IP Library Granted Patent US 12,620,087
Granted Patent B2
US 12,620,087 · App. 18/094,649 · Granted May 5, 2026

Dianet: a deep learning based architecture to diagnose diabetes using retinal images only

Inventor: Tanvir Alam (Doha, QA)
Assignee: HAMAD BIN KHALIFA UNIVERSITY
G06T7/0012A61B5/7267A61B5/7275G06N3/098G06T3/40G06T7/11G06N3/0464G06T2207/20081G06T2207/20084G06T2207/20132G06T2207/30041
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,620,087
App. No.
18/094,649
Granted
May 5, 2026
Kind
B2
Abstract

A method of training a convolutional neural network model to predict diabetes from an image of a retina is provided. The method of training a convolutional neural network includes processing a first dataset, wherein processing the first dataset comprises: extracting a circular region from a retinal image, resizing the circular region, cropping the circular region, and placing the circular region onto a black background; training an initial model using a second dataset to yield a first model; training the first model using a third dataset to yield a second model; and training the second model using the first dataset to yield a third model.

Claims (51)

1 . A method of training a convolutional neural network model to predict diabetes from an image of a retina, comprising:

processing a first dataset, wherein processing the first dataset comprises:

extracting a circular region from a retinal image;

resizing the circular region;

cropping the circular region; and

placing the circular region onto a black background;

training an initial model using a second dataset to yield a first model;

training the first model using a third dataset to yield a second model; and

training the second model using the first dataset to yield a third model-,

wherein the third dataset comprises a plurality of retinal images labeled based on the severity of diabetic retinopathy.

2 . The method of training a convolutional neural network model to predict diabetes from the image of a retina of claim 1 , wherein processing the first dataset outputs an image having a retina with a radius of 300 pixels.

3 . The method of training a convolutional neural network model to predict diabetes from the image of a retina of claim 1 , wherein the initial model is a DenseNet model.

4 . The method of training a convolutional neural network model to predict diabetes from the image of a retina of claim 3 , wherein the DenseNet model is a 121-layer variant DenseNet model.

5 . The method of training a convolutional neural network model to predict diabetes from the image of a retina of claim 1 , wherein the first dataset comprises a plurality of retinal images including a first group of retinal images and a second group of retinal images.

6 . The method of training a convolutional neural network model to predict diabetes from the image of a retina of claim 5 , wherein the first group of retinal images relates to a control group and the second group of retinal images relates to a diabetes group.

7 . A convolutional neural network model architecture to predict diabetes from an image of a retina, comprising:

a DenseNet-121 backbone;

a final layer outputting a predictive label corresponding to a diabetic prediction or a non-diabetic prediction;

a pair of pooling layers; and

a first composite layer, a second composite layer, and a third composite layer,

wherein the pair of pooling layers comprise a global average pooling layer and a global max pooling layer.

8 . The convolutional neural network model architecture of claim 7 , wherein the final layer is a single neuron layer.

9 . The convolutional neural network model architecture of claim 7 , wherein the first composite layer comprises a first sequence of a plurality of layers, the second composite layer comprises a second sequence of a plurality of layers, and the third composite layer comprises a third sequence of a plurality of layers.

10 . The convolutional neural network model architecture of claim 9 , wherein the first sequence of the plurality of layers comprises a batch normalization layer, a dropout layer, a linear layer, and a rectified linear unit layer.

11 . The convolutional neural network model architecture of claim 9 , wherein the second sequence of the plurality of layers comprises a batch normalization layer, a dropout layer, a linear layer, and a rectified linear unit layer.

12 . The convolutional neural network model architecture of claim 9 , wherein the third sequence of the plurality of layers comprises a batch normalization layer, a dropout layer, and the final layer for outputting the predictive label.

