Cargando…

Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation

Background: Deep learning (DL) could predict isocitrate dehydrogenase (IDH) mutation status from MRIs. Yet, previous work focused on CNNs with refined tumor segmentation. To bridge the gap, this study aimed to evaluate the feasibility of developing a Transformer-based network to predict the IDH muta...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Jiangfen, Xu, Qian, Shen, Yiqing, Chen, Weidao, Xu, Kai, Qi, Xian-Rong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9369996/
https://www.ncbi.nlm.nih.gov/pubmed/35956236
http://dx.doi.org/10.3390/jcm11154625
_version_ 1784766651741241344
author Wu, Jiangfen
Xu, Qian
Shen, Yiqing
Chen, Weidao
Xu, Kai
Qi, Xian-Rong
author_facet Wu, Jiangfen
Xu, Qian
Shen, Yiqing
Chen, Weidao
Xu, Kai
Qi, Xian-Rong
author_sort Wu, Jiangfen
collection PubMed
description Background: Deep learning (DL) could predict isocitrate dehydrogenase (IDH) mutation status from MRIs. Yet, previous work focused on CNNs with refined tumor segmentation. To bridge the gap, this study aimed to evaluate the feasibility of developing a Transformer-based network to predict the IDH mutation status free of refined tumor segmentation. Methods: A total of 493 glioma patients were recruited from two independent institutions for model development (TCIA; N = 259) and external test (AHXZ; N = 234). IDH mutation status was predicted directly from T2 images with a Swin Transformer and conventional ResNet. Furthermore, to investigate the necessity of refined tumor segmentation, seven strategies for the model input image were explored: (i) whole tumor slice; (ii–iii) tumor mask and/or not edema; (iv–vii) tumor bounding box of 0.8, 1.0, 1.2, 1.5 times. Performance comparison was made among the networks of different architectures along with different image input strategies, using area under the curve (AUC) and accuracy (ACC). Finally, to further boost the performance, a hybrid model was built by incorporating the images with clinical features. Results: With the seven proposed input strategies, seven Swin Transformer models and seven ResNet models were built, respectively. Based on the seven Swin Transformer models, an averaged AUC of 0.965 (internal test) and 0.842 (external test) were achieved, outperforming 0.922 and 0.805 resulting from the seven ResNet models, respectively. When a bounding box of 1.0 times was used, Swin Transformer (AUC = 0.868, ACC = 80.7%), achieved the best results against the one that used tumor segmentation (Tumor + Edema, AUC = 0.862, ACC = 78.5%). The hybrid model that integrated age and location features into images yielded improved performance (AUC = 0.878, Accuracy = 82.0%) over the model that used images only. Conclusions: Swin Transformer outperforms the CNN-based ResNet in IDH prediction. Using bounding box input images benefits the DL networks in IDH prediction and makes the IDH prediction free of refined glioma segmentation feasible.
format Online
Article
Text
id pubmed-9369996
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93699962022-08-12 Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation Wu, Jiangfen Xu, Qian Shen, Yiqing Chen, Weidao Xu, Kai Qi, Xian-Rong J Clin Med Article Background: Deep learning (DL) could predict isocitrate dehydrogenase (IDH) mutation status from MRIs. Yet, previous work focused on CNNs with refined tumor segmentation. To bridge the gap, this study aimed to evaluate the feasibility of developing a Transformer-based network to predict the IDH mutation status free of refined tumor segmentation. Methods: A total of 493 glioma patients were recruited from two independent institutions for model development (TCIA; N = 259) and external test (AHXZ; N = 234). IDH mutation status was predicted directly from T2 images with a Swin Transformer and conventional ResNet. Furthermore, to investigate the necessity of refined tumor segmentation, seven strategies for the model input image were explored: (i) whole tumor slice; (ii–iii) tumor mask and/or not edema; (iv–vii) tumor bounding box of 0.8, 1.0, 1.2, 1.5 times. Performance comparison was made among the networks of different architectures along with different image input strategies, using area under the curve (AUC) and accuracy (ACC). Finally, to further boost the performance, a hybrid model was built by incorporating the images with clinical features. Results: With the seven proposed input strategies, seven Swin Transformer models and seven ResNet models were built, respectively. Based on the seven Swin Transformer models, an averaged AUC of 0.965 (internal test) and 0.842 (external test) were achieved, outperforming 0.922 and 0.805 resulting from the seven ResNet models, respectively. When a bounding box of 1.0 times was used, Swin Transformer (AUC = 0.868, ACC = 80.7%), achieved the best results against the one that used tumor segmentation (Tumor + Edema, AUC = 0.862, ACC = 78.5%). The hybrid model that integrated age and location features into images yielded improved performance (AUC = 0.878, Accuracy = 82.0%) over the model that used images only. Conclusions: Swin Transformer outperforms the CNN-based ResNet in IDH prediction. Using bounding box input images benefits the DL networks in IDH prediction and makes the IDH prediction free of refined glioma segmentation feasible. MDPI 2022-08-08 /pmc/articles/PMC9369996/ /pubmed/35956236 http://dx.doi.org/10.3390/jcm11154625 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wu, Jiangfen
Xu, Qian
Shen, Yiqing
Chen, Weidao
Xu, Kai
Qi, Xian-Rong
Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation
title Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation
title_full Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation
title_fullStr Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation
title_full_unstemmed Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation
title_short Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation
title_sort swin transformer improves the idh mutation status prediction of gliomas free of mri-based tumor segmentation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9369996/
https://www.ncbi.nlm.nih.gov/pubmed/35956236
http://dx.doi.org/10.3390/jcm11154625
work_keys_str_mv AT wujiangfen swintransformerimprovestheidhmutationstatuspredictionofgliomasfreeofmribasedtumorsegmentation
AT xuqian swintransformerimprovestheidhmutationstatuspredictionofgliomasfreeofmribasedtumorsegmentation
AT shenyiqing swintransformerimprovestheidhmutationstatuspredictionofgliomasfreeofmribasedtumorsegmentation
AT chenweidao swintransformerimprovestheidhmutationstatuspredictionofgliomasfreeofmribasedtumorsegmentation
AT xukai swintransformerimprovestheidhmutationstatuspredictionofgliomasfreeofmribasedtumorsegmentation
AT qixianrong swintransformerimprovestheidhmutationstatuspredictionofgliomasfreeofmribasedtumorsegmentation