Predicting Alzheimer's disease CSF core biomarkers: a multimodal Machine Learning approach.

Introduction: Alzheimer's disease (AD) is a progressive neurodegenerative disorder. Current core cerebrospinal fluid (CSF) AD biomarkers, widely employed for diagnosis, require a lumbar puncture to be performed, making them impractical as screening tools. Considering the role of sleep disturbances in AD, recent research suggests quantitative sleep electroencephalography features as potential non-invasive biomarkers of AD pathology. However, quantitative analysis of comprehensive polysomnography (PSG) signals remains relatively understudied. PSG is a non-invasive test enabling qualitative and quantitative analysis of a wide range of parameters, offering additional insights alongside other biomarkers. Machine Learning (ML) gained interest for its ability to discern intricate patterns within complex datasets, offering promise in AD neuropathology detection. Therefore, this study aims to evaluate the effectiveness of a multimodal ML approach in predicting core AD CSF biomarkers. Methods: Mild-moderate AD patients were prospectively recruited for PSG, followed by testing of CSF and blood samples for biomarkers. PSG signals underwent preprocessing to extract non-linear, time domain and frequency domain statistics quantitative features. Multiple ML algorithms were trained using four subsets of input features: clinical variables (CLINVAR), conventional PSG parameters (SLEEPVAR), quantitative PSG signal features (PSGVAR) and a combination of all subsets (ALL). Cross-validation techniques were employed to evaluate model performance and ensure generalizability. Regression models were developed to determine the most effective variable combinations for explaining variance in the biomarkers. Results: On 49 subjects, Gradient Boosting Regressors achieved the best results in estimating biomarkers levels, using different loss functions for each biomarker: least absolute deviation (LAD) for the Aß42, least squares (LS) for p-tau and Huber for t-tau. The ALL subset demonstrated the lowest training errors for all three biomarkers, albeit with varying test performance. Specifically, the SLEEPVAR subset yielded the best test performance in predicting Aß42, while the ALL subset most accurately predicted p-tau and t-tau due to the lowest test errors. Conclusions: Multimodal ML can help predict the outcome of CSF biomarkers in early AD by utilizing non-invasive and economically feasible variables. The integration of computational models into medical practice offers a promising tool for the screening of patients at risk of AD, potentially guiding clinical decisions.

Automatic classification of normal and abnormal cell division using deep learning.

In recent years, there has been a surge in the development of methods for cell segmentation and tracking, with initiatives like the Cell Tracking Challenge driving progress in the field. Most studies focus on regular cell population videos in which cells are segmented and followed, and parental relationships annotated. However, DNA damage induced by genotoxic drugs or ionizing radiation produces additional abnormal events since it leads to behaviors like abnormal cell divisions (resulting in a number of daughters different from two) and cell death. With this in mind, we developed an automatic mitosis classifier to categorize small mitosis image sequences centered around one cell as "Normal" or "Abnormal." These mitosis sequences were extracted from videos of cell populations exposed to varying levels of radiation that affect the cell cycle's development. We explored several deep-learning architectures and found that a network with a ResNet50 backbone and including a Long Short-Term Memory (LSTM) layer produced the best results (mean F1-score: 0.93 ± 0.06). In the future, we plan to integrate this classifier with cell segmentation and tracking to build phylogenetic trees of the population after genomic stress.

Computational Hyperspectral Microflow Cytometry.

Miniaturized flow cytometry has significant potential for portable applications, such as cell-based diagnostics and the monitoring of therapeutic cell manufacturing, however, the performance of current techniques is often limited by the inability to resolve spectrally-overlapping fluorescence labels. Here, the study presents a computational hyperspectral microflow cytometer (CHC) that enables accurate discrimination of spectrally-overlapping fluorophores labeling single cells. CHC employs a dispersive optical element and an optimization algorithm to detect the full fluorescence emission spectrum from flowing cells, with a high spectral resolution of ≈3 nm in the range from 450 to 650 nm. CHC also includes a dedicated microfluidic device that ensures in-focus imaging through viscoelastic sheathless focusing, thereby enhancing the accuracy and reliability of microflow cytometry analysis. The potential of CHC for analyzing T lymphocyte subpopulations and monitoring changes in cell composition during T cell expansion is demonstrated. Overall, CHC represents a major breakthrough in microflow cytometry and can facilitate its use for immune cell monitoring.

