# US 2023/0066166 A1 · Eye state assessment method and electronic device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0066166 A1 - Document ID: US20230066166A1 - Status: Published application - Kind: A1 - Application number: 17/506,703 - Filed: 2021-10-21 - Published: 2023-03-02 - Earliest claimed: 2021-08-26 - Assignees: Acer Incorporated; National Taiwan University Hospital - Applicants: Acer Incorporated; National Taiwan University Hospital - Inventors: Yi-Jin Huang; Chien-Hung Li; Wei-Hao Chang; Hung-Sheng Hsu; Ming-Chi Kuo; Jehn-Yu Huang - Web page: https://patentgrep.com/patent/US20230066166A1 ## CPC - G06T 7/0012: {Biomedical image inspection} - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - A61B 3/0025: {characterised by electronic signal processing, e.g. eye models} - A61B 3/12: for looking at the eye fundus, e.g. ophthalmoscopes (A61B3/13 takes precedence) - A61B 3/14: Arrangements specially adapted for eye photography - A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor} - G06V 10/809: {of classification results, e.g. where the classifiers operate on the same input data} - G06V 10/82: using neural networks - G06V 40/18: Eye characteristics, e.g. of the iris - G06V 40/193: {Preprocessing; Feature extraction} - G16H 30/40: for processing medical images, e.g. editing - G16H 50/30: for calculating health indices; for individual health risk assessment - G06T 2207/10024: Color image - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30041: Eye; Retina; Ophthalmic - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract The disclosure provides an eye state assessment method and an electronic device. The method includes: obtaining an optic disc image area from a first fundus photography and generating multiple optic cup-to-disc ratio assessment results by multiple first models based on the optic disc image area; obtaining a first assessment result of an eye based on the optic cup-to-disc ratio assessment results; performing multiple data augmentation operations on the first fundus photography to generate multiple second fundus photographies; generating multiple retinal nerve fiber layer (RNFL) defect assessment results by multiple second models based on the second fundus photographies; obtaining a second assessment result of the eye based on the RNFL defect assessment results; and obtaining an optic nerve assessment result of the eye based on the first assessment result and the second assessment result. ## Claims ### Claim 1 An eye state assessment method for an electronic device, comprising: obtaining a first fundus photography of an eye, wherein the first fundus photography comprises an optic disc image area; obtaining the optic disc image area from the first fundus photography and generating a plurality of optic cup-to-disc ratio assessment results by a plurality of first models based on the optic disc image area; obtaining a first assessment result of the eye based on the optic cup-to-disc ratio assessment results; performing a plurality of data augmentation operations on the first fundus photography to generate a plurality of second fundus photographies respectively corresponding to the data augmentation operations; generating a plurality of retinal nerve fiber layer defect assessment results by a plurality of second models based on the second fundus photographies; obtaining a second assessment result of the eye based on the retinal nerve fiber layer defect assessment results; and obtaining an optic nerve assessment result of the eye based on the first assessment result and the second assessment result. ### Claim 2 (depends on 1) The method according to claim 1, wherein the first fundus photography comprises a color fundus photography of the eye, and the color fundus photography does not have black borders. ### Claim 3 (depends on 1) The method according to claim 1, wherein a step of obtaining the optic disc image area from the first fundus photography comprises: inputting the first fundus photography to a reference neural network, wherein the reference neural network recognizes the optic disc image area in the first fundus photography in response to the first fundus photography, and outputs the optic disc image area. ### Claim 4 (depends on 1) The method according to claim 1, wherein the first models comprise N neural networks, and each of the optic cup-to-disc ratio assessment results indicates whether an optic cup-to-disc ratio of the eye is normal or abnormal, wherein N is an odd number. ### Claim 5 (depends on 4) The method according to claim 4, wherein a step of obtaining the first assessment result of the eye based on the optic cup-to-disc ratio assessment results comprises: identifying a plurality of first results indicating normality from the optic cup-to-disc ratio assessment results, and identifying a plurality of second results indicating abnormality from the optic cup-to-disc ratio assessment results; determining that the first assessment result indicates normality in response to determining that the first results are more than the second results; and determining that the first assessment result indicates abnormality in response to determining that the first results are less than the second results. ### Claim 6 (depends on 1) The method according to claim 1, wherein the first models comprise a first neural network, and the method comprises: inputting the optic disc image area to the first neural network, wherein the first neural network outputs one of the optic cup-to-disc ratio assessment results in response to the optic disc image area. ### Claim 7 (depends on 1) The method according to claim 1, wherein the first models comprise a second neural network, and the method comprises: inputting the optic disc image area into the second neural network, wherein the second neural network outputs a first optic cup-to-disc ratio of