Intensity Correction and Standardization for Electron Microscopy Data

Oleh Dzyubachyk, Roman I Koning, Aat A Mulder, M. Christina Avramut, Frank GA Faas, Abraham J Koster
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR 143:148-157, 2021.

Abstract

Intensity of acquired electron microscopy data is subjected to large variability due to the interplay of many different factors, such as microscope and camera settings used for data acquisition, sample thickness, specimen staining protocol and more. In this work, we developed an efficient method for performing intensity inhomogeneity correction on a single set of combined transmission electron microscopy (TEM) images and demonstrated its positive impact on training a neural network on these data. In addition, we investigated what impact different intensity standardization methods have on the training performance, both for data originating from a single source as well as from several different sources. As a concrete example, we considered the problem of segmenting mitochondria from EM data and demonstrated that we were able to obtain promising results when training our network on a large array of highly-variable in-house TEM data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v143-dzyubachyk21a, title = {Intensity Correction and Standardization for Electron Microscopy Data}, author = {Dzyubachyk, Oleh and Koning, Roman I and Mulder, Aat A and Avramut, M. Christina and Faas, Frank GA and Koster, Abraham J}, booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning}, pages = {148--157}, year = {2021}, editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris}, volume = {143}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v143/dzyubachyk21a/dzyubachyk21a.pdf}, url = {https://proceedings.mlr.press/v143/dzyubachyk21a.html}, abstract = {Intensity of acquired electron microscopy data is subjected to large variability due to the interplay of many different factors, such as microscope and camera settings used for data acquisition, sample thickness, specimen staining protocol and more. In this work, we developed an efficient method for performing intensity inhomogeneity correction on a single set of combined transmission electron microscopy (TEM) images and demonstrated its positive impact on training a neural network on these data. In addition, we investigated what impact different intensity standardization methods have on the training performance, both for data originating from a single source as well as from several different sources. As a concrete example, we considered the problem of segmenting mitochondria from EM data and demonstrated that we were able to obtain promising results when training our network on a large array of highly-variable in-house TEM data.} }
Endnote
%0 Conference Paper %T Intensity Correction and Standardization for Electron Microscopy Data %A Oleh Dzyubachyk %A Roman I Koning %A Aat A Mulder %A M. Christina Avramut %A Frank GA Faas %A Abraham J Koster %B Proceedings of the Fourth Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2021 %E Mattias Heinrich %E Qi Dou %E Marleen de Bruijne %E Jan Lellmann %E Alexander Schläfer %E Floris Ernst %F pmlr-v143-dzyubachyk21a %I PMLR %P 148--157 %U https://proceedings.mlr.press/v143/dzyubachyk21a.html %V 143 %X Intensity of acquired electron microscopy data is subjected to large variability due to the interplay of many different factors, such as microscope and camera settings used for data acquisition, sample thickness, specimen staining protocol and more. In this work, we developed an efficient method for performing intensity inhomogeneity correction on a single set of combined transmission electron microscopy (TEM) images and demonstrated its positive impact on training a neural network on these data. In addition, we investigated what impact different intensity standardization methods have on the training performance, both for data originating from a single source as well as from several different sources. As a concrete example, we considered the problem of segmenting mitochondria from EM data and demonstrated that we were able to obtain promising results when training our network on a large array of highly-variable in-house TEM data.
APA
Dzyubachyk, O., Koning, R.I., Mulder, A.A., Avramut, M.C., Faas, F.G. & Koster, A.J.. (2021). Intensity Correction and Standardization for Electron Microscopy Data. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 143:148-157 Available from https://proceedings.mlr.press/v143/dzyubachyk21a.html.

Related Material