Age-related morphometrics of normal adrenal glands based on deep learning-aided segmentation

Adrenal gland volume measurement in depressed patients

PURPOSE

Prior studies have shown contradicting results regarding adrenal gland volume (AGV) in depressed patients, with some reporting significant enlargement and others not. The aim of this study was to retrospectively compare CT image segmentations of the adrenal glands in patients with depression to a control group with stringent exclusion criteria to minimize confounding factors.

METHODS

We included patients diagnosed with depression (ICD-10: F32/33) who underwent abdominal CT imaging between 2012 and 2022 and did not have any other psychiatric disorders. Diagnoses that could potentially influence AGV were excluded. The resulting 31 depressed patients were compared to a matching control group of 31 patients without depression. The AGV was manually segmented in thin-sliced reconstructions (≤1 mm).

RESULTS

Total AGV in the depressed group was 6.78 (5.19-7.56) cm3 compared to 6.90 (5.54-10.05) cm3 in the control group. There was no significant difference in AGV between the two groups after adjusting for age, height, and weight. A positive correlation was observed between AGV and height (r = 0.41, p < 0.001) and weight (r = 0.52, p < 0.001). Males showed significantly larger AGV than females (p ≤ 0.001), and left AGV was significantly larger than right AGV (p < 0.001). Patients within the depressed group who underwent imaging after a suicide attempt showed larger total AGV compared to the control group, though not statistically significant.

CONCLUSION

AGV is not increased in the well-selected cohort of depressed patients in this study, which contrasts with some previous reports in literature. Further multi-centric studies are required to identify potentially influencing factors such as attempted suicide.

Localization and Classification of Adrenal Masses in Multiphase Computed Tomography: Retrospective Study

BACKGROUND

The incidence of adrenal incidentalomas is increasing annually, and most types of adrenal masses require surgical intervention. Accurate classification of common adrenal masses based on tumor computed tomography (CT) images by radiologists or clinicians requires extensive experience and is often challenging, which increases the workload of radiologists and leads to unnecessary adrenal surgeries. There is an urgent need for a fully automated, noninvasive, and precise approach for the identification and accurate classification of common adrenal masses.

OBJECTIVE

This study aims to enhance diagnostic efficiency and transform the current clinical practice of preoperative diagnosis of adrenal masses.

METHODS

This study is a retrospective analysis that includes patients with adrenal masses who underwent adrenalectomy from January 1, 2021, to May 31, 2023, at Center 1 (internal dataset), and from January 1, 2016, to May 31, 2023, at Center 2 (external dataset). The images include unenhanced, arterial, and venous phases, with 21,649 images used for the training set, 2406 images used for the validation set, and 12,857 images used for the external test set. We invited 3 experienced radiologists to precisely annotate the images, and these annotations served as references. We developed a deep learning-based adrenal mass detection model, Multi-Attention YOLO (MA-YOLO), which can automatically localize and classify 6 common types of adrenal masses. In order to scientifically evaluate the model performance, we used a variety of evaluation metrics, in addition, we compared the improvement in diagnostic efficacy of 6 doctors after incorporating model assistance.

RESULTS

A total of 516 patients were included. In the external test set, the MA-YOLO model achieved an intersection over union of 0.838, 0.885, and 0.890 for the localization of 6 types of adrenal masses in unenhanced, arterial, and venous phase CT images, respectively. The corresponding mean average precision for classification was 0.885, 0.913, and 0.915, respectively. Additionally, with the assistance of this model, the classification diagnostic performance of 6 radiologists and clinicians for adrenal masses improved. Except for adrenal cysts, at least 1 physician significantly improved diagnostic performance for the other 5 types of tumors. Notably, in the categories of adrenal adenoma (for senior clinician: P=.04, junior radiologist: P=.01, and senior radiologist: P=.01) and adrenal cortical carcinoma (junior clinician: P=.02, junior radiologist: P=.01, and intermediate radiologist: P=.001), half of the physicians showed significant improvements after using the model for assistance.

CONCLUSIONS

The MA-YOLO model demonstrates the ability to achieve efficient, accurate, and noninvasive preoperative localization and classification of common adrenal masses in CT examinations, showing promising potential for future applications.

Characterization of adrenal glands on computed tomography with a 3D V-Net-based model

OBJECTIVES

To evaluate the performance of a 3D V-Net-based segmentation model of adrenal lesions in characterizing adrenal glands as normal or abnormal.

METHODS

A total of 1086 CT image series with focal adrenal lesions were retrospectively collected, annotated, and used for the training of the adrenal lesion segmentation model. The dice similarity coefficient (DSC) of the test set was used to evaluate the segmentation performance. The other cohort, consisting of 959 patients with pathologically confirmed adrenal lesions (external validation dataset 1), was included for validation of the classification performance of this model. Then, another consecutive cohort of patients with a history of malignancy (N = 479) was used for validation in the screening population (external validation dataset 2). Parameters of sensitivity, accuracy, etc., were used, and the performance of the model was compared to the radiology report in these validation scenes.

