Prediction of cavernous sinus invasion in patients with Cushing's disease by magnetic resonance imaging

Predictors of Durable Remission After Successful Surgery for Cushing Disease: Results From the Multicenter RAPID Registry

BACKGROUND AND OBJECTIVE

Cushing disease (CD) affects mortality and quality of life along with limited long-term remission, underscoring the need to better identify recurrence risk. The identification of surgical or imaging predictors for CD remission after transsphenoidal surgery has yielded some inconsistent results and has been limited by single-center, single-surgeon, or meta-analyses studies. We sought to evaluate the multicenter Registry of Adenomas of the Pituitary and Related Disorders (RAPID) database of academic US pituitary centers to assess whether robust nonhormonal recurrence predictors could be elucidated.

METHODS

Patients with treated CD from 2011 to 2023 were included. The perioperative and long-term characteristics of CD patients with and without recurrence were assessed using univariable and multivariable analyses.

RESULTS

Of 383 patients with CD from 26 surgeons achieving postoperative remission, 288 (75.2%) maintained remission at last follow-up while 95 (24.8%) showed recurrence (median time to recurrence 9.99 ± 1.34 years). Patients with recurrence required longer postoperative hospital stays (5 ± 3 vs 4 ± 2 days, P = .002), had larger average tumor volumes (1.76 ± 2.53 cm 3 vs 0.49 ± 1.17 cm 3 , P = .0001), and more often previously failed prior treatment (31.1% vs 14.9%, P = .001) mostly being prior surgery. Multivariable hazard prediction models for tumor recurrence found younger age (odds ratio [OR] = 0.95, P = .002) and Knosp grade of 0 (OR = 0.09, reference Knosp grade 4, P = .03) to be protective against recurrence. Comparison of Knosp grade 0 to 2 vs 3 to 4 showed that lower grades had reduced risk of recurrence (OR = 0.27, P = .04). Other factors such as length of stay, surgeon experience, prior tumor treatment, and Knosp grades 1, 2, or 3 failed to reach levels of statistical significance in multivariable analysis.

CONCLUSION

This multicenter study centers suggests that the strongest predictors of recurrence include tumor size/invasion and age. This insight can help with patient counseling and prognostication. Long-term follow-up is necessary for patients, and early treatment of small tumors may improve outcomes.

Multi-center application of a convolutional neural network for preoperative detection of cavernous sinus invasion in pituitary adenomas

OBJECTIVE

Cavernous sinus invasion (CSI) plays a pivotal role in determining management in pituitary adenomas. The study aimed to develop a Convolutional Neural Network (CNN) model to diagnose CSI in multiple centers.

METHODS

A total of 729 cases were retrospectively obtained in five medical centers with (n = 543) or without CSI (n = 186) from January 2011 to December 2021. The CNN model was trained using T1-enhanced MRI from two pituitary centers of excellence (n = 647). The other three municipal centers (n = 82) as the external testing set were imported to evaluate the model performance. The area-under-the-receiver-operating-characteristic-curve values (AUC-ROC) analyses were employed to evaluate predicted performance. Gradient-weighted class activation mapping (Grad-CAM) was used to determine models' regions of interest.

RESULTS

The CNN model achieved high diagnostic accuracy (0.89) in identifying CSI in the external testing set, with an AUC-ROC value of 0.92 (95% CI, 0.88-0.97), better than CSI clinical predictor of diameter (AUC-ROC: 0.75), length (AUC-ROC: 0.80), and the three kinds of dichotomizations of the Knosp grading system (AUC-ROC: 0.70-0.82). In cases with Knosp grade 3A (n = 24, CSI rate, 0.35), the accuracy the model accounted for 0.78, with sensitivity and specificity values of 0.72 and 0.78, respectively. According to the Grad-CAM results, the views of the model were confirmed around the sellar region with CSI.

CONCLUSIONS

The deep learning model is capable of accurately identifying CSI and satisfactorily able to localize CSI in multicenters.

Reoperation for Recurrent and Persistent Cushing's Disease without Visible MRI Findings

PURPOSE

Transsphenoidal surgery is the first-line treatment for Cushing's disease (CD), even with negative preoperative magnetic resonance imaging (MRI) results. Some patients with persistent or recurring hypercortisolism have negative MRI findings after the initial surgery. We aimed to analyze the efficacy of repeat surgery in two groups of patients and determine if there is an association between positive MRI findings and early remission.

PATIENTS AND METHODS

Clinical, imaging, and biochemical information of 42 patients who underwent repeat surgery by a single neurosurgeon between 2002 and 2021 was retrospectively analyzed. We compared the endocrinological, histopathological, and surgical outcomes before and after repeat surgery among 14 CD patients with negative MRI findings and 28 patients with positive MRI findings.

