Primary versus revision transsphenoidal resection for nonfunctioning pituitary macroadenomas: matched cohort study

Prediction of intraoperative cerebrospinal fluid leaks in endoscopic endonasal transsphenoidal pituitary surgery based on a deep neural network model trained with MRI images: a pilot study

Objective

This study aimed to investigate the reliability of a deep neural network (DNN) model trained only on contrast-enhanced T1 (T1CE) images for predicting intraoperative cerebrospinal fluid (ioCSF) leaks in endoscopic transsphenoidal surgery (EETS).

Methods

396 pituitary adenoma (PA) cases were reviewed, only primary PAs with Hardy suprasellar Stages A, B, and C were included in this study. The T1CE images of these patients were collected, and sagittal and coronal T1CE slices were selected for training the DNN model. The model performance was evaluated and tested, and its interpretability was explored.

Results

A total of 102 PA cases were enrolled in this study, 51 from the ioCSF leakage group, and 51 from the non-ioCSF leakage group. 306 sagittal and 306 coronal T1CE slices were collected as the original dataset, and data augmentation was applied before model training and testing. In the test dataset, the DNN model provided a single-slice prediction accuracy of 97.29%, a sensitivity of 98.25%, and a specificity of 96.35%. In clinical test, the accuracy of the DNN model in predicting ioCSF leaks in patients reached 84.6%. The feature maps of the model were visualized and the regions of interest for prediction were the tumor roof and suprasellar region.

Conclusion

In this study, the DNN model could predict ioCSF leaks based on preoperative T1CE images, especially in PAs in Hardy Stages A, B, and C. The region of interest in the model prediction-making process is similar to that of humans. DNN models trained with preoperative MRI images may provide a novel tool for predicting ioCSF leak risk for PA patients.

Postsurgical outcomes of nonfunctioning pituitary adenomas: a patient-level meta-analysis

BACKGROUND

Surgical resection is the main treatment for symptomatic nonfunctioning pituitary adenomas (NFPA). We aimed to analyze the impact of surgical approach, completeness of resection, and postoperative radiotherapy on long-term progression-free survival (PFS) of NFPA, using individual patient data (IPD) meta-analysis.

METHODS

An electronic literature searched was conducted on PubMed, EMBASE, and Web of Science from database inception to 6 November 2022. Studies describing the natural history of surgically resected NFPA, with provision of Kaplan-Meier curves, were included. These were digitized to obtain IPD, which was pooled in one-stage and two-stage meta-analysis to determine hazard ratios (HRs) and 95%CIs of gross total resection (GTR) versus subtotal resection (STR), and postoperative radiotherapy versus none. An indirect analysis of single-arm data between endoscopic endonasal (EES) and microscopic transsphenoidal (MTS) surgical technique was also performed.

RESULTS

Altogether, eleven studies (3941 patients) were retrieved. PFS was significantly lower in STR than GTR (shared-frailty HR 0.32, 95%CI 0.27-0.39, p < 0.001). Postoperative radiotherapy significantly improved PFS compared to no radiotherapy (shared-frailty HR 0.20, 95%CI 0.15-0.26, p < 0.001), including in the subgroup of patients with STR (shared-frailty HR 0.12, 95%CI 0.08-0.18, p < 0.001). Similar PFS was observed between EES and MTS (indirect HR 1.09, 95%CI 0.92-1.30, p = 0.301).

CONCLUSIONS

This systematic review and patient-level meta-analysis provides a robust prognostication of surgically treated NFPA. We reinforce current guidelines stating that GTR should be the standard of surgical resection. Postoperative radiotherapy is of considerable benefit, especially for patients with STR. Surgical approach does not significantly affect long-term prognosis.

REGISTRATION

PROSPERO CRD42022374034.

Post-operative surveillance for somatotroph, lactotroph and non-functional pituitary adenomas after curative resection: a systematic review

CONTEXT

Pituitary tumors are the third most common brain tumor and yet there is no standardization of the surveillance schedule and assessment modalities after transsphenoidal surgery.

EVIDENCE ACQUISITION

OVID, EMBASE and the Cochrane Library databases were systematically screened from database inception to March 5, 2020. Inclusion and exclusion criteria were designed to capture studies examining detection of pituitary adenoma recurrence in patients 18 years of age and older following surgical resection with curative intent.

EVIDENCE SYNTHESIS

A total of 7936 abstracts were screened, with 812 articles reviewed in full text and 77 meeting inclusion criteria for data extraction. A pooled analysis demonstrated recurrence rates at 1 year, 5 years and 10 years for non-functioning pituitary adenomas (NFPA; N = 3533 participants) were 1%, 17%, and 33%, for prolactin-secreting adenomas (PSPA; N = 1295) were 6%, 21%, and 28%, and for growth-hormone pituitary adenomas (GHPA; N = 1257) were 3%, 8% and 13%, respectively. Rates of recurrence prior to 1 year were 0% for NFPA, 1-2% for PSPA and 0% for GHPA. The mean time to disease recurrence for NFPA, PSPA and GHPA were 4.25, 2.52 and 4.18 years, respectively.

