pyM2aia: Python interface for mass spectrometry imaging with focus on deep learning.

SUMMARY: Python is the most commonly used language for deep learning (DL). Existing Python packages for mass spectrometry imaging (MSI) data are not optimized for DL tasks. We, therefore, introduce pyM2aia, a Python package for MSI data analysis with a focus on memory-efficient handling, processing and convenient data-access for DL applications. pyM2aia provides interfaces to its parent application M2aia, which offers interactive capabilities for exploring and annotating MSI data in imzML format. pyM2aia utilizes the image input and output routines, data formats, and processing functions of M2aia, ensures data interchangeability, and enables the writing of readable and easy-to-maintain DL pipelines by providing batch generators for typical MSI data access strategies. We showcase the package in several examples, including imzML metadata parsing, signal processing, ion-image generation, and, in particular, DL model training and inference for spectrum-wise approaches, ion-image-based approaches, and approaches that use spectral and spatial information simultaneously. AVAILABILITY AND IMPLEMENTATION: Python package, code and examples are available at (https://m2aia.github.io/m2aia).

Spatial probabilistic mapping of metabolite ensembles in mass spectrometry imaging.

Mass spectrometry imaging vows to enable simultaneous spatially resolved investigation of hundreds of metabolites in tissues, but it primarily relies on traditional ion images for non-data-driven metabolite visualization and analysis. The rendering and interpretation of ion images neither considers nonlinearities in the resolving power of mass spectrometers nor does it yet evaluate the statistical significance of differential spatial metabolite abundance. Here, we outline the computational framework moleculaR ( https://github.com/CeMOS-Mannheim/moleculaR ) that is expected to improve signal reliability by data-dependent Gaussian-weighting of ion intensities and that introduces probabilistic molecular mapping of statistically significant nonrandom patterns of relative spatial abundance of metabolites-of-interest in tissue. moleculaR also enables cross-tissue statistical comparisons and collective molecular projections of entire biomolecular ensembles followed by their spatial statistical significance evaluation on a single tissue plane. It thereby fosters the spatially resolved investigation of ion milieus, lipid remodeling pathways, or complex scores like the adenylate energy charge within the same image.

M2aia-Interactive, fast, and memory-efficient analysis of 2D and 3D multi-modal mass spectrometry imaging data.

BACKGROUND: Mass spectrometry imaging (MSI) is a label-free analysis method for resolving bio-molecules or pharmaceuticals in the spatial domain. It offers unique perspectives for the examination of entire organs or other tissue specimens. Owing to increasing capabilities of modern MSI devices, the use of 3D and multi-modal MSI becomes feasible in routine applications-resulting in hundreds of gigabytes of data. To fully leverage such MSI acquisitions, interactive tools for 3D image reconstruction, visualization, and analysis are required, which preferably should be open-source to allow scientists to develop custom extensions. FINDINGS: We introduce M2aia (MSI applications for interactive analysis in MITK), a software tool providing interactive and memory-efficient data access and signal processing of multiple large MSI datasets stored in imzML format. M2aia extends MITK, a popular open-source tool in medical image processing. Besides the steps of a typical signal processing workflow, M2aia offers fast visual interaction, image segmentation, deformable 3D image reconstruction, and multi-modal registration. A unique feature is that fused data with individual mass axes can be visualized in a shared coordinate system. We demonstrate features of M2aia by reanalyzing an N-glycan mouse kidney dataset and 3D reconstruction and multi-modal image registration of a lipid and peptide dataset of a mouse brain, which we make publicly available. CONCLUSIONS: To our knowledge, M2aia is the first extensible open-source application that enables a fast, user-friendly, and interactive exploration of large datasets. M2aia is applicable to a wide range of MSI analysis tasks.

Computational Analysis of Alzheimer Amyloid Plaque Composition in 2D- and Elastically Reconstructed 3D-MALDI MS Images.

MALDI mass spectrometry imaging (MSI) enables label-free, spatially resolved analysis of a wide range of analytes in tissue sections. Quantitative analysis of MSI datasets is typically performed on single pixels or manually assigned regions of interest (ROIs). However, many sparse, small objects such as Alzheimer's disease (AD) brain deposits of amyloid peptides called plaques are neither single pixels nor ROIs. Here, we propose a new approach to facilitate the comparative computational evaluation of amyloid plaque-like objects by MSI: a fast PLAQUE PICKER tool that enables a statistical evaluation of heterogeneous amyloid peptide composition. Comparing two AD mouse models, APP NL-G-F and APP PS1, we identified distinct heterogeneous plaque populations in the NL-G-F model but only one class of plaques in the PS1 model. We propose quantitative metrics for the comparison of technical and biological MSI replicates. Furthermore, we reconstructed a high-accuracy 3D-model of amyloid plaques in a fully automated fashion, employing rigid and elastic MSI image registration using structured and plaque-unrelated reference ion images. Statistical single-plaque analysis in reconstructed 3D-MSI objects revealed the Aß1-42Arc peptide to be located either in the core of larger plaques or in small plaques without colocalization of other Aß isoforms. In 3D, a substantially larger number of small plaques were observed than that indicated by the 2D-MSI data, suggesting that quantitative analysis of molecularly diverse sparsely-distributed features may benefit from 3D-reconstruction. Data are available via ProteomeXchange with identifier PXD020824.

