Three-dimensional prostate CT segmentation through fine-tuning of a pre-trained neural network using no reference labeling

Kayla Caughlin, Maysam Shahedi, Jonathan E. Shoag, Christopher Barbieri, Daniel Margolis, Baowei Fei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Accurate segmentation of the prostate on computed tomography (CT) has many diagnostic and therapeutic applications. However, manual segmentation is time-consuming and suffers from high inter- and intra-observer variability. Computerassisted approaches are useful to speed up the process and increase the reproducibility of the segmentation. Deep learningbased segmentation methods have shown potential for quick and accurate segmentation of the prostate on CT images. However, difficulties in obtaining manual, expert segmentations on a large quantity of images limit further progress. Thus, we proposed an approach to train a base model on a small, manually-labeled dataset and fine-tuned the model using unannotated images from a large dataset without any manual segmentation. The datasets used for pre-training and finetuning the base model have been acquired in different centers with different CT scanners and imaging parameters. Our fine-tuning method increased the validation and testing Dice scores. A paired, two-tailed t-test shows a significant change in test score (p = 0.017) demonstrating that unannotated images can be used to increase the performance of automated segmentation models.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2021
Subtitle of host publicationImage-Guided Procedures, Robotic Interventions, and Modeling
EditorsCristian A. Linte, Jeffrey H. Siewerdsen
PublisherSPIE
ISBN (Electronic)9781510640252
DOIs
StatePublished - 2021
EventMedical Imaging 2021: Image-Guided Procedures, Robotic Interventions, and Modeling - Virtual, Online
Duration: Feb 15 2021Feb 19 2021

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11598
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2021: Image-Guided Procedures, Robotic Interventions, and Modeling
CityVirtual, Online
Period2/15/212/19/21

Keywords

  • Computed tomography (CT)
  • Deep learning
  • Fine tuning
  • Image segmentation
  • Pre-trained neural networks
  • Prostate

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Three-dimensional prostate CT segmentation through fine-tuning of a pre-trained neural network using no reference labeling'. Together they form a unique fingerprint.

Cite this