Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network
In recent years, convolutional neural networks (CNNs) have found many applications in medical image analysis. Having enough labeled data, CNNs could be trained to learn image features and used for object localization, classification, and segmentation. Although there are many interests in building an...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9145538/ |
| _version_ | 1818557633583382528 |
|---|---|
| author | Bashir Zeimarani Marly Guimaraes Fernandes Costa Nilufar Zeimarani Nurani Sabrina Ramos Bianco Wagner Coelho De Albuquerque Pereira Cicero Ferreira Fernandes Costa Filho |
| author_facet | Bashir Zeimarani Marly Guimaraes Fernandes Costa Nilufar Zeimarani Nurani Sabrina Ramos Bianco Wagner Coelho De Albuquerque Pereira Cicero Ferreira Fernandes Costa Filho |
| author_sort | Bashir Zeimarani |
| collection | DOAJ |
| description | In recent years, convolutional neural networks (CNNs) have found many applications in medical image analysis. Having enough labeled data, CNNs could be trained to learn image features and used for object localization, classification, and segmentation. Although there are many interests in building and improving automated systems for medical image analysis, lack of reliable and publicly available biomedical datasets makes such a task difficult. In this work, the effectiveness of CNNs for the classification of breast lesions in ultrasound (US) images will be studied. First, due to a limited number of training data, we use a custom-built CNN with a few hidden layers and apply regularization techniques to improve the performance. Second, we use transfer learning and adapt some pre-trained models for our dataset. The dataset used in this work consists of a limited number of cases, 641 in total, histopathologically categorized (413 benign and 228 malignant lesions). To assess how the results of our classifier generalize on our data set, a 5-fold cross-validation were employed, where in each fold 80% of data were used for training and the 20% for testing. Accuracy and the area under the ROC curve (AUC) were used as the main performance metrics. Before applying any regularizations techniques, we achieved an overall accuracy of 85.98% for tumor classification, and the AUC equal to 0.94. After applying image augmentation and regularization, the accuracy and the AUC increased to 92.05% and 0.97, respectively. Using a pre-trained model, we achieved an overall accuracy of 87.07% and an AUC equal to 0.96. The obtained results demonstrated the effectiveness of our custom architecture for classification of tumors in this small US imaging dataset, surpassing some traditional learning algorithm based on manual feature selection. |
| first_indexed | 2024-12-14T00:02:05Z |
| format | Article |
| id | doaj.art-70f97f255cb747438cde019373c0ce1d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T00:02:05Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-70f97f255cb747438cde019373c0ce1d2022-12-21T23:26:15ZengIEEEIEEE Access2169-35362020-01-01813334913335910.1109/ACCESS.2020.30108639145538Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural NetworkBashir Zeimarani0https://orcid.org/0000-0002-7555-8880Marly Guimaraes Fernandes Costa1Nilufar Zeimarani Nurani2https://orcid.org/0000-0002-1426-6905Sabrina Ramos Bianco3https://orcid.org/0000-0002-0902-3570Wagner Coelho De Albuquerque Pereira4https://orcid.org/0000-0001-5880-3242Cicero Ferreira Fernandes Costa Filho5https://orcid.org/0000-0003-3325-5715Federal University of Amazonas, Manaus, BrazilFederal University of Amazonas, Manaus, BrazilSetor de Imagem, Fundação Centro de Controle de Oncologia do Estado do Amazonas–FCECON, Manaus, BrazilSetor de Imagem, Fundação Centro de Controle de Oncologia do Estado do Amazonas–FCECON, Manaus, BrazilBiomedical Engineering Program, COPPE, Federal University of Rio de Janeiros, Rio de Janeiro, BrazilFederal University of Amazonas, Manaus, BrazilIn recent years, convolutional neural networks (CNNs) have found many applications in medical image analysis. Having enough labeled data, CNNs could be trained to learn image features and used for object localization, classification, and segmentation. Although there are many interests in building and improving automated systems for medical image analysis, lack of reliable and publicly available biomedical datasets makes such a task difficult. In this work, the effectiveness of CNNs for the classification of breast lesions in ultrasound (US) images will be studied. First, due to a limited number of training data, we use a custom-built CNN with a few hidden layers and apply regularization techniques to improve the performance. Second, we use transfer learning and adapt some pre-trained models for our dataset. The dataset used in this work consists of a limited number of cases, 641 in total, histopathologically categorized (413 benign and 228 malignant lesions). To assess how the results of our classifier generalize on our data set, a 5-fold cross-validation were employed, where in each fold 80% of data were used for training and the 20% for testing. Accuracy and the area under the ROC curve (AUC) were used as the main performance metrics. Before applying any regularizations techniques, we achieved an overall accuracy of 85.98% for tumor classification, and the AUC equal to 0.94. After applying image augmentation and regularization, the accuracy and the AUC increased to 92.05% and 0.97, respectively. Using a pre-trained model, we achieved an overall accuracy of 87.07% and an AUC equal to 0.96. The obtained results demonstrated the effectiveness of our custom architecture for classification of tumors in this small US imaging dataset, surpassing some traditional learning algorithm based on manual feature selection.https://ieeexplore.ieee.org/document/9145538/Breast tumorultrasound imagesconvolutional neural networktransfer learning |
| spellingShingle | Bashir Zeimarani Marly Guimaraes Fernandes Costa Nilufar Zeimarani Nurani Sabrina Ramos Bianco Wagner Coelho De Albuquerque Pereira Cicero Ferreira Fernandes Costa Filho Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network IEEE Access Breast tumor ultrasound images convolutional neural network transfer learning |
| title | Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network |
| title_full | Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network |
| title_fullStr | Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network |
| title_full_unstemmed | Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network |
| title_short | Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network |
| title_sort | breast lesion classification in ultrasound images using deep convolutional neural network |
| topic | Breast tumor ultrasound images convolutional neural network transfer learning |
| url | https://ieeexplore.ieee.org/document/9145538/ |
| work_keys_str_mv | AT bashirzeimarani breastlesionclassificationinultrasoundimagesusingdeepconvolutionalneuralnetwork AT marlyguimaraesfernandescosta breastlesionclassificationinultrasoundimagesusingdeepconvolutionalneuralnetwork AT nilufarzeimaraninurani breastlesionclassificationinultrasoundimagesusingdeepconvolutionalneuralnetwork AT sabrinaramosbianco breastlesionclassificationinultrasoundimagesusingdeepconvolutionalneuralnetwork AT wagnercoelhodealbuquerquepereira breastlesionclassificationinultrasoundimagesusingdeepconvolutionalneuralnetwork AT ciceroferreirafernandescostafilho breastlesionclassificationinultrasoundimagesusingdeepconvolutionalneuralnetwork |