Small Extracellular Vesicles Promote Stiffness-mediated Metastasis.

Tissue stiffness is a critical prognostic factor in breast cancer and is associated with metastatic progression. Here we show an alternative and complementary hypothesis of tumor progression whereby physiologic matrix stiffness affects the quantity and protein cargo of small extracellular vesicles (EV) produced by cancer cells, which in turn aid cancer cell dissemination. Primary patient breast tissue released by cancer cells on matrices that model human breast tumors (25 kPa; stiff EVs) feature increased adhesion molecule presentation (ITGα2ß1, ITGα6ß4, ITGα6ß1, CD44) compared with EVs from softer normal tissue (0.5 kPa; soft EVs), which facilitates their binding to extracellular matrix proteins including collagen IV, and a 3-fold increase in homing ability to distant organs in mice. In a zebrafish xenograft model, stiff EVs aid cancer cell dissemination. Moreover, normal, resident lung fibroblasts treated with stiff and soft EVs change their gene expression profiles to adopt a cancer-associated fibroblast phenotype. These findings show that EV quantity, cargo, and function depend heavily on the mechanical properties of the extracellular microenvironment. SIGNIFICANCE: Here we show that the quantity, cargo, and function of breast cancer-derived EVs vary with mechanical properties of the extracellular microenvironment.

Mechanical and Functional Responses in Astrocytes under Alternating Deformation Modes Using Magneto-Active Substrates.

This work introduces NeoMag, a system designed to enhance cell mechanics assays in substrate deformation studies. NeoMag uses multidomain magneto-active materials to mechanically actuate the substrate, transmitting reversible mechanical cues to cells. The system boasts full flexibility in alternating loading substrate deformation modes, seamlessly adapting to both upright and inverted microscopes. The multidomain substrates facilitate mechanobiology assays on 2D and 3D cultures. The integration of the system with nanoindenters allows for precise evaluation of cellular mechanical properties under varying substrate deformation modes. The system is used to study the impact of substrate deformation on astrocytes, simulating mechanical conditions akin to traumatic brain injury and ischemic stroke. The results reveal local heterogeneous changes in astrocyte stiffness, influenced by the orientation of subcellular regions relative to substrate strain. These stiffness variations, exceeding 50% in stiffening and softening, and local deformations significantly alter calcium dynamics. Furthermore, sustained deformations induce actin network reorganization and activate Piezo1 channels, leading to an initial increase followed by a long-term inhibition of calcium events. Conversely, fast and dynamic deformations transiently activate Piezo1 channels and disrupt the actin network, causing long-term cell softening. These findings unveil mechanical and functional alterations in astrocytes during substrate deformation, illustrating the multiple opportunities this technology offers.

MLL1 regulates cytokine-driven cell migration and metastasis.

Cell migration is a critical contributor to metastasis. Cytokine production and its role in cancer cell migration have been traditionally associated with immune cells. We find that the histone methyltransferase Mixed-Lineage Leukemia 1 (MLL1) controls 3D cell migration via cytokines, IL-6, IL-8, and TGF-ß1, secreted by the cancer cells themselves. MLL1, with its scaffold protein Menin, controls actin filament assembly via the IL-6/8/pSTAT3/Arp3 axis and myosin contractility via the TGF-ß1/Gli2/ROCK1/2/pMLC2 axis, which together regulate dynamic protrusion generation and 3D cell migration. MLL1 also regulates cell proliferation via mitosis-based and cell cycle-related pathways. Mice bearing orthotopic MLL1-depleted tumors exhibit decreased lung metastatic burden and longer survival. MLL1 depletion leads to lower metastatic burden even when controlling for the difference in primary tumor growth rates. Combining MLL1-Menin inhibitor with paclitaxel abrogates tumor growth and metastasis, including preexistent metastasis. These results establish MLL1 as a potent regulator of cell migration and highlight the potential of targeting MLL1 in patients with metastatic disease.

Small extracellular vesicles promote stiffness-mediated metastasis.

