loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Gabriel Oliveira ; Lucas David ; Rafael Padilha ; Ana Paula da Silva ; Francine de Paula ; Lucas Infante ; Lucio Jorge ; Patricia Xavier and Zanoni Dias

Affiliation: Institute of Computing, University of Campinas, Campinas, SP, Brazil

Keyword(s): Deep Learning, Dataset Bias, Model Interpretability, Medical image diagnosis, Retinal OCT Analysis.

Abstract: Deep learning classifiers can achieve high accuracy in many medical imaging analysis problems. However, when evaluating images from outside the training distribution — e.g., from new patients or generated by different medical equipment — their performance is often hindered, highlighting that they might have learned specific characteristics and biases of the training set and can not generalize to real-world scenarios. In this work, we discuss how Transfer Learning, the standard training technique employed in most visual medical tasks in the literature, coupled with small and poorly collected datasets, can induce the model to capture such biases and data collection artifacts. We use the classification of eye diseases from retinal OCT images as the backdrop for our discussion, evaluating several well-established convolutional neural network architectures for this problem. Our experiments showed that models can achieve high accuracy in this problem, yet when we interpret their decisions and learned features, they often pay attention to regions of the images unrelated to diseases. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.236.116.27

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Oliveira, G.; David, L.; Padilha, R.; Paula da Silva, A.; de Paula, F.; Infante, L.; Jorge, L.; Xavier, P. and Dias, Z. (2022). Bias Assessment in Medical Imaging Analysis: A Case Study on Retinal OCT Image Classification. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-547-0; ISSN 2184-433X, SciTePress, pages 574-580. DOI: 10.5220/0010867400003116

@conference{icaart22,
author={Gabriel Oliveira. and Lucas David. and Rafael Padilha. and Ana {Paula da Silva}. and Francine {de Paula}. and Lucas Infante. and Lucio Jorge. and Patricia Xavier. and Zanoni Dias.},
title={Bias Assessment in Medical Imaging Analysis: A Case Study on Retinal OCT Image Classification},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2022},
pages={574-580},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010867400003116},
isbn={978-989-758-547-0},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Bias Assessment in Medical Imaging Analysis: A Case Study on Retinal OCT Image Classification
SN - 978-989-758-547-0
IS - 2184-433X
AU - Oliveira, G.
AU - David, L.
AU - Padilha, R.
AU - Paula da Silva, A.
AU - de Paula, F.
AU - Infante, L.
AU - Jorge, L.
AU - Xavier, P.
AU - Dias, Z.
PY - 2022
SP - 574
EP - 580
DO - 10.5220/0010867400003116
PB - SciTePress