Systematic Review of Pituitary Gland and Pituitary Adenoma Automatic Segmentation Techniques in Magnetic Resonance Imaging

TL;DR

This systematic review analyzes recent automatic segmentation techniques for pituitary glands and adenomas in MRI, highlighting deep learning methods like U-Net, their performance, and the need for further improvements for clinical use.

Contribution

It provides a comprehensive synthesis of existing automatic segmentation methods, emphasizing the prevalence of deep learning models and identifying gaps in current research.

Findings

Deep learning, especially U-Net, dominates current segmentation approaches.

Automatic methods achieve variable Dice scores, often below optimal levels.

Further research needed for consistent performance, especially on small structures.

Abstract

Purpose: Accurate segmentation of both the pituitary gland and adenomas from magnetic resonance imaging (MRI) is essential for diagnosis and treatment of pituitary adenomas. This systematic review evaluates automatic segmentation methods for improving the accuracy and efficiency of MRI-based segmentation of pituitary adenomas and the gland itself. Methods: We reviewed 34 studies that employed automatic and semi-automatic segmentation methods. We extracted and synthesized data on segmentation techniques and performance metrics (such as Dice overlap scores). Results: The majority of reviewed studies utilized deep learning approaches, with U-Net-based models being the most prevalent. Automatic methods yielded Dice scores of 0.19--89.00\% for pituitary gland and 4.60--96.41\% for adenoma segmentation. Semi-automatic methods reported 80.00--92.10\% for pituitary gland and 75.90--88.36\% for adenoma segmentation. Conclusion: Most studies did not report important metrics such as MR field strength, age and adenoma size. Automated segmentation techniques such as U-Net-based models show promise, especially for adenoma segmentation, but further improvements are needed to achieve consistently good performance in small structures like the normal pituitary gland. Continued innovation and larger, diverse datasets are likely critical to enhancing clinical applicability.