TY - JOUR
T1 - Evaluating the Quality of Serial EM Sections with Deep Learning
AU - Bank Tavakoli, Mahsa
AU - Morgan, Josh L.
N1 - Publisher Copyright:
© 2024 The Author(s).
PY - 2024/6/1
Y1 - 2024/6/1
N2 - Automated image acquisition can significantly improve the throughput of serial section scanning electron microscopy (ssSEM). However, image quality can vary from image to image depending on autofocusing and beam stigmation. Automatically evaluating the quality of images is, therefore, important for efficiently generating high-quality serial section scanning electron microscopy (ssSEM) datasets. We tested several convolutional neural networks for their ability to reproduce user-generated evaluations of ssSEM image quality. We found that a modification of ResNet-50 that we term quality evaluation Network (QEN) reliably predicts user-generated quality scores. Running QEN in parallel to ssSEM image acquisition therefore allows users to quickly identify imaging problems and flag images for retaking. We have publicly shared the Python code for evaluating images with QEN, the code for training QEN, and the training dataset.(Figure presented.)
AB - Automated image acquisition can significantly improve the throughput of serial section scanning electron microscopy (ssSEM). However, image quality can vary from image to image depending on autofocusing and beam stigmation. Automatically evaluating the quality of images is, therefore, important for efficiently generating high-quality serial section scanning electron microscopy (ssSEM) datasets. We tested several convolutional neural networks for their ability to reproduce user-generated evaluations of ssSEM image quality. We found that a modification of ResNet-50 that we term quality evaluation Network (QEN) reliably predicts user-generated quality scores. Running QEN in parallel to ssSEM image acquisition therefore allows users to quickly identify imaging problems and flag images for retaking. We have publicly shared the Python code for evaluating images with QEN, the code for training QEN, and the training dataset.(Figure presented.)
KW - convolutional neural networks (CNNs)
KW - deep learning
KW - image quality evaluation
KW - serial section scanning electron microscopy (ssSEM)
UR - http://www.scopus.com/inward/record.url?scp=85197999642&partnerID=8YFLogxK
U2 - 10.1093/mam/ozae033
DO - 10.1093/mam/ozae033
M3 - Article
C2 - 38701183
AN - SCOPUS:85197999642
SN - 1431-9276
VL - 30
SP - 501
EP - 507
JO - Microscopy and Microanalysis
JF - Microscopy and Microanalysis
IS - 3
ER -