Methylphenidate Differentially Affects Intrinsic Functional Connectivity of the Salience Network in Adult ADHD Treatment Responders and Non-Responders

Positron emission tomography (PET) studies have shown involvement of the striatum when treating adult attention-deficit/hyperactivity disorder (ADHD) with methylphenidate (MPH). Results from resting-state functional magnetic resonance imaging (rs-fMRI) for the same issue were less unequivocal. Here, a new analytical framework was set up to investigate medication effects using seed-based rs-fMRI analysis to infer brain regions with alterations in intrinsic functional connectivity (IFC) corresponding with ADHD symptom reduction. In a within-subjects study design, 53 stimulant-naïve adult ADHD patients were investigated before and after 6 weeks of MPH treatment, using two major clinical symptom scales and rs-fMRI. The same data were acquired in a sample of 50 age- and sex-matched healthy controls at baseline. A consensual atlas provided seeds for five predefined major resting-state networks. In order to avoid biasing of medication effects due to putative treatment failure, the entire ADHD sample was first categorized into treatment Responders (N = 36) and Non-Responders (N = 17) using machine learning-based classification with the clinical scales as primary data. Imaging data revealed medication effects only in Responders. In that group, IFC of bilateral putamen changed significantly with medication and approached almost normal levels of IFC. Present results align well with results from previous PET studies, with seed-based rs-fMRI as an entirely different neuroimaging method.

Two-Dimensional and Three-Dimensional Time-of-Flight Secondary Ion Mass Spectrometry Image Feature Extraction Using a Spatially Aware Convolutional Autoencoder

Feature extraction algorithms are an important class of unsupervised methods used to reduce data dimensionality. They have been applied extensively for time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging─commonly, matrix factorization (MF) techniques such as principal component analysis have been used. A limitation of MF is the assumption of linearity, which is generally not accurate for ToF-SIMS data. Recently, nonlinear autoencoders have been shown to outperform MF techniques for ToF-SIMS image feature extraction. However, another limitation of most feature extraction methods (including autoencoders) that is particularly important for hyperspectral data is that they do not consider spatial information. To address this limitation, we describe the application of the convolutional autoencoder (CNNAE) to hyperspectral ToF-SIMS imaging data. The CNNAE is an artificial neural network developed specifically for hyperspectral data that uses convolutional layers for image encoding, thereby explicitly incorporating pixel neighborhood information. We compared the performance of the CNNAE with other common feature extraction algorithms for two biological ToF-SIMS imaging data sets. We investigated the extracted features and used the dimensionality-reduced data to train additional ML algorithms. By converting two-dimensional convolutional layers to three-dimensional (3D), we also showed how the CNNAE can be extended to 3D ToF-SIMS images. In general, the CNNAE produced features with significantly higher contrast and autocorrelation than other techniques. Furthermore, histologically recognizable features in the data were more accurately represented. The extension of the CNNAE to 3D data also provided an important proof of principle for the analysis of more complex 3D data sets.

Fast visual exploration of mass spectrometry images with interactive dynamic spectral similarity pseudocoloring

Mass Spectrometry Imaging (MSI) is an established and still evolving technique for the spatial analysis of molecular co-location in biological samples. Nowadays, MSI is expanding into new domains such as clinical pathology. In order to increase the value of MSI data, software for visual analysis is required that is intuitive and technique independent. Here, we present QUIMBI (QUIck exploration tool for Multivariate BioImages) a new tool for the visual analysis of MSI data. QUIMBI is an interactive visual exploration tool that provides the user with a convenient and straightforward visual exploration of morphological and spectral features of MSI data. To improve the overall quality of MSI data by reducing non-tissue specific signals and to ensure optimal compatibility with QUIMBI, the tool is combined with the new pre-processing tool ProViM (Processing for Visualization and multivariate analysis of MSI Data), presented in this work. The features of the proposed visual analysis approach for MSI data analysis are demonstrated with two use cases. The results show that the use of ProViM and QUIMBI not only provides a new fast and intuitive visual analysis, but also allows the detection of new co-location patterns in MSI data that are difficult to find with other methods.