Tissue stiffness is a critical prognostic factor in breast cancer and is associated with metastatic progression. Here we show an alternative and complementary hypothesis of tumor progression whereby physiological matrix stiffness affects the quantity and protein cargo of small EVs produced by cancer cells, which in turn drive their metastasis. Primary patient breast tissue produces significantly more EVs from stiff tumor tissue than soft tumor adjacent tissue. EVs released by cancer cells on matrices that model human breast tumors (25 kPa; stiff EVs) feature increased adhesion molecule presentation (ITGα 2 ß 1 , ITGα 6 ß 4 , ITGα 6 ß 1 , CD44) compared to EVs from softer normal tissue (0.5 kPa; soft EVs), which facilitates their binding to extracellular matrix (ECM) protein collagen IV, and a 3-fold increase in homing ability to distant organs in mice. In a zebrafish xenograft model, stiff EVs aid cancer cell dissemination through enhanced chemotaxis. Moreover, normal, resident lung fibroblasts treated with stiff and soft EVs change their gene expression profiles to adopt a cancer associated fibroblast (CAF) phenotype. These findings show that EV quantity, cargo, and function depend heavily on the mechanical properties of the extracellular microenvironment.

Tumor proliferation and invasion are intrinsically coupled and unraveled through tunable spheroid and physics-based models.

Proliferation and invasion are two key drivers of tumor growth that are traditionally considered independent multicellular processes. However, these processes are intrinsically coupled through a maximum carrying capacity, i.e., the maximum spatial cell concentration supported by the tumor volume, total cell count, nutrient access, and mechanical properties of the tissue stroma. We explored this coupling of proliferation and invasion through in vitro and in silico methods where we modulated the mechanical properties of the tumor and the surrounding extracellular matrix. E-cadherin expression and stromal collagen concentration were manipulated in a tunable breast cancer spheroid to determine the overall impacts of these tumor variables on net tumor proliferation and continuum invasion. We integrated these results into a mixed-constitutive formulation to computationally delineate the influences of cellular and extracellular adhesion, stiffness, and mechanical properties of the extracellular matrix on net proliferation and continuum invasion. This framework integrates biological in vitro data into concise computational models of invasion and proliferation to provide more detailed physical insights into the coupling of these key tumor processes and tumor growth. STATEMENT OF SIGNIFICANCE: Tumor growth involves expansion into the collagen-rich stroma through intrinsic coupling of proliferation and invasion within the tumor continuum. These processes are regulated by a maximum carrying capacity that is determined by the total cell count, tumor volume, nutrient access, and mechanical properties of the surrounding stroma. The influences of biomechanical parameters (i.e., stiffness, cell elongation, net proliferation rate and cell-ECM friction) on tumor proliferation or invasion cannot be unraveled using experimental methods alone. By pairing a tunable spheroid system with computational modeling, we delineated the interdependencies of each system parameter on tumor proliferation and continuum invasion, and established a concise computational framework for studying tumor mechanobiology.

The Cell Tracking Challenge: 10 years of objective benchmarking.

The Cell Tracking Challenge is an ongoing benchmarking initiative that has become a reference in cell segmentation and tracking algorithm development. Here, we present a significant number of improvements introduced in the challenge since our 2017 report. These include the creation of a new segmentation-only benchmark, the enrichment of the dataset repository with new datasets that increase its diversity and complexity, and the creation of a silver standard reference corpus based on the most competitive results, which will be of particular interest for data-hungry deep learning-based strategies. Furthermore, we present the up-to-date cell segmentation and tracking leaderboards, an in-depth analysis of the relationship between the performance of the state-of-the-art methods and the properties of the datasets and annotations, and two novel, insightful studies about the generalizability and the reusability of top-performing methods. These studies provide critical practical conclusions for both developers and users of traditional and machine learning-based cell segmentation and tracking algorithms.

Integration of longitudinal deep-radiomics and clinical data improves the prediction of durable benefits to anti-PD-1/PD-L1 immunotherapy in advanced NSCLC patients.

