Transformer-based factorized encoder for classification of pneumoconiosis on 3D CT images

In the past decade, deep learning methods have been implemented in the medical image fields and have achieved good performance. Recently, deep learning algorithms have been successful in the evaluation of diagnosis on lung images. Although chest radiography (CR) is the standard data modality for dia...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computers in biology and medicine Ročník 150; s. 106137
Hlavní autori: Huang, Yingying, Si, Yang, Hu, Bingliang, Zhang, Yan, Wu, Shuang, Wu, Dongsheng, Wang, Quan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States Elsevier Ltd 01.11.2022
Elsevier Limited
Predmet:
3D convolutional autoencoder
Algorithms
Classification
Coders
Computed tomography
Datasets
Deep learning
Feature extraction
Feature maps
Humans
Image classification
Inter-slice interaction
Internal Medicine
Intra-slice interaction
Lesions
Lungs
Machine learning
Medical imaging
Other
Pneumoconiosis
Pneumoconiosis - diagnostic imaging
Radiography
Standard data
Thorax
Tomography, X-Ray Computed
Transformer-based factorized encoder
Transformers
Transformer-based factorized encoder
Intra-slice interaction
Inter-slice interaction
3D convolutional autoencoder
ISSN:0010-4825, 1879-0534, 1879-0534
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In the past decade, deep learning methods have been implemented in the medical image fields and have achieved good performance. Recently, deep learning algorithms have been successful in the evaluation of diagnosis on lung images. Although chest radiography (CR) is the standard data modality for diagnosing pneumoconiosis, computed tomography (CT) typically provides more details of the lesions in the lung. Thus, a transformer-based factorized encoder (TBFE) was proposed and first applied for the classification of pneumoconiosis depicted on 3D CT images. Specifically, a factorized encoder consists of two transformer encoders. The first transformer encoder enables the interaction of intra-slice by encoding feature maps from the same slice of CT. The second transformer encoder explores the inter-slice interaction by encoding feature maps from different slices. In addition, the lack of grading standards on CT for labeling the pneumoconiosis lesions. Thus, an acknowledged CR-based grading system was applied to mark the corresponding pneumoconiosis CT stage. Then, we pre-trained the 3D convolutional autoencoder on the public LIDC-IDRI dataset and fixed the parameters of the last convolutional layer of the encoder to extract CT feature maps with underlying spatial structural information from our 3D CT dataset. Experimental results demonstrated the superiority of the TBFE over other 3D-CNN networks, achieving an accuracy of 97.06%, a recall of 89.33%, precision of 90%, and an F1-score of 93.33%, using 10-fold cross-validation. •This was the first deep learning study to classify pneumoconiosis on 3D CT images.•TBFE captures the intra-slice relationship and the slice-level information exchange.•TBFE is applied in clinical practice to promote the early diagnosis of pneumoconiosis.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0010-4825
1879-0534
1879-0534
DOI:10.1016/j.compbiomed.2022.106137