CONCLUSIONS

This comprehensive review of the literature quantified the recurrence rates for commonly observed pituitary adenomas after transsphenoidal surgical resection with curative intent. Our findings suggest that surveillance within 1 year may be of low yield. Further clinical trials and cohort studies investigating cost-effectiveness of surveillance schedules and impact on quality of life of patients under surveillance will provide further insight to optimize follow-up.

Endoscopic Endonasal Skull Base Surgery Complication Avoidance: A Contemporary Review

The endoscopic endonasal approach (EEA) provides a direct trajectory to ventral skull base lesions, avoidance of brain retraction, and clear visualization of cranial nerves as they exit skull base foramina. Despite these benefits, the EEA is not without complications. Here, we review published literature highlighting complications associated with the EEA including cerebrospinal fluid (CSF) leak, cranial nerve (CN) dysfunction, pituitary gland dysfunction, internal carotid artery (ICA) injury, infection, and others; we place special emphasis on discussing the prevention of these complications. As widespread adoption of the EEA continues, it becomes critical to educate surgeons regarding potential complications and their prevention while identifying gaps in the current literature to guide future research and advances in clinical care.

Changes in the Sphenoid Bone Encountered During the Endoscopic Endonasal Transsphenoidal Approach

OBJECTIVES

We estimated volume changes in the posterior bony wall of the sphenoid sinus, as well as alterations in nasal function (including olfactory function and subjective symptoms), after sphenoid mucosal repositioning using the endoscopic endonasal transsphenoidal approach (EETSA).

METHODS

During 2010 and 2021, 13 patients underwent sphenoid mucosal repositioning during EETSA, while 24 patients (the control group) did not. Pre- and postoperative paranasal sinus computed tomography and the Mimics program were used to evaluate three-dimensional changes in the posterior wall of the sphenoid sinus. All patients underwent the Connecticut Chemosensory Clinical Research Center (CCCRC) test, the Cross-Cultural Smell Identification Test (CCSIT), Nasal Obstruction Symptoms Evaluation (NOSE), the Sino-Nasal Outcome Test-20 (SNOT-20), and visual analog scale (VAS) evaluation.

RESULTS

The increase in the volume of the posterior wall of the sphenoid sinus after surgery was objectively smaller in the sphenoid mucosal repositioning group than in the control group (P = .046). However, this did not affect olfactory function (as revealed by the CCCRC test or the CCSIT) or subjective symptoms (as revealed by the NOSE, SNOT-20, and VAS scores) (all P > .05).

CONCLUSION

Surgical closure via sphenoid mucosal repositioning during EETSA reduces the volume of the posterior wall of the sphenoid sinus and facilitates re-operation. We suggest that sphenoid mucosal repositioning is appropriate during EETSA.

LEVEL OF EVIDENCE

4 Laryngoscope, 2022.

Interpretable Machine Learning-Based Prediction of Intraoperative Cerebrospinal Fluid Leakage in Endoscopic Transsphenoidal Pituitary Surgery: A Pilot Study

Purpose  Transsphenoidal surgery (TSS) for pituitary adenomas can be complicated by the occurrence of intraoperative cerebrospinal fluid (CSF) leakage (IOL). IOL significantly affects the course of surgery predisposing to the development of postoperative CSF leakage, a major source of morbidity and mortality in the postoperative period. The authors trained and internally validated the Random Forest (RF) prediction model to preoperatively identify patients at high risk for IOL. A locally interpretable model-agnostic explanations (LIME) algorithm is employed to elucidate the main drivers behind each machine learning (ML) model prediction. Methods  The data of 210 patients who underwent TSS were collected; first, risk factors for IOL were identified via conventional statistical methods (multivariable logistic regression). Then, the authors trained, optimized, and audited a RF prediction model. Results  IOL reported in 45 patients (21.5%). The recursive feature selection algorithm identified the following variables as the most significant determinants of IOL: Knosp's grade, sellar Hardy's grade, suprasellar Hardy's grade, tumor diameter (on X, Y, and Z axes), intercarotid distance, and secreting status (nonfunctioning and growth hormone [GH] secreting). Leveraging the predictive values of these variables, the RF prediction model achieved an area under the curve (AUC) of 0.83 (95% confidence interval [CI]: 0.78; 0.86), significantly outperforming the multivariable logistic regression model (AUC = 0.63). Conclusion  A RF model that reliably identifies patients at risk for IOL was successfully trained and internally validated. ML-based prediction models can predict events that were previously judged nearly unpredictable; their deployment in clinical practice may result in improved patient care and reduced postoperative morbidity and healthcare costs.

