@inbook{f4e0f3d2810f44618f3ea2069c04a2f0,
title = "Lesion-wise evaluation for effective performance monitoring of small object segmentation",
abstract = "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. ",
keywords = "Data imbalance, Evaluation, Microbleed",
author = "Irme Groothuis and Sudre, {Carole H.} and Silvia Ingala and Jo Barnes and Gispert, {Juan Domingo} and Lauge S{\o}rensen and Akshay Pai and Mads Nielsen and Sebastien Ourselin and Cardoso, {M. Jorge} and Frederik Barkhof and Marc Modat",
note = "Funding Information: This project has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under the Marie Sk lodowska-Curie grant agreement No 721820. Funding Information: The authors would like to thank the ADNI and ALFA consortia for providing access to their data. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the P6000 GPU used for this research. Publisher Copyright: {\textcopyright} 2021 SPIE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; Medical Imaging 2021: Image Processing ; Conference date: 15-02-2021 Through 19-02-2021",
year = "2021",
doi = "10.1117/12.2580734",
language = "English",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Ivana Isgum and Landman, {Bennett A.}",
booktitle = "Medical Imaging 2021",
}
