Deep learning for the prediction of the chemotherapy response of metastatic colorectal cancer: comparing and combining H&E staining histopathology and infrared spectral histopathology.

Colorectal cancer is a global public health problem with one of the highest death rates. It is the second most deadly type of cancer and the third most frequently diagnosed in the world. The present study focused on metastatic colorectal cancer (mCRC) patients who had been treated with chemotherapy-based regimen for which it remains uncertainty about the efficacy for all eligible patients. This is a major problem, as it is not yet possible to test different therapies in view of the consequences on the health of the patients and the risk of progression. Here, we propose a method to predict the efficacy of an anticancer treatment in an individualized way, using a deep learning model constructed on the retrospective analysis of the primary tumor of several patients. Histological sections from tumors were imaged by standard hematoxylin and eosin (HE) staining and infrared spectroscopy (IR). Images obtained were then processed by a convolutional neural network (CNN) to extract features and correlate them with the subsequent progression-free survival (PFS) of each patient. Separately, HE and IR imaging resulted in a PFS prediction with an error of 6.6 and 6.3 months respectively (28% and 26% of the average PFS). Combining both modalities allowed to decrease the error to 5.0 months (21%). The inflammatory state of the stroma seemed to be one of the main features detected by the CNN. Our pilot study suggests that multimodal imaging analyzed with deep learning methods allow to give an indication of the effectiveness of a treatment when choosing.

Multimodal Analytical Platform on a Multiplexed Surface Plasmon Resonance Imaging Chip for the Analysis of Extracellular Vesicle Subsets.

Extracellular vesicles (EVs) are membrane-derived, tiny vesicles produced by all cells that range from 50 to several hundreds of nanometers in diameter and are used as a means of intercellular communication. They are emerging as promising diagnostic and therapeutic tools for a variety of diseases. There are two main biogenesis processes used by cells to produce EVs with differences in size, composition, and content. Due to their high complexity in size, composition, and cell origin, their characterization requires a combination of analytical techniques. This project involves the development of a new generation of multiparametric analytical platforms with increased throughput for the characterization of subpopulations of EVs. To achieve this goal, the work starts from the nanobioanalytical platform (NBA) established by the group, which allows an original investigation of EVs based on a combination of multiplexed biosensing methods with metrological and morphomechanical analyses by atomic force microscopy (AFM) of vesicular targets trapped on a microarray biochip. The objective was to complete this EV investigation with a phenotypic and molecular analysis by Raman spectroscopy. These developments enable the proposal of a multimodal and easy-to-use analytical solution for the discrimination of EV subsets in biological fluids with clinical potential.

Identification of circulating biomarkers of Crohn's disease and spondyloarthritis using Fourier transform infrared spectroscopy.

Crohn's disease (CD) and spondyloarthritis (SpA) are two inflammatory diseases sharing many common features (genetic polymorphism, armamentarium). Both diseases lack diagnostic markers of certainty. While the diagnosis of CD is made by a combination of clinical, and biological criteria, the diagnosis of SpA may take several years to be confirmed. Based on the hypothesis that CD and SpA alter the biochemical profile of plasma, the objective of this study was to evaluate the analytical capability of Fourier transform infrared spectroscopy (FTIR) in identifying spectral biomarkers. Plasma from 104 patients was analyzed. After data processing of the spectra by Extended Multiplicative Signal Correction and linear discriminant analysis, we demonstrated that it was possible to distinguish CD and SpA from controls with an accuracy of 97% and 85% respectively. Spectral differences were mainly associated with proteins and lipids. This study showed that FTIR analysis is efficient to identify plasma biosignatures specific to CD or SpA.

Extracellular matrix in multicellular aggregates acts as a pressure sensor controlling cell proliferation and motility.

Imposed deformations play an important role in morphogenesis and tissue homeostasis, both in normal and pathological conditions. To perceive mechanical perturbations of different types and magnitudes, tissues need appropriate detectors, with a compliance that matches the perturbation amplitude. By comparing results of selective osmotic compressions of CT26 mouse cells within multicellular aggregates and global aggregate compressions, we show that global compressions have a strong impact on the aggregates growth and internal cell motility, while selective compressions of same magnitude have almost no effect. Both compressions alter the volume of individual cells in the same way over a shor-timescale, but, by draining the water out of the extracellular matrix, the global one imposes a residual compressive mechanical stress on the cells over a long-timescale, while the selective one does not. We conclude that the extracellular matrix is as a sensor that mechanically regulates cell proliferation and migration in a 3D environment.