Surgical Experience of Transcranial Approaches to Large-to-Giant Pituitary Adenomas in Knosp Grade 4

Pituitary adenomas in Knosp grade 4 are difficult to resect completely and are generally involved in poor prognosis, because of the close relationship between the tumor and internal carotid. In this study, the authors retrospectively reviewed the outcome of different transcranial approaches in the management of large-to-giant pituitary adenomas in Knosp grade 4. A total of 42 patients with large-to-giant pituitary adenomas in Knosp grade 4, who underwent craniotomy in the Pituitary Disease Subdivision, Department of Neurosurgery, Beijing Tiantan Hospital, between March 2012 and March 2015 were included in this study. Clinical characteristics, surgical methods, complications, and outcomes were evaluated. The median age was 45 years (range, 19-73 years old), and 42.9% of the enrolled cases were men. The mean tumor diameter was 43.6 mm, and the mean volume was 30.9 cm³. 26 patients underwent the frontolateral approach, while 16 cases accepted the frontotemporal approach. Gross total resection was achieved in 11 patients (26.2%), near total in 26 (61.9%), and subtotal in 5 (11.9%). The adenomas were larger, and the distance of the tumor extending to the lateral skull base was also further in the frontotemporal approach cases. The surgical time was shorter, and the bleeding volume was less in the frontolateral approach cases. Subsellar extension was associated with incomplete resection in pituitary macroadenomas of Knosp grade 4. The craniotomy is still an effective treatment for pituitary macroadenomas in Knosp grade 4.

Do We Need Intraoperative Magnetic Resonance Imaging in All Endoscopic Endonasal Pituitary Adenoma Surgery Cases? A Retrospective Study

There are previous reports investigating effectiveness of intraoperative magnetic resonance imaging (IO-MRI) in pituitary adenoma surgery but there is no clear data in the literature recommending when there is no need of intraoperative scan. This retrospective analysis was based on determining which patients does not need any IO-MRI scan following endoscopic endonasal pituitary adenoma surgery. Patients with functional or non-functional pituitary adenomas that were operated via endoscopic endonasal approach (EEA) between June 2017 and May 2019 were enrolled. Patients younger than 18 years old, patients who did not underwent IO-MRI procedure or not operated via EEA were excluded from the study. Hence, this study is designed to clarify if IO-MRI is useful in both functional and non-functional pituitary adenomas, functional adenomas did not split into subgroups. A total of 200 patients treated with pituitary adenoma were included. In Knosp Grade 0 – 2 group, primary surgeon’s opinion and IO-MRI findings were compatible in 150 patients (98.6%). In Knosp Grade 3 – 4 correct prediction were performed in 32 (66.6%) patients. When incorrectly predicted Knosp Grade 3 – 4 patients (n = 16) was analyzed, in 13 patients there were still residual tumor in cavernous sinus and in 3 patients there were no residual tumor. Fisher’s exact test showed there is a statistically significant difference of correct prediction between two different Knosp Grade groups (two-tailed P < 0.0001). Eighteen patients had a residual tumor extending to the suprasellar and parasellar regions which second most common site for residual tumor. Our findings demonstrate that there is no need of IO-MRI scan while operating adenomas limited in the sellae and not invading the cavernous sinus. However, we strongly recommend IO-MRI if there is any suprasellar and parasellar extension and/or cavernous sinus invasion.

Cerebrospinal Fluid Leak after Transsphenoidal Surgery: A Systematic Review and Meta-analysis

Background Cerebrospinal fluid (CSF) leak is widely recognized as a challenging and commonly occurring postoperative complication of transsphenoidal surgery (TSS).

The primary objective of this study is to benchmark the current prevalence of CSF leak after TSS in the adult population.

Methods The authors followed the PRISMA guidelines. The PubMed, Embase, and Cochrane Library databases were searched for articles reporting CSF leak after TSS in the adult population. Meta-analysis was performed using the Untransformed Proportion metric in OpenMetaAnalyst. For two between-group comparisons a generalized linear mixed model was applied.

Results We identified 2,408 articles through the database search, of which 70, published since 2015, were included in this systematic review. These studies yielded 24,979 patients who underwent a total of 25,034 transsphenoidal surgeries. The overall prevalence of postoperative CSF leak was 3.4% (95% confidence interval or CI 2.8–4.0%). The prevalence of CSF leak found in patients undergoing pituitary adenoma resection was 3.2% (95% CI 2.5–4.2%), whereas patients who underwent TSS for another indication had a CSF leak prevalence rate of 7.1% (95% CI 3.0–15.7%) (odds ratio [OR] 2.3, 95% CI 0.9–5.7). Patients with cavernous sinus invasion (OR 3.0, 95% CI 1.1–8.7) and intraoperative CSF leak (OR 5.9, 95% CI 3.8–9.0) have increased risk of postoperative CSF leak. Previous TSS and microscopic surgery are not significantly associated with postoperative CSF leak.

Conclusion The overall recent prevalence of CSF leak after TSS in adults is 3.4%. Intraoperative CSF leak and cavernous sinus invasion appear to be significant risk factors for postoperative CSF leak.

