Enabling large-scale screening of Barrett's esophagus using weakly supervised deep learning in histopathology.

Timely detection of Barrett's esophagus, the pre-malignant condition of esophageal adenocarcinoma, can improve patient survival rates. The Cytosponge-TFF3 test, a non-endoscopic minimally invasive procedure, has been used for diagnosing intestinal metaplasia in Barrett's. However, it depends on pathologist's assessment of two slides stained with H&E and the immunohistochemical biomarker TFF3. This resource-intensive clinical workflow limits large-scale screening in the at-risk population. To improve screening capacity, we propose a deep learning approach for detecting Barrett's from routinely stained H&E slides. The approach solely relies on diagnostic labels, eliminating the need for expensive localized expert annotations. We train and independently validate our approach on two clinical trial datasets, totaling 1866 patients. We achieve 91.4% and 87.3% AUROCs on discovery and external test datasets for the H&E model, comparable to the TFF3 model. Our proposed semi-automated clinical workflow can reduce pathologists' workload to 48% without sacrificing diagnostic performance, enabling pathologists to prioritize high risk cases.

Multiscale biochemical mapping of the brain through deep-learning-enhanced high-throughput mass spectrometry.

Spatial omics technologies can reveal the molecular intricacy of the brain. While mass spectrometry imaging (MSI) provides spatial localization of compounds, comprehensive biochemical profiling at a brain-wide scale in three dimensions by MSI with single-cell resolution has not been achieved. We demonstrate complementary brain-wide and single-cell biochemical mapping using MEISTER, an integrative experimental and computational mass spectrometry (MS) framework. Our framework integrates a deep-learning-based reconstruction that accelerates high-mass-resolving MS by 15-fold, multimodal registration creating three-dimensional (3D) molecular distributions and a data integration method fitting cell-specific mass spectra to 3D datasets. We imaged detailed lipid profiles in tissues with millions of pixels and in large single-cell populations acquired from the rat brain. We identified region-specific lipid contents and cell-specific localizations of lipids depending on both cell subpopulations and anatomical origins of the cells. Our workflow establishes a blueprint for future development of multiscale technologies for biochemical characterization of the brain.

Integrative Multiscale Biochemical Mapping of the Brain via Deep-Learning-Enhanced High-Throughput Mass Spectrometry.

Elucidating the spatial-biochemical organization of the brain across different scales produces invaluable insight into the molecular intricacy of the brain. While mass spectrometry imaging (MSI) provides spatial localization of compounds, comprehensive chemical profiling at a brain-wide scale in three dimensions by MSI with single-cell resolution has not been achieved. We demonstrate complementary brain-wide and single-cell biochemical mapping via MEISTER, an integrative experimental and computational mass spectrometry framework. MEISTER integrates a deep-learning-based reconstruction that accelerates high-mass-resolving MS by 15-fold, multimodal registration creating 3D molecular distributions, and a data integration method fitting cell-specific mass spectra to 3D data sets. We imaged detailed lipid profiles in tissues with data sets containing millions of pixels, and in large single-cell populations acquired from the rat brain. We identified region-specific lipid contents, and cell-specific localizations of lipids depending on both cell subpopulations and anatomical origins of the cells. Our workflow establishes a blueprint for future developments of multiscale technologies for biochemical characterization of the brain.

Single-Cell and Subcellular Analysis Using Ultrahigh Resolution 21 T MALDI FTICR Mass Spectrometry.

The mammalian brain contains ∼20,000 distinct lipid species that contribute to its structural organization and function. The lipid profiles of cells change in response to a variety of cellular signals and environmental conditions that result in modulation of cell function through alteration of phenotype. The limited sample material combined with the vast chemical diversity of lipids makes comprehensive lipid profiling of individual cells challenging. Here, we leverage the resolving power of a 21 T Fourier-transform ion cyclotron resonance (FTICR) mass spectrometer for chemical characterization of individual hippocampal cells at ultrahigh mass resolution. The accuracy of the acquired data allowed differentiation of freshly isolated and cultured hippocampal cell populations, as well as finding differences in lipids between the soma and neuronal processes of the same cell. Differences in lipids include TG 42:2 observed solely in the cell bodies and SM 34:1;O2 found only in the cellular processes. The work represents the first mammalian single cells analyzed at ultrahigh resolution and is an advance in the performance of mass spectrometry (MS) for single-cell research.

Probe-based mass spectrometry approaches for single-cell and single-organelle measurements.

