IonMorphNet: Generalizable Learning of Ion Image Morphologies for Peak Picking in Mass Spectrometry Imaging

TL;DR

IonMorphNet is a novel spatial-structure-aware model for ion image analysis in MSI that enables generalizable, data-driven peak picking and tumor classification without extensive hyperparameter tuning.

Contribution

It introduces IonMorphNet, a model trained on curated datasets to perform peak picking and tumor classification, improving accuracy and generalization over existing methods.

Findings

Improves peak picking performance by +7% mSCF1 over state-of-the-art methods.

Achieves up to +7.3% Balanced Accuracy in tumor classification tasks.

Enables fully data-driven analysis without task-specific hyperparameter tuning.

Abstract

Peak picking is a fundamental preprocessing step in Mass Spectrometry Imaging (MSI), where each sample is represented by hundreds to thousands of ion images. Existing approaches require careful dataset-specific hyperparameter tuning, and often fail to generalize across acquisition protocols. We introduce IonMorphNet, a spatial-structure-aware representation model for ion images that enables fully data-driven peak picking without any task-specific supervision. We curate 53 publicly available MSI datasets and define six structural classes capturing representative spatial patterns in ion images to train standard image backbones for structural pattern classification. Once trained, IonMorphNet can assess ion images and perform peak picking without additional hyperparameter tuning. Using a ConvNeXt V2-Tiny backbone, our approach improves peak picking performance by +7 % mSCF1 compared to state-of-the-art methods across multiple datasets. Beyond peak picking, we demonstrate that spatially informed channel reduction enables a 3D CNN for patch-based tumor classification in MSI. This approach matches or exceeds pixel-wise spectral classifiers by up to +7.3 % Balanced Accuracy on three tumor classification tasks, indicating meaningful ion image selection. The source code and model weights are available at https://github.com/CeMOS-IS/IonMorphNet.