Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder
Abstract Discrimination of ovarian tumors is necessary for proper treatment. In this study, we developed a convolutional neural network model with a convolutional autoencoder (CNN-CAE) to classify ovarian tumors. A total of 1613 ultrasound images of ovaries with known pathological diagnoses were pre...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-20653-2 |
| _version_ | 1811238874789183488 |
|---|---|
| author | Yuyeon Jung Taewan Kim Mi-Ryung Han Sejin Kim Geunyoung Kim Seungchul Lee Youn Jin Choi |
| author_facet | Yuyeon Jung Taewan Kim Mi-Ryung Han Sejin Kim Geunyoung Kim Seungchul Lee Youn Jin Choi |
| author_sort | Yuyeon Jung |
| collection | DOAJ |
| description | Abstract Discrimination of ovarian tumors is necessary for proper treatment. In this study, we developed a convolutional neural network model with a convolutional autoencoder (CNN-CAE) to classify ovarian tumors. A total of 1613 ultrasound images of ovaries with known pathological diagnoses were pre-processed and augmented for deep learning analysis. We designed a CNN-CAE model that removes the unnecessary information (e.g., calipers and annotations) from ultrasound images and classifies ovaries into five classes. We used fivefold cross-validation to evaluate the performance of the CNN-CAE model in terms of accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). Gradient-weighted class activation mapping (Grad-CAM) was applied to visualize and verify the CNN-CAE model results qualitatively. In classifying normal versus ovarian tumors, the CNN-CAE model showed 97.2% accuracy, 97.2% sensitivity, and 0.9936 AUC with DenseNet121 CNN architecture. In distinguishing malignant ovarian tumors, the CNN-CAE model showed 90.12% accuracy, 86.67% sensitivity, and 0.9406 AUC with DenseNet161 CNN architecture. Grad-CAM showed that the CNN-CAE model recognizes valid texture and morphology features from the ultrasound images and classifies ovarian tumors from these features. CNN-CAE is a feasible diagnostic tool that is capable of robustly classifying ovarian tumors by eliminating marks on ultrasound images. CNN-CAE demonstrates an important application value in clinical conditions. |
| first_indexed | 2024-04-12T12:49:57Z |
| format | Article |
| id | doaj.art-e50d8dcea4fb476f889ae6d0689e620d |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T12:49:57Z |
| publishDate | 2022-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-e50d8dcea4fb476f889ae6d0689e620d2022-12-22T03:32:31ZengNature PortfolioScientific Reports2045-23222022-10-0112111010.1038/s41598-022-20653-2Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoderYuyeon Jung0Taewan Kim1Mi-Ryung Han2Sejin Kim3Geunyoung Kim4Seungchul Lee5Youn Jin Choi6Department of Obstetrics and Gynecology, Soonchunhyang University Bucheon Hospital, Soonchunhyang University College of MedicineDepartment of Mechanical Engineering, Pohang University of Science and Technology (POSTECH)Division of Life Sciences, College of Life Sciences and Bioengineering, Incheon National UniversityDepartment of Obstetrics and Gynecology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of KoreaDepartment of Obstetrics and Gynecology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of KoreaDepartment of Mechanical Engineering, Pohang University of Science and Technology (POSTECH)Department of Obstetrics and Gynecology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of KoreaAbstract Discrimination of ovarian tumors is necessary for proper treatment. In this study, we developed a convolutional neural network model with a convolutional autoencoder (CNN-CAE) to classify ovarian tumors. A total of 1613 ultrasound images of ovaries with known pathological diagnoses were pre-processed and augmented for deep learning analysis. We designed a CNN-CAE model that removes the unnecessary information (e.g., calipers and annotations) from ultrasound images and classifies ovaries into five classes. We used fivefold cross-validation to evaluate the performance of the CNN-CAE model in terms of accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). Gradient-weighted class activation mapping (Grad-CAM) was applied to visualize and verify the CNN-CAE model results qualitatively. In classifying normal versus ovarian tumors, the CNN-CAE model showed 97.2% accuracy, 97.2% sensitivity, and 0.9936 AUC with DenseNet121 CNN architecture. In distinguishing malignant ovarian tumors, the CNN-CAE model showed 90.12% accuracy, 86.67% sensitivity, and 0.9406 AUC with DenseNet161 CNN architecture. Grad-CAM showed that the CNN-CAE model recognizes valid texture and morphology features from the ultrasound images and classifies ovarian tumors from these features. CNN-CAE is a feasible diagnostic tool that is capable of robustly classifying ovarian tumors by eliminating marks on ultrasound images. CNN-CAE demonstrates an important application value in clinical conditions.https://doi.org/10.1038/s41598-022-20653-2 |
| spellingShingle | Yuyeon Jung Taewan Kim Mi-Ryung Han Sejin Kim Geunyoung Kim Seungchul Lee Youn Jin Choi Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder Scientific Reports |
| title | Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder |
| title_full | Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder |
| title_fullStr | Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder |
| title_full_unstemmed | Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder |
| title_short | Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder |
| title_sort | ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder |
| url | https://doi.org/10.1038/s41598-022-20653-2 |
| work_keys_str_mv | AT yuyeonjung ovariantumordiagnosisusingdeepconvolutionalneuralnetworksandadenoisingconvolutionalautoencoder AT taewankim ovariantumordiagnosisusingdeepconvolutionalneuralnetworksandadenoisingconvolutionalautoencoder AT miryunghan ovariantumordiagnosisusingdeepconvolutionalneuralnetworksandadenoisingconvolutionalautoencoder AT sejinkim ovariantumordiagnosisusingdeepconvolutionalneuralnetworksandadenoisingconvolutionalautoencoder AT geunyoungkim ovariantumordiagnosisusingdeepconvolutionalneuralnetworksandadenoisingconvolutionalautoencoder AT seungchullee ovariantumordiagnosisusingdeepconvolutionalneuralnetworksandadenoisingconvolutionalautoencoder AT younjinchoi ovariantumordiagnosisusingdeepconvolutionalneuralnetworksandadenoisingconvolutionalautoencoder |