RESULTS

The DSC of the test set of the segmentation model was 0.900 (0.810-0.965) (median (interquartile range)). The model showed sensitivities and accuracies of 99.7%, 98.3% and 87.2%, 62.2% in external validation datasets 1 and 2, respectively. It showed no significant difference comparing to radiology reports in external validation datasets 1 and lesion-containing groups of external validation datasets 2 (p = 1.000 and p > 0.05, respectively).

CONCLUSION

The 3D V-Net-based segmentation model of adrenal lesions can be used for the binary classification of adrenal glands.

CRITICAL RELEVANCE STATEMENT

A 3D V-Net-based segmentation model of adrenal lesions can be used for the detection of abnormalities of adrenal glands, with a high accuracy in the pre-surgical scene as well as a high sensitivity in the screening scene.

KEY POINTS

Adrenal lesions may be prone to inter-observer variability in routine diagnostic workflow. The study developed a 3D V-Net-based segmentation model of adrenal lesions with DSC 0.900 in the test set. The model showed high sensitivity and accuracy of abnormalities detection in different scenes.

Exploring the Benefits of a Reduced-Port Approach in Robotic Posterior Retroperitoneoscopic Adrenalectomy: A Comparative Study of the Two-Port and Three-Port Techniques

Background: Robotic adrenalectomy has become a surgical treatment option for benign and selected malignant adrenal diseases. We aimed to evaluate the eligibility of two-port robotic posterior retroperitoneoscopic adrenalectomy (PRA) as an alternative to the conventional three-port technique by comparing their surgical outcomes. Materials and Methods: This retrospective cohort study compared the clinicopathological factors and surgical outcomes among 197 patients who underwent two-port or three-port robotic adrenalectomy between 2016 and 2020 in a single tertiary center. For further evaluation, propensity score matching was performed to reduce the selection bias in population characteristics. Results: Patients were categorized by the number of ports (two-port group, 87; and three-port group, 110). The two-port group compared with the three-port group was significantly older (P = .006) and had a smaller mean tumor size (P = .003) and shorter mean operation time (P = .001). Upon comparing clinicopathologic characteristics according to adrenal disorders, for pheochromocytoma, the three-port group had a larger tumor size and a longer operation time. For Cushing's syndrome, the operation time was short and numeric rating scale pain score was significantly low in the two-port group. After propensity score matching, the two-port group had a short operation time and a significantly low postoperative pain score (P < .05). Predictive factors associated with prolonged operation time included male gender, an increased number of ports, and large tumor size. Conclusions: The two-port technique resulted in a shorter operation time and lower pain score compared with the three-port technique. The two-port technique may be a safe alternative to the conventional three-port technique for robotic PRA.

Asymmetric Adrenals: Sexual Dimorphism of Adrenal Tumors

CONTEXT

Sexual dimorphism has direct consequences on the incidence and survival of cancer. Early and accurate diagnosis is crucial to improve prognosis.

OBJECTIVE

This work aimed to characterized the influence of sex and adrenal asymmetry on the emergence of adrenal tumors.

METHODS

We conducted a multicenter, observational study involving 8037 patients with adrenal tumors, including adrenocortical carcinoma (ACC), aldosterone-producing adenoma (APA), cortisol-secreting adrenocortical adenomas (CSAs), non-aldosterone-producing adrenal cortical adenoma (NAPACA), pheochromocytoma (PCC), and neuroblastoma (NB), and investigated tumor lateralization according to sex. Human adrenal tissues (n = 20) were analyzed with a multiomics approach that allows determination of gene expression, catecholamine, and steroid contents in a single sample. In addition, we performed a literature review of computed tomography and magnetic resonance imaging-based studies examining adrenal gland size.

RESULTS

ACC (n = 1858); CSA (n = 68), NAPACA (n = 2174), and PCC (n = 1824) were more common in females than in males (female-to-male ratio: 1.1:1-3.8:1), whereas NBs (n = 2320) and APAs (n = 228) were less prevalent in females (0.8:1). ACC, APA, CSA, NAPACA, and NB occurred more frequently in the left than in the right adrenal (left-to-right ratio: 1.1:1-1.8:1), whereas PCC arose more often in the right than in the left adrenal (0.8:1). In both sexes, the left adrenal was larger than the right adrenal; females have smaller adrenals than males.

CONCLUSION

Adrenal asymmetry in both sexes may be related to the pathogenesis of adrenal tumors and should be considered during the diagnosis of these tumors.