AUC 0.931, sensitivity 0.735, specificity 1.000, accuracy 0.851; P = 1.00) datasets.

CONCLUSIONS

Our study showed the potential ability of a machine learning model and a simplified scoring system based on clinical and 18F-FDG-PET/CT imaging features to predict AMs in patients with indeterminate adrenal nodules and extra-adrenal malignancies. The simplified scoring system is simple, convenient, and easy to popularize.

Natural Language Processing of Computed Tomography Reports to Label Metastatic Phenotypes With Prognostic Significance in Patients With Colorectal Cancer

PURPOSE

Natural language processing (NLP) applied to radiology reports can help identify clinically relevant M1 subcategories of patients with colorectal cancer (CRC). The primary purpose was to compare the overall survival (OS) of CRC according to American Joint Committee on Cancer TNM staging and explore an alternative classification. The secondary objective was to estimate the frequency of metastasis for each organ.

METHODS

Retrospective study of CRC who underwent computed tomography (CT) chest, abdomen, and pelvis between July 1, 2009, and March 26, 2019, at a tertiary cancer center, previously labeled for the presence or absence of metastasis by an NLP prediction model. Patients were classified in M0, M1a, M1b, and M1c (American Joint Committee on Cancer), or an alternative classification on the basis of the metastasis organ number: M1, single; M2, two; M3, three or more organs. Cox regression models were used to estimate hazard ratios; Kaplan-Meier curves were used to visualize survival curves using the two M1 subclassifications.

RESULTS

Nine thousand nine hundred twenty-eight patients with a total of 48,408 CT chest, abdomen, and pelvis reports were included. On the basis of NLP prediction, the median OS of M1a, M1b, and M1c was 4.47, 1.72, and 1.52 years, respectively. The median OS of M1, M2, and M3 was 4.24, 2.05, and 1.04 years, respectively. Metastases occurred most often in liver (35.8%), abdominopelvic lymph nodes (32.9%), lungs (29.3%), peritoneum (22.0%), thoracic nodes (19.9%), bones (9.2%), and pelvic organs (7.5%). Spleen and adrenal metastases occurred in < 5%.

CONCLUSION

NLP applied to a large radiology report database can identify clinically relevant metastatic phenotypes and be used to investigate new M1 substaging for CRC. Patients with three or more metastatic disease organs have the worst prognosis, with an OS of 1 year.

Diagnostic Accuracy of CT Texture Analysis in Adrenal Masses: A Systematic Review

Adrenal incidentalomas (AIs) are incidentally discovered adrenal neoplasms. Overt endocrine secretion (glucocorticoids, mineralocorticoids, and catecholamines) and malignancy (primary or metastatic disease) are assessed at baseline evaluation. Size, lipid content, and washout characterise benign AIs (respectively, <4 cm, <10 Hounsfield unit, and rapid release); nonetheless, 30% of adrenal lesions are not correctly indicated. Recently, image-based texture analysis from computed tomography (CT) may be useful to assess the behaviour of indeterminate adrenal lesions. We performed a systematic review to provide the state-of-the-art of texture analysis in patients with AI. We considered 9 papers (from 70 selected), with a median of 125 patients (range 20–356). Histological confirmation was the most used criteria to differentiate benign from the malignant adrenal mass. Unenhanced or contrast-enhanced data were available in all papers; TexRAD and PyRadiomics were the most used software. Four papers analysed the whole volume, and five considered a region of interest. Different texture features were reported, considering first- and second-order statistics. The pooled median area under the ROC curve in all studies was 0.85, depicting a high diagnostic accuracy, up to 93% in differentiating adrenal adenoma from adrenocortical carcinomas. Despite heterogeneous methodology, texture analysis is a promising diagnostic tool in the first assessment of patients with adrenal lesions.

