Multi-encoder U-Net for Oral Squamous Cell Carcinoma Image Segmentation
Oral tumors are responsible for about 170,000 deaths every year in the World. In this paper, we focus on oral squamous cell carcinoma (OSCC), which represents up to 80-90 % of all malignant neoplasms of the oral cavity. We present a novel deep learning-based method for segmenting whole slide image (...
Published in: | 2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA) |
---|---|
Main Authors: | , , , , |
Other Authors: | , , , , |
Format: | Conference Object |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers Inc.
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/11563/169198 https://doi.org/10.1109/MeMeA54994.2022.9856482 |
id |
ftunivbasilicata:oai:iris.unibas.it:11563/169198 |
---|---|
record_format |
openpolar |
spelling |
ftunivbasilicata:oai:iris.unibas.it:11563/169198 2024-04-14T08:18:00+00:00 Multi-encoder U-Net for Oral Squamous Cell Carcinoma Image Segmentation Pennisi A. Bloisi D. D. Nardi D. Varricchio S. Merolla F. Pennisi, A. Bloisi, D. D. Nardi, D. Varricchio, S. Merolla, F. 2022 https://hdl.handle.net/11563/169198 https://doi.org/10.1109/MeMeA54994.2022.9856482 eng eng Institute of Electrical and Electronics Engineers Inc. place:345 E 47TH ST, NEW YORK, NY 10017 USA info:eu-repo/semantics/altIdentifier/isbn/978-1-6654-8299-8 info:eu-repo/semantics/altIdentifier/wos/WOS:000861225100076 ispartofbook:2022 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2022 - Conference Proceedings 17th IEEE International Symposium on Medical Measurements and Applications, MeMeA 2022 firstpage:1 lastpage:6 https://hdl.handle.net/11563/169198 doi:10.1109/MeMeA54994.2022.9856482 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85137853459 info:eu-repo/semantics/restrictedAccess deep learning Medical imaging tumor segmentation info:eu-repo/semantics/conferenceObject 2022 ftunivbasilicata https://doi.org/10.1109/MeMeA54994.2022.9856482 2024-03-21T17:28:47Z Oral tumors are responsible for about 170,000 deaths every year in the World. In this paper, we focus on oral squamous cell carcinoma (OSCC), which represents up to 80-90 % of all malignant neoplasms of the oral cavity. We present a novel deep learning-based method for segmenting whole slide image (WSI) samples at the pixel level. The proposed method is a modification of the well-known U-Net architecture through a multi-encoder structure. In particular, our network, called Multi-encoder U-Net, is a multi-encoder single decoder network that takes as input an image and splits it in tiles. For each tile, there is an encoder responsible for encoding it in the latent space, then a convolutional layer is responsible for merging the tiles into a single layer. Each layer of the decoder takes as input the previous up-sampled layer and concatenate it with the layer made by merging the corresponding layers of the multiple encoders. Experiments have been carried out on the publicly available ORal Cancer Annotated (ORCA) dataset, which contains annotated data from the TCGA repository. Quantitative experimental results, obtained using three different quality metrics, demonstrate the effectiveness of the proposed approach, which achieves 82% Pixel-wise Accuracy, 0.82 Dice similarity score, and 0.72 Mean Intersection Over Union. Conference Object Orca Università degli Studi della Basilicata: CINECA IRIS 2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA) 1 6 |
institution |
Open Polar |
collection |
Università degli Studi della Basilicata: CINECA IRIS |
op_collection_id |
ftunivbasilicata |
language |
English |
topic |
deep learning Medical imaging tumor segmentation |
spellingShingle |
deep learning Medical imaging tumor segmentation Pennisi A. Bloisi D. D. Nardi D. Varricchio S. Merolla F. Multi-encoder U-Net for Oral Squamous Cell Carcinoma Image Segmentation |
topic_facet |
deep learning Medical imaging tumor segmentation |
description |
Oral tumors are responsible for about 170,000 deaths every year in the World. In this paper, we focus on oral squamous cell carcinoma (OSCC), which represents up to 80-90 % of all malignant neoplasms of the oral cavity. We present a novel deep learning-based method for segmenting whole slide image (WSI) samples at the pixel level. The proposed method is a modification of the well-known U-Net architecture through a multi-encoder structure. In particular, our network, called Multi-encoder U-Net, is a multi-encoder single decoder network that takes as input an image and splits it in tiles. For each tile, there is an encoder responsible for encoding it in the latent space, then a convolutional layer is responsible for merging the tiles into a single layer. Each layer of the decoder takes as input the previous up-sampled layer and concatenate it with the layer made by merging the corresponding layers of the multiple encoders. Experiments have been carried out on the publicly available ORal Cancer Annotated (ORCA) dataset, which contains annotated data from the TCGA repository. Quantitative experimental results, obtained using three different quality metrics, demonstrate the effectiveness of the proposed approach, which achieves 82% Pixel-wise Accuracy, 0.82 Dice similarity score, and 0.72 Mean Intersection Over Union. |
author2 |
Pennisi, A. Bloisi, D. D. Nardi, D. Varricchio, S. Merolla, F. |
format |
Conference Object |
author |
Pennisi A. Bloisi D. D. Nardi D. Varricchio S. Merolla F. |
author_facet |
Pennisi A. Bloisi D. D. Nardi D. Varricchio S. Merolla F. |
author_sort |
Pennisi A. |
title |
Multi-encoder U-Net for Oral Squamous Cell Carcinoma Image Segmentation |
title_short |
Multi-encoder U-Net for Oral Squamous Cell Carcinoma Image Segmentation |
title_full |
Multi-encoder U-Net for Oral Squamous Cell Carcinoma Image Segmentation |
title_fullStr |
Multi-encoder U-Net for Oral Squamous Cell Carcinoma Image Segmentation |
title_full_unstemmed |
Multi-encoder U-Net for Oral Squamous Cell Carcinoma Image Segmentation |
title_sort |
multi-encoder u-net for oral squamous cell carcinoma image segmentation |
publisher |
Institute of Electrical and Electronics Engineers Inc. |
publishDate |
2022 |
url |
https://hdl.handle.net/11563/169198 https://doi.org/10.1109/MeMeA54994.2022.9856482 |
genre |
Orca |
genre_facet |
Orca |
op_relation |
info:eu-repo/semantics/altIdentifier/isbn/978-1-6654-8299-8 info:eu-repo/semantics/altIdentifier/wos/WOS:000861225100076 ispartofbook:2022 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2022 - Conference Proceedings 17th IEEE International Symposium on Medical Measurements and Applications, MeMeA 2022 firstpage:1 lastpage:6 https://hdl.handle.net/11563/169198 doi:10.1109/MeMeA54994.2022.9856482 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85137853459 |
op_rights |
info:eu-repo/semantics/restrictedAccess |
op_doi |
https://doi.org/10.1109/MeMeA54994.2022.9856482 |
container_title |
2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA) |
container_start_page |
1 |
op_container_end_page |
6 |
_version_ |
1796317375094587392 |