TY - JOUR
T1 - FAN
T2 - Fourier Assignment Network for autofocus based on deep learning
AU - Liu, Qizheng
AU - Mao, Xintian
AU - Wang, Jiansheng
AU - Zhang, Qing
AU - Wang, Yan
AU - Pang, Baochuan
AU - Li, Qingli
N1 - Publisher Copyright:
© 2025
PY - 2025/8
Y1 - 2025/8
N2 - AI-driven digital pathology is transforming the field, prioritizing the enhancement of image quality. In the data acquisition phase, the performance of autofocus algorithms significantly influences imaging quality. To tackle this challenge, we introduce the Fourier Assignment Network (FAN), a novel and lightweight neural network architecture aimed at predicting the defocus distance in microscopic images. FAN estimates the defocus distance using single-shot images, thus eliminating the requirement for extra hardware. Extensive experiments conducted on our dataset confirm its effectiveness, with an average error of 0.9μm across 1374 sample groups, markedly surpassing the performance of existing lightweight neural networks. Moreover, FAN is the most efficient among surveyed networks, with only 0.14G FLOPs and 0.85M parameters. The real-time and precise autofocus capability of FAN marks a notable advancement in digital pathology, providing a dependable, hardware-independent solution to enhance diagnostic accuracy.
AB - AI-driven digital pathology is transforming the field, prioritizing the enhancement of image quality. In the data acquisition phase, the performance of autofocus algorithms significantly influences imaging quality. To tackle this challenge, we introduce the Fourier Assignment Network (FAN), a novel and lightweight neural network architecture aimed at predicting the defocus distance in microscopic images. FAN estimates the defocus distance using single-shot images, thus eliminating the requirement for extra hardware. Extensive experiments conducted on our dataset confirm its effectiveness, with an average error of 0.9μm across 1374 sample groups, markedly surpassing the performance of existing lightweight neural networks. Moreover, FAN is the most efficient among surveyed networks, with only 0.14G FLOPs and 0.85M parameters. The real-time and precise autofocus capability of FAN marks a notable advancement in digital pathology, providing a dependable, hardware-independent solution to enhance diagnostic accuracy.
KW - Autofocus
KW - Deep learning
KW - Digital pathology
KW - Microscopy
UR - https://www.scopus.com/pages/publications/85218145492
U2 - 10.1016/j.optlastec.2025.112579
DO - 10.1016/j.optlastec.2025.112579
M3 - 文章
AN - SCOPUS:85218145492
SN - 0030-3992
VL - 186
JO - Optics and Laser Technology
JF - Optics and Laser Technology
M1 - 112579
ER -