Spatial self-supervised Peak Learning and correlation-based Evaluation of peak picking in Mass Spectrometry Imaging

2026-03-11

AI Summary

This study addresses the limited generalizability of existing mass spectrometry imaging (MSI) peak extraction methods on heterogeneous data and the absence of reliable evaluation criteria grounded in genuine tissue morphology. To overcome these challenges, the authors propose a spatial self-supervised peak learning network that, for the first time, integrates spatial self-supervised learning into MSI peak extraction. The method employs an autoencoder to jointly encode spectral and spatial information and learns attention masks to enable structure-aware peak selection. Furthermore, the work introduces the first evaluation framework based on expert-annotated segmentation masks to objectively quantify the spatial coherence of extracted peaks. Experiments on four public MSI datasets demonstrate that the proposed approach significantly outperforms state-of-the-art methods, yielding peaks with markedly improved spatial structural consistency, thereby validating its generalizability, robustness, and the efficacy of the proposed evaluation protocol.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Mass spectrometry imaging (MSI) enables label-free visualization of molecular distributions across tissue samples but generates large and complex datasets that require effective peak picking to reduce data size while preserving meaningful biological information. Existing peak picking approaches perform inconsistently across heterogeneous datasets, and their evaluation is often limited to synthetic data or manually selected ion images that do not fully represent real-world challenges in MSI. To address these limitations, we propose an autoencoder-based spatial self-supervised peak learning neural network that selects spatially structured peaks by learning an attention mask leveraging both spatial and spectral information. We further introduce an evaluation procedure based on expert-annotated segmentation masks, allowing a more representative and spatially grounded assessment of peak picking performance. We evaluate our approach on four diverse public MSI datasets using our proposed evaluation procedure. Our approach consistently outperforms state-of-the-art peak picking methods by selecting spatially structured peaks, thus demonstrating its efficacy. These results highlight the value of our spatial self-supervised network in comparison to contemporary state-of-the-art methods. The evaluation procedure can be readily applied to new MSI datasets, thereby providing a consistent and robust framework for the comparison of spatially structured peak picking methods across different datasets.

Problem

• Mass Spectrometry Imaging
• peak picking
• spatial evaluation
• heterogeneous datasets
• data reduction

Innovation

• spatial self-supervised learning
• peak picking
• mass spectrometry imaging
• attention mask
• expert-annotated evaluation