A Fully Automated Robot for the Preparation of Fungal Samples for FTIR Spectroscopy Using Deep Learning

Ya Xiong, Volha Shapaval, Achim Kohler, Jichun Li, Pal Johan From

Research output: Contribution to journalArticleResearchpeer-review

16 Downloads (Pure)

Abstract

Manual preparation of fungal samples for Fourier Transform Infrared (FTIR) spectroscopy involves sample washing, homogenization, concentration and spotting, which requires time-consuming and repetitive operations, making it unsuitable for screening studies. This paper presents the design and development of a fully automated robot for the preparation of fungal samples for FTIR spectroscopy. The whole system was constructed based on a previously-developed ultrasonication robot module, by adding a newly-designed centrifuge module and a newly-developed liquid handling module. The liquid handling module consists of a high accuracy electric pipette for spotting and a low accuracy syringe pump for sample washing and concentration. A dual robotic arm system with a gripper connects all of the hardware components. Furthermore, a camera on the liquid handling module uses deep learning to identify the labware settings, which includes the number and positions of well plates and pipette tips. Machine vision on the ultrasonication robot module can detect the sample wells and return the locations to the liquid handling module, which makes the system hand-free for users. Tight integration of all the modules enables the robot to process up to two 96-well microtiter (MTP) plates of samples simultaneously. Performance evaluation shows the deep learning based approach can detect four classes of labware with high average precision, from 0.93 to 1.0. In addition, tests of all procedures show that the robot is able to provide homogeneous sample spots for FTIR spectroscopy with high positional accuracy and spot coverage rate.
Original languageEnglish
Pages (from-to)132763-132774
Number of pages12
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 16 Sep 2019

Fingerprint

Fourier transform infrared spectroscopy
Robots
Liquids
Washing
Syringes
Robotic arms
Grippers
Centrifuges
Computer vision
Screening
Cameras
Deep learning
Pumps
Hardware

Cite this

Xiong, Ya ; Shapaval, Volha ; Kohler, Achim ; Li, Jichun ; From, Pal Johan. / A Fully Automated Robot for the Preparation of Fungal Samples for FTIR Spectroscopy Using Deep Learning. In: IEEE Access. 2019 ; Vol. 7. pp. 132763-132774.
@article{7e52eb615a3e47b1851b05b77c0a0f30,
title = "A Fully Automated Robot for the Preparation of Fungal Samples for FTIR Spectroscopy Using Deep Learning",
abstract = "Manual preparation of fungal samples for Fourier Transform Infrared (FTIR) spectroscopy involves sample washing, homogenization, concentration and spotting, which requires time-consuming and repetitive operations, making it unsuitable for screening studies. This paper presents the design and development of a fully automated robot for the preparation of fungal samples for FTIR spectroscopy. The whole system was constructed based on a previously-developed ultrasonication robot module, by adding a newly-designed centrifuge module and a newly-developed liquid handling module. The liquid handling module consists of a high accuracy electric pipette for spotting and a low accuracy syringe pump for sample washing and concentration. A dual robotic arm system with a gripper connects all of the hardware components. Furthermore, a camera on the liquid handling module uses deep learning to identify the labware settings, which includes the number and positions of well plates and pipette tips. Machine vision on the ultrasonication robot module can detect the sample wells and return the locations to the liquid handling module, which makes the system hand-free for users. Tight integration of all the modules enables the robot to process up to two 96-well microtiter (MTP) plates of samples simultaneously. Performance evaluation shows the deep learning based approach can detect four classes of labware with high average precision, from 0.93 to 1.0. In addition, tests of all procedures show that the robot is able to provide homogeneous sample spots for FTIR spectroscopy with high positional accuracy and spot coverage rate.",
author = "Ya Xiong and Volha Shapaval and Achim Kohler and Jichun Li and From, {Pal Johan}",
year = "2019",
month = "9",
day = "16",
doi = "10.1109/ACCESS.2019.2941704",
language = "English",
volume = "7",
pages = "132763--132774",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

A Fully Automated Robot for the Preparation of Fungal Samples for FTIR Spectroscopy Using Deep Learning. / Xiong, Ya; Shapaval, Volha; Kohler, Achim; Li, Jichun; From, Pal Johan.

In: IEEE Access, Vol. 7, 16.09.2019, p. 132763-132774.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A Fully Automated Robot for the Preparation of Fungal Samples for FTIR Spectroscopy Using Deep Learning

AU - Xiong, Ya

AU - Shapaval, Volha

AU - Kohler, Achim

AU - Li, Jichun

AU - From, Pal Johan

PY - 2019/9/16

Y1 - 2019/9/16

N2 - Manual preparation of fungal samples for Fourier Transform Infrared (FTIR) spectroscopy involves sample washing, homogenization, concentration and spotting, which requires time-consuming and repetitive operations, making it unsuitable for screening studies. This paper presents the design and development of a fully automated robot for the preparation of fungal samples for FTIR spectroscopy. The whole system was constructed based on a previously-developed ultrasonication robot module, by adding a newly-designed centrifuge module and a newly-developed liquid handling module. The liquid handling module consists of a high accuracy electric pipette for spotting and a low accuracy syringe pump for sample washing and concentration. A dual robotic arm system with a gripper connects all of the hardware components. Furthermore, a camera on the liquid handling module uses deep learning to identify the labware settings, which includes the number and positions of well plates and pipette tips. Machine vision on the ultrasonication robot module can detect the sample wells and return the locations to the liquid handling module, which makes the system hand-free for users. Tight integration of all the modules enables the robot to process up to two 96-well microtiter (MTP) plates of samples simultaneously. Performance evaluation shows the deep learning based approach can detect four classes of labware with high average precision, from 0.93 to 1.0. In addition, tests of all procedures show that the robot is able to provide homogeneous sample spots for FTIR spectroscopy with high positional accuracy and spot coverage rate.

AB - Manual preparation of fungal samples for Fourier Transform Infrared (FTIR) spectroscopy involves sample washing, homogenization, concentration and spotting, which requires time-consuming and repetitive operations, making it unsuitable for screening studies. This paper presents the design and development of a fully automated robot for the preparation of fungal samples for FTIR spectroscopy. The whole system was constructed based on a previously-developed ultrasonication robot module, by adding a newly-designed centrifuge module and a newly-developed liquid handling module. The liquid handling module consists of a high accuracy electric pipette for spotting and a low accuracy syringe pump for sample washing and concentration. A dual robotic arm system with a gripper connects all of the hardware components. Furthermore, a camera on the liquid handling module uses deep learning to identify the labware settings, which includes the number and positions of well plates and pipette tips. Machine vision on the ultrasonication robot module can detect the sample wells and return the locations to the liquid handling module, which makes the system hand-free for users. Tight integration of all the modules enables the robot to process up to two 96-well microtiter (MTP) plates of samples simultaneously. Performance evaluation shows the deep learning based approach can detect four classes of labware with high average precision, from 0.93 to 1.0. In addition, tests of all procedures show that the robot is able to provide homogeneous sample spots for FTIR spectroscopy with high positional accuracy and spot coverage rate.

U2 - 10.1109/ACCESS.2019.2941704

DO - 10.1109/ACCESS.2019.2941704

M3 - Article

VL - 7

SP - 132763

EP - 132774

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -