Neural network based algorithm for breast cancer detection
Fang, Ziwen (2025)
Kandidaatintyö
2025
School of Engineering Science, Tietotekniikka
Kaikki oikeudet pidätetään.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2025060358440
https://urn.fi/URN:NBN:fi-fe2025060358440
Tiivistelmä
In today's social environment, women are increasingly at risk of developing breast cancer, which has surpassed lung cancer as the most common cancer today. However, if breast cancer can be detected at an early stage and measures can be taken, it will effectively improve the survival chances of breast cancer patients.
With the continuous development of artificial intelligence, it shows a broad prospect in the medical field. In this paper, we try to apply artificial intelligence to the field of breast cancer detection, by using the neural network-based U-Net model to help doctors perform early detection of breast cancer. In this paper, breast cancer image data from kaggle are selected to improve the data generalization ability through data enhancement, and then Python is used to train and detect the model, and the model accuracy is gradually improved through loss function, optimizer, and early stopping strategy. According to the experimental results, the model finally achieves a pixel segmentation accuracy of about 80%.
With the continuous development of artificial intelligence, it shows a broad prospect in the medical field. In this paper, we try to apply artificial intelligence to the field of breast cancer detection, by using the neural network-based U-Net model to help doctors perform early detection of breast cancer. In this paper, breast cancer image data from kaggle are selected to improve the data generalization ability through data enhancement, and then Python is used to train and detect the model, and the model accuracy is gradually improved through loss function, optimizer, and early stopping strategy. According to the experimental results, the model finally achieves a pixel segmentation accuracy of about 80%.