MIMO U-Net: Efficient Cell Segmentation and Counting in Microscopy Image Sequences

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11140%2F23%3A10469133" target="_blank" >RIV/00216208:11140/23:10469133 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1117/12.2655627" target="_blank" >https://doi.org/10.1117/12.2655627</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1117/12.2655627" target="_blank" >10.1117/12.2655627</a>

Result language

angličtina

Original language name

MIMO U-Net: Efficient Cell Segmentation and Counting in Microscopy Image Sequences

Original language description

Automatic cell quantification in microscopy images can accelerate biomedical research. There has been significant progress in the 3D segmentation of neurons in fluorescence microscopy. However, it remains a challenge in bright-field microscopy due to the low Signal-to-Noise Ratio and signals from out-of-focus neurons. Automatic neuron counting in bright-field z-stacks is often performed on Extended Depth of Field images or on only one thick focal plane image. However, resolving overlapping cells that are located at different z-depths is a challenge. The overlap can be resolved by counting every neuron in its best focus z-plane because of their separation on the z-axis. Unbiased stereology is the state-of-the-art for total cell number estimation. The segmentation boundary for cells is required in order to incorporate the unbiased counting rule for stereology application. Hence, we perform counting via segmentation. We propose to achieve neuron segmentation in the optimal focal plane by posing the binary segmentation task as a multi-class multi-label task. Also, we propose to efficiently use a 2D U-Net for inter-image feature learning in a Multiple Input Multiple Output system that poses a binary segmentation task as a multi-class multi-label segmentation task. We demonstrate the accuracy and efficiency of the MIMO approach using a bright-field microscopy z-stack dataset locally prepared by an expert. The proposed MIMO approach is also validated on a dataset from the Cell Tracking Challenge achieving comparable results to a compared method equipped with memory units. Our z-stack dataset is available at https://tinyurl.com/wncfxn9m.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

30100 - Basic medicine

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

MEDICAL IMAGING 2023

ISBN

978-1-5106-6047-2

ISSN

1605-7422

e-ISSN

—

Number of pages

7

Pages from-to

1-7

Publisher name

SPIE-INT SOC OPTICAL ENGINEERING

Place of publication

BELLINGHAM

Event location

San Diego

Event date

Feb 19, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001011463700025