Lesion-wise evaluation for effective performance monitoring of small object segmentation

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

  • Irme Groothuis
  • Carole H. Sudre
  • Silvia Ingala
  • Jo Barnes
  • Juan Domingo Gispert
  • Lauge Sørensen
  • Akshay Pai
  • Nielsen, Mads
  • Sebastien Ourselin
  • M. Jorge Cardoso
  • Frederik Barkhof
  • Marc Modat

Object detection in medical images using deep learning is a challenging task, due to the imbalance often present in the data. Deep learning algorithms require large amount of balanced data to achieve optimal performance, as well as close monitoring and ne-tuning of hyper parameters. For most applications, such performance monitoring is done by simply feeding unseen data trough the network, and then using the loss function for evaluation. In the case of small or sparse objects, the loss function might not able to describe the features needed, but such features can be hard to capture in a loss function. In this paper we introduce a lesion-wise whole volume validation tool, which allows more a more accurate performance monitoring of segmentation of small and sparse objects. We showcase the efficacy of our tool by applying it to the task of microbleed segmentation, and compare the behaviour of lesionwise-whole volume validation compared to well known segmentation loss functions. Microbleeds are visible as small (less than 10 mm), ovoid hypo-intensities on T2∗-weighted and susceptibility weighted magnetic resonance images. Detection of microbleeds is clinically relevant, as microbleeds can indicate the risk of recurrent stroke, and are used as imaging biomarker for various neurodegenerative diseases. Manual detection or segmentation is time consuming and error prone, and suffers from high inter- and intraobserver variability. Due to the sparsity and small size of the lesions, the data is severely imbalanced.

Original languageEnglish
Title of host publicationMedical Imaging 2021 : Image Processing
EditorsIvana Isgum, Bennett A. Landman
Publication date2021
Article number1159608
ISBN (Electronic)9781510640214
Publication statusPublished - 2021
Externally publishedYes
EventMedical Imaging 2021: Image Processing - Virtual, Online, United States
Duration: 15 Feb 202119 Feb 2021


ConferenceMedical Imaging 2021: Image Processing
LandUnited States
ByVirtual, Online
SponsorThe Society of Photo-Optical Instrumentation Engineers (SPIE)
SeriesProgress in Biomedical Optics and Imaging - Proceedings of SPIE

Bibliographical note

Publisher Copyright:
© 2021 SPIE.

    Research areas

  • Data imbalance, Evaluation, Microbleed

ID: 300692591