Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism
Lung cancer ranks among the most common types of cancer. Noninvasive computer-aided diagnosis can enable large-scale rapid screening of potential patients with lung cancer. Deep learning methods have already been applied for the automatic diagnosis of lung cancer in the past. Due to restrictions cau...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/6153657 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832568171513511936 |
|---|---|
| author | RuoXi Qin Zhenzhen Wang LingYun Jiang Kai Qiao Jinjin Hai Jian Chen Junling Xu Dapeng Shi Bin Yan |
| author_facet | RuoXi Qin Zhenzhen Wang LingYun Jiang Kai Qiao Jinjin Hai Jian Chen Junling Xu Dapeng Shi Bin Yan |
| author_sort | RuoXi Qin |
| collection | DOAJ |
| description | Lung cancer ranks among the most common types of cancer. Noninvasive computer-aided diagnosis can enable large-scale rapid screening of potential patients with lung cancer. Deep learning methods have already been applied for the automatic diagnosis of lung cancer in the past. Due to restrictions caused by single modality images of dataset as well as the lack of approaches that allow for a reliable extraction of fine-grained features from different imaging modalities, research regarding the automated diagnosis of lung cancer based on noninvasive clinical images requires further study. In this paper, we present a deep learning architecture that combines the fine-grained feature from PET and CT images that allow for the noninvasive diagnosis of lung cancer. The multidimensional (regarding the channel as well as spatial dimensions) attention mechanism is used to effectively reduce feature noise when extracting fine-grained features from each imaging modality. We conduct a comparative analysis of the two aspects of feature fusion and attention mechanism through quantitative evaluation metrics and the visualization of deep learning process. In our experiments, we obtained an area under the ROC curve of 0.92 (balanced accuracy = 0.72) and a more focused network attention which shows the effective extraction of the fine-grained feature from each imaging modality. |
| format | Article |
| id | doaj-art-cd06383e1ad6474ba10a92a1f76db24c |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-cd06383e1ad6474ba10a92a1f76db24c2025-02-03T00:59:42ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/61536576153657Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention MechanismRuoXi Qin0Zhenzhen Wang1LingYun Jiang2Kai Qiao3Jinjin Hai4Jian Chen5Junling Xu6Dapeng Shi7Bin Yan8PLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaDepartment of Radiology, Henan Provincial People’s Hospital, Zhengzhou 450002, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaDepartment of Radiology, Henan Provincial People’s Hospital, Zhengzhou 450002, ChinaDepartment of Radiology, Henan Provincial People’s Hospital, Zhengzhou 450002, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaLung cancer ranks among the most common types of cancer. Noninvasive computer-aided diagnosis can enable large-scale rapid screening of potential patients with lung cancer. Deep learning methods have already been applied for the automatic diagnosis of lung cancer in the past. Due to restrictions caused by single modality images of dataset as well as the lack of approaches that allow for a reliable extraction of fine-grained features from different imaging modalities, research regarding the automated diagnosis of lung cancer based on noninvasive clinical images requires further study. In this paper, we present a deep learning architecture that combines the fine-grained feature from PET and CT images that allow for the noninvasive diagnosis of lung cancer. The multidimensional (regarding the channel as well as spatial dimensions) attention mechanism is used to effectively reduce feature noise when extracting fine-grained features from each imaging modality. We conduct a comparative analysis of the two aspects of feature fusion and attention mechanism through quantitative evaluation metrics and the visualization of deep learning process. In our experiments, we obtained an area under the ROC curve of 0.92 (balanced accuracy = 0.72) and a more focused network attention which shows the effective extraction of the fine-grained feature from each imaging modality.http://dx.doi.org/10.1155/2020/6153657 |
| spellingShingle | RuoXi Qin Zhenzhen Wang LingYun Jiang Kai Qiao Jinjin Hai Jian Chen Junling Xu Dapeng Shi Bin Yan Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism Complexity |
| title | Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism |
| title_full | Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism |
| title_fullStr | Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism |
| title_full_unstemmed | Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism |
| title_short | Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism |
| title_sort | fine grained lung cancer classification from pet and ct images based on multidimensional attention mechanism |
| url | http://dx.doi.org/10.1155/2020/6153657 |
| work_keys_str_mv | AT ruoxiqin finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism AT zhenzhenwang finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism AT lingyunjiang finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism AT kaiqiao finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism AT jinjinhai finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism AT jianchen finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism AT junlingxu finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism AT dapengshi finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism AT binyan finegrainedlungcancerclassificationfrompetandctimagesbasedonmultidimensionalattentionmechanism |