Utility of intraoperative ultrasonography for resection of pituitary adenomas: a comparative retrospective study

BACKGROUND

The evolution of pituitary surgery has made it a safe and effective form of treatment; however, risks of inadequate tumor resection, cerebrospinal fluid (CSF) leak, pituitary dysfunction, and vascular injury still exist. The use of intraoperative ultrasonography (IOUS) in pituitary surgery has been well described. Recent advancements in ultrasound technology have allowed for expanded utility as described here.

METHODS

A retrospective review was performed between January 2016 and December 2019. One hundred thirty-eight patients (mean age 53.7 years, 47% females) were identified undergoing transsphenoidal surgery for pituitary tumors. Thirty-four patients had IOUS performed using a side-firing ultrasound probe, while 104 did not. Data was analyzed for preoperative (demographics, clinical, and radiographic features), perioperative (blood loss, operative time), and postoperative (complications, length of stay, hormone remission, and extent of resection) outcomes.

RESULTS

There were no significant differences in patient age, gender, tumor volume, Knosp grade, and hormone-secreting status between the two groups. Patients treated using IOUS had significantly higher rates of gross total resection (79% vs. 44%, p = 0.0008), shorter operative times (74 vs. 146 min, p < 0.0001), lower blood loss (119 vs. 284 cc, p < 0.0001), and hospital stays (2.9 vs. 4.2 days, p = 0.001). Overall complication rates were lower in the IOUS group compared to standard pituitary surgery but did not reach significance.

CONCLUSIONS

Recent improvements in ultrasound technology have allowed for miniaturization of probes capable of delivering high-resolution images. The use of IOUS in transsphenoidal pituitary surgery may significantly increase rates of gross total resection, while decreasing blood loss, hospital LOS, and operative time.

Comparative study of complications after primary and revision transsphenoidal endoscopic surgeries

A preferred treatment for residual/recurrent pituitary adenomas has not been established. The existence of higher complication rates for revision surgeries remains under debate. This study aimed to compare complication rates of primary and revision transsphenoidal endoscopic surgeries and to identify risk factors for complications. Data from 144 primary and 39 revision surgeries were analysed. The surgical complications evaluated were intraoperative and postoperative cerebrospinal fluid (CSF) leaks; meningitis; permanent diabetes insipidus (DI) and hypopituitarism; worsening visual acuity; ophthalmoplegias; visual field defects; otorhinolaryngological, systemic and vascular complications; and death. The variables that were potentially associated with surgical complications were gender, age, comorbidities, lumbar drain use, duration of lumbar drain use, invasion of the sphenoid and cavernous sinuses, presence and degree of suprasellar expansion, preoperative identification of the pituitary, CSF leaks and intraoperative pituitary identification. Intraoperative CSF leaks, visual field losses and worsening visual acuity were more common for revision surgeries. There were no between-group differences in the occurrence of postoperative CSF leaks; systemic, vascular and otorhinolaryngological complications; meningitis; DI and hypopituitarism; ophthalmoplegias; or death. Intraoperative identification of the pituitary was associated with lower rates of permanent DI and hypopituitarism, systemic complications, intraoperative CSF leaks and worsening visual acuity. Suprasellar expansion increased the risk of intraoperative CSF leaks but not endocrinological deficits or visual impairment. Intraoperative CSF leaks were associated with postoperative CSF leaks, meningitis, anterior hypopituitarism, DI and worsening visual acuity. Intraoperative CSF leaks, worsening visual acuity and visual field losses were more common in reoperated patients.

Surgical Outcomes Following Repeat Transsphenoidal Surgery for Nonfunctional Pituitary Adenomas: A Retrospective Comparative Study

BACKGROUND

Endonasal transsphenoidal surgery (ETSS) remains the preferred treatment for recurrent or residual nonfunctional pituitary adenomas (NFPAs). However, surgical complications and outcomes with repeat ETSS are unclear.

OBJECTIVE

To compare outcomes from primary and repeat ETSS in patients with NFPAs.

METHODS

Retrospective review of ETSS for NFPAs at USC University Hospital and LAC + USC Medical Center between 2000 and 2015. Patients with ≥3-mo follow-up data were included. Patients were categorized as primary or repeat ETSS. Patient and tumor characteristics were compared preoperatively, and postoperative outcomes were analyzed.

RESULTS

Two hundred sixty-eight patients (89%) met the inclusion criteria (primary ETSS = 211 and repeat ETSS = 57) with a mean follow-up time of 38 mo (range 3-235 mo). Both groups had similar demographics, endocrine function, and tumor characteristics. Surgical complication rates were similar and no mortalities were observed. Repeat ETSS patients had a higher rate of new postoperative panhypopituitarism (primary ETSS: 0.5% vs repeat ETSS: 7.1%, P = .011), lower rates of gross total resection (GTR; primary ETSS: 59.2% vs repeat ETSS: 26.3%, P = .001), and greater rates of postoperative radiosurgery (36.8% vs 24.2%, P = .009). At 2-yr follow-up, progression-free survival on MRI was similar in both groups (primary ETSS: 97.9% vs repeat ETSS: 95.4%, log-rank test P = .807).

