We present a machine learning-aided quantum sensing approach for distinguishing Alzheimer's pathologies. Using a versatile entangled photon source, we analyzed brain samples of different mouse models, achieving high classification accuracy validated through confocal microscopy.
Photon entanglement, a key feature of quantum correlations, provides a level of coherence absent in classical correlations, potentially offering new information when interacting with biological matter. One promising application is using entanglement decoherence to distinguish between healthy and diseased samples. However, achieving this requires efficient entangled photon sources capable of surviving through biological samples for reliable detection. In this work, we show the applicability of a polarization-entangled photon source as a label-free diagnostic tool for distinguishing between transgenic mouse models of amyloidosis and tauopathy and their respective control strains. We investigated cortical and hippocampal regions of these models, and our findings revealed greater preservation of entanglement in the transgenic samples compared to controls. To further enhance classification accuracy, we employed a supervised machine learning approach, achieving reliable distinctions between disease and control groups in unseen test samples. The quantum-based results were further validated through confocal imaging of the transgenic and control samples. These findings suggest that quantum sensing could serve as a label-free approach for distinguishing biological samples, with potential applications in the study of neurodegenerative disorders.
Photon entanglement, a key feature of quantum correlations, provides a level of coherence absent in classical correlations, potentially offering new information when interacting with biological matter. One promising application is using entanglement decoherence to distinguish between healthy and diseased samples. However, achieving this requires efficient entangled photon sources capable of surviving through biological samples for reliable detection. In this work, we show the applicability of a polarization-entangled photon source as a label-free diagnostic tool for distinguishing between transgenic mouse models of amyloidosis and tauopathy and their respective control strains. We investigated cortical and hippocampal regions of these models, and our findings revealed greater preservation of entanglement in the transgenic samples compared to controls. To further enhance classification accuracy, we employed a supervised machine learning approach, achieving reliable distinctions between disease and control groups in unseen test samples. The quantum-based results were further validated through confocal imaging of the transgenic and control samples. These findings suggest that quantum sensing could serve as a label-free approach for distinguishing biological samples, with potential applications in the study of neurodegenerative disorders.
Photon entanglement, a key feature of quantum correlations, provides a level of coherence absent in classical correlations, potentially offering new information when interacting with biological matter. One promising application is using entanglement decoherence to distinguish between healthy and diseased samples. However, achieving this requires efficient entangled photon sources capable of surviving through biological samples for reliable detection. In this work, we show the applicability of a polarization-entangled photon source as a label-free diagnostic tool for distinguishing between transgenic mouse models of amyloidosis and tauopathy and their respective control strains. We investigated cortical and hippocampal regions of these models, and our findings revealed greater preservation of entanglement in the transgenic samples compared to controls. To further enhance classification accuracy, we employed a supervised machine learning approach, achieving reliable distinctions between disease and control groups in unseen test samples. The quantum-based results were further validated through confocal imaging of the transgenic and control samples. These findings suggest that quantum sensing could serve as a label-free approach for distinguishing biological samples, with potential applications in the study of neurodegenerative disorders.
Photon entanglement, a key feature of quantum correlations, provides a level of coherence absent in classical correlations, potentially offering new information when interacting with biological matter. One promising application is using entanglement decoherence to distinguish between healthy and diseased samples. However, achieving this requires efficient entangled photon sources capable of surviving through biological samples for reliable detection. In this work, we show the applicability of a polarization-entangled photon source as a label-free diagnostic tool for distinguishing between transgenic mouse models of amyloidosis and tauopathy and their respective control strains. We investigated cortical and hippocampal regions of these models, and our findings revealed greater preservation of entanglement in the transgenic samples compared to controls. To further enhance classification accuracy, we employed a supervised machine learning approach, achieving reliable distinctions between disease and control groups in unseen test samples. The quantum-based results were further validated through confocal imaging of the transgenic and control samples. These findings suggest that quantum sensing could serve as a label-free approach for distinguishing biological samples, with potential applications in the study of neurodegenerative disorders.
Alzheimer’s is a progressive and degenerative brain disorder causing impairment in memory and cognitive function. It is the most common form of Dementia and the prevalence of Alzheimer’s disease (AD) increases with each decade of life. This usually starts in late middle age to old age resulting in progressive memory loss, impaired thinking, disorientation and changes in personality. Neurons are first lost in the hippocampus (the brain’s centre for memory and learning), and presence of neurofibrillary tangles and plaques containing beta-amyloid cells. Owing to the progressive nature of the disease and the complex structure of the brain, the exact causes, mechanisms and how Alzheimer’s spread is not completely understood thereby inhibiting in the production of a cure for the disease. Quantum Machine Learning (QML) is a promising area of research for the detection and diagnosis of Alzheimer’s disease. PET scan helps in diagnosing Alzheimer’s by detecting the amyloid plaques and tau tangles. It reveals areas with reduced metabolism, which helps differentiate Alzheimer’s from other conditions. Quantum computing provides a more efficient model for different disease classification tasks than classical machine learning approaches. In this study, we propose a model based on quantum machine learning classifiers to classify Alzheimer’s disease. This showcases the feasibility of Quantum enhanced classification and detection of AD for extremely limited medical datasets.
The generation, manipulation and quantification of non-classical light, such as quantum-entangled photon pairs, differs significantly from methods with classical light. Thus, quantum measures could be harnessed to give new information about the interaction of light with matter. In this study we investigate if quantum entanglement can be used to diagnose disease. In particular, we test whether brain tissue from subjects suffering from Alzheimer's disease can be distinguished from healthy tissue. We find that this is indeed the case. Polarization-entangled photons traveling through brain tissue lose their entanglement via a decohering scattering interaction that gradually renders the light in a maximally mixed state. We found that in thin tissue samples (between 120 and 600 micrometers) photons decohere to a distinguishable lesser degree in samples with Alzheimer's disease than in healthy-control ones. Thus, it seems feasible that quantum measures of entangled photons could be used as a means to identify brain samples with the neurodegenerative disease.