Bookmark Saya

arXiv Open Access 2019

Improving localization-based approaches for breast cancer screening exam classification

Thibault Févry Jason Phang Nan Wu S. Gene Kim Linda Moy +2 lainnya
Lihat Sumber

Abstrak

We trained and evaluated a localization-based deep CNN for breast cancer screening exam classification on over 200,000 exams (over 1,000,000 images). Our model achieves an AUC of 0.919 in predicting malignancy in patients undergoing breast cancer screening, reducing the error rate of the baseline (Wu et al., 2019a) by 23%. In addition, the models generates bounding boxes for benign and malignant findings, providing interpretable predictions.

Topik & Kata Kunci

eess.IV cs.CV stat.ML

Penulis (7)

T

Thibault Févry

J

Jason Phang

N

Nan Wu

S

S. Gene Kim

L

Linda Moy

K

Kyunghyun Cho

K

Krzysztof J. Geras

Format Sitasi

APA MLA BibTeX
Févry, T., Phang, J., Wu, N., Kim, S.G., Moy, L., Cho, K. et al. (2019). Improving localization-based approaches for breast cancer screening exam classification. https://arxiv.org/abs/1908.00615

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2019
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