13 . A method of training a convolutional neural network model to predict diabetes from the image of a retina, comprising:

processing a first dataset and a second dataset, wherein processing the first dataset and the second dataset comprises:

extracting a circular region from a retinal image;

resizing the circular region;

cropping the circular region; and

placing the circular region onto a black background;

training a DenseNet-121 model using an third dataset to yield a first model;

training the first model using the second dataset to yield a second model; and

training the second model using the first dataset to yield a third model,

wherein the third model has an architecture comprising:

a DenseNet-121 backbone;

a global average pooling layer;

a global max pooling layer;

a first composite layer;

a second composite layer; and

a third composite layer.

14 . The method of training a convolutional neural network model to predict diabetes from the image of a retina of claim 13 , wherein the third composite layer comprises:

a batch normalization layer,

a dropout layer; and

a final layer outputting a predictive label corresponding to a diabetic prediction or a non-diabetic prediction.

15 . The method of training a convolutional neural network model to predict diabetes from the image of a retina of claim 13 , wherein the first composite layer comprises:

a batch normalization layer;

a dropout layer;

a linear layer; and

a rectified linear unit layer.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 17, 2025
From: QATAR FOUNDATION FOR EDUCATION, SCIENCE & COMMUNITY DEVELOPMENT
To: HAMAD BIN KHALIFA UNIVERSITY
Reel/Frame 069936/0656 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 2, 2023
From: ALAM, TANVIR
To: QATAR FOUNDATION FOR EDUCATION, SCIENCE AND COMMUNITY DEVELOPMENT
Reel/Frame 065438/0882 →
Continuity (2)
Provisional Application 63298473 · Jan 11, 2022
Related Publication 20230222650A1 · Jul 13, 2023
References Cited (21)
US 10257487B1 · Tamatam · 2019 [cited by examiner]
US 20100037059A1 · Sun · 2010 [cited by examiner]
US 20170310935A1 · Sinclair · 2017 [cited by examiner]
US 20180060722A1 · Hwang · 2018 [cited by examiner]
US 20180122068A1 · Garnavi · 2018 [cited by examiner]
US 20180235467A1 · Celenk · 2018 [cited by examiner]
US 20190104722A1 · Slaughter · 2019 [cited by examiner]
US 20190221313A1 · Rim · 2019 [cited by examiner]
US 20200058123A1 · Liao · 2020 [cited by examiner]
US 20200160999A1 · Rim · 2020 [cited by examiner]
US 20200191553A1 · Rothberg · 2020 [cited by examiner]
US 20200193004A1 · West · 2020 [cited by examiner]
US 20200258215A1 · Kashyap · 2020 [cited by examiner]
US 20210327062A1 · Choi · 2021 [cited by examiner]
Islam, Mohammad Tariqul, et al. “DiaNet: A deep learning based architecture to diagnose diabetes using retinal images only.” Ieee Access 9 (2021): 15686-15695. (Year: 2021). [cited by examiner]
Kim, K. M., et al. “Development of a Fundus Image-Based Deep Learning Diagnostic Tool for Various Retinal Diseases.” J. Pers. Med 11 (2021): 321. (Year: 2021). [cited by examiner]
Rajpurkar, Pranav, et al. “Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning.” arXiv preprint arXiv: 1711.05225 (2017). (Year: 2017). [cited by examiner]
Graham; “Kaggle Diabetic Retinopathy Detection competition report”; Aug. 6, 2015; Department of Statistics and Centre for Complexity Science, University of Warwick; (9 pages). [cited by applicant]
Sisodia, et al.; “Prediction of Diabetes using Classification Algorithms”; ScienceDirect; 2018; (8 pages). [cited by applicant]
Bora, et al.; “Predicting the risk of developing diabetic retinopathy using deep learning”; Lancet Digit Health 2021; vol. 3, Jan. 2021; (10 pages). [cited by applicant]
Huang, et al.; “Densely Connected Convolutional Networks”; CVPR; https://openaccess.thecvf.com/content_cvpr_2017/papers/Huang_Densely_Connected_Convolutional_CVPR_2017_paper.pdf; 2017; (9 pages). [cited by applicant]