Pituitary Adenoma Segmentation

TL;DR

This paper introduces an automated segmentation method for pituitary adenomas in MRI scans, achieving high accuracy and significantly reducing segmentation time compared to manual methods.

Contribution

The study adapts a previously developed segmentation scheme for glioblastoma to pituitary adenomas, demonstrating its effectiveness and efficiency in clinical MRI data.

Findings

Average DSC of 77.49% indicating high segmentation accuracy

Segmentation time reduced to less than 4 seconds from nearly 4 minutes

Method successfully compares with expert manual segmentation

Abstract

Sellar tumors are approximately 10-15% among all intracranial neoplasms. The most common sellar lesion is the pituitary adenoma. Manual segmentation is a time-consuming process that can be shortened by using adequate algorithms. In this contribution, we present a segmentation method for pituitary adenoma. The method is based on an algorithm we developed recently in previous work where the novel segmentation scheme was successfully used for segmentation of glioblastoma multiforme and provided an average Dice Similarity Coefficient (DSC) of 77%. This scheme is used for automatic adenoma segmentation. In our experimental evaluation, neurosurgeons with strong experiences in the treatment of pituitary adenoma performed manual slice-by-slice segmentation of 10 magnetic resonance imaging (MRI) cases. Afterwards, the segmentations were compared with the segmentation results of the proposed method via the DSC. The average DSC for all data sets was 77.49% +/- 4.52%. Compared with a manual segmentation that took, on the average, 3.91 +/- 0.54 minutes, the overall segmentation in our implementation required less than 4 seconds.