Multi-Instance Classification of Breast Tumor Ultrasound Images Using Convolutional Neural Networks and Transfer Learning

Alexandru Ciobotaru; Maria Aurora Bota; Dan Ioan Goța; Liviu Cristian Miclea

doi:10.3390/bioengineering10121419

Multi-Instance Classification of Breast Tumor Ultrasound Images Using Convolutional Neural Networks and Transfer Learning

Bioengineering (Basel). 2023 Dec 13;10(12):1419. doi: 10.3390/bioengineering10121419.

Authors

Alexandru Ciobotaru¹, Maria Aurora Bota², Dan Ioan Goța¹, Liviu Cristian Miclea¹

Affiliations

¹ Department of Automation, Faculty of Automation and Computer Science, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, Romania.
² Department of Advanced Computing Sciences, Faculty of Sciences and Engineering, Maastricht University, 6229 EN Maastricht, The Netherlands.

Abstract

Background: Breast cancer is arguably one of the leading causes of death among women around the world. The automation of the early detection process and classification of breast masses has been a prominent focus for researchers in the past decade. The utilization of ultrasound imaging is prevalent in the diagnostic evaluation of breast cancer, with its predictive accuracy being dependent on the expertise of the specialist. Therefore, there is an urgent need to create fast and reliable ultrasound image detection algorithms to address this issue.

Methods: This paper aims to compare the efficiency of six state-of-the-art, fine-tuned deep learning models that can classify breast tissue from ultrasound images into three classes: benign, malignant, and normal, using transfer learning. Additionally, the architecture of a custom model is introduced and trained from the ground up on a public dataset containing 780 images, which was further augmented to 3900 and 7800 images, respectively. What is more, the custom model is further validated on another private dataset containing 163 ultrasound images divided into two classes: benign and malignant. The pre-trained architectures used in this work are ResNet-50, Inception-V3, Inception-ResNet-V2, MobileNet-V2, VGG-16, and DenseNet-121. The performance evaluation metrics that are used in this study are as follows: Precision, Recall, F1-Score and Specificity.

Results: The experimental results show that the models trained on the augmented dataset with 7800 images obtained the best performance on the test set, having 94.95 ± 0.64%, 97.69 ± 0.52%, 97.69 ± 0.13%, 97.77 ± 0.29%, 95.07 ± 0.41%, 98.11 ± 0.10%, and 96.75 ± 0.26% accuracy for the ResNet-50, MobileNet-V2, InceptionResNet-V2, VGG-16, Inception-V3, DenseNet-121, and our model, respectively.

Conclusion: Our proposed model obtains competitive results, outperforming some state-of-the-art models in terms of accuracy and training time.

Keywords: Convolutional Neural Networks; breast cancer; computer vision; deep learning; transfer learning; ultrasound images.

Grants and funding

This research received no external funding.