Overview
massNet combines learned spectral representations with supervised tissue classification and exploration of discriminating peaks.
What can this tool do?
Common uses
- Learn spectral features and classify tissue regions in mass-spectrometry images.
Scientific fit
Primary function
Machine learning and prediction
Analysis types
Spatial metabolomics
Data compatibility
Inputs
Imaging data, Sample metadata
Outputs
Imaging data, Statistical results
Input formats
HDF5 spectra, m/z, tissue labels and pixel coordinates
Output formats
Classification probabilities, maps, learned features and plots
Scope and considerations
Designed for
- massNet combines learned spectral representations with supervised tissue classification and exploration of discriminating peaks.
Not designed for
- A ready-to-use clinical diagnostic or direct raw-vendor-file importer.
Important requirements
- Prepared arrays matching Main.py; labels for supervised training and evaluation.
- Legacy Python 3.6, Keras 2.2 and TensorFlow 1.8 environment documented by the authors; adaptation may be needed.
Considerations
- The published example concerns tumor-bearing mouse-brain MSI; assess transfer to other tissues and instruments.
- Keep independent specimens separate during evaluation to avoid leakage between correlated pixels.
Access and documentation
The repository supplies the 3D Slicer Software License agreement. This is research software; no installation or performance validation was performed.
License: 3D Slicer Software License
Evidence and review
Enveda intake checked against official documentation, license information and primary DOI/title/year on 2026-10-22. Editorial review only; no execution or independent benchmark.
Core publications
Resource papers, direct updates and tool-specific methods. Selection policy.
- massNet: integrated processing and classification of spatially resolved mass spectrometry data using deep learning for rapid tumor delineation. Bioinformatics (2022). doi:10.1093/bioinformatics/btac032
Related tools
Entry history
Changes to this catalogue entry, not the tool's software release history. Acceptance and editorial review are separate.
- 2026-10-23 · First committed entry
Add ten reviewed Enveda tools with input and applicability limits
View change · Entry at this revision