CONCLUSION

At experienced tertiary pituitary centers, repeat ETSS for NFPAs was associated with a similar incidence of surgical complications as primary ETSS. However, repeat ETSS carried a higher rate for worsening endocrine dysfunction and a lower rate of GTR.

Real-life analysis of 280 patients with surgically treated acromegaly: a single-center experience from 2008 to 2015

OBJECTIVE

The purpose of this study was to analyze the clinical and biochemical outcome of consecutive patients with acromegaly after microscopic transsphenoidal surgery (MTS) at a single center over an 8-year period.

METHODS

A retrospective analysis of patients with acromegaly treated via MTS between 2008 and 2015 at the authors’ center was performed. The mean follow-up was 29 months (range 1–120 months). Parameters investigated included tumor size, pre- and postoperative insulin-like growth factor–I, growth hormone levels, pretreatment, perioperative complications, and clinical outcome.

RESULTS

A total of 280 patients with acromegaly were treated surgically at the authors’ center over the abovementioned time frame and were included in analyses. For 231 of these patients, complete follow-up data were available for evaluation. One hundred eighty-eight patients (81%) showed remission initially according to current criteria. So far, 23 of these patients relapsed in the further course, so that on follow-up 165 patients (71%) demonstrated full remission by surgery alone. Most patients in whom remission after surgery failed were treated with somatostatin receptor ligands and/or dopamine agonists as second-line treatment. The main postoperative complications included transient hyponatremia and diabetes insipidus (13/280; 4.6%). CSF leakage only occurred in 2 cases (2/280; 0.7%). No surgery-related death occurred.

CONCLUSIONS

The data underline the effectiveness of MTS in acromegaly. Many patients with recurrent disease or incomplete tumor resection can be successfully managed pharmacologically.

ICAR: endoscopic skull-base surgery

BACKGROUND

Endoscopic skull-base surgery (ESBS) is employed in the management of diverse skull-base pathologies. Paralleling the increased utilization of ESBS, the literature in this field has expanded rapidly. However, the rarity of these diseases, the inherent challenges of surgical studies, and the continued learning curve in ESBS have resulted in significant variability in the quality of the literature. To consolidate and critically appraise the available literature, experts in skull-base surgery have produced the International Consensus Statement on Endoscopic Skull-Base Surgery (ICAR:ESBS).

METHODS

Using previously described methodology, topics spanning the breadth of ESBS were identified and assigned a literature review, evidence-based review or evidence-based review with recommendations format. Subsequently, each topic was written and then reviewed by skull-base surgeons in both neurosurgery and otolaryngology. Following this iterative review process, the ICAR:ESBS document was synthesized and reviewed by all authors for consensus.

RESULTS

The ICAR:ESBS document addresses the role of ESBS in primary cerebrospinal fluid (CSF) rhinorrhea, intradural tumors, benign skull-base and orbital pathology, sinonasal malignancies, and clival lesions. Additionally, specific challenges in ESBS including endoscopic reconstruction and complication management were evaluated.

CONCLUSION

A critical review of the literature in ESBS demonstrates at least the equivalency of ESBS with alternative approaches in pathologies such as CSF rhinorrhea and pituitary adenoma as well as improved reconstructive techniques in reducing CSF leaks. Evidence-based recommendations are limited in other pathologies and these significant knowledge gaps call upon the skull-base community to embrace these opportunities and collaboratively address these shortcomings.

Outcomes of the Endoscopic Transsphenoidal Surgery for Resection of Pituitary Adenomas Utilizing Extracapsular Dissection Technique with a Cotton Swab

Purpose

The purpose of this study was to determine the effectiveness and safety of a cotton swab for extracapsular dissection in endoscopic transsphenoidal surgery (ETSS) for pituitary adenoma (PA).

Materials and Methods

A retrospective review of patients undergoing ETSS for PA from 2014 to 2017 was undertaken. Only patients with extracapsular dissection by cotton swab with the intent to completely remove the tumor were included. Assessment of the prospectively recorded clinical, laboratory, and radiographic presentation as well as the intra- and postoperative data was carried out. Factors influencing the extent of resection were analyzed.

Results

Of the 222 patients, one hundred cases met the inclusion criteria. The cohort consisted of 81 nonfunctioning and 19 functioning PAs. Fifty patients presented with visual disturbance and 34 patients had prior surgical treatment. The majority of PAs was macroadenoma (97%) with 73% modified Hardy Stage C and 38% Knosp Grade 4. Intraoperative cerebrospinal fluid (CSF) leakage was the most frequently noted complication (78%). Meningitis occurred in three cases and repeat ETSS for CSF leakage repair was necessary in three patients. No death or vascular injury was observed. At 12 months after ETSS, magnetic resonance imaging scan confirmed 43% complete tumor resection. Previous surgery and Knosp Grade 4 were the strong factors for incomplete PA removal by multivariate logistic regression analysis. For functioning PAs, thirteen patients (68.42%) achieved biochemical remission.

