Deep Learning based implementation for probabilistic classification of mass spectrometry imaging (MSI) data without prior peak picking.
Paper: Abdelmoula et al. "massNet: integrated processing and classification of spatially resolved mass spectrometry data using deep learning for rapid tumor delineation", bioRxiv 2021. https://www.biorxiv.org/content/10.1101/2021.05.06.442938v1.abstract
License: massNet code is shared under the 3D Slicer Software License agreement.
We have implemented our machine learning model using the following software items:
1- Python(3.6.12)
2- Keras (2.2.0) with a Tensorflow(1.8.0) backend.
3- Packages: numpy(1.15.4), sklearn(0.23.2), scipy(1.0.0), seaborn (0.9.0), Pandas(1.1.1.), and h5py(2.7.1)
If you used this code, please cite: Abdelmoula et al. "massNet: integrated processing and classification of spatially resolved mass spectrometry data using deep learning for rapid tumor delineation", bioRxiv 2021.