RESULTS

Immediate remission was achieved in 29 patients (69.0%) who underwent repeat surgery. Among all patients, 28 (66.7%) had MRI findings consistent with solid lesions. There was no significant difference in remission rates between the recurrence and persistence groups (77.8% vs. 57.1%, odds ratio = 2.625, 95% confidence interval = 0.651 to 10.586). Patients in remission after repeat surgery were not associated with positive MRI findings (odds ratio = 3.667, 95% confidence interval = 0.920 to 14.622).

CONCLUSIONS

In terms of recurrence, repeat surgery in patients with either positive or negative MRI findings showed reasonable remission rates. For persistent disease with positive MRI findings, repeat surgery is still an option; however, more solid evidence is needed to determine if negative MRI findings are predictors for failed reoperations for persistent hypercortisolism.

Resection of the Cavernous Sinus Medial Wall Improves Remission Rate in Functioning Pituitary Tumors: Retrospective Analysis of 248 Consecutive Cases

BACKGROUND

The purpose of transsphenoidal surgery (TSS) for a functioning pituitary tumor (FPT) is to achieve endocrinological remission. The biggest challenge is aggressive tumor resection invading the cavernous sinus (CS).

OBJECTIVE

To evaluate the effects of the medial wall of CS (MWCS) resection during FPT surgery.

METHODS

Consecutive FPTs were reviewed for CS invasion (CSI) between April 2018 and December 2021. We operated on more than 250 FPTs, including 134 somatotroph tumors, 70 corticotroph tumors, 35 lactotroph tumors, and 9 thyrotroph tumors.

RESULTS

The patients were classified into 3 groups based on the relationship between the tumor and the CS: group A (no clear wall invasion), in which MWCS was not removed because of no tumorous direct contact with MWCS (N = 92) and group B (possible wall invasion), where MWCS was removed because we were not confident of MWCS invasion (N = 102). Among these 102 patients, histological tumor invasion was confirmed in 45 of 79 patients (57%) for whom histology findings were available. Tumors invading the CS clearly during surgery were classified into the "clear CS invasion" (group C: N = 55) group. The overall complete remission rate in group B was 94%, which was as high as that in group A (87%). Moreover, we clarified that microscopic invasion of MWCS could not always be predicted from Knosp grading.

CONCLUSION

MWCS invasion occurred in 57% of cases confirmed histologically where it was unclear during surgery, and its resection can improve the overall complete remission rate in FPT cases.

Application of Convolutional Neural Network in the Diagnosis of Cavernous Sinus Invasion in Pituitary Adenoma

Objectives

Convolutional neural network (CNN) is a deep-learning method for image classification and recognition based on a multi-layer NN. In this study, CNN was used to accurately assess cavernous sinus invasion (CSI) in pituitary adenoma (PA).

Methods

A total of 371 patients with PA were enrolled in the retrospective study. The cohort was divided into the invasive (n = 102) and non-invasive groups (n = 269) based on surgically confirmed CSI. Images were selected on the T1-enhanced imaging on MR scans. The cohort underwent a fivefold division of randomized datasets for cross-validation. Then, a tenfold augmented dataset (horizontal flip and rotation) of the training set was enrolled in the pre-trained Resnet50 model for transfer learning. The testing set was imported into the trained model for evaluation. Gradient-weighted class activation mapping (Grad-CAM) was used to obtain the occlusion map. The diagnostic values were compared with different dichotomizations of the Knosp grading system (grades 0-1/2-4, 0-2/3a-4, and 0-3a/3b-4).

Results

Based on Knosp grades, 20 cases of grade 0, 107 cases of grade 1, 82 cases of grade 2, 104 cases of grade 3a, 22 cases of grade 3b, and 36 cases of grade 4 were recorded. The CSI rates were 0%, 3.7%, 18.3%, 37.5%, 54.5%, and 88.9%. The predicted accuracies of the three dichotomies were 60%, 74%, and 81%. The area under the receiver operating characteristic (AUC-ROC) of Knosp grade for CSI prediction was 0.84; the cutoff was 2.5 with a Youden value of 0.62. The accuracies of the CNN model ranged from 0.80 to 0.96, with AUC-ROC values ranging from 0.89 to 0.98. The Grad-CAM saliency maps confirmed that the region of interest of the model was around the sellar region.

Conclusions

We constructed a CNN model with a high proficiency at CSI diagnosis. A more accurate CSI identification was achieved with the constructed CNN than the Knosp grading system.

Transsphenoidal Surgery of Corticotroph Adenomas With Cavernous Sinus Invasion: Results in a Series of 86 Consecutive Patients

Objective

Transsphenoidal surgery (TSS) is the first-line treatment for corticotroph adenomas. Although most corticotroph adenomas are noninvasive microadenomas, a small subset of them invading cavernous sinus (CS) is notoriously difficult to manage. The aim of this study was to evaluate the surgical outcome of corticotroph adenomas with CSI from a single center.

Patients and Methods

The clinical features and outcomes of CD patients who underwent TSS between January 2000 and September 2019 at Peking Union Medical College Hospital were collected from medical records. The clinical, endocrinological, radiological, histopathological, and surgical outcomes, and a minimum 12-month follow-up of patients with corticotroph adenomas invading CS were retrospectively reviewed.

