Prognostic value of macular ganglion cell layer thickness for visual outcome in parasellar tumors

Predicting visual recovery in pituitary adenoma patients post-endoscopic endonasal transsphenoidal surgery: Harnessing delta-radiomics of the optic chiasm from MRI

OBJECTIVES

To investigate whether morphological changes after surgery and delta-radiomics of the optic chiasm obtained from routine MRI could help predict postoperative visual recovery of pituitary adenoma patients.

METHODS

A total of 130 pituitary adenoma patients were retrospectively enrolled and divided into the recovery group (n = 87) and non-recovery group (n = 43) according to visual outcome 1 year after endoscopic endonasal transsphenoidal surgery. Morphological parameters of the optic chiasm were measured preoperatively and postoperatively, including chiasmal thickness, deformed angle, and suprasellar extension. Delta-radiomics of the optic chiasm were calculated based on features extracted from preoperative and postoperative coronal T2-weighted images, followed by machine learning modeling using least absolute shrinkage and selection operator wrapped with support vector machine through fivefold cross-validation in the development set. The delta-radiomic model was independently evaluated in the test set, and compared with the combined model that incorporated delta-radiomics, significant clinical and morphological parameters.

RESULTS

Postoperative morphological changes of the optic chiasm could not significantly be used as predictors for the visual outcome. In contrast, the delta-radiomics model represented good performances in predicting visual recovery, with an AUC of 0.821 in the development set and 0.811 in the independent test set. Moreover, the combined model that incorporated age and delta-radiomics features of the optic chiasm achieved the highest AUC of 0.841 and 0.840 in the development set and independent test set, respectively.

CONCLUSIONS

Our proposed machine learning models based on delta-radiomics of the optic chiasm can be used to predict postoperative visual recovery of pituitary adenoma patients.

CLINICAL RELEVANCE STATEMENT

Our delta-radiomics-based models from MRI enable accurate visual recovery predictions in pituitary adenoma patients who underwent endoscopic endonasal transsphenoidal surgery, facilitating better clinical decision-making and ultimately improving patient outcomes.

KEY POINTS

• Prediction of the postoperative visual outcome for pituitary adenoma patients is important but challenging. • Delta-radiomics of the optic chiasm after surgical decompression represented better prognostic performances compared with its morphological changes. • The proposed machine learning models can serve as novel approaches to predict visual recovery for pituitary adenoma patients in clinical practice.

Preoperative volume of the optic chiasm is an easily obtained predictor for visual recovery of pituitary adenoma patients following endoscopic endonasal transsphenoidal surgery: a cohort study

BACKGROUND

Predicting the postoperative visual outcome of pituitary adenoma patients is important but remains challenging. This study aimed to identify a novel prognostic predictor which can be automatically obtained from routine MRI using a deep learning approach.

MATERIALS AND METHODS

A total of 220 pituitary adenoma patients were prospectively enrolled and stratified into the recovery and nonrecovery groups according to the visual outcome at 6 months after endoscopic endonasal transsphenoidal surgery. The optic chiasm was manually segmented on preoperative coronal T2WI, and its morphometric parameters were measured, including suprasellar extension distance, chiasmal thickness, and chiasmal volume. Univariate and multivariate analyses were conducted on clinical and morphometric parameters to identify predictors for visual recovery. Additionally, a deep learning model for automated segmentation and volumetric measurement of optic chiasm was developed with nnU-Net architecture and evaluated in a multicenter data set covering 1026 pituitary adenoma patients from four institutions.

RESULTS

Larger preoperative chiasmal volume was significantly associated with better visual outcomes ( P =0.001). Multivariate logistic regression suggested it could be taken as the independent predictor for visual recovery (odds ratio=2.838, P <0.001). The auto-segmentation model represented good performances and generalizability in internal (Dice=0.813) and three independent external test sets (Dice=0.786, 0.818, and 0.808, respectively). Moreover, the model achieved accurate volumetric evaluation of the optic chiasm with an intraclass correlation coefficient of more than 0.83 in both internal and external test sets.

CONCLUSION

The preoperative volume of the optic chiasm could be utilized as the prognostic predictor for visual recovery of pituitary adenoma patients after surgery. Moreover, the proposed deep learning-based model allowed for automated segmentation and volumetric measurement of the optic chiasm on routine MRI.