Conclusion

Cotton swab for extracapsular dissection proved its clinical effectiveness and safety. In spite of the technique, negative predictors for complete PA resection were parasellar extension and previous surgery.

Utility of deep neural networks in predicting gross-total resection after transsphenoidal surgery for pituitary adenoma: a pilot study

OBJECTIVEGross-total resection (GTR) is often the primary surgical goal in transsphenoidal surgery for pituitary adenoma. Existing classifications are effective at predicting GTR but are often hampered by limited discriminatory ability in moderate cases and by poor interrater agreement. Deep learning, a subset of machine learning, has recently established itself as highly effective in forecasting medical outcomes. In this pilot study, the authors aimed to evaluate the utility of using deep learning to predict GTR after transsphenoidal surgery for pituitary adenoma.METHODSData from a prospective registry were used. The authors trained a deep neural network to predict GTR from 16 preoperatively available radiological and procedural variables. Class imbalance adjustment, cross-validation, and random dropout were applied to prevent overfitting and ensure robustness of the predictive model. The authors subsequently compared the deep learning model to a conventional logistic regression model and to the Knosp classification as a gold standard.RESULTSOverall, 140 patients who underwent endoscopic transsphenoidal surgery were included. GTR was achieved in 95 patients (68%), with a mean extent of resection of 96.8% ± 10.6%. Intraoperative high-field MRI was used in 116 (83%) procedures. The deep learning model achieved excellent area under the curve (AUC; 0.96), accuracy (91%), sensitivity (94%), and specificity (89%). This represents an improvement in comparison with the Knosp classification (AUC: 0.87, accuracy: 81%, sensitivity: 92%, specificity: 70%) and a statistically significant improvement in comparison with logistic regression (AUC: 0.86, accuracy: 82%, sensitivity: 81%, specificity: 83%) (all p < 0.001).CONCLUSIONSIn this pilot study, the authors demonstrated the utility of applying deep learning to preoperatively predict the likelihood of GTR with excellent performance. Further training and validation in a prospective multicentric cohort will enable the development of an easy-to-use interface for use in clinical practice.

The Zurich Pituitary Score predicts utility of intraoperative high-field magnetic resonance imaging in transsphenoidal pituitary adenoma surgery

BACKGROUND

It is currently unclear if there are subsets of patients undergoing transsphenoidal surgery (TSS) in which intraoperative high-field magnetic resonance imaging (3T-iMRI) is particularly advantageous. We aimed to investigate whether a radiological grading scale predicts the utility of 3T-iMRI in pituitary adenoma (PA) TSS.

METHODS

From a prospective registry, patients who underwent endoscopic TSS for PA using 3T-iMRI were identified. Adenomas were graded using the Zurich Pituitary Score (ZPS). We assessed improvement after 3T-iMRI in terms of gross total resection (GTR), residual volume (RV), and extent of resection (EOR).

RESULTS

Among 95 patients, rates of conversion to GTR after 3T-iMRI decreased steadily from 33% for grade I to 0% for grade IV adenomas, with a statistically significant conversion rate only for grade I (p = 0.008) and grade II (p < 0.001). All grade I adenomas were completely resected after 3T-iMRI. Median RV change was statistically significant for grades I to III, but not for grade IV (p = 0.625). EOR improvement ranged from a median change of 0.0% (IQR 0.0-4.5%) for grade I to 4.4% (IQR 0.0-9.0%) for grade IV, with a significant improvement only for grades I to III (p < 0.05).

CONCLUSIONS

Interestingly, this study shows that clinical utility of 3T-iMRI is highest in the more "simple" adenomas (ZPS grades I-II) than for the more "complex" ones (ZPS grade III-IV). Grade I adenomas are amenable to GTR if 3T-iMRI is implemented. In grade III adenomas, EOR and RV can be improved to clinically relevant levels. Conversely, in grade IV adenomas, 3T-iMRI may be of limited use.

Neural network-based identification of patients at high risk for intraoperative cerebrospinal fluid leaks in endoscopic pituitary surgery

OBJECTIVE

Although rates of postoperative morbidity and mortality have become relatively low in patients undergoing transnasal transsphenoidal surgery (TSS) for pituitary adenoma, cerebrospinal fluid (CSF) fistulas remain a major driver of postoperative morbidity. Persistent CSF fistulas harbor the potential for headache and meningitis. The aim of this study was to investigate whether neural network-based models can reliably identify patients at high risk for intraoperative CSF leakage.

METHODS

From a prospective registry, patients who underwent endoscopic TSS for pituitary adenoma were identified. Risk factors for intraoperative CSF leaks were identified using conventional statistical methods. Subsequently, the authors built a prediction model for intraoperative CSF leaks based on deep learning.

