Image classification software tools | Mass spectrometry imaging analysis
Tumor classification using imaging mass spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data.
Assists users to analyze mass spectrometry imaging data. SCILS Lab includes a lot of functionalities allowing researchers to display multiple samples in both 2D and 3D and permitting a multitude of applications in pharmaceutical, medical, and industrial research. This software is composed of several features among which comparative analysis for uncovering discriminative m/z-markers, classification model calculation based on training data and classification of new samples, or extraction of underlying trends.
A mass spectrometry imaging toolbox for statistical analysis. Cardinal is an R package that implements statistical and computational tools for analyzing mass spectrometry imaging datasets, including methods for efficient pre-processing, spatial segmentation, and classification.
Organizes and processes multimodal mass spectrometry imaging data. HDI Software allows users to interrogate complex imaging data. The software enables the integration of multimodal imaging experiments for SYNAPT G2-Si as well as DESI imaging for Xevo G2-XS Mass Spectrometers. Some of its benefits are the image clarity and integrity, as well as Sequential sample acquisition for accelerated throughput.
Enables extraction of tumor specific spectral patterns from mass spectrometry imaging (MSI) data. ‘Supervised_NMF_Methods_for_MALDI’ consists of an extension of the classical non-negative matrix factorization (NMF) framework obtained by incorporating the class information on the training data into the NMF feature extraction step. This approach's potential for tumor typing was evaluated using matrix-assisted laser desorption/ionization (MALDI) MSI.
Classifies tumors in imaging mass spectrometry (IMS). Deep_Learning_for_Tumor_Classification_in_IMS is based on a deep neural network method. It starts by pre-processing data and handles separately each spectrum measured in a tissue spot by IMS. This tool can compute several convolutional and non-linear transforms of the input data in order to retrieve high-level abstractions for the classification stage.