Ocular Optical Coherence Tomography in the Evaluation of Sellar and Parasellar Masses: A Review

Compression of the anterior visual pathways by sellar and parasellar masses can produce irreversible and devastating visual loss. Optical coherence tomography (OCT) is a noninvasive high-resolution ocular imaging modality routinely used in ophthalmology clinics for qualitative and quantitative analysis of optic nerve and retinal structures, including the retinal ganglion cells. By demonstrating structural loss of the retinal ganglion cells whose axons form the optic nerve before decussating in the optic chiasm, OCT imaging of the optic nerve and retina provides an excellent tool for detection and monitoring of compressive optic neuropathies and chiasmopathies due to sellar and parasellar masses. Recent studies have highlighted the role of OCT imaging in the diagnosis, follow-up, and prognostication of the visual outcomes in patients with chiasmal compression. OCT parameters of optic nerve and macular scans such as peripapillary retinal nerve fiber layer thickness and macular ganglion cell thickness are correlated with the degree of visual loss; additionally, OCT can detect clinically significant optic nerve and chiasmal compression before visual field loss is revealed on automated perimetry. Preoperative values of OCT optic nerve and macular parameters represent a prognostic tool for postoperative visual outcome. This review provides a qualitative analysis of the current applications of OCT imaging of the retina and optic nerve in patients with anterior visual pathway compression from sellar and parasellar masses. We also review the role of new technologies such as OCT-angiography, which could improve the prognostic ability of OCT to predict postoperative visual function.

Diagnostic and Prognostic Utility of Optical Coherence Tomography in Patients with Sellar/Suprasellar Lesions with Chiasm Impingement: A Systematic Review/ Meta-Analyses

BACKGROUND

In this review, we appraised the current literature on the utility of optical coherence tomography (OCT) as a diagnostic and predictive factor for postoperative visual function outcomes in patients with sellar/suprasellar lesions with chiasmal impingement.

METHODS

A systematic search of PubMed, CINAHL, Scopus, and Cochrane Library was conducted following PRISMA guidelines. Included studies described diagnostic or prognostic utility of OCT in patients with sellar/suprasellar lesions with chiasmal impingement. Meta-analysis was represented with mean difference (MD) with 95% confidence intervals. Meta-regression was performed to determine predictive factors of visual outcomes.

RESULTS

Forty-eight articles were identified for final pooled analysis, representing a total of 2,435 patients with compressive sellar/suprasellar lesions and 952 healthy controls. Mean age was 43.3(11.4) years, with 1,494(48.8%) male and 1,566(51.2%) female patients. Mean retinal nerve fiber layer(RNFL) was significantly different in the study population compared to healthy controls(75.8μ[13.2] vs 91.4μ[10.8], p<0.00001). The nasal segment of RNFL had the largest mean difference (MD -9.76[-12.39, -7.13], p<0.0001). Visual acuity, visual field mean deviation (VF-MD), and visual field pattern standard deviation, all showed significant differences between the study population and healthy controls as well(p<0.0001). Meta-regressions showed significant predictive capability of preoperative RNFL in determining visual function outcome (p<0.05).

CONCLUSION

Our findings provide promising support for the growing evidence that OCT parameters can be utilized as both a diagnostic and prognostic tool for patients with compression of the optic apparatus. There is a need for further studies to gain a better understanding of OCTs and to improve patient outcomes.

Prognostic Utility of Optical Coherence Tomography for Visual Outcome After Extended Endoscopic Endonasal Surgery for Adult Craniopharyngiomas

INTRODUCTION

Owing to the close vicinity of the optic chiasma, visual dysfunction is known as one of the most common surgical indications and postoperative complications in adult patients with craniopharyngiomas, probably leading to poor quality of life. Historically, very few consistent predictive factors associated with the visual outcome are identified, which may not be helpful for patient counseling and preoperative decision making. Recently, optical coherence tomography (OCT) serving as a novel high-resolution imaging technique can assess the retinal morphology by measuring the circumpapillary retinal nerve fiber layer (cpRNFL) and macular ganglion cell complex thickness. However, few studies have examined the prognostic utility of OCT parameters for visual outcome after surgery for craniopharyngiomas. This study aims to use the largest series to evaluate the association between OCT parameters and visual outcome after extended endoscopic endonasal surgery (EEES) for primary craniopharyngiomas in adults.

MATERIAL AND METHODS

From October 2018 to October 2020, one hundred and seventy eyes in 88 adult patients with newly confirmed craniopharyngiomas were retrospectively reviewed and pertinent prognostic factors were analyzed.

RESULTS

Gross total resection was performed in 82 (93.2%) patients. The median postoperative follow-up time was 10.9 months. Multiple logistic regression analysis showed that increased temporal cpRNFL thickness was associated with higher odds of visual acuity (VA) improvement and maintenance (OR = 1.070; 95% CI, 1.005-1.140; p = 0.035), and greater inferior cpRNFL thickness was significantly associated with visual field (VF) improvement and maintenance (OR = 1.034; 95% CI, 1.001-1.068; p = 0.046). Furthermore, tight adhesion between optic nerves and craniopharyngiomas was demonstrated as an independent adverse factor for either postoperative VA or VF (p = 0.048, p = 0.030, respectively). The ROC results further verified the robustness of the prediction model either in VA (AUC = 0.843; 95% CI, 0.734-0.952; p < 0.001) or VF (AUC = 0.849; 95% CI, 0.741-0.958; p < 0.001).