RESULTS

Intraoperative CSF leaks occurred in 45 (29%) of 154 patients. No risk factors for CSF leaks were identified using conventional statistical methods. The deep neural network-based prediction model classified 88% of patients in the test set correctly, with an area under the curve of 0.84. Sensitivity (83%) and specificity (89%) were high. The positive predictive value was 71%, negative predictive value was 94%, and F1 score was 0.77. High suprasellar Hardy grade, prior surgery, and older age contributed most to the predictions.

CONCLUSIONS

The authors trained and internally validated a robust deep neural network-based prediction model that identifies patients at high risk for intraoperative CSF. Machine learning algorithms may predict outcomes and adverse events that were previously nearly unpredictable, thus enabling safer and improved patient care and better patient counseling.

[Differential diagnosis and treatment of pituitary adenomas]

Pituitary adenomas are among the most common primary brain tumors. These tumors can produce all hormones of the anterior pituitary and thus cause endocrine diseases. Compression of the pituitary gland, the surrounding cranial nerves, or brain structures can lead to hypopituitarism, cranial nerve deficits, or diverse neurological symptoms. Visual impairment, typically with bitemporal hemianopsia, is the most common cardinal symptom. The diagnostic workup requires broad interdisciplinary cooperation. With the exception of prolactinoma, the treatment of choice for symptomatic pituitary adenoma is transnasal transsphenoidal resection. For prolactinoma, dopamine agonistic therapy is the primary treatment. Adequate hormone replacement therapy is essential in cases of hypopituitarism. Long-term follow-up is a vital part of the treatment concept.

Transsphenoidal pituitary surgery: comparison of two sellar reconstruction techniques and their effect on postoperative cerebrospinal fluid leakage

Transsphenoidal surgery is a common procedure in patients with pituitary adenomas. Several techniques have been previously postulated to achieve sufficient sellar reconstruction to avoid cerebrospinal fluid (CSF) leakage. We analyzed our institutional database concerning two sellar reconstruction techniques and development of postoperative CSF leakage. From 2009 to 2015, 255 patients underwent transsphenoidal pituitary surgery at our institution. According to the technique used for sellar reconstruction, patients were divided into two groups: (1) with muscle patch and fibrin glue and (2) with fibrin glue alone. Postoperative CSF leakage occurred in 7% of the patients. Occurrence of postoperative CSF leakage did not differ significantly between both sellar reconstruction techniques (p = 0.2). Patients who underwent sellar reconstruction with fibrin glue alone had significantly shorter operating time (p < 0.0001), as well as shorter length of hospital stay (p = 0.01). On multivariate analysis, occurrence of intraoperative CSF leakage was the only predictor for postoperative CSF leakage (p < 0.0001). The present data suggests that sellar reconstruction after transsphenoidal pituitary surgery seems to be equally effective in preventing postoperative CSF leakage. However, the use of fibrin glue alone results in shorter hospital stay and operating time without exposing patients to more frequent CSF leakage.

Evolution of Technique in Endoscopic Transsphenoidal Surgery for Pituitary Adenoma: A Single Institution Experience from 220 Procedures

Introduction Endoscopic transsphenoidal surgery (ETSS) for pituitary adenoma (PA) has been a recent shift from the traditional microscopic technique. Although some literature demonstrated superiority of ETSS over the microscopic method and some evaluated mono- vs. binostril access within the ETSS, none had explored the potential influence of dedicated instrument, as this procedure had evolved, on patients' outcomes when compared to traditional microscopic tools. Objective To investigate our own clinical and radiographic outcomes of ETSS for PA with its technical evolution over time as well as a significance of, having vs. lacking, the special endoscopic tools. Methods Included patients underwent ETSS for PA performed by the first author (AH). Prospectively recorded patients' data concerning pre-, intra- and postoperative clinical and radiographic assessments were subject to analysis. The three groups of differently evolving ETSS techniques, beginning with mononostril (MN) to binostril ETSS with standard microsurgical instruments (BN1) and, lastly, binostril ETSS with specially-designed endoscopic tools (BN2), were examined for their impact on the intra- and, short- and long-term, postoperative results. Also, the survival after ETSS for PA, as defined by the need for reintervention in each technical group, was appraised. Results From January 2006 to 2012, there were 47, 101 and 72 ETSS, from 183 patients, in the MN, BN1 and BN2 cohorts, respectively. Significant preoperative findings were greater proportion of patients with prior surgery (p=0.01) and tumors with parasellar extension (p=0.02) in the binostril (BN1&2) than the MN group. Substantially shorter operative time and less amount of blood loss were evident as our technique had evolved (p<0.001). Despite higher incidence, and more advanced grades, of cerebrospinal fluid leakage in the binostril groups (p < 0.001), the requirement for post-ETSS surgical repair was less than the mononostril cohort (p=0.04). At six-month follow-up (n=214), quantitative radiographic outcome analysis was markedly superior in BN2. Consequently, long-term result was better in this latest technical group. Important negative risk factors, from multivariate Cox regression analysis, were prior surgery, Knosp grade, and firm tumor while BN1, BN2 and percentages of anteroposterior dimension PA removal had positive effect on longer survival. Conclusion The evolution of technique for ETSS for PA from MN to BN2 has shown its efficacy by improving intra- and postoperative outcomes in our study cohorts. Based on our results, not only that a neurosurgeon, wishing to start performing ETSS, should enroll in a formal fellowship training but he/she should also utilize advanced endoscopic tools, as we have proved its superior results in dealing with PA.

