Automated Classification of Idiopathic Pulmonary Fibrosis in Pathological Images Using Convolutional Neural Network and Generative Adversarial Networks
Interstitial pneumonia of uncertain cause is referred to as idiopathic interstitial pneumonia (IIP). Among the various types of IIPs, the prognosis of cases of idiopathic pulmonary fibrosis (IPF) is extremely poor, and accurate differentiation between IPF and non-IPF pneumonia is critical. In this s...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/12/3195 |
| _version_ | 1827641036126552064 |
|---|---|
| author | Atsushi Teramoto Tetsuya Tsukamoto Ayano Michiba Yuka Kiriyama Eiko Sakurai Kazuyoshi Imaizumi Kuniaki Saito Hiroshi Fujita |
| author_facet | Atsushi Teramoto Tetsuya Tsukamoto Ayano Michiba Yuka Kiriyama Eiko Sakurai Kazuyoshi Imaizumi Kuniaki Saito Hiroshi Fujita |
| author_sort | Atsushi Teramoto |
| collection | DOAJ |
| description | Interstitial pneumonia of uncertain cause is referred to as idiopathic interstitial pneumonia (IIP). Among the various types of IIPs, the prognosis of cases of idiopathic pulmonary fibrosis (IPF) is extremely poor, and accurate differentiation between IPF and non-IPF pneumonia is critical. In this study, we consider deep learning (DL) methods owing to their excellent image classification capabilities. Although DL models require large quantities of training data, collecting a large number of pathological specimens is difficult for rare diseases. In this study, we propose an end-to-end scheme to automatically classify IIPs using a convolutional neural network (CNN) model. To compensate for the lack of data on rare diseases, we introduce a two-step training method to generate pathological images of IIPs using a generative adversarial network (GAN). Tissue specimens from 24 patients with IIPs were scanned using a whole slide scanner, and the resulting images were divided into patch images with a size of 224 × 224 pixels. A progressive growth GAN (PGGAN) model was trained using 23,142 IPF images and 7817 non-IPF images to generate 10,000 images for each of the two categories. The images generated by the PGGAN were used along with real images to train the CNN model. An evaluation of the images generated by the PGGAN showed that cells and their locations were well-expressed. We also obtained the best classification performance with a detection sensitivity of 97.2% and a specificity of 69.4% for IPF using DenseNet. The classification performance was also improved by using PGGAN-generated images. These results indicate that the proposed method may be considered effective for the diagnosis of IPF. |
| first_indexed | 2024-03-09T17:08:43Z |
| format | Article |
| id | doaj.art-ca6a2c41f6ea43a390ac2da3f1698a1f |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T17:08:43Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-ca6a2c41f6ea43a390ac2da3f1698a1f2023-11-24T14:20:22ZengMDPI AGDiagnostics2075-44182022-12-011212319510.3390/diagnostics12123195Automated Classification of Idiopathic Pulmonary Fibrosis in Pathological Images Using Convolutional Neural Network and Generative Adversarial NetworksAtsushi Teramoto0Tetsuya Tsukamoto1Ayano Michiba2Yuka Kiriyama3Eiko Sakurai4Kazuyoshi Imaizumi5Kuniaki Saito6Hiroshi Fujita7School of Medical Sciences, Fujita Health University, Toyoake 470-1192, JapanGraduate School of Medicine, Fujita Health University, Toyoake 470-1192, JapanGraduate School of Medicine, Fujita Health University, Toyoake 470-1192, JapanGraduate School of Medicine, Fujita Health University, Toyoake 470-1192, JapanGraduate School of Medicine, Fujita Health University, Toyoake 470-1192, JapanGraduate School of Medicine, Fujita Health University, Toyoake 470-1192, JapanSchool of Medical Sciences, Fujita Health University, Toyoake 470-1192, JapanFaculty of Engineering, Gifu University, Gifu 501-1194, JapanInterstitial pneumonia of uncertain cause is referred to as idiopathic interstitial pneumonia (IIP). Among the various types of IIPs, the prognosis of cases of idiopathic pulmonary fibrosis (IPF) is extremely poor, and accurate differentiation between IPF and non-IPF pneumonia is critical. In this study, we consider deep learning (DL) methods owing to their excellent image classification capabilities. Although DL models require