Association of Cerebrospinal Fluid Volume with Cerebral Vasospasm After Aneurysmal Subarachnoid Hemorrhage: A Retrospective Volumetric Analysis.

BACKGROUND: In aneurysmal subarachnoid hemorrhage (SAH), clot volume has been shown to correlate with the development of radiographic vasospasm (VS), while the role of cerebrospinal fluid (CSF) volume remains largely elusive in the literature. We evaluated CSF volume as a potential surrogate for VS in addition to SAH volume in this retrospective series. PATIENTS AND METHODS: From a consecutive cohort of aneurysmal SAH (n= 320), cases were included when angiographic evaluation for VS was performed (n= 125). SAH and CSF volumes were volumetrically quantified using an algorithm-assisted segmentation approach on initial computed tomography after ictus. Association with VS was analyzed using regression analysis. Receiver operating characteristic (ROC) curves were used to evaluate predictive accuracy of volumetric measures for VS and to identify cutoffs for risk stratification. RESULTS: Among 125 included cases, angiography showed VS in 101 (VS+), while no VS was observed in 24 (VS-) cases. In volumetric analysis, mean SAH volume was significantly larger (26.8 ± 21.1 ml vs. 12.6 ± 12.2 ml, p= 0.001), while mean CSF volume was significantly smaller (63.0 ± 31.2 ml vs. 85.7 ± 62.8, p= 0.03) in VS+ compared to VS- cases, respectively. The absence of correlation for SAH and CSF volumes (Pearson R - 0.05, p= 0.58) indicated independence of both measures of the subarachnoid compartment, which was a prerequisite for CSF to act as a new surrogate for VS not related to SAH. Regression analysis confirmed an increased risk of VS with increasing SAH (OR 1.06, 95% CI 1.02-1.11, p= 0.006), while CSF had a protective effect toward VS (OR 0.99, 95% CI 0.98-0.99, p= 0.02). SAH/CSF ratio was also associated with VS (OR 1.03, 95% CI 1.01-1.05, p= 0.015). ROC curves suggested cutoffs at 120 ml CSF and 20 ml SAH for VS stratification. Combination of variables improved stratification accuracy compared to use of SAH alone. CONCLUSION: This study provides a proof of concept for CSF correlating with angiographic VS after aneurysmal SAH. Quantification of CSF in conjunction with SAH might enhance risk stratification and exhibit advantages over traditional scores. The association of CSF has to be corroborated for delayed cerebral ischemia to further establish CSF as a surrogate parameter.

Development and Validation of an Automatic Segmentation Algorithm for Quantification of Intracerebral Hemorrhage.

BACKGROUND AND PURPOSE: ABC/2 is still widely accepted for volume estimations in spontaneous intracerebral hemorrhage (ICH) despite known limitations, which potentially accounts for controversial outcome-study results. The aim of this study was to establish and validate an automatic segmentation algorithm, allowing for quick and accurate quantification of ICH. METHODS: A segmentation algorithm implementing first- and second-order statistics, texture, and threshold features was trained on manual segmentations with a random-forest methodology. Quantitative data of the algorithm, manual segmentations, and ABC/2 were evaluated for agreement in a study sample (n=28) and validated in an independent sample not used for algorithm training (n=30). RESULTS: ABC/2 volumes were significantly larger compared with either manual or algorithm values, whereas no significant differences were found between the latter (P<0.0001; Friedman+Dunn's multiple comparison). Algorithm agreement with the manual reference was strong (concordance correlation coefficient 0.95 [lower 95% confidence interval 0.91]) and superior to ABC/2 (concordance correlation coefficient 0.77 [95% confidence interval 0.64]). Validation confirmed agreement in an independent sample (algorithm concordance correlation coefficient 0.99 [95% confidence interval 0.98], ABC/2 concordance correlation coefficient 0.82 [95% confidence interval 0.72]). The algorithm was closer to respective manual segmentations than ABC/2 in 52/58 cases (89.7%). CONCLUSIONS: An automatic segmentation algorithm for volumetric analysis of spontaneous ICH was developed and validated in this study. Algorithm measurements showed strong agreement with manual segmentations, whereas ABC/2 exhibited its limitations, yielding inaccurate overestimations of ICH volume. The refined, yet time-efficient, quantification of ICH by the algorithm may facilitate evaluation of clot volume as an outcome predictor and trigger for surgical interventions in the clinical setting.