Exploring the chemical content of individual cells not only reveals underlying cell-to-cell chemical heterogeneity but is also a key component in understanding how cells combine to form emergent properties of cellular networks and tissues. Recent technological advances in many analytical techniques including mass spectrometry (MS) have improved instrumental limits of detection and laser/ion probe dimensions, allowing the analysis of micron and submicron sized areas. In the case of MS, these improvements combined with MS's broad analyte detection capabilities have enabled the rise of single-cell and single-organelle chemical characterization. As the chemical coverage and throughput of single-cell measurements increase, more advanced statistical and data analysis methods have aided in data visualization and interpretation. This review focuses on secondary ion MS and matrix-assisted laser desorption/ionization MS approaches for single-cell and single-organelle characterization, which is followed by advances in mass spectral data visualization and analysis.

Data-Driven and Machine Learning-Based Framework for Image-Guided Single-Cell Mass Spectrometry.

Improved throughput of analysis and lowered limits of detection have allowed single-cell chemical analysis to go beyond the detection of a few molecules in such volume-limited samples, enabling researchers to characterize different functional states of individual cells. Image-guided single-cell mass spectrometry leverages optical and fluorescence microscopy in the high-throughput analysis of cellular and subcellular targets. In this work, we propose DATSIGMA (DAta-driven Tools for Single-cell analysis using Image-Guided MAss spectrometry), a workflow based on data-driven and machine learning approaches for feature extraction and enhanced interpretability of complex single-cell mass spectrometry data. Here, we implemented our toolset with user-friendly programs and tested it on multiple experimental data sets that cover a wide range of biological applications, including classifying various brain cell types. Because it is open-source, it offers a high level of customization and can be easily adapted to other types of single-cell mass spectrometry data.

Implantable Aptamer-Graphene Microtransistors for Real-Time Monitoring of Neurochemical Release in Vivo.

The real-time monitoring of neurochemical release in vivo plays a critical role in understanding the biochemical process of the complex nervous system. Current technologies for such applications, including microdialysis and fast-scan cyclic voltammetry, suffer from limited spatiotemporal resolution or poor selectivity. Here, we report a soft implantable aptamer-graphene microtransistor probe for real-time monitoring of neurochemical release. As a demonstration, we show the monitoring of dopamine with nearly cellular-scale spatial resolution, high selectivity (dopamine sensor >19-fold over norepinephrine), and picomolar sensitivity, simultaneously. Systematic benchtop evaluations, ex vivo experiments, and in vivo studies in mice models highlight the key features and demonstrate the capability of capturing the dopamine release dynamics evoked by pharmacological stimulation, suggesting the potential applications in basic neuroscience studies and studying neurological disease-related processes. The developed system can be easily adapted for monitoring other neurochemicals and drugs by simply replacing the aptamers functionalized on the graphene microtransistors.

Enhancing the Throughput of FT Mass Spectrometry Imaging Using Joint Compressed Sensing and Subspace Modeling.

Mass spectrometry imaging (MSI) allows for untargeted mapping of the chemical composition of tissues with attomole detection limits. MSI using Fourier transform (FT)-based mass spectrometers, such as FT-ion cyclotron resonance (FT-ICR), grants the ability to examine the chemical space with unmatched mass resolution and mass accuracy. However, direct imaging of large tissue samples using FT-ICR is slow. In this work, we present an approach that combines the subspace modeling of ICR temporal signals with compressed sensing to accelerate high-resolution FT-ICR MSI. A joint subspace and spatial sparsity constrained model computationally reconstructs high-resolution MSI data from the sparsely sampled transients with reduced duration, allowing a significant reduction in imaging time. Simulation studies and experimental implementation of the proposed method in investigation of brain tissues demonstrate a 10-fold enhancement in throughput of FT-ICR MSI, without the need for instrumental or hardware modifications.

Active label cleaning for improved dataset quality under resource constraints.

Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have a confounding effect on the assessment of model performance. Nevertheless, employing experts to remove label noise by fully re-annotating large datasets is infeasible in resource-constrained settings, such as healthcare. This work advocates for a data-driven approach to prioritising samples for re-annotation-which we term "active label cleaning". We propose to rank instances according to estimated label correctness and labelling difficulty of each sample, and introduce a simulation framework to evaluate relabelling efficacy. Our experiments on natural images and on a specifically-devised medical imaging benchmark show that cleaning noisy labels mitigates their negative impact on model training, evaluation, and selection. Crucially, the proposed approach enables correcting labels up to 4 × more effectively than typical random selection in realistic conditions, making better use of experts' valuable time for improving dataset quality.

Image-guided MALDI mass spectrometry for high-throughput single-organelle characterization.