large quantities of training data, collecting a large number of pathological specimens is difficult for rare diseases. In this study, we propose an end-to-end scheme to automatically classify IIPs using a convolutional neural network (CNN) model. To compensate for the lack of data on rare diseases, we introduce a two-step training method to generate pathological images of IIPs using a generative adversarial network (GAN). Tissue specimens from 24 patients with IIPs were scanned using a whole slide scanner, and the resulting images were divided into patch images with a size of 224 × 224 pixels. A progressive growth GAN (PGGAN) model was trained using 23,142 IPF images and 7817 non-IPF images to generate 10,000 images for each of the two categories. The images generated by the PGGAN were used along with real images to train the CNN model. An evaluation of the images generated by the PGGAN showed that cells and their locations were well-expressed. We also obtained the best classification performance with a detection sensitivity of 97.2% and a specificity of 69.4% for IPF using DenseNet. The classification performance was also improved by using PGGAN-generated images. These results indicate that the proposed method may be considered effective for the diagnosis of IPF.https://www.mdpi.com/2075-4418/12/12/3195idiopathic interstitial pneumoniasclassificationconvolutional neural networkgenerative adversarial networks |
| spellingShingle | Atsushi Teramoto Tetsuya Tsukamoto Ayano Michiba Yuka Kiriyama Eiko Sakurai Kazuyoshi Imaizumi Kuniaki Saito Hiroshi Fujita Automated Classification of Idiopathic Pulmonary Fibrosis in Pathological Images Using Convolutional Neural Network and Generative Adversarial Networks Diagnostics idiopathic interstitial pneumonias classification convolutional neural network generative adversarial networks |
| title | Automated Classification of Idiopathic Pulmonary Fibrosis in Pathological Images Using Convolutional Neural Network and Generative Adversarial Networks |
| title_full | Automated Classification of Idiopathic Pulmonary Fibrosis in Pathological Images Using Convolutional Neural Network and Generative Adversarial Networks |
| title_fullStr | Automated Classification of Idiopathic Pulmonary Fibrosis in Pathological Images Using Convolutional Neural Network and Generative Adversarial Networks |
| title_full_unstemmed | Automated Classification of Idiopathic Pulmonary Fibrosis in Pathological Images Using Convolutional Neural Network and Generative Adversarial Networks |
| title_short | Automated Classification of Idiopathic Pulmonary Fibrosis in Pathological Images Using Convolutional Neural Network and Generative Adversarial Networks |
| title_sort | automated classification of idiopathic pulmonary fibrosis in pathological images using convolutional neural network and generative adversarial networks |
| topic | idiopathic interstitial pneumonias classification convolutional neural network generative adversarial networks |
| url | https://www.mdpi.com/2075-4418/12/12/3195 |
| work_keys_str_mv | AT atsushiteramoto automatedclassificationofidiopathicpulmonaryfibrosisinpathologicalimagesusingconvolutionalneuralnetworkandgenerativeadversarialnetworks AT tetsuyatsukamoto automatedclassificationofidiopathicpulmonaryfibrosisinpathologicalimagesusingconvolutionalneuralnetworkandgenerativeadversarialnetworks AT ayanomichiba automatedclassificationofidiopathicpulmonaryfibrosisinpathologicalimagesusingconvolutionalneuralnetworkandgenerativeadversarialnetworks AT yukakiriyama automatedclassificationofidiopathicpulmonaryfibrosisinpathologicalimagesusingconvolutionalneuralnetworkandgenerativeadversarialnetworks AT eikosakurai automatedclassificationofidiopathicpulmonaryfibrosisinpathologicalimagesusingconvolutionalneuralnetworkandgenerativeadversarialnetworks AT kazuyoshiimaizumi automatedclassificationofidiopathicpulmonaryfibrosisinpathologicalimagesusingconvolutionalneuralnetworkandgenerativeadversarialnetworks AT kuniakisaito automatedclassificationofidiopathicpulmonaryfibrosisinpathologicalimagesusingconvolutionalneuralnetworkandgenerativeadversarialnetworks AT hiroshifujita automatedclassificationofidiopathicpulmonaryfibrosisinpathologicalimagesusingconvolutionalneuralnetworkandgenerativeadversarialnetworks |