• RAHAJANIAINA Andriamasinoro
• RATIARISON Adolph

As others cancer diseases, breast cancer is a serious problem of human life and especially for the women. One way to predict and know its state is the use of artificial intelligence. In this paper, we proposed a very practical solution to classify breast cancer ultrasound images that can be used on mobile devices such as smartphones. The proposed lightweight model was the combination of mobilNetV3Small and a customized version of the SSDLiteX auxiliary stage. The Balancing technical was used to perform the highest results. After more experiments, the proposed approach achieved 96% for an overall accuracy and for the global F1-score. The results saw that our model is less complex, lightweight and could be deployed on the mobile device. Moreover, the result demonstrates that our system surpassed others preview models using the same kind of the dataset.

breast cancer disease, lightweight deep learning model, breast cancer classification.

"BREAST CANCER ULTRASOUND IMAGES CLASSIFICATION USING A LIGHTWEIGHT MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.f459-f463, December-2024, Available :http://www.jetir.org/papers/JETIR2412553.pdf

"BREAST CANCER ULTRASOUND IMAGES CLASSIFICATION USING A LIGHTWEIGHT MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppf459-f463, December-2024, Available at : http://www.jetir.org/papers/JETIR2412553.pdf