Resection of pituitary macroadenomas via the pseudocapsule along the posterior tumor margin: a cohort study and technical note

OBJECTIVE Extracapsular resection of pituitary microadenomas improves remission rates, but the application of pseudocapsular techniques for macroadenomas has not been well described. In larger tumors, the extremely thin, compressed normal gland or its complete absence along the tumor's anterior surface limits the application of the traditional pseudocapsular technique that can be used for microadenomas. However, in the authors' experience, the interface between the pseudocapsule at the posterior margin of the adenoma and the compressed normal gland behind it is universally present, providing a surgical dissection plane. In mid-2010, the authors began using a new surgical technique to identify and use this interface for the resection of larger macroadenomas, a technique that can be used with the microscope or the endoscope. METHODS The authors performed a cohort study using prospectively collected preoperative imaging reports and operative details and retrospectively reviewed postoperative images and clinical follow-up of patients with a pituitary macroadenoma 20-40 mm in maximum diameter undergoing microscopic transsphenoidal resection. Since dissection of the tumor capsule only pertains to encapsulated tumor within the sella and not to tumor invading the cavernous sinus, assessment of tumor removal of noninvasive tumors emphasized the entire tumor, while that of invasive tumors emphasized the intrasellar component only. The incidence of residual tumor on postoperative imaging, new-onset endocrinopathy, and recovery of preoperative pituitary deficits was compared between patients who underwent surgery before (Group A) and after (Group B) implementation of the new technique. RESULTS There were 34 consecutive patients in Group A and 74 consecutive patients in Group B. Tumors in 18 (53%) Group A and 40 (54%) Group B patients had no evidence of cavernous sinus invasion on MRI. Use of the posterior pseudocapsule technique reduced the incidence of intrasellar residual tumor on postoperative MRI for tumors without cavernous sinus invasion (39% [Group A] vs 10%, p < 0.05) and in all tumors regardless of invasion (50% vs 18%, p < 0.005). The incidence of new endocrinopathy was less likely (25% vs 12%, p = 0.098) and the recovery of prior deficits more likely (13% vs 27%, p = 0.199) among patients treated using the pseudocapsule approach, although the differences are not statistically significant. CONCLUSIONS Use of the posterior pseudocapsule dissection plane can enhance the resection of pituitary macroadenomas.

The Value of Intraoperative Magnetic Resonance Imaging in Endoscopic and Microsurgical Transsphenoidal Pituitary Adenoma Resection

BACKGROUND

The routine use of intraoperative magnetic resonance imaging (iMRI) helps to achieve gross total resection in transsphenoidal pituitary surgery. We compared the added value of iMRI for extent of resection in endoscopic versus microsurgical transsphenoidal adenomectomy.

METHODS

A total of 96 patients with pituitary adenoma were included. Twenty-eight consecutive patients underwent endoscopic transsphenoidal tumor resection. For comparison, we used a historic cohort of 68 consecutive patients treated microsurgically. We evaluated the additional resection after conducting iMRI using intraoperative and late postoperative volumetric tumor analysis 3 months after surgery. Demographic data, clinical symptoms, and complications as well as pituitary function were evaluated.

RESULTS

We found significantly fewer additional resections after conducting iMRI in the endoscopic group (P = 0.042). The difference was even more profound in Knosp grade 0-2 adenomas (P = 0.029). There was no significant difference in Knosp grade 3-4 adenomas (P = 0.520). The endoscopic approach was associated with smaller intraoperative tumor volume (P = 0.023). No significant difference was found between both techniques in postoperative tumor volume (P = 0.228). Satisfactory results of pituitary function were significantly more often associated with an endoscopic approach in the multiple regression analysis (P = 0.007; odds ratio, 17.614; confidence interval 95%, 2.164-143.396).

CONCLUSIONS

With the endoscopic approach, significantly more tumor volume reduction was achieved before conducting iMRI, decreasing the need for further resection. This finding was even more pronounced in adenomas graded Knosp 0-2. In the case of extensive and invasive adenomas with infiltration of cavernous sinus and suprasellar or parasellar extension, additional tumor resection and increase in the extent of resection was achieved with iMRI in both groups. The endoscopic approach seems to result in better endocrine outcomes, especially in Knosp grade 0-2 pituitary adenomas.