Peptidergic dense-core vesicles are involved in packaging and releasing neuropeptides and peptide hormones-critical processes underlying brain, endocrine and exocrine function. Yet, the heterogeneity within these organelles, even for morphologically defined vesicle types, is not well characterized because of their small volumes. We present image-guided, high-throughput mass spectrometry-based protocols to chemically profile large populations of both dense-core vesicles and lucent vesicles for their lipid and peptide contents, allowing observation of the chemical heterogeneity within and between these two vesicle populations. The proteolytic processing products of four prohormones are observed within the dense-core vesicles, and the mass spectral features corresponding to the specific peptide products suggest three distinct dense-core vesicle populations. Notable differences in the lipid mass range are observed between the dense-core and lucent vesicles. These single-organelle mass spectrometry approaches are adaptable to characterize a range of subcellular structures.

An endogenous opioid circuit determines state-dependent reward consumption.

µ-Opioid peptide receptor (MOPR) stimulation alters respiration, analgesia and reward behaviour, and can induce substance abuse and overdose1-3. Despite its evident importance, the endogenous mechanisms for MOPR regulation of consummatory behaviour have remained unknown4. Here we report that endogenous MOPR regulation of reward consumption in mice acts through a specific dorsal raphe to nucleus accumbens projection. MOPR-mediated inhibition of raphe terminals is necessary and sufficient to determine consummatory response, while select enkephalin-containing nucleus accumbens ensembles are engaged prior to reward consumption, suggesting that local enkephalin release is the source of the endogenous MOPR ligand. Selective modulation of nucleus accumbens enkephalin neurons and CRISPR-Cas9-mediated disruption of enkephalin substantiate this finding. These results isolate a fundamental endogenous opioid circuit for state-dependent consumptive behaviour and suggest alternative mechanisms for opiate modulation of reward.

Accelerating Fourier Transform-Ion Cyclotron Resonance Mass Spectrometry Imaging Using a Subspace Approach.

We present a subspace method that accelerates data acquisition using Fourier transform-ion cyclotron resonance (FT-ICR) mass spectrometry imaging (MSI). For MSI of biological tissue samples, there is a finite number of heterogeneous tissue types with distinct chemical profiles that introduce redundancy in the high-dimensional measurements. Our subspace model exploits the redundancy in data measured from whole-slice tissue samples by decomposing the transient signals into linear combinations of a set of basis transients with the desired spectral resolution. This decomposition allowed us to design a strategy that acquires a subset of long transients for basis determination and short transients for the remaining pixels, drastically reducing the acquisition time. The computational reconstruction strategy can maintain high-mass-resolution and spatial-resolution MSI while providing a 10-fold improvement in throughput. We validated the capability of the subspace model using a rat sagittal brain slice imaging data set. Comprehensive evaluation of the quality of the mass spectral and ion images demonstrated that the reconstructed data produced by the reported method required only 15% of the typical acquisition time and exhibited both qualitative and quantitative consistency when compared to the original data. Our method enables either higher sample throughput or higher-resolution images at similar acquisition lengths, providing greater flexibility in obtaining FT-ICR MSI measurements.

Causality matters in medical imaging.

Causal reasoning can shed new light on the major challenges in machine learning for medical imaging: scarcity of high-quality annotated data and mismatch between the development dataset and the target environment. A causal perspective on these issues allows decisions about data collection, annotation, preprocessing, and learning strategies to be made and scrutinized more transparently, while providing a detailed categorisation of potential biases and mitigation techniques. Along with worked clinical examples, we highlight the importance of establishing the causal relationship between images and their annotations, and offer step-by-step recommendations for future studies.

Single-Cell Classification Using Mass Spectrometry through Interpretable Machine Learning.

The brain consists of organized ensembles of cells that exhibit distinct morphologies, cellular connectivity, and dynamic biochemistries that control the executive functions of an organism. However, the relationships between chemical heterogeneity, cell function, and phenotype are not always understood. Recent advancements in matrix-assisted laser desorption/ionization mass spectrometry have enabled the high-throughput, multiplexed chemical analysis of single cells, capable of resolving hundreds of molecules in each mass spectrum. We developed a machine learning workflow to classify single cells according to their mass spectra based on cell groups of interest (GOI), e.g., neurons vs astrocytes. Three data sets from various cell groups were acquired on three different mass spectrometer platforms representing thousands of individual cell spectra that were collected and used to validate the single cell classification workflow. The trained models achieved >80% classification accuracy and were subjected to the recently developed instance-based model interpretation framework, SHapley Additive exPlanations (SHAP), which locally assigns feature importance for each single-cell spectrum. SHAP values were used for both local and global interpretations of our data sets, preserving the chemical heterogeneity uncovered by the single-cell analysis while offering the ability to perform supervised analysis. The top contributing mass features to each of the GOI were ranked and selected using mean absolute SHAP values, highlighting the features that are specific to the defined GOI. Our approach provides insight into discriminating the chemical profiles of the single cells through interpretable machine learning, facilitating downstream analysis and validation.

