BRANET: A mobil application for breast image classification based on deep learning algorithms

Abstract

[EN] Mobile health apps are widely used for breast cancer detection using artifcial intelligence algorithms, providing radiologists with second opinions and reducing false diagnoses. This study aims to develop an open-source mobile app named "BraNet" for 2D breast imaging segmentation and classifcation using deep learning algorithms. During the phase of-line, an SNGAN model was previously trained for synthetic image generation, and subsequently, these images were used to pre-trained SAM and ResNet18 segmentation and classifcation models. During phase online, the BraNet app was developed using the react native framework, ofering a modular deep-learning pipeline for mammography (DM) and ultrasound (US) breast imaging classifcation. This application operates on a client-server architecture and was implemented in Python for iOS and Android devices. Then, two diagnostic radiologists were given a reading test of 290 total original RoI images to assign the perceived breast tissue type. The reader's agreement was assessed using the kappa coefcient. The BraNet App Mobil exhibited the highest accuracy in benign and malignant US images (94.7%/93.6%) classifcation compared to DM during training I (80.9%/76.9%) and training II (73.7/72.3%). The information contrasts with radiological experts¿ accuracy, with DM classifcation being 29%, concerning US 70% for both readers, because they achieved a higher accuracy in US ROI classifcation than DM images. The kappa value indicates a fair agreement (0.3) for DM images and moderate agreement (0.4) for US images in both readers. It means that not only the amount of data is essential in training deep learning algorithms. Also, it is vital to consider the variety of abnormalities, especially in the mammography data, where several BI-RADS categories are present (microcalcifcations, nodules, mass, asymmetry, and dense breasts) and can afect the API accuracy model.