Author:
Isaksson Lars Johannes,Pepa Matteo,Summers Paul,Zaffaroni Mattia,Vincini Maria Giulia,Corrao Giulia,Mazzola Giovanni Carlo,Rotondi Marco,Lo Presti Giuliana,Raimondi Sara,Gandini Sara,Volpe Stefania,Haron Zaharudin,Alessi Sarah,Pricolo Paola,Mistretta Francesco Alessandro,Luzzago Stefano,Cattani Federica,Musi Gennaro,Cobelli Ottavio De,Cremonesi Marta,Orecchia Roberto,Marvaso Giulia,Petralia Giuseppe,Jereczek-Fossa Barbara Alicja
Abstract
Abstract
Background
Contouring of anatomical regions is a crucial step in the medical workflow and is both time-consuming and prone to intra- and inter-observer variability. This study compares different strategies for automatic segmentation of the prostate in T2-weighted MRIs.
Methods
This study included 100 patients diagnosed with prostate adenocarcinoma who had undergone multi-parametric MRI and prostatectomy. From the T2-weighted MR images, ground truth segmentation masks were established by consensus from two expert radiologists. The prostate was then automatically contoured with six different methods: (1) a multi-atlas algorithm, (2) a proprietary algorithm in the Syngo.Via medical imaging software, and four deep learning models: (3) a V-net trained from scratch, (4) a pre-trained 2D U-net, (5) a GAN extension of the 2D U-net, and (6) a segmentation-adapted EfficientDet architecture. The resulting segmentations were compared and scored against the ground truth masks with one 70/30 and one 50/50 train/test data split. We also analyzed the association between segmentation performance and clinical variables.
Results
The best performing method was the adapted EfficientDet (model 6), achieving a mean Dice coefficient of 0.914, a mean absolute volume difference of 5.9%, a mean surface distance (MSD) of 1.93 pixels, and a mean 95th percentile Hausdorff distance of 3.77 pixels. The deep learning models were less prone to serious errors (0.854 minimum Dice and 4.02 maximum MSD), and no significant relationship was found between segmentation performance and clinical variables.
Conclusions
Deep learning-based segmentation techniques can consistently achieve Dice coefficients of 0.9 or above with as few as 50 training patients, regardless of architectural archetype. The atlas-based and Syngo.via methods found in commercial clinical software performed significantly worse (0.855$$-$$
-
0.887 Dice).
Publisher
Springer Science and Business Media LLC
Subject
Radiology, Nuclear Medicine and imaging
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献