Aggregating efficient transformer and CNN networks using learnable fuzzy measure for breast tumor malignancy prediction in ultrasound images

Automated classification of tumors in breast ultrasound (BUS) using deep learning-based methods has achieved remarkable success recently. The initial performance of the individual convolutional neural networks (CNNs) and vision-Transformer have been encouraging. However, artifacts like shadows, low contrast, speckle noise, and variations in tumor shape and sizes impose a kind of uncertainty that limits the performance of existing methods. The interpretation of classification results with a high confidence rate is strongly required in a real clinical setting. This work proposes an efficient method for predicting breast tumor malignancy (EPTM) in BUS images. EPTM comprises heterogeneous deep learning-based feature extraction models and a Choquet integral-based fusion mechanism. Specifically, EPTM incorporates efficient CNN and vision-Transformer methods to build accurate individual breast tumor malignancy prediction models (IMMs). The heterogeneous IMMs ensure complete feature representation of the breast tumors as each CNN or vision-Transformer captures different textural patterns in BUS images. EPTM applies learnable fuzzy measure-based Choquet integral to fuse the predictions of IMMs, where the gray wolf optimizer is employed for generating fuzzy measures. The experimental results confirm the versatility of the EPTM method evaluated on two publicly available datasets, namely UDIAT BUS and Baheya Hospital. EPTM yielded state-of-the-art results with the area under the curve of 0.932 and 0.98, respectively, in the UDIAT BUS and Baheya Hospital datasets. The source code of the proposed model is publicly available at https://github.com/vivek231/breastUS-classification.