In depth investigation of collagen non-enzymatic glycation by Raman spectroscopy.

Non-enzymatic glycation is a post-translational modification of long-lived matrix proteins such as type I collagen. It occurs during aging and leads to the formation of advanced glycation end-products (AGEs). AGE accumulation is associated with severe complications in chronic and age-related diseases. The assessment of modifications induced by this (patho)physiological process represents an interest in biology and medicine for a better patient care. The objective of our work was to position the interest of Raman spectroscopy in the quantification of collagen glycation. Two types of in vitro glycation were used by incubating collagen samples, at different durations, with ribose or glyoxylic acid; these reducing agents acting on the chemical specificity of the glycation reaction. Glycation efficiency was evaluated by the liquid chromatography coupled to tandem mass spectrometry (LC-MS/MS) quantification of carboxymethyllysine (CML) and pentosidine, which are among the most studied AGEs. Raman data were processed by PCA coupled to validity indices and Lasso regression as multivariate analysis tools. Regression models were constructed by considering the LC-MS/MS results as reference values. A marked variability was observed within the Raman datasets making difficult the identification of spectral differences between control and ribose-treated collagen samples. By taking advantage of the chemical specificity of the glyoxylic acid treatment leading to CML formation, on one hand, and the feature selection included in the Lasso algorithm, on the other hand, Raman markers associated with glycation were identified. The assigned vibrations corresponded to modifications of side chains of collagen. In addition, a threshold of CML concentration was determined as quantitative indicator of the applicability of Raman spectroscopy for potential patient follow-up purposes. Although lacking in sensitivity to directly detect AGEs in collagen, Raman spectroscopy allows to highlight the molecular modifications of collagen induced by glycation.

Measuring cell displacements in opaque tissues: dynamic light scattering in the multiple scattering regime.

Coherent light scattered by tissues brings structural and dynamic information, at depth, that standard imaging techniques cannot reach. Dynamics of cells or sub-cellular elements can be measured thanks to dynamic light scattering in thin samples (single scattering regime) or thanks to diffusive wave spectroscopy in thick samples (diffusion regime). Here, we address the intermediate regime and provide an analytical relationship between scattered light fluctuations and the distribution of cell displacements as a function of time. We illustrate our method by characterizing cell motility inside half millimeter thick multicellular aggregates.

Nanostickers for cells: a model study using cell-nanoparticle hybrid aggregates.

We present direct evidence that nanoparticles (NPs) can stick together cells that are inherently non-adhesive. Using cadherin-depleted S180 murine cells lines, which exhibit very low cell-cell adhesion, we show that NPs can assemble dispersed single cells into large cohesive aggregates. The dynamics of aggregation, which is controlled by diffusion and collision, can be described as a second-order kinetic law characterized by a rate of collision that depends on the size, concentration, and surface chemistry of the NPs. We model the cell-cell adhesion induced by the "nanostickers" using a three-state dynamical model, where the NPs are free, adsorbed on the cell membrane or internalized by the cells. We define a "sticking efficiency parameter" to compare NPs and look for the most efficient type of NP. We find that 20 nm carboxylated polystyrene NPs are more efficient nanostickers than 20 nm silica NPs which were reported to induce fast wound healing and to glue soft tissues. Nanostickers, by increasing the cohesion of tissues and tumors, may have important applications for tissue engineering and cancer treatment.

Effect of an osmotic stress on multicellular aggregates.

There is increasing evidence that multicellular structures respond to mechanical cues, such as the confinement and compression exerted by the surrounding environment. In order to understand the response of tissues to stress, we investigate the effect of an isotropic stress on different biological systems. The stress is generated using the osmotic pressure induced by a biocompatible polymer. We compare the response of multicellular spheroids, individual cells and matrigel to the same osmotic perturbation. Our findings indicate that the osmotic pressure occasioned by polymers acts on these systems like an isotropic mechanical stress. When submitted to this pressure, the volume of multicellular spheroids decreases much more than one could expect from the behavior of individual cells.