Breast Lesion Classification in Ultrasound Images Using Deep Convolutional Neural Network

Abstract

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 crossvalidation 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.

An Optimized Radiomics Model Based on Automated Breast Volume Scan Images to Identify Breast Lesions

“…15 Recently, a radiomics study based on breast ultrasonography has shown good performance classifying breast benign and malignant lesions. 16,17 Because machine learning methods might appear in different performances when applied to different scenarios. 9,18,19 Therefore, it is necessary to explore the most appropriate feature selections and classifiers to construct the optimal radiomics model in various clinical fields.…”

“…Radiomics can be coupled with various imaging examinations, such as mammography, ultrasonography, computed tomography, and magnetic resonance imaging 15 . Recently, a radiomics study based on breast ultrasonography has shown good performance classifying breast benign and malignant lesions 16,17 . Because machine learning methods might appear in different performances when applied to different scenarios 9,18,19 .…”

An image classification deep-learning algorithm for shrapnel detection from ultrasound images

“…Briefly, images were imported, and the validation and training splits were generated followed by verification that the proper images were loaded using Matplotlib. The initial architecture of the algorithm was designed to include image augmentation and dropout regularization similar to previous research efforts to minimize overfitting 32 (Fig. 1 ).…”

A Multi-Task Learning Framework for Automated Segmentation and Classification of Breast Tumors From Ultrasound Images

“…Deep learning based methods can overcome the limitations of traditional methods with their powerful feature extraction capability. Zeimarin et al 31 reported enhanced performance in tumor classification while using a custom CNN model with regularization technique. More than the custom-built CNN, several architectures which are trained on large dataset, can easily be fine tuned for classification of tumors.…”