the eye in response to the optic disc image area; determining that one of the optic cup-to-disc ratio assessment results corresponding to the second neural network indicates abnormality in response to determining that the first optic cup-to-disc ratio is higher than a preset threshold; and determining that one of the optic cup-to-disc ratio assessment results corresponding to the second neural network indicates normality in response to determining that the first optic cup-to-disc ratio is not higher than the preset threshold. ### Claim 8 (depends on 1) The method according to claim 1, wherein the optic disc image area comprises an optic cup image area, the first models comprise a third neural network, and the method comprises: inputting the optic disc image area into the third neural network, wherein the third neural network outputs an optic cup axial length of the eye in response to the optic cup image area, and outputs an optic disc axial length of the eye in response to the optic disc image area; obtaining a second optic cup-to-disc ratio of the eye based on the optic cup axial length and the optic disc axial length; determining that one of the optic cup-to-disc ratio assessment results corresponding to the third neural network indicates abnormality in response to determining that the second optic cup-to-disc ratio is higher than a preset threshold; and determining that one of the optic cup-to-disc ratio assessment results corresponding to the third neural network indicates normality in response to determining that the second optic cup-to-disc ratio is not higher than the preset threshold value. ### Claim 9 (depends on 1) The method according to claim 1, wherein a step of generating the retinal nerve fiber layer defect assessment results by the second models based on the second fundus photographies comprises: inputting one of the second fundus photographies into one of the second models, wherein the one of the second models outputs a confidence value of prediction as one of the retinal nerve fiber layer defect assessment results in response to the one of the second fundus photographies, wherein the confidence value of prediction indicates a degree of abnormality of the eye. ### Claim 10 (depends on 9) The method according to claim 9, wherein a step of obtaining the second assessment result of the eye based on the retinal nerve fiber layer defect assessment results comprises: obtaining a square difference between the confidence value of prediction corresponding to each of the second models and a reference base value, and identifying a candidate model in the second models accordingly, wherein the square difference corresponding to the candidate model is the largest among the second modes; determining that the second assessment result of the eye indicates abnormality in response to determining that the confidence value of prediction corresponding to the candidate model is higher than the reference base value; and determining that the second assessment result of the eye indicates normality in response to determining that the confidence value of prediction corresponding to the candidate model is not higher than the reference base value. ### Claim 11 (depends on 1) The method described in claim 1, wherein the first assessment result indicates normality or abnormality, the second assessment result indicates normality or abnormality, and a step of obtaining an optic nerve assessment result of the eye based on the first assessment result and the second assessment result comprises: determining that the optic nerve assessment result of the eye belongs to a first risk level in response to determining that the first assessment result indicates normality and the second assessment result indicates normality; determining that the optic nerve assessment result of the eye belongs to a second risk degree in response to determining that the first assessment result indicates abnormality and the second assessment result indicates normality, wherein the second risk degree is greater than the first risk degree; determining that the optic nerve assessment result of the eye belongs to a third risk degree in response to determining that the first assessment result indicates normality and the second assessment result indicates abnormality, wherein the third risk degree is greater than the second risk degree; and determining that the optic nerve assessment result of the eye belongs to a fourth risk degree in response to determining that the first assessment result indicates abnormality and the second assessment result indicates abnormality, wherein the fourth risk degree is greater than the third risk degree. ### Claim 12 An electronic device, comprising: a storage circuit, storing a program code; a processor, coupled to the storage circuit and accessing the program code to execute: obtaining a first fundus photography of an eye, wherein the first fundus photography comprises an optic disc image area; obtaining the optic disc image area from the first fundus photography and generating a plurality of optic cup-to-disc ratio assessment results by a plurality of first models based on the optic disc image area; obtaining a first assessment result of the eye based on the optic cup-to-disc ratio assessment results; performing a plurality of data augmentation operations on the first fundus photography to generate a plurality of second fundus photographies respectively corresponding to the data augmentation operations; generating a plurality of retinal nerve fiber layer defect assessment results by a plurality of second models based on the second fundus photographies; obtaining a second assessment result of the eye based on the retinal nerve fiber layer defect assessment results; and obtaining an optic nerve assessment result of the eye based on the first assessment result and the second assessment result.