Prognostic significance of intraoperative change in the fractional anisotropy and the volume of the optic chiasma during resection of suprasellar 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.

Diffusion Tensor Imaging and Neurite Orientation Dispersion and Density Imaging Assessment of Optic Pathway Function in Patients With Anterior Visual Pathway Compression

BACKGROUND

In patients with sellar or parasellar tumors, it is crucial to evaluate visual field impairment in the preoperative stage and to predict visual field improvement after the surgery. The purpose of this study was to investigate the associations of diffusion tensor imaging (DTI) and neurite orientation dispersion and density imaging (NODDI) parameters in the optic radiations with preoperative and postoperative visual field impairment.

METHODS

This prospective study included 81 participants with sellar or parasellar tumors. Multishell diffusion imaging and a visual field impairment score (VFIS) were acquired before and after the surgery. The multishell diffusion-weighted imaging was acquired to measure the neurite density and neurite orientation dispersion, as well as the diffusivity. DTI parameters were fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity, and radial diffusivity (RD). NODDI provided intracellular volume fraction (Vic), the orientation dispersion index, and isotropic volume fraction (Viso). The associations of DTI and NODDI parameters in the optic radiations with VFIS were investigated, adjusting for age, tumor height, and symptom duration.

RESULTS

Among 162 optic radiations, 117 were functionally impaired in the preoperative stage. FA and Vic had significant negative correlations, whereas MD and RD had significant positive correlations with the VFIS (all P < 0.001). In the preoperative stage, lower FA (P = 0.001; odds ratio = 0.750) and Vic (P = 0.003; OR = 0.827) and higher MD (P = 0.007; OR = 1.244) and RD (P < 0.001; OR = 1.361) were significantly associated with the presence of visual field impairment. For the degree of postoperative improvement, preoperative lower Vic (P = 0.034; OR = 0.910) and higher MD (P = 0.037; OR = 1.103) and RD (P = 0.047; OR = 1.090) were significantly associated with more postoperative improvement.

CONCLUSIONS

DTI and NODDI parameters in the optic radiations were correlated with VFIS and associated with preoperative visual field impairments and postoperative improvement. It may help in predicting visual field improvement after the surgery in patients with sellar or parasellar tumors.

The Visual Acuity Outcome and Relevant Factors Affecting Visual Improvement in Pediatric Sporadic Chiasmatic-Hypothalamic Glioma Patients Who Received Surgery

Background: The role and effectiveness of primary surgical treatment for sporadic chiasmatic–hypothalamic glioma (CHG) are not clear. The present study was to describe sporadic CHG visual acuity (VA) outcomes after surgery and to analyze the relevant factors affecting VA improvement.

Methods: Forty-five pediatric sporadic CHG patients who met the inclusion criteria were included in a retrospective study. All patients received primary intratumor partial resection. Disease characteristics, treatment strategies, complications, and VA outcome were analyzed. Univariate and multivariate analyses were performed to identify relevant factors of VA improvement. Receiver operating characteristic (ROC) analysis was performed to evaluate the predictive accuracy of measurement indexes.

Results: There were 77 eyes of 45 children suffering from various levels of VA impairment before surgical treatment, and only 13 eyes had normal vision. Patients with resection extents >70, 50–70, and <50% accounted for 26.67, 24.44, and 48.89%, respectively. The percentages of VA maintained and deteriorated in normal vision eyes were 61.54 and 38.46%. The percentages of VA improved, maintained, and deteriorated in visually impaired eyes after surgery were 29.87, 45.45, and 24.68%, respectively. There was a positive correlation between the IVA level and VA improvement. There was no significant difference in VA improvement between the different resection extents. Blindness occurred in ~4.4%. Approximately 11.1% of the children had complications that affected quality of life, which correlated with resection extent. IVA and tumor size were correlated with VA improvement. The AUC for IVA + tumor size predicting VA improvement was 0.831. The cutoff points for IVA level and tumor volume were 4.5 and 43.50 cm³, respectively.

Conclusions: IVA and tumor size were correlated with VA improvement after primary intratumor partial resection. Children with IVA ≥ level 5 were more likely to achieve visual improvement after decompression surgery, but decompression had limited effectiveness on vision improvement in patients with tumor volumes ≥ 43.50 cm³. Performing resections < 50% was safe and did not reduce the effect of decompression to improve VA.

Increased resting-state functional connectivity in suprasellar tumor patients with postoperative visual improvement

Background and Objective: Large suprasellar tumors often compress the optic chiasm and give rise to visual impairment. Most patients have significantly improved visual function at 1 to 4 months after chiasmal decompression surgery, and only a few individuals regain normal vision at 1 week after surgery. How the recovery of visual function in these patients affects the visual cortex is not fully understood. In this study, we aimed to investigate alterations in brain functional connectivity (FC) in suprasellar tumor patients with visual improvement using resting-state functional magnetic resonance imaging (rs-fMRI). Methods: This longitudinal study was conducted on 13 suprasellar tumor patients who had ophthalmological examinations and rs-fMRI at the following time points: within 1-week preoperation (Pre-op), 1-week postoperation (Post-1w) and 1-month postoperation (Post-1m). The visual impairment score (VIS), local functional correlation (LCOR) and FC values were subjected to one-way ANOVA. Pearson correlation coefficients between changes in the LCOR and clinical factors were calculated. Results: The VIS was significantly decreased at both Post-1w and Post-1m compared to that at Pre-op. Whole-brain analysis of LCOR values showed that the left V1 (primary occipital cortex) was increased significantly at Post-1m compared to that at Pre-op (p < 0.05, FDR corrected). ROI analysis exhibited a significant negative correlation between the LCOR and VIS changes at Post-1m compared to those at Pre-op (p < 0.05, r = - 0.60). FC analysis within the visual network showed that the FC strengths were significantly increased between the left V5 and the left V4, right V3a, left V3, left V2d, and right V5 at Post-1m compared to those at Pre-op (p < 0.05, FDR corrected). Additionally, the FC strengths were significantly increased between the left V5 and the left V1, right orbital-frontal gyrus and left posterior supramarginal gyrus at the whole-brain network level at Post-1m compared to those at Pre-op (p < 0.05, FDR corrected). Conclusions: Postoperative visual improvement can be reflected by the increased FC of the visual cortex at Post-1w and Post-1m, especially at Post-1m. The LCOR value of the left V1 was associated with improved visual outcomes and may be used to objectively assess early visual recovery after chiasmal decompression at Post-1m.