Prediction of the Recurrence of Non-Functioning Pituitary Adenomas Using Preoperative Supra-Intra Sellar Volume and Tumor-Carotid Distance

To study the currently available data of recurrence rates of functioning and nonfunctioning pituitary adenomas following surgical cure and to analyze associated predisposing factors, which are not well established. A systematic literature search was conducted using Medline, Embase, Web of Science and the Cochran Library for studies reporting data on recurrence of pituitary adenoma after surgery, in nonfunctioning adenoma (NF), prolactinoma (PRL) acromegaly (ACRO) and Cushing’s disease (CUSH). Of 557 initially retrieved potential relevant studies 143 were selected. Recurrence in NFA was defined as reappearance of tumor on MRI or CT. Increase of hormone levels above normal limits as set by the authors after initial remission was used to indicate recurrence in the functioning tumor types. Remission percentage was lowest in NFA compared with other tumor types (P < 0.001). Surgery-related hypopituitarism was more frequent in CUSH than in the other tumors (P < 0.001). Recurrence, expressed as percentage of the cured population or as ratio of recurrence and total patient years of follow-up was highest in PRL (P < 0.001). The remission percentage did not improve over 3 decades of publications, but there was a modest decrease in recurrence rate (P = 0.04). Recurrences peaked between 1 and 5 years after surgery. Most of the studies with a sufficient number of recurrences did not apply multivariate statistics, and mentioned at best associated factors. Age, gender, tumor size and invasion were generally unrelated to recurrence. For functioning adenomas a low postoperative hormone concentration was a prognostically favorable factor. In NFA no specific factor predicted recurrence. Recurrence rate differs between pituitary adenomas, being highest in patients with prolactinoma, with the highest incidence of recurrence between 1 and 5 years after surgery in all adenomas. Patients with NFA have a lower chance of remission than patients with functioning adenomas. The postoperative basal hormone level is the most important predictor for recurrence in functioning adenomas, while in NFA no single convincing factor could be identified.

In this study, we present pituitary adenoma volumetry using the free and open source medical image computing platform for biomedical research: (3D) Slicer. Volumetric changes in cerebral pathologies like pituitary adenomas are a critical factor in treatment decisions by physicians and in general the volume is acquired manually. Therefore, manual slice-by-slice segmentations in magnetic resonance imaging (MRI) data, which have been obtained at regular intervals, are performed. In contrast to this manual time consuming slice-by-slice segmentation process Slicer is an alternative which can be significantly faster and less user intensive. In this contribution, we compare pure manual segmentations of ten pituitary adenomas with semi-automatic segmentations under Slicer. Thus, physicians drew the boundaries completely manually on a slice-by-slice basis and performed a Slicer-enhanced segmentation using the competitive region-growing based module of Slicer named GrowCut. Results showed that the time and user effort required for GrowCut-based segmentations were on average about thirty percent less than the pure manual segmentations. Furthermore, we calculated the Dice Similarity Coefficient (DSC) between the manual and the Slicer-based segmentations to proof that the two are comparable yielding an average DSC of 81.97±3.39%.

Gross-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. Data 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. Overall, 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). In 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.