The Mass Spectrometry society of Japan - The 68th Annual Conference on Mass Spectrometry, Japan
Japanese

Abstract

Table of contents

Timetable

Plenary Lectures

Award Lecture

Oral Sessions (Day1, Day2, Day3)

Poster Presentations (Day1, Day2, Day3)

Panel Discussion

Luncheon Seminars (Day1, Day2, Day3)

Corporate Program

Poster Presentations

Day 3, June 24（Fri.）　　Room P (501, 502 and 503)

3P-25　　PDF

The improvement of qualities of mass images using machine-learning model made by scanning electron microscope images.

(JEOL)
oTakaya Satoh, Masahiko Takei, Fuminori Uematsu

The matrix-assisted laser desorption/ionization imaging mass spectrometry (MALDI-MSI) is used in various applications to investigate target compounds' localization. One of the issues of MALDI-MSI is the relatively low signal-to-noise ratio of extracted imaging data. It is due to the ununiform matrix application to the sample surface or low ion intensities from limited pixel regions. To solve the issue, we have developed the method to improve a quality of extracted mass imaging data using the machine learning model made by scanning electron microscope images. We have confirmed that the application of the machine learning model can improve the signal-to-noise ratio of extracted mass images.