BACKGROUND: Identifying predictive non-invasive biomarkers of immunotherapy response is crucial to avoid premature treatment interruptions or ineffective prolongation. Our aim was to develop a non-invasive biomarker for predicting immunotherapy clinical durable benefit, based on the integration of radiomics and clinical data monitored through early anti-PD-1/PD-L1 monoclonal antibodies treatment in patients with advanced non-small cell lung cancer (NSCLC). METHODS: In this study, 264 patients with pathologically confirmed stage IV NSCLC treated with immunotherapy were retrospectively collected from two institutions. The cohort was randomly divided into a training (n = 221) and an independent test set (n = 43), ensuring the balanced availability of baseline and follow-up data for each patient. Clinical data corresponding to the start of treatment was retrieved from electronic patient records, and blood test variables after the first and third cycles of immunotherapy were also collected. Additionally, traditional radiomics and deep-radiomics features were extracted from the primary tumors of the computed tomography (CT) scans before treatment and during patient follow-up. Random Forest was used to implementing baseline and longitudinal models using clinical and radiomics data separately, and then an ensemble model was built integrating both sources of information. RESULTS: The integration of longitudinal clinical and deep-radiomics data significantly improved clinical durable benefit prediction at 6 and 9 months after treatment in the independent test set, achieving an area under the receiver operating characteristic curve of 0.824 (95% CI: [0.658,0.953]) and 0.753 (95% CI: [0.549,0.931]). The Kaplan-Meier survival analysis showed that, for both endpoints, the signatures significantly stratified high- and low-risk patients (p-value< 0.05) and were significantly correlated with progression-free survival (PFS6 model: C-index 0.723, p-value = 0.004; PFS9 model: C-index 0.685, p-value = 0.030) and overall survival (PFS6 models: C-index 0.768, p-value = 0.002; PFS9 model: C-index 0.736, p-value = 0.023). CONCLUSIONS: Integrating multidimensional and longitudinal data improved clinical durable benefit prediction to immunotherapy treatment of advanced non-small cell lung cancer patients. The selection of effective treatment and the appropriate evaluation of clinical benefit are important for better managing cancer patients with prolonged survival and preserving quality of life.

ABANICCO: A New Color Space for Multi-Label Pixel Classification and Color Analysis.

Classifying pixels according to color, and segmenting the respective areas, are necessary steps in any computer vision task that involves color images. The gap between human color perception, linguistic color terminology, and digital representation are the main challenges for developing methods that properly classify pixels based on color. To address these challenges, we propose a novel method combining geometric analysis, color theory, fuzzy color theory, and multi-label systems for the automatic classification of pixels into 12 conventional color categories, and the subsequent accurate description of each of the detected colors. This method presents a robust, unsupervised, and unbiased strategy for color naming, based on statistics and color theory. The proposed model, "ABANICCO" (AB ANgular Illustrative Classification of COlor), was evaluated through different experiments: its color detection, classification, and naming performance were assessed against the standardized ISCC-NBS color system; its usefulness for image segmentation was tested against state-of-the-art methods. This empirical evaluation provided evidence of ABANICCO's accuracy in color analysis, showing how our proposed model offers a standardized, reliable, and understandable alternative for color naming that is recognizable by both humans and machines. Hence, ABANICCO can serve as a foundation for successfully addressing a myriad of challenges in various areas of computer vision, such as region characterization, histopathology analysis, fire detection, product quality prediction, object description, and hyperspectral imaging.

Single Plane Illumination Microscopy for Microfluidic Device Imaging.

Three-dimensional imaging of live processes at a cellular level is a challenging task. It requires high-speed acquisition capabilities, low phototoxicity, and low mechanical disturbances. Three-dimensional imaging in microfluidic devices poses additional challenges as a deep penetration of the light source is required, along with a stationary setting, so the flows are not perturbed. Different types of fluorescence microscopy techniques have been used to address these limitations; particularly, confocal microscopy and light sheet fluorescence microscopy (LSFM). This manuscript proposes a novel architecture of a type of LSFM, single-plane illumination microscopy (SPIM). This custom-made microscope includes two mirror galvanometers to scan the sample vertically and reduce shadowing artifacts while avoiding unnecessary movement. In addition, two electro-tunable lenses fine-tune the focus position and reduce the scattering caused by the microfluidic devices. The microscope has been fully set up and characterized, achieving a resolution of 1.50 µm in the x-y plane and 7.93 µm in the z-direction. The proposed architecture has risen to the challenges posed when imaging microfluidic devices and live processes, as it can successfully acquire 3D volumetric images together with time-lapse recordings, and it is thus a suitable microscopic technique for live tracking miniaturized tissue and disease models.

