Imaging Errors in Distinguishing Pituitary Adenomas From Other Sellar Lesions

Distinguishing Pituitary Metastasis and Pituitary Neuroendocrine Tumors through Conventional MR Imaging and Clinical Features

BACKGROUND AND PURPOSE

Given their overlapping features, pituitary metastases frequently imitate pituitary neuroendocrine tumors in neuroimaging studies. This study aimed to distinguish pituitary metastases from pituitary neuroendocrine tumors on the basis of conventional MR imaging and clinical features as a practical approach.

MATERIALS AND METHODS

In this 2-center retrospective study, backward from January 2024, preoperative pituitary MR imaging examinations of 22 pituitary metastases and 74 pituitary neuroendocrine tumors were analyzed. Exclusion criteria were as follows: absence of a definitive histopathologic diagnosis, history of pituitary surgery or radiation therapy before MR imaging, and pituitary neuroendocrine tumors treated with medical therapy. Two radiologists systematically evaluated 13 conventional MR imaging features that have been reported more commonly as indicative of pituitary metastases and pituitary neuroendocrine tumors in the literature. Age, sex, history of cancer, and maximum tumor size constituted the clinical/epidemiologic features. The primary cancer origin for this study was also noted. Univariable and multivariable logistic regression was used for the selection of variables, determining independent predictors, and modeling. Interobserver agreement was evaluated for all imaging parameters using the Cohen κ statistic or intraclass correlation coefficient.

RESULTS

A total of 22 patients with pituitary metastases (8 women; mean age, 49.5 [SD, 13] years) and 74 patients with pituitary neuroendocrine tumors (36 women; mean age, 50.1 [SD, 11] years) were enrolled. There was no statistically significant distributional difference in age, sex, or maximum tumor size between the 2 groups. Lung cancer (9/22; 41%) was the most commonly reported primary tumor, followed by breast (3/22; 13.6%) and unknown cancer (3/22; 13.6%). Logistic regression revealed 3 independent predictors: rapid growth on control MR imaging, masslike or nodular expansion of the pituitary stalk, and a history of cancer. The model based on these 3 features achieved an area under the curve, accuracy, sensitivity, specificity, and Brier score of 0.987 (95% CI, 0.964-1), 97.9% (95% CI, 92.7%-99.8%), 95.5% (95% CI, 77.2%-99.9%), 98.6% (95% CI, 92.7%-100%), and 0.025, respectively.

CONCLUSIONS

Two conventional features based on pituitary MR imaging with the clinical variable of history of cancer had satisfying predictive performance, making them potential discriminators between pituitary metastases and pituitary neuroendocrine tumors. In cases in which differentiation between pituitary metastases and pituitary neuroendocrine tumors poses a challenge, the results of this study may help with the diagnosis.

Three-Dimensional Fast Spin Echo Pituitary MRI in Treatment-Naïve Cushing's Disease: Reduced Impact of Reader Experience and Increased Diagnostic Accuracy

BACKGROUND

In patients with Cushing's disease, the preoperative identification of pituitary adenomas is crucial to treatment. However, increasing diagnostic accuracy remains an unresolved issue.

PURPOSE

To evaluate the diagnostic accuracy and the impact of readers' experience regarding high-resolution contrast-enhanced magnetic resonance imaging (hrMRI) for identifying pituitary adenomas in comparison with conventional contrast-enhanced MRI (cMRI) and dynamic contrast-enhanced MRI (dMRI).

STUDY TYPE

Retrospective.

POPULATION

Sixty-five patients (median age, 39 years; interquartile range [IQR], 28-53 years; 60% females) with treatment-naïve Cushing's disease.

FIELD STRENGTH/SEQUENCE

3-T, seven fast spin echo sequences.

ASSESSMENT

The diagnostic accuracies of identifying pituitary adenomas on cMRI, dMRI, combined cMRI and dMRI (cdMRI), and hrMRI were independently evaluated by six readers with three experience levels (high: >20 years, modest: 10-20 years, low: <10 years; two readers for each experience level). Readers were asked to localize the lesion, and measure its diameter on the sequence where identified. The reference standard was postoperative histopathology. The impact of readers' experience and interobserver agreement were assessed. Image quality was assessed using a 5-point Likert scale, including overall image quality, sharpness, and structural conspicuity.

STATISTICAL TESTS

McNemar's test, Cochran's test, Wilcoxon signed-rank test, Mann-Whitney U test, and κ statistics for interobserver agreement. A P-value <0.05 was considered statistically significant.

RESULTS

For identifying pituitary adenomas (median diameter, 5 mm; IQR, 4-5 mm), hrMRI had significantly higher sensitivity (87.7%-93.8%) than cMRI, dMRI, and cdMRI (52.3%-75.4%) for readers with different experience levels. The interobserver agreement was moderate (κ = 0.461-0.523). The sensitivity for hrMRI was comparable between readers with different experience levels (P = 0.371). All image quality scores on hrMRI were significantly higher than cMRI and dMRI (5.0 vs. 4.0).