Unsupervised machine learning for exploratory data analysis in imaging mass spectrometry

Imaging mass spectrometry (IMS) is a rapidly advancing molecular imaging modality that can map the spatial distribution of molecules with high chemical specificity. IMS does not require prior tagging of molecular targets and is able to measure a large number of ions concurrently in a single experiment. While this makes it particularly suited for exploratory analysis, the large amount and high-dimensional nature of data generated by IMS techniques make automated computational analysis indispensable. Research into computational methods for IMS data has touched upon different aspects, including spectral preprocessing, data formats, dimensionality reduction, spatial registration, sample classification, differential analysis between IMS experiments, and data-driven fusion methods to extract patterns corroborated by both IMS and other imaging modalities. In this work, we review unsupervised machine learning methods for exploratory analysis of IMS data, with particular focus on (a) factorization, (b) clustering, and (c) manifold learning. To provide a view across the various IMS modalities, we have attempted to include examples from a range of approaches including matrix assisted laser desorption/ionization, desorption electrospray ionization, and secondary ion mass spectrometry-based IMS. This review aims to be an entry point for both (i) analytical chemists and mass spectrometry experts who want to explore computational techniques; and (ii) computer scientists and data mining specialists who want to enter the IMS field. © 2019 The Authors. Mass Spectrometry Reviews published by Wiley Periodicals, Inc. Mass SpecRev 00:1-47, 2019.

Colocalization Features for Classification of Tumors Using Desorption Electrospray Ionization Mass Spectrometry Imaging

Supervised modeling of mass spectrometry imaging (MSI) data is a crucial component for the detection of the distinct molecular characteristics of cancerous tissues. Currently, two types of supervised analyses are mainly used on MSI data: pixel-wise segmentation of sample images and whole-sample-based classification. A large number of mass spectra associated with each MSI sample can represent a challenge for designing models that simultaneously preserve the overall molecular content while capturing valuable information contained in the MSI data. Furthermore, intensity-related batch effects can introduce biases in the statistical models. Here we introduce a method based on ion colocalization features that allows the classification of whole tissue specimens using MSI data, which naturally preserves the spatial information associated the with the mass spectra and is less sensitive to possible batch effects. Finally, we propose data visualization strategies for the inspection of the derived networks, which can be used to assess whether the correlation differences are related to coexpression/suppression or disjoint spatial localization patterns and can suggest hypotheses based on the underlying mechanisms associated with the different classes of analyzed samples.

Scores for standardization of on-tissue digestion of formalin-fixed paraffin-embedded tissue in MALDI-MS imaging

On-slide digestion of formalin-fixed and paraffin-embedded human biopsy tissue followed by mass spectrometry imaging of resulting peptides may have the potential to become an additional analytical modality in future ePathology. Multiple workflows have been described for dewaxing, antigen retrieval, digestion and imaging in the past decade. However, little is known about suitable statistical scores for method comparison and systematic workflow standardization required for development of processes that would be robust enough to be compatible with clinical routine. To define scores for homogeneity of tissue processing and imaging as well as inter-day repeatability for five different processing methods, we used human liver and gastrointestinal stromal tumor tissue, both judged by an expert pathologist to be >98% histologically homogeneous. For mean spectra-based as well as pixel-wise data analysis, we propose the coefficient of determination R², the natural fold-change (natFC) value and the digest efficiency DE% as readily accessible scores. Moreover, we introduce two scores derived from principal component analysis, the variance of the mean absolute deviation, MAD, and the interclass overlap, J_overlap, as computational scores that may help to avoid user bias during future workflow development. This article is part of a Special Issue entitled: MALDI Imaging, edited by Dr. Corinna Henkel and Prof. Peter Hoffmann.