The prevalence and spectrum of reported incidental adrenal abnormalities in abdominal computed tomography of cancer patients: The experience of a comprehensive cancer center

BACKGROUND

The increasing use of computed tomography (CT) has identified many patients with incidental adrenal lesions. Further evaluation of these lesions is often dependent on the language used in the radiology report. Compared to the general population, patients with cancer have a higher risk for adrenal abnormalities, yet data on the prevalence and type of incidental adrenal lesions reported on radiologic reports in cancer patients is limited. In this study, we aimed to determine the prevalence and nature of adrenal abnormalities as an incidental finding reported on radiology reports of cancer patients evaluated for reasons other than suspected adrenal pathology.

METHODS

Radiology reports of patients who underwent abdominal CT within 30 days of presentation to a tertiary cancer center were reviewed and analyzed. We used natural language processing to perform a multi-class text classification of the adrenal reports. Patients who had CT for suspected adrenal mass including adrenal protocol CT were excluded. Three independent abstractors manually reviewed abnormal and questionable results, and we measured the interobserver agreement.

RESULTS

From June 1, 2006, to October 1, 2017, a total of 600,399 abdominal CT scans were performed including 66,478 scans obtained within 30 days of the patient's first presentation. Of these, 58,512 were eligible after applying the exclusion criteria. Adrenal abnormalities were identified in 7,817 (13.4%) reports, with adrenal nodularity (3,401 [43.5%]), adenomas (1,733 [22.2%]), and metastases (1,337 [17.1%]) being the most reported categories. Only 10 cases (0.1%) were reported as primary adrenal carcinomas and 2 as pheochromocytoma. Interobserver agreement using 300 reports yielded a Fleiss kappa of 0.893, implying almost perfect agreement between the abstractors.

CONCLUSIONS

Incidental adrenal abnormalities are commonly reported in abdominal CT reports of cancer patients. As the terminology used by radiologists to describe these findings greatly determine the subsequent management plans, further studies are needed to correlate some of these findings to the actual confirmed diagnosis based on hormonal, histological and follow-up data and ascertain the impact of such reported findings on patients' outcomes.

Distinguishing between metastatic and benign adrenal masses in patients with extra-adrenal malignancies

BACKGROUND AND OBJECTIVES

The adrenal gland is a common organ involved in metastasis. This study aimed to compare adrenal metastases (AMs) and adrenal benign masses (ABMs) of patients with extra-adrenal malignancies during the staging or follow-up.

METHODS

We retrospectively collected data from 120 patients with AMs and 87 patients with ABMs. The clinical characteristics, imaging features, pathology, and treatment regimes were analyzed.

RESULTS

The most common types of extra-adrenal malignancies in patients with ABMs included thyroid, kidney, and gynecological cancers. On the other hand, lung and kidney cancers and lymphoma were the most frequent primary cancers of AMs. The age and incidence of symptoms were significantly higher in patients with AM. Radiological analysis showed that AMs tended to have larger tumor sizes and higher attenuation values than ABMs on pre-contrast computed tomography (CT). The diagnostic accuracy of positron emission tomography-CT for AM was 94.1%. An adrenal biopsy had a diagnostic accuracy of 92.5%. A multivariate logistic regression model demonstrated that the origins of extra-adrenal malignancies, the enhancement pattern, and attenuation values in pre-contrast CT were independent predictors of AMs. The sensitivity and specificity of this predictive model of combination was 92.5% and 74.1%, respectively.

CONCLUSIONS

The differential diagnosis between AMs and ABMs is extremely important. The combination of origin of first malignancy, enhancement pattern and CT value in non-enhanced phase is a valuable model for predicting AMs.

Frequently asked questions and answers (if any) in patients with adrenal incidentaloma

PURPOSE

Adrenal incidentalomas (AIs) are incidentally discovered adrenal masses, during an imaging study undertaken for other reasons than the suspicion of adrenal disease. Their management is not a minor concern for patients and health-care related costs, since their increasing prevalence in the aging population. The exclusion of malignancy is the first question to attempt, then a careful evaluation of adrenal hormones is suggested. Surgery should be considered in case of overt secretion (primary aldosteronism, adrenal Cushing's Syndrome or pheochromocytoma), however the management of subclinical secretion is still a matter of debate.

