Method and system for estimating early progression of dementia from human head images
A system for non-invasive estimation of dementia progression. The system includes a computer device and a server. The computer device obtains an image of a subject's head from at least one angle. The server and/or computer device includes a plurality of machine learning models configured to: analyze the image for patterns related to dementia symptoms; and estimate progress of said dementia symptoms of said subject based on the analysis. The server and/or computer device pre-processes the image by performing a plurality of pre-processing steps comprising: importing the image; detecting eyes and shape of the head based on a previously trained machine learning model; rotating the image based on detection of the eyes and shape of the head; normalizing the image to one standard.
1. A computer-implemented method for non-invasive estimation of dementia progression of a subject, said method comprising:
obtaining a plurality of still images which includes at least said subject's head from at least one angle; and
identifying, said subject's head in said plurality of still images;
processing, by a computer device and/or a server, said plurality of still images by performing a plurality of pre-processing steps;
generating, by said server and/or said computer device, at least one dataset based on external features of said subject's head from said plurality still images;
analyzing, by a plurality of machine learning models configured within said server and/or said computer device, said at least one dataset for patterns related to dementia symptoms, wherein said at least one dataset is analysed using said plurality of machine learning models trained on datasets based on external features of at least heads of dementia-diagnosed subjects; and
estimating, by said machine learning models, progress of said dementia symptoms of said subject based on said analysis.
2. The computer-implemented method of claim 1 , wherein said plurality of pre-processing steps comprising:
importing said plurality of still images;
detecting eyes and shape of the head based on one or more previously trained machine learning models;
rotating the image based on detection of the eyes and shape of the head to one standard;
normalizing the image to said one standard.
3. The computer-implemented method of claim 1 , comprising a step of communicating the progress estimated by the machine learning models to the subject.
4. The computer-implemented method of claim 1 , comprising a step of displaying one or more variables that are determining the progress of the dementia symptoms.
5. The computer-implemented method of claim 1 , comprising a step of checking whether an input of subject-related information has been correctly entered.
6. The computer-implemented method of claim 1 , comprising a step of estimating the age of the subject based on a previously trained machine learning model.
7. The computer-implemented method of claim 1 , comprising a step of generating a visualization of internal properties of the brain of the subject.
8. The computer-implemented method of claim 1 , comprising a step of combining data of the subject obtained through an electroencephalography (EEG) device with the dataset of the image.
9. The computer-implemented method of claim 1 , wherein said obtaining said plurality of still images comprises:
capturing said plurality of still images.
10. The computer-implemented method of claim 9 , wherein said plurality of still images is captured using a camera or a computer device with a camera, such as a mobile phone.
11. The computer-implemented method of claim 10 , comprising a step of detecting, by a gyroscope and an accelerometer, orientation of said camera or said computer device.
12. The computer-implemented method of claim 9 , comprising a step of detecting lighting quality conditions and image quality conditions before capturing said image plurality of still images and prompting said subject to adjust said lighting quality conditions and/or said image quality conditions.
13. The computer-implemented method of claim 1 , wherein answers to a questionnaire from the subject are received.
14. The computer-implemented method of claim 1 , wherein said images are analyzed for the presence of artefacts and objects in the image that may indicate an increased risk of dementia.
15. The computer-implemented method of claim 1 , wherein a metadata of the images is analyzed for patterns indicative of dementia.
16. The computer-implemented method of claim 1 , wherein a temporal analysis of the subject's head images is performed by comparing a plurality of areas of the subject's head based on a recent set of one or more images with a plurality of areas of the subject's face in an older set of one or more images, and analyzing differences between these sets to estimate dementia progression.
17. The computer-implemented method of claim 1 , wherein an emotion recognition model is applied to each image and said images are analyzed for temporal patterns of emotional deficit that may indicate dementia progression.