11 results about "Biomarker identification" patented technology

Systems and methods for determining the health status of a retina of a subject. An optical coherence tomography (OCT) volume image of a retina of a subject may be received. A health indication output is generated, via a deep learning model, using the OCT volume image. The health indication output indicates a level of association between the OCT volume image and a selected health status category for the retina. A map output for the deep learning model is generated using a saliency mapping algorithm, generating a map output for the deep learning model using a saliency mapping algorithm. The map output indicates a level of contribution of a set of regions in the OCT volume image to the health indication output generated by the deep learning model.

The application discloses a 7T magnetic resonance head and neck tumor radiotherapy response evaluation system, belongs to the field of medical imaging and tumor radiotherapy, and comprises an ultrahigh-field multi-modal image acquisition module, a multi-phase accurate registration and radiomics feature extraction module, an early response biomarker identification module and an adaptive treatment decision support module. The high resolution, high signal-to-noise ratio and multi-nuclide imaging capability of the 7T ultrahigh-field magnetic resonance are utilized to acquire multi-modal images before and during treatment, more than 200 features are extracted through accurate registration and radiomics analysis, the treatment response is predicted based on the Delta feature and the deep learning model 2 to 3 weeks after the start of radiotherapy, the prediction accuracy reaches 87.5%, the prediction is 3 to 4 weeks earlier than the conventional evaluation, decision support is provided for timely adjustment of the treatment strategy, a closed-loop feedback mechanism is established, the clinical verification results are used to optimize the parameters of each module reversely, and continuous improvement is realized.

A method, computer system, and a computer program product for biomarker identification is provided. The present invention may include generating a plurality of higher-order joint cumulants based on an input data matrix. The present invention may include identifying one or more significant higher-order joint cumulant groups from the plurality of higher-order joint cumulants. The present invention may include embedding the one or more significant higher-order joint cumulant groups into a lower dimensional network. The present invention may include identifying one or more biomarkers.

Disclosed are method and apparatus for identifying biomarkers and in particular for identifying biomarkers for use in making clinical assessments, such as early diagnostic, diagnostic, disease stage, disease severity, disease subtype, response to therapy or prognostic assessments. In one particular example, the techniques are applied to allow assessments of patients suffering from, suspected of suffering from, or with clinical signs of SIRS (Systemic Inflammatory Response Syndrome) being either infection-negative SIRS or infection-positive SIRS.

Disclosed are systems and methods for predicting patient response to a treatment option. In one embodiment, the image slides from patient tissue samples are divided into patches and morphological patterns correlated with a disease outcome are labeled and given a patch-level score, based on whether the morphological patterns occur only in patients with good outcomes or patients with poor outcomes. A patient-level score can be generated based, at least partly, on the patch-level scores. Patch-level scores can identify regions of interest for targeted biomarker identification.

The invention relates to the technical field of computer technology and biomedicine cross application, in particular to a multi-task cooperation method combining disease progression prediction and multi-mode biomarker recognition, which comprises the following steps of: according to a multi-mode biomarker, longitudinal brain image data and cognitive behavior data, determining whether the multi-mode biomarker is identified or not; constructing a longitudinal disease progress prediction model based on the time series data; optimizing parameters in the prediction model based on the defined objective function according to the multi-modal biomarker and the longitudinal brain image data to obtain an optimized longitudinal disease progress prediction model; and predicting a new cognitive behavior score from the to-be-identified multi-modal biomarker and the longitudinal brain image data through the optimized longitudinal disease progress prediction model. By integrating image data, gene data and environment information, a multi-modal data fusion model is constructed, and intelligent prediction of disease progress trend and automatic identification of key risk factors are realized.

Schizophrenia (SCZ) is the most debilitating of the Serious Mental Illnesses, a group of disorders affecting 4.8% of Arizona adults. The lack of a biologically based test makes diagnosing SCZ difficult, particularly for the 40% of Arizonans in areas with inadequate mental health care. Even under ideal circumstances, it can take months to years to accurately diagnose SCZ and identify an effective medication regimen. There is a critical need to identify biological markers to rapidly diagnose SCZ, which will lead to faster symptom resolution and improved patient outcomes. Methods described herein capitalize on the long-recognized association between SCZ risk and immune system dysfunction by stimulating peripheral blood immune cells with immunogenic agents to gain insight into disrupted pathways of gene expression in the brain. The immune stimulation of peripheral blood cells produces a unique pattern of gene expression, which will differ between SCZ and healthy control subjects.

Provided herein are minimally invasive compositions, methods, systems, kits and uses for biomarkers derived from the plasma proteome that identify, predict, and monitor organ health, aging, dysfunction and disease in humans. Said methods comprise a) obtaining a sample from said subject; b) measuring the concentrations of two or more proteins from said organ in said sample from said subject wherein said concentrations of said two or more proteins provides a biological age of said organ in health and / or disease; and c) comparing said biological age of said organ to a chronological age of said subject, wherein a gap between said biological age of said organ and said chronological age of said subject identifies accelerated and slowed aging of said organ.

The invention discloses a 7T magnetic resonance head and neck tumor radiotherapy response evaluation system, which belongs to the field of medical imaging and tumor radiotherapy and comprises an ultrahigh-field multi-modal image acquisition module, a multi-temporal precise registration and radiomics feature extraction module, an early response biomarker recognition module and a self-adaptive treatment decision support module. The high resolution, the high signal-to-noise ratio and the multi-nuclide imaging capability of 7T ultrahigh-field magnetic resonance are utilized, multi-modal images are collected before treatment and during treatment, more than 200 features are extracted through accurate registration and radiomics analysis, treatment response is predicted 2-3 weeks at the beginning of radiotherapy based on Delta features and a deep learning model, the prediction accuracy rate reaches 87.5%, and the prediction result is accurate. The method is 3-4 weeks earlier than conventional evaluation, decision support is provided for timely adjustment of treatment strategies, a closed-loop feedback mechanism is established for the system, parameters of all modules are reversely optimized according to clinical verification results, and continuous improvement is achieved.

The application discloses a multi-modal critical edge biomarker identification method, takes an individual cancer patient as a dynamic network system, combines a dynamic network theory biomarker theory and a multi-modal evolutionary algorithm, performs hidden space search by using a restricted Boltzmann machine on the basis of an MMPDNB model, and is a new multi-modal PDENB identification model. Firstly, a PEN of the cancer individual patient is constructed. Then, an optimization objective function is designed. Finally, a multi-modal optimization algorithm is used to search for a PDENB set. The application can not only promote the researches on a mathematical model and an algorithm design of the PDENB identification problem, but also help to understand the individual heterogeneity of the cancer, and realize the early diagnosis and treatment of the cancer individual patient.

Disclosed are method and apparatus for identifying biomarkers and in particular for identifying biomarkers for use in making clinical assessments, such as early diagnostic, diagnostic, disease stage, disease severity, disease subtype, response to therapy or prognostic assessments. In one particular example, the techniques are applied to allow assessments of patients suffering from, suspected of suffering from, or with clinical signs of SIRS (Systemic Inflammatory Response Syndrome) being either infection-negative SIRS or infection-positive SIRS.