METHODS

The aim of the present narrative review is to offer a practical guidance regarding the management of AI, by providing evidence-based answers to frequently asked questions.

CONCLUSION

The clinical experience is of utmost importance: a personalized diagnostic-therapeutic approach, based upon multidisciplinary discussion, is suggested.

A multidisciplinary approach to the management of adrenal incidentaloma

An adrenal incidentaloma (AI) is an adrenal neoplasm incidentally discovered during an imaging unrelated to suspected adrenal disease. The aim of the present review is to offer practical guidance on the multidisciplinary approach of AIs.Areas covered:The prevalence of AI is high in the aging population (up to 5-8%); however, hormonally active or malignant conditions are rare. After the discovery of an AI, it is suggested to assess in parallel if the mass is potentially malignant and functionally active. The answer to the former question is mainly based on medical history (extra-adrenal malignancies, new-onset of signs or symptoms) and imaging (conventional radiology and/or nuclear medicine). The answer to the latter question is a complete endocrine evaluation of both cortical (glucocorticoids, mineralocorticoids) and medullary (catecholamines) secretion.Expert opinion:A multidisciplinary discussion is suggested for patients with adrenal disease, after the exclusion of nonfunctioning benign cortical adenoma, in order to plan a close and tailored follow-up for the suspected malignant or functioning forms. Surgery is advised for patients with malignant disease (adrenocortical cancer) or with clinically relevant secreting neoplasm (primary aldosteronism, Cushing's syndrome, and pheochromocytoma).

Adrenal Tumors Found During Staging and Surveillance for Colorectal Cancer: Benign Incidentalomas or Metastatic Disease?

OBJECTIVE

To evaluate the incidence of adrenal metastases in patient with colorectal cancer (CRC) and determine the clinical and radiographic features associated metastatic CRC to the adrenal glands.

MATERIALS AND METHODS

The review of consecutive adults with newly diagnosed CRC found to have adrenal tumors > 1 cm in size on staging or surveillance CT scans with at least two scans to evaluate progression or stability of disease.

RESULTS

Fifty-eight of 856 (6.8%) CRC patients had an adrenal tumor. Forty-three patients (74%) with 46 adrenal tumors had benign adrenal tumors, and 15 (26%) patients with 17 adrenal tumors had metastatic disease. On univariate analysis, patients with metastatic CRC had larger adrenal tumors (26.7 mm vs 12.4 mm, p < 0.01), a higher mean CEA (239 ng/mL vs 14.2 ng/mL, p = 0.03), and were more likely to have other sites of metastatic disease seen on imaging 8/43 (19%) vs 14/15 (93%), p < 0.01. On multivariable analysis, adrenal tumor size > 1.8 cm (OR 49.6 CI 8-306), CEA > 2.5 ng/mL (OR 15.8 CI 1.7-144) and other metastatic disease seen on imaging (OR 68.1 CI 7-661) were independently associated with adrenal metastases.

CONCLUSION

CRC patients with small adrenal tumors, normal CEA levels and no evidence of other metastatic disease are unlikely to have spread to the adrenal glands. Adrenal tumors found during staging and surveillance of CRC patients should be evaluated with appropriate imaging and biochemical analysis.

Solitary adrenal metastasis from salivary duct carcinoma of the parotid gland successfully treated by surgery: A case report

RATIONALE

Salivary duct carcinoma (SDC) is a rare and highly aggressive cancer with a poor prognosis. SDC demonstrates a potential for invasive growth with early regional and distant metastasis to organs, such as bone, lung, liver, and brain. Because, adrenal gland metastasis from SDC is rare, its treatment options are not well established. Herein, we report a case of SDC metastasis from the parotid gland to the adrenal gland, which was successfully treated by surgery.

PATIENT CONCERNS

The patient had an abnormal but painless lump on the right parotid gland. The size of the mass had increased over a period of 3 years. The patient underwent complete removal of the right parotid gland and radical neck dissection followed by adjuvant radiotherapy and chemotherapy. Two years later, a mass was identified in the left adrenal gland by computed tomography. As no local recurrence or metastasis to other organs was observed, the patient underwent adrenalectomy.