Deep learning based domain adaptation for mitochondria segmentation on EM volumes.

BACKGROUND AND OBJECTIVE: Accurate segmentation of electron microscopy (EM) volumes of the brain is essential to characterize neuronal structures at a cell or organelle level. While supervised deep learning methods have led to major breakthroughs in that direction during the past years, they usually require large amounts of annotated data to be trained, and perform poorly on other data acquired under similar experimental and imaging conditions. This is a problem known as domain adaptation, since models that learned from a sample distribution (or source domain) struggle to maintain their performance on samples extracted from a different distribution or target domain. In this work, we address the complex case of deep learning based domain adaptation for mitochondria segmentation across EM datasets from different tissues and species. METHODS: We present three unsupervised domain adaptation strategies to improve mitochondria segmentation in the target domain based on (1) state-of-the-art style transfer between images of both domains; (2) self-supervised learning to pre-train a model using unlabeled source and target images, and then fine-tune it only with the source labels; and (3) multi-task neural network architectures trained end-to-end with both labeled and unlabeled images. Additionally, to ensure good generalization in our models, we propose a new training stopping criterion based on morphological priors obtained exclusively in the source domain. The code and its documentation are publicly available at https://github.com/danifranco/EM_domain_adaptation. RESULTS: We carried out all possible cross-dataset experiments using three publicly available EM datasets. We evaluated our proposed strategies and those of others based on the mitochondria semantic labels predicted on the target datasets. CONCLUSIONS: The methods introduced here outperform the baseline methods and compare favorably to the state of the art. In the absence of validation labels, monitoring our proposed morphology-based metric is an intuitive and effective way to stop the training process and select in average optimal models.

Stable Deep Neural Network Architectures for Mitochondria Segmentation on Electron Microscopy Volumes.

Electron microscopy (EM) allows the identification of intracellular organelles such as mitochondria, providing insights for clinical and scientific studies. In recent years, a number of novel deep learning architectures have been published reporting superior performance, or even human-level accuracy, compared to previous approaches on public mitochondria segmentation datasets. Unfortunately, many of these publications make neither the code nor the full training details public, leading to reproducibility issues and dubious model comparisons. Thus, following a recent code of best practices in the field, we present an extensive study of the state-of-the-art architectures and compare them to different variations of U-Net-like models for this task. To unveil the impact of architectural novelties, a common set of pre- and post-processing operations has been implemented and tested with each approach. Moreover, an exhaustive sweep of hyperparameters has been performed, running each configuration multiple times to measure their stability. Using this methodology, we found very stable architectures and training configurations that consistently obtain state-of-the-art results in the well-known EPFL Hippocampus mitochondria segmentation dataset and outperform all previous works on two other available datasets: Lucchi++ and Kasthuri++. The code and its documentation are publicly available at https://github.com/danifranco/EM_Image_Segmentation .

Reduction of motion effects in myocardial arterial spin labeling.

PURPOSE: To evaluate the accuracy and reproducibility of myocardial blood flow measurements obtained under different breathing strategies and motion correction techniques with arterial spin labeling. METHODS: A prospective cardiac arterial spin labeling study was performed in 12 volunteers at 3 Tesla. Perfusion images were acquired twice under breath-hold, synchronized-breathing, and free-breathing. Motion detection based on the temporal intensity variation of a myocardial voxel, as well as image registration based on pairwise and groupwise approaches, were applied and evaluated in synthetic and in vivo data. A region of interest was drawn over the mean perfusion-weighted image for quantification. Original breath-hold datasets, analyzed with individual regions of interest for each perfusion-weighted image, were considered as reference values. RESULTS: Perfusion measurements in the reference breath-hold datasets were in line with those reported in literature. In original datasets, prior to motion correction, myocardial blood flow quantification was significantly overestimated due to contamination of the myocardial perfusion with the high intensity signal of blood pool. These effects were minimized with motion detection or registration. Synthetic data showed that accuracy of the perfusion measurements was higher with the use of registration, in particular after the pairwise approach, which probed to be more robust to motion. CONCLUSION: Satisfactory results were obtained for the free-breathing strategy after pairwise registration, with higher accuracy and robustness (in synthetic datasets) and higher intrasession reproducibility together with lower myocardial blood flow variability across subjects (in in vivo datasets). Breath-hold and synchronized-breathing after motion correction provided similar results, but these breathing strategies can be difficult to perform by patients.

