Fast Mitochondria Detection for Connectomics

Vincent Casser, Kai Kang, Hanspeter Pfister, Daniel Haehn
; Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:111-120, 2020.

Abstract

High-resolution connectomics data allows for the identification of dysfunctional mitochondria which are linked to a variety of diseases such as autism or bipolar. However, manual analysis is not feasible since datasets can be petabytes in size. We present a fully automatic mitochondria detector based on a modified U-Net architecture that yields high accuracy and fast processing times. We evaluate our method on multiple real-world connectomics datasets, including an improved version of the EPFL mitochondria benchmark. Our results show an Jaccard index of up to 0.90 with inference times lower than 16ms for a $512\times512$px image tile. This speed is faster than the acquisition speed of modern electron microscopes, enabling mitochondria detection in real-time. Our detector ranks first for real-time detection when compared to previous works and data, results, and code are openly available.

Cite this Paper


BibTeX
@InProceedings{pmlr-v121-casser20a, title = {Fast Mitochondria Detection for Connectomics}, author = {Casser, Vincent and Kang, Kai and Pfister, Hanspeter and Haehn, Daniel}, pages = {111--120}, year = {2020}, editor = {Tal Arbel and Ismail Ben Ayed and Marleen de Bruijne and Maxime Descoteaux and Herve Lombaert and Christopher Pal}, volume = {121}, series = {Proceedings of Machine Learning Research}, address = {Montreal, QC, Canada}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/casser20a/casser20a.pdf}, url = {http://proceedings.mlr.press/v121/casser20a.html}, abstract = {High-resolution connectomics data allows for the identification of dysfunctional mitochondria which are linked to a variety of diseases such as autism or bipolar. However, manual analysis is not feasible since datasets can be petabytes in size. We present a fully automatic mitochondria detector based on a modified U-Net architecture that yields high accuracy and fast processing times. We evaluate our method on multiple real-world connectomics datasets, including an improved version of the EPFL mitochondria benchmark. Our results show an Jaccard index of up to 0.90 with inference times lower than 16ms for a $512\times512$px image tile. This speed is faster than the acquisition speed of modern electron microscopes, enabling mitochondria detection in real-time. Our detector ranks first for real-time detection when compared to previous works and data, results, and code are openly available.} }
Endnote
%0 Conference Paper %T Fast Mitochondria Detection for Connectomics %A Vincent Casser %A Kai Kang %A Hanspeter Pfister %A Daniel Haehn %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-casser20a %I PMLR %J Proceedings of Machine Learning Research %P 111--120 %U http://proceedings.mlr.press %V 121 %W PMLR %X High-resolution connectomics data allows for the identification of dysfunctional mitochondria which are linked to a variety of diseases such as autism or bipolar. However, manual analysis is not feasible since datasets can be petabytes in size. We present a fully automatic mitochondria detector based on a modified U-Net architecture that yields high accuracy and fast processing times. We evaluate our method on multiple real-world connectomics datasets, including an improved version of the EPFL mitochondria benchmark. Our results show an Jaccard index of up to 0.90 with inference times lower than 16ms for a $512\times512$px image tile. This speed is faster than the acquisition speed of modern electron microscopes, enabling mitochondria detection in real-time. Our detector ranks first for real-time detection when compared to previous works and data, results, and code are openly available.
APA
Casser, V., Kang, K., Pfister, H. & Haehn, D.. (2020). Fast Mitochondria Detection for Connectomics. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in PMLR 121:111-120

Related Material