Battery-free, lightweight, injectable microsystem for in vivo wireless pharmacology and optogenetics.

Pharmacology and optogenetics are widely used in neuroscience research to study the central and peripheral nervous systems. While both approaches allow for sophisticated studies of neural circuitry, continued advances are, in part, hampered by technology limitations associated with requirements for physical tethers that connect external equipment to rigid probes inserted into delicate regions of the brain. The results can lead to tissue damage and alterations in behavioral tasks and natural movements, with additional difficulties in use for studies that involve social interactions and/or motions in complex 3-dimensional environments. These disadvantages are particularly pronounced in research that demands combined optogenetic and pharmacological functions in a single experiment. Here, we present a lightweight, wireless, battery-free injectable microsystem that combines soft microfluidic and microscale inorganic light-emitting diode probes for programmable pharmacology and optogenetics, designed to offer the features of drug refillability and adjustable flow rates, together with programmable control over the temporal profiles. The technology has potential for large-scale manufacturing and broad distribution to the neuroscience community, with capabilities in targeting specific neuronal populations in freely moving animals. In addition, the same platform can easily be adapted for a wide range of other types of passive or active electronic functions, including electrical stimulation.

Wireless optofluidic brain probes for chronic neuropharmacology and photostimulation.

Both in vivo neuropharmacology and optogenetic stimulation can be used to decode neural circuitry, and can provide therapeutic strategies for brain disorders. However, current neuronal interfaces hinder long-term studies in awake and freely behaving animals, as they are limited in their ability to provide simultaneous and prolonged delivery of multiple drugs, are often bulky and lack multifunctionality, and employ custom control systems with insufficiently versatile selectivity for output mode, animal selection and target brain circuits. Here, we describe smartphone-controlled, minimally invasive, soft optofluidic probes with replaceable plug-like drug cartridges for chronic in vivo pharmacology and optogenetics with selective manipulation of brain circuits. We demonstrate the use of the probes for the control of the locomotor activity of mice for over four weeks via programmable wireless drug delivery and photostimulation. Owing to their ability to deliver both drugs and photopharmacology into the brain repeatedly over long time periods, the probes may contribute to uncovering the basis of neuropsychiatric diseases.

A Motivational and Neuropeptidergic Hub: Anatomical and Functional Diversity within the Nucleus Accumbens Shell.

The mesocorticolimbic pathway is canonically known as the "reward pathway." Embedded within the center of this circuit is the striatum, a massive and complex network hub that synthesizes motivation, affect, learning, cognition, stress, and sensorimotor information. Although striatal subregions collectively share many anatomical and functional similarities, it has become increasingly clear that it is an extraordinarily heterogeneous region. In particular, the nucleus accumbens (NAc) medial shell has repeatedly demonstrated that the rules dictated by more dorsal aspects of the striatum do not apply or are even reversed in functional logic. These discrepancies are perhaps most easily captured when isolating the functions of various neuromodulatory peptide systems within the striatum. Endogenous peptides are thought to play a critical role in modulating striatal signals to either amplify or dampen evoked behaviors. Here we describe the anatomical-functional backdrop upon which several neuropeptides act within the NAc to modulate behavior, with a specific emphasis on nucleus accumbens medial shell and stress responsivity. Additionally, we propose that, as the field continues to dissect fast neurotransmitter systems within the NAc, we must also provide considerable contextual weight to the roles local peptides play in modulating these circuits to more comprehensively understand how this important subregion gates motivated behaviors.

Endogenous and Exogenous Opioids in Pain.

Opioids are the most commonly used and effective analgesic treatments for severe pain, but they have recently come under scrutiny owing to epidemic levels of abuse and overdose. These compounds act on the endogenous opioid system, which comprises four G protein-coupled receptors (mu, delta, kappa, and nociceptin) and four major peptide families (ß-endorphin, enkephalins, dynorphins, and nociceptin/orphanin FQ). In this review, we first describe the functional organization and pharmacology of the endogenous opioid system. We then summarize current knowledge on the signaling mechanisms by which opioids regulate neuronal function and neurotransmission. Finally, we discuss the loci of opioid analgesic action along peripheral and central pain pathways, emphasizing the pain-relieving properties of opioids against the affective dimension of the pain experience.