Results

Eighty-six patients with corticotroph adenomas invading CS were included in the study. The average age at TSS was 37.7 years (range, 12 to 67 years), with a female-to-male ratio of 3.1:1 (65/21). The median duration of symptoms was 52.6 months (range, 1.0 to 264 months). The average of maximum diameter of tumor was 17.6 mm (range, 4.5–70 mm). All included 86 patients underwent TSS using a microscopic or an endoscopic approach. Gross total resection was achieved in 63 patients (73.3%), subtotal resection was attained in 18 (20.9%), and partial resection was achieved in 5 (5.8%). After surgery, the overall postoperative immediate remission rate was 48.8% (42/86); 51.2% (44/86) of patients maintained persistent hypercortisolism. In 42 patients with initial remission, 16.7% (7/42) experienced a recurrence. In these patients with persistent disease and recurrent CD, data about further treatment were available for 30 patients. Radiotherapy was used for 15 patients, and 4 (26.7%) of them achieved biochemical remission. Repeat TSS was performed in 5 patients, and none achieved remission. Medication was administered in 4 patients, and one of them obtained disease control. Adrenalectomy was performed in 6 patients, and 5 (83.3%) achieved biochemical remission. At the last follow-up, 10 of 30 patients (33.3%) were in remission, and 20 patients still had persistent disease.

The remission rate in corticotroph adenomas with cavernous sinus invasion (CSI) that underwent gross total resection and first TSS was significantly higher than that in patients undergoing subtotal resection, partial resection, and a second TSS (all p < 0.05). However, there was no significant difference in the remission rate between patients with different tumor sizes, Knosp grades, and surgical approaches (p > 0.05).

Conclusion

The management of corticotroph adenomas with CSI remain a therapeutic challenge due to incomplete resection of invasive and/or a large adenoma. With the application of multiple techniques, approximately half of the patients could achieve gross total resection and biochemical remission via TSS by experienced neurosurgeons. The extent of tumor resection and the number of operations were associated with surgical remission rate in corticotroph adenomas with CSI. If the remission was not achieved by surgery, other treatments including radiotherapy, medical therapy, and even bilateral adrenalectomy are required.

Assessment of magnetic resonance imaging criteria for the diagnosis of cavernous sinus invasion by pituitary tumors

Cavernous sinus invasion (CSI) by pituitary tumors is associated with subtotal resection and persistent endocrinopathy. The Knosp classification is a magnetic resonance imaging (MRI) tool used to define CSI in the 2017 World Health Organization Classification. However, alternative criteria may have superior diagnostic performance. This study aimed to assess the diagnostic performance of four MRI criteria, using a combination of endoscopy and day 1 MRI as the reference standard for CSI. A cross-sectional study was conducted including patients treated with endoscopic endonasal transsphenoidal surgery for pituitary macroadenomas, recruited from a tertiary pituitary multidisciplinary center in Sydney, Australia between September 2013, and February 2021. The diagnostic performances of four MRI criteria were assessed: the Knosp criteria, percentage encasement of the internal carotid (PEICA), venous compartment obliteration (VCO), and the Fernandez-Miranda classification. Reference CSI was defined using a combination of intraoperative endoscopy and day 1 MRI. A total of 210 cavernous sinuses (105 patients), were analyzed, (51.7 ± 16.3yrs, 43% female), of which 18% had CSI. CSI was best diagnosed by Knosp ≥ 2 (63% sensitivity and 89% specificity), PEICA ≥ 28% (84% sensitivity and 77% specificity) and VCO of ≥ 3 compartments (65% sensitivity and 89% specificity). CSI was unlikely if any of the following signs were present: Knosp < 1, PEICA < 28%, preservation of the medial or superior compartments or sparing of the superior Fernandez-Miranda compartment (negative predictive value 95%, 95%, 94%, 91% and 92% respectively). In conclusion, alternatives to the Knops criteria including PEICA and VCO can aid CSI diagnosis.

Pituitary Adenomas and Invasiveness from Anatomo-Surgical, Radiological, and Histological Perspectives: A Systematic Literature Review

Invasiveness in pituitary adenomas has been defined and investigated from multiple perspectives, with varying results when its predictive value is considered. A systematic literature review, following PRISMA guidelines, was performed, searching PubMed and Scopus databases with terms that included molecular markers, histological, radiological, anatomical and surgical data on invasiveness of pituitary adenomas. The results showed that differing views are still present for anatomical aspects of the sellar region that are relevant to the concept of invasiveness; radiological and histological diagnoses are still limited, but might improve in the future, especially if they are related to surgical findings, which have become more accurate thanks to the introduction of the endoscope. The aim is to achieve a correct distinction between truly invasive pituitary adenomas from those that, in contrast, present with extension in the parasellar area through natural pathways. At present, diagnosis of invasiveness should be based on a comprehensive analysis of radiological, intra-operative and histological findings.