Single Object Spectrum Training for 2D NMR Signals Detection

Hadeel Saad Alghamdi; Alexei Lisitsa; Igor Barsukov; Rudi Grosman

doi:10.1117/12.3056329

Single Object Spectrum Training for 2D NMR Signals Detection

Hadeel Saad Alghamdi
, Alexei Lisitsa
, Igor Barsukov
, Rudi Grosman

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Peak picking in two-dimensional Nuclear Magnetic Resonance (NMR) spectra represents a significant research challenge and requires substantial time and effort for effective analysis. While machine learning methods have been introduced for peak detection and segmentation [1], the variable sizes, intensities, and positions of NMR peaks often lead models to inaccurately identify peaks, resulting in a high rate of false detections. To address this issue, we have adopted a novel training strategy called Single Object Spectrum Training. This method focuses on learning from simpler cases of peaks, enhancing the model's ability to accurately identify individual peaks within complex spectra.

Original language	English
Title of host publication	Seventeenth International Conference on Machine Vision, ICMV 2024
Editors	Wolfgang Osten
Publisher	SPIE
ISBN (Electronic)	9781510688278
DOIs	https://doi.org/10.1117/12.3056329
State	Published - 2025
Externally published	Yes
Event	17th International Conference on Machine Vision, ICMV 2024 - Edinburg, United Kingdom Duration: 10 Oct 2024 → 13 Oct 2024

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	13517
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	17th International Conference on Machine Vision, ICMV 2024
Country/Territory	United Kingdom
City	Edinburg
Period	10/10/24 → 13/10/24

Bibliographical note

Publisher Copyright:
© 2025 SPIE.

Keywords

Mask R-CNN
NMR
Overlapping
Peaks
Single Object Spectrum

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.3056329

Cite this

@inproceedings{2c04531d96bf475d88abda97a6e69e18,

title = "Single Object Spectrum Training for 2D NMR Signals Detection",

abstract = "Peak picking in two-dimensional Nuclear Magnetic Resonance (NMR) spectra represents a significant research challenge and requires substantial time and effort for effective analysis. While machine learning methods have been introduced for peak detection and segmentation [1], the variable sizes, intensities, and positions of NMR peaks often lead models to inaccurately identify peaks, resulting in a high rate of false detections. To address this issue, we have adopted a novel training strategy called Single Object Spectrum Training. This method focuses on learning from simpler cases of peaks, enhancing the model's ability to accurately identify individual peaks within complex spectra.",

keywords = "Mask R-CNN, NMR, Overlapping, Peaks, Single Object Spectrum",

author = "Alghamdi, \{Hadeel Saad\} and Alexei Lisitsa and Igor Barsukov and Rudi Grosman",

note = "Publisher Copyright: {\textcopyright} 2025 SPIE.; 17th International Conference on Machine Vision, ICMV 2024 ; Conference date: 10-10-2024 Through 13-10-2024",

year = "2025",

doi = "10.1117/12.3056329",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Wolfgang Osten",

booktitle = "Seventeenth International Conference on Machine Vision, ICMV 2024",

address = "United States",

}

Alghamdi, HS, Lisitsa, A, Barsukov, I & Grosman, R 2025, Single Object Spectrum Training for 2D NMR Signals Detection. in W Osten (ed.), Seventeenth International Conference on Machine Vision, ICMV 2024., 135170P, Proceedings of SPIE - The International Society for Optical Engineering, vol. 13517, SPIE, 17th International Conference on Machine Vision, ICMV 2024, Edinburg, United Kingdom, 10/10/24. https://doi.org/10.1117/12.3056329

Single Object Spectrum Training for 2D NMR Signals Detection. / Alghamdi, Hadeel Saad; Lisitsa, Alexei; Barsukov, Igor et al.
Seventeenth International Conference on Machine Vision, ICMV 2024. ed. / Wolfgang Osten. SPIE, 2025. 135170P (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13517).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Single Object Spectrum Training for 2D NMR Signals Detection

AU - Alghamdi, Hadeel Saad

AU - Lisitsa, Alexei

AU - Barsukov, Igor

AU - Grosman, Rudi

PY - 2025

Y1 - 2025

N2 - Peak picking in two-dimensional Nuclear Magnetic Resonance (NMR) spectra represents a significant research challenge and requires substantial time and effort for effective analysis. While machine learning methods have been introduced for peak detection and segmentation [1], the variable sizes, intensities, and positions of NMR peaks often lead models to inaccurately identify peaks, resulting in a high rate of false detections. To address this issue, we have adopted a novel training strategy called Single Object Spectrum Training. This method focuses on learning from simpler cases of peaks, enhancing the model's ability to accurately identify individual peaks within complex spectra.

AB - Peak picking in two-dimensional Nuclear Magnetic Resonance (NMR) spectra represents a significant research challenge and requires substantial time and effort for effective analysis. While machine learning methods have been introduced for peak detection and segmentation [1], the variable sizes, intensities, and positions of NMR peaks often lead models to inaccurately identify peaks, resulting in a high rate of false detections. To address this issue, we have adopted a novel training strategy called Single Object Spectrum Training. This method focuses on learning from simpler cases of peaks, enhancing the model's ability to accurately identify individual peaks within complex spectra.

KW - Mask R-CNN

KW - NMR

KW - Overlapping

KW - Peaks

KW - Single Object Spectrum

UR - https://www.scopus.com/pages/publications/105000172452

U2 - 10.1117/12.3056329

DO - 10.1117/12.3056329

M3 - Conference contribution

AN - SCOPUS:105000172452

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Seventeenth International Conference on Machine Vision, ICMV 2024

A2 - Osten, Wolfgang

PB - SPIE

T2 - 17th International Conference on Machine Vision, ICMV 2024

Y2 - 10 October 2024 through 13 October 2024

ER -

Single Object Spectrum Training for 2D NMR Signals Detection

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this