CONCLUSION

Preoperative OCT can effectively predict visual outcome after EEES for adult craniopharyngiomas. It can also serve as a reliable alternative to evaluate preoperative visual field defects, especially for patients with lower compliance. Tight adhesion was confirmed as an independent risk factor for postoperative visual outcome. The OCT-based multivariable prediction models developed in the present study may contribute to patient counseling on visual prognosis.

Interocular symmetry of optical coherence tomography parameters in healthy children and adolescents

Evaluation of interocular asymmetry of optical coherence tomography (OCT) parameters is important for the glaucoma and optic neuropathies. This study was performed to evaluate the interocular asymmetry of OCT parameters in healthy children and adolescents. The circumpapillary retinal nerve fiber layer (RNFL) thickness, optic nerve head (ONH) parameters, and macular ganglion cell-inner plexiform layer (GCIPL) thickness were measured in 620 eyes of 310 healthy children and adolescents using Cirrus HD-OCT. The interocular asymmetry (right eye-left eye) in the OCT parameters was analyzed. The mean ± standard deviation age was 10.3 ± 3.7 years (range 5-17). The right eyes showed thinner superior quadrant RNFL, thicker nasal and temporal quadrant RNFL, lesser rim and disc areas, and thinner average, superior, and superonasal GCIPL than the left eyes (P < 0.05). The 2.5th and 97.5th percentile interocular difference tolerance limits were - 9.0 μm and 11.0 μm for average RNFL thickness, - 0.21 and 0.18 for average cup-to-disc ratio, and - 4.0 μm and 4.0 μm for average GCIPL thickness, respectively. Interocular differences were found in RNFL thickness, ONH parameters, and GCIPL thickness in healthy children and adolescents. These findings should be considered when comparing OCT parameters between the right and left eyes.

Machine Learning-Based Radiomics of the Optic Chiasm Predict Visual Outcome Following Pituitary Adenoma Surgery

Preoperative prediction of visual recovery after pituitary adenoma surgery remains a challenge. We aimed to investigate the value of MRI-based radiomics of the optic chiasm in predicting postoperative visual field outcome using machine learning technology. A total of 131 pituitary adenoma patients were retrospectively enrolled and divided into the recovery group (N = 79) and the non-recovery group (N = 52) according to visual field outcome following surgical chiasmal decompression. Radiomic features were extracted from the optic chiasm on preoperative coronal T2-weighted imaging. Least absolute shrinkage and selection operator regression were first used to select optimal features. Then, three machine learning algorithms were employed to develop radiomic models to predict visual recovery, including support vector machine (SVM), random forest and linear discriminant analysis. The prognostic performances of models were evaluated via five-fold cross-validation. The results showed that radiomic models using different machine learning algorithms all achieved area under the curve (AUC) over 0.750. The SVM-based model represented the best predictive performance for visual field recovery, with the highest AUC of 0.824. In conclusion, machine learning-based radiomics of the optic chiasm on routine MR imaging could potentially serve as a novel approach to preoperatively predict visual recovery and allow personalized counseling for individual pituitary adenoma patients.

Recent advances and future directions on the use of optical coherence tomography in neuro-ophthalmology

Optical coherence tomography (OCT) is a noninvasive imaging technique used to qualitatively and quantitatively analyze various layers of the retina. OCT of the retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform layer (GCIPL) is particularly useful in neuro-ophthalmology for the evaluation of patients with optic neuropathies and retrochiasmal visual pathway disorders. OCT allows for an objective quantification of edema and atrophy of the RNFL and GCIPL, which may be evident before obvious clinical signs and visual dysfunction develop. Enhanced depth imaging OCT allows for visualization of deep structures of the optic nerve and has emerged as the gold standard for the detection of optic disc drusen. In the evaluation of compressive optic neuropathies, OCT RNFL and GCIPL thicknesses have been established as the most important visual prognostic factor. There is increasing evidence that inclusion of OCT as part of the diagnostic criteria for multiple sclerosis (MS) increases its sensitivity. Moreover, OCT of the RNFL and GCIPL may be helpful in the early detection and monitoring the treatment of conditions such as MS and Alzheimer's disease. OCT is an important aspect of the neuro-ophthalmologic assessment and its use is likely to increase moving forward.