DIAGNOSES

Metastasis of SDC in the adrenal gland was confirmed by histopathological examination of the adrenalectomized specimen.

INTERVENTIONS

After adrenalectomy, the patient was followed-up without adjuvant therapy.

OUTCOMES

The patient was well and alive during the 13-month postoperative follow-up period without any complications.

LESSONS

Surgical resection of solitary metastatic lesion may show a survival benefit with metastatic SDC.

Long-term survival after adrenal metastasectomy from colorectal cancer: a report of two cases

Background

Solitary adrenal metastasis from colorectal cancer is rare. Adrenal metastasis is usually detected with synchronous multiple metastases in other organs and is, therefore, considered to be unsuitable for surgical resection. The long-term outcomes of patients with solitary adrenal metastasectomy from colorectal cancer have been reported; however, the survival advantage has not been established. We herein report two cases of curative adrenal resection in patients with solitary adrenal metastasis from colorectal cancer who achieved long-term survival of > 9 years without recurrence after surgical resection.

Case presentation

The first case involved a 71-year-old man who underwent abdominoperineal rectal resection for rectal cancer. Preoperative CT revealed a mass in the right adrenal, which was growing after surgery. After chemotherapy the adrenal mass decreased in size, and adrenalectomy was performed at 8 months after the first surgery. A pathological examination confirmed metastasis from rectal cancer. The patient received adjuvant chemotherapy and is currently alive without recurrence at 9 years after the adrenalectomy. The second case involved a 53-year-old man who underwent sigmoidectomy for sigmoid colon cancer. Four years later, lobectomy was performed for isolated lung metastasis. Twenty months later, PET-CT revealed solitary metastasis in the left adrenal gland and adrenalectomy was performed. A histopathological examination revealed metastatic adenocarcinoma of sigmoid cancer. Postoperative chemotherapy was administered after adrenalectomy and the patient is currently alive and apparently disease-free at more than 9 years after undergoing adrenal metastasectomy.

Conclusion

Curative resection for solitary adrenal metastasis from colorectal cancer may be beneficial for survival.

Patients with extra-adrenal malignancies and adrenal lesions have similar rates of subclinical hypercortisolism compared with patients with true adrenal incidentalomas

OBJECTIVE

During follow-up in cancer patients, adrenal lesions are frequently found by computer tomography imaging. In these patients, the frequency of subclinical Cushing's syndrome (SCS) has not been fully explored. The aim of the present study was to investigate the presence of SCS in cancer patients with adrenal lesions in comparison to patients with true adrenal incidentalomas.

DESIGN

We studied 95 patients with adrenal lesions: 57 patients (group A, 20 males and 37 females) had a history of extra-adrenal malignancy and adrenal lesions were discovered during staging of the primary cancer, and 38 patients (group B, 6 males and 32 females) had adrenal incidentalomas. The two groups had similar BMI. All patients had unenhanced HU < 10 in computed tomography to ensure low risk of adrenal metastatic disease. Patients' morning plasma cortisol levels and ACTH were measured. An overnight 1 mg dexamethasone suppression test (ODST) was performed in all participants; in case of abnormal results, 24-h urine cortisol and the low-dose dexamethasone suppression test were additionally conducted. The cutoffs of morning cortisol values used for ODST were 1.8 and 5 μg/dl.

RESULTS

When the cutoff of 1.8 μg/dl for suppressed morning cortisol was used, 42.1% of group A and 39.5% of group B had abnormal results (p = 0.95). By using the threshold of 5 μg/dl after ODST, 5.3% of group A and 13.2% of group B did not have suppressed cortisol levels with the 1 mg ODST (p = 0.18). The main factors found to influence suppressed cortisol levels after ODST in both groups were BMI and size of the adrenal lesion.

CONCLUSIONS

Patients with extra-adrenal malignancies and adrenal lesions had similar rates of subclinical hypercortisolemia compared to patients with true adrenal incidentalomas.