DATA CONCLUSION

For identifying pituitary adenomas in patients with treatment-naïve Cushing's disease, hrMRI may show high diagnostic accuracy and seems not to be affected by readers' experience.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Sellar metastasis: A rare intraoperative finding - surgical treatment, strategies and outcome

OBJECTIVE

The sellar region, though uncommon for metastatic spread, may become more prevalent due to longer survival of patients with metastatic malignancies. Compression of adjacent vital anatomy can cause disabling symptoms and endocrine disturbances, leading to significant morbidity METHODS: This study analyzed sellar pathologies treated via endonasal approach from January 2011 to December 2021 to assess the incidence of sellar metastases. Patient demographics, presenting symptoms, radiological and histological findings, management, and outcomes were evaluated RESULTS: Among 334 patients treated during the study period, eight (2.3 %) had metastases confirmed histopathologically, with one having a known malignant tumor history. Preoperative imaging suspected malignancy or metastasis in two cases. Diagnosis was unexpectedly confirmed in 57 % of cases. Subtotal resection was achieved in three cases, near-total resection in one. Mean follow-up was 2.4 years, with 71 % mortality CONCLUSIONS: The sellar region can manifest metastatic disease, with sellar symptoms potentially indicating neoplastic disease onset. Rapid hormonal dysfunction or ophthalmoplegia suggests metastasis, even without a known primary. Further meta analysis of reported cases is necessary to determine the incidence and optimal treatment of these rare metastases.

Generating novel pituitary datasets from open-source imaging data and deep volumetric segmentation

PURPOSE

The estimated incidence of pituitary adenomas in the general population is 10-30%, yet radiographic diagnosis remains a challenge. Diagnosis is complicated by the heterogeneity of radiographic features in both normal (e.g. complex anatomy, pregnancy) and pathologic states (e.g. primary endocrinopathy, hypophysitis). Clinical symptoms and laboratory testing are often equivocal, which can result in misdiagnosis or unnecessary specialist referrals. Computer vision models can aid in pituitary adenoma diagnosis; however, a major challenge to model development is the lack of dedicated pituitary imaging datasets. We hypothesized that deep volumetric segmentation models trained to extract the sellar and parasellar region from existing whole-brain MRI scans could be used to generate a novel dataset of pituitary imaging.

METHODS

Six open-source whole-brain MRI datasets, created for research purposes, were included for model development. Deep learning-based volumetric segmentation models were trained using 318 manually annotated MRI scans from a single open-source MRI dataset. Out-of-distribution volumetric segmentation performance was then tested on 418 MRIs from five held-out research datasets.

RESULTS

On our annotated images, agreement between manual and model volumetric segmentations was high. Dice scores (a measure of overlap) ranged 0.76-0.82 for both in-distribution and out-of-distribution model testing. In total, 6,755 MRIs from six data sources were included in the final generated pituitary dataset.

CONCLUSIONS

We present the first and largest dataset of pituitary imaging constructed using existing MRI data and deep volumetric segmentation models trained to identify sellar and parasellar anatomy. The model generalizes well across patient populations and MRI scanner types. We hope our pituitary dataset will be an integral part of future machine learning research on pituitary pathologies.

Rapid Automated Analysis of Skull Base Tumor Specimens Using Intraoperative Optical Imaging and Artificial Intelligence

BACKGROUND

Accurate specimen analysis of skull base tumors is essential for providing personalized surgical treatment strategies. Intraoperative specimen interpretation can be challenging because of the wide range of skull base pathologies and lack of intraoperative pathology resources.

OBJECTIVE

To develop an independent and parallel intraoperative workflow that can provide rapid and accurate skull base tumor specimen analysis using label-free optical imaging and artificial intelligence.

METHODS

We used a fiber laser-based, label-free, nonconsumptive, high-resolution microscopy method (<60 seconds per 1 × 1 mm2), called stimulated Raman histology (SRH), to image a consecutive, multicenter cohort of patients with skull base tumor. SRH images were then used to train a convolutional neural network model using 3 representation learning strategies: cross-entropy, self-supervised contrastive learning, and supervised contrastive learning. Our trained convolutional neural network models were tested on a held-out, multicenter SRH data set.

RESULTS

SRH was able to image the diagnostic features of both benign and malignant skull base tumors. Of the 3 representation learning strategies, supervised contrastive learning most effectively learned the distinctive and diagnostic SRH image features for each of the skull base tumor types. In our multicenter testing set, cross-entropy achieved an overall diagnostic accuracy of 91.5%, self-supervised contrastive learning 83.9%, and supervised contrastive learning 96.6%. Our trained model was able to segment tumor-normal margins and detect regions of microscopic tumor infiltration in meningioma SRH images.

CONCLUSION

SRH with trained artificial intelligence models can provide rapid and accurate intraoperative analysis of skull base tumor specimens to inform surgical decision-making.

Diagnostic Error in Neuro-ophthalmology: Avenues to Improve

Purpose of Review

To highlight potential avenues to reduce preventable diagnostic error of neuro-ophthalmic conditions and avoid patient harm.

Recent Findings

Recent prospective studies and studies of patient harm have advanced our understanding. Additionally, recent studies of fundus photography, telemedicine, and artificial intelligence highlight potential avenues for diagnostic improvement.

Summary

Diagnostic error of neuro-ophthalmic conditions can often be traced to failure to gather an adequate history, perform a complete physical exam, obtain adequate/appropriate neuroimaging, and generate a complete, appropriate differential diagnosis. Improving triage and identification of neuro-ophthalmic conditions by other providers and increasing access to subspecialty neuro-ophthalmology evaluation are essential avenues to reduce diagnostic error. Further research should evaluate the relationship between misdiagnosis and patient harm, and help identify the most impactful potential targets for improvement.