Innovations in ex vivo Light Sheet Fluorescence Microscopy.

Light Sheet Fluorescence Microscopy (LSFM) has revolutionized how optical imaging of biological specimens can be performed as this technique allows to produce 3D fluorescence images of entire samples with a high spatiotemporal resolution. In this manuscript, we aim to provide readers with an overview of the field of LSFM on ex vivo samples. Recent advances in LSFM architectures have made the technique widely accessible and have improved its acquisition speed and resolution, among other features. These developments are strongly supported by quantitative analysis of the huge image volumes produced thanks to the boost in computational capacities, the advent of Deep Learning techniques, and by the combination of LSFM with other imaging modalities. Namely, LSFM allows for the characterization of biological structures, disease manifestations and drug effectivity studies. This information can ultimately serve to develop novel diagnostic procedures, treatments and even to model the organs physiology in healthy and pathological conditions.

Use of the p-values as a size-dependent function to address practical differences when analyzing large datasets.

Biomedical research has come to rely on p-values as a deterministic measure for data-driven decision-making. In the largely extended null hypothesis significance testing for identifying statistically significant differences among groups of observations, a single p-value is computed from sample data. Then, it is routinely compared with a threshold, commonly set to 0.05, to assess the evidence against the hypothesis of having non-significant differences among groups, or the null hypothesis. Because the estimated p-value tends to decrease when the sample size is increased, applying this methodology to datasets with large sample sizes results in the rejection of the null hypothesis, making it not meaningful in this specific situation. We propose a new approach to detect differences based on the dependence of the p-value on the sample size. We introduce new descriptive parameters that overcome the effect of the size in the p-value interpretation in the framework of datasets with large sample sizes, reducing the uncertainty in the decision about the existence of biological differences between the compared experiments. The methodology enables the graphical and quantitative characterization of the differences between the compared experiments guiding the researchers in the decision process. An in-depth study of the methodology is carried out on simulated and experimental data. Code availability at https://github.com/BIIG-UC3M/pMoSS .

DeepImageJ: A user-friendly environment to run deep learning models in ImageJ.

DeepImageJ is a user-friendly solution that enables the generic use of pre-trained deep learning models for biomedical image analysis in ImageJ. The deepImageJ environment gives access to the largest bioimage repository of pre-trained deep learning models (BioImage Model Zoo). Hence, nonexperts can easily perform common image processing tasks in life-science research with deep learning-based tools including pixel and object classification, instance segmentation, denoising or virtual staining. DeepImageJ is compatible with existing state of the art solutions and it is equipped with utility tools for developers to include new models. Very recently, several training frameworks have adopted the deepImageJ format to deploy their work in one of the most used softwares in the field (ImageJ). Beyond its direct use, we expect deepImageJ to contribute to the broader dissemination and reuse of deep learning models in life sciences applications and bioimage informatics.

Predicting MHC I restricted T cell epitopes in mice with NAP-CNB, a novel online tool.

Lack of a dedicated integrated pipeline for neoantigen discovery in mice hinders cancer immunotherapy research. Novel sequential approaches through recurrent neural networks can improve the accuracy of T-cell epitope binding affinity predictions in mice, and a simplified variant selection process can reduce operational requirements. We have developed a web server tool (NAP-CNB) for a full and automatic pipeline based on recurrent neural networks, to predict putative neoantigens from tumoral RNA sequencing reads. The developed software can estimate H-2 peptide ligands, with an AUC comparable or superior to state-of-the-art methods, directly from tumor samples. As a proof-of-concept, we used the B16 melanoma model to test the system's predictive capabilities, and we report its putative neoantigens. NAP-CNB web server is freely available at http://biocomp.cnb.csic.es/NeoantigensApp/ with scripts and datasets accessible through the download section.