Explainability Applied to a Deep-Learning Based Algorithm for Lung Nodule Segmentation

Arman Zafaranchi, Arman Zafaranchi, Francesca Lizzi, Alessandra Retico, Camilla Scapicchio, Camilla Scapicchio, Maria Evelina Fantacci, Maria Evelina Fantacci

2024

Abstract

Deep learning and computer-aided detection (CAD) methods play a pivotal role in the early detection and diagnosis of various cancer types. The significance of AI in the medical field has become particularly pronounced during the coronavirus pandemic. This study aims to develop a deep learning-based system for segmenting and detecting nodules in the lung parenchyma, utilizing the Luna-16 challenge dataset. The algorithm is divided into two phases: the first phase involves lung segmentation using the previously developed LungQuant algorithm to identify the region of interest (ROI), and the second phase employs a specifically designed and fine-tuned Attention Res-UNet for nodule segmentation. Additionally, the explainable AI (XAI) technique, Grad-CAM, was used to demonstrate the reliability of the proposed algorithm for clinical application. In the initial phase, the LungQuant algorithm achieved an average Dice Similarity Coefficient (DSC) of 90%. For nodule segmentation, the DSC scores were 81% test sets. The model also achieved average sensitivity and specificity metrics of 0.86 and 0.92.

Paper Citation

in Harvard Style

Zafaranchi A., Lizzi F., Retico A., Scapicchio C. and Evelina Fantacci M. (2024). Explainability Applied to a Deep-Learning Based Algorithm for Lung Nodule Segmentation. In Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - Volume 1: EXPLAINS; ISBN 978-989-758-720-7, SciTePress, pages 132-138. DOI: 10.5220/0013014600003886

in Bibtex Style

@conference{explains24,
author={Arman Zafaranchi and Francesca Lizzi and Alessandra Retico and Camilla Scapicchio and Maria Evelina Fantacci},
title={Explainability Applied to a Deep-Learning Based Algorithm for Lung Nodule Segmentation},
booktitle={Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - Volume 1: EXPLAINS},
year={2024},
pages={132-138},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013014600003886},
isbn={978-989-758-720-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - Volume 1: EXPLAINS
TI - Explainability Applied to a Deep-Learning Based Algorithm for Lung Nodule Segmentation
SN - 978-989-758-720-7
AU - Zafaranchi A.
AU - Lizzi F.
AU - Retico A.
AU - Scapicchio C.
AU - Evelina Fantacci M.
PY - 2024
SP - 132
EP - 138
DO - 10.5220/0013014600003886
PB - SciTePress