A hybrid features fusion-based framework for classification of breast micronodules using ultrasonography

Abstract

Background: Breast cancer is one of the leading diseases worldwide. According to estimates by the National Breast Cancer Foundation, over 42,000 women are expected to die from this disease in 2024.

Objective: The prognosis of breast cancer depends on the early detection of breast micronodules and the ability to distinguish benign from malignant lesions. Ultrasonography is a crucial radiological imaging technique for diagnosing the illness because it allows for biopsy and lesion characterization. The user's level of experience and knowledge is vital since ultrasonographic diagnosis relies on the practitioner's expertise. Furthermore, computer-aided technologies significantly contribute by potentially reducing the workload of radiologists and enhancing their expertise, especially when combined with a large patient volume in a hospital setting.

Method: This work describes the development of a hybrid CNN system for diagnosing benign and malignant breast cancer lesions. The models InceptionV3 and MobileNetV2 serve as the foundation for the hybrid framework. Features from these models are extracted and concatenated individually, resulting in a larger feature set. Finally, various classifiers are applied for the classification task.

Results: The model achieved the best results using the softmax classifier, with an accuracy of over 95%.

Conclusion: Computer-aided diagnosis greatly assists radiologists and reduces their workload. Therefore, this research can serve as a foundation for other researchers to build clinical solutions.

Keywords: Breast cancer detection; Computer-aided diagnosis (CAD); Hybrid CNN framework; InceptionV3; MobileNetV2; Ultrasonography.

Fig. 1

Sample images from dataset

Fig. 2

Methodology for Classification of Breast Ultrasonography

Fig. 3

Inception V3 Architecture. The model takes an input in the format 299 × 299 × 3 and outputs the 8 × 8 × 2048. Inception V3 introduced the factorized 7 × 7 convolutions as well as batch normalization in the auxiliary classifier and performed label smoothing

Fig. 4

MobileNet V2 Architecture. The model takes an input of 224 × 224 × 3, and it is based on inverted residual connections between the bottleneck layers. The model in intermediately uses the depth-wise convolutions as a source of non-linearity

Fig. 5

Accuracy Comparison on 70/30 Train/Test Ratio

Fig. 6

Classification Performance Comparison