IP Library Granted Patent US 12697071
Granted Patent B2
US 12697071 · App. 17/278,377 · Granted Aug 4, 2026

Deep learning Lyme disease diagnosis

Inventors: Seth D. Billings (Pellston, MI); Philippe M. Burlina (Rockville, MD); Neil J. Joshi (Laurel, MD); John N. Aucott (Lutherville, MD); Elise Ng (Baltimore, MD)
Assignee: THE JOHNS HOPKINS UNIVERSITY
A61B5/7267A61B5/0077A61B5/444A61B5/6898A61B5/7282G06N3/08G06T7/0014G16H50/20A61B2576/02G06T2207/20081G06T2207/20084G06T2207/30088G06T2207/30096
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 12697071
App. No.
17/278,377
Granted
Aug 4, 2026
Kind
B2
Abstract

Techniques for diagnosing Lyme disease are presented. The techniques may include obtaining a digital photo of a skin lesion, providing the digital photo to a deep learning convolutional neural network, such that an output diagnosis is provided. The deep learning convolutional neural network may be trained using a training corpus including a plurality of digital training images annotated according to one of a plurality of training image diagnoses, where the plurality of training image diagnoses include at least one Lyme disease type, normal skin, and at least one non-Lyme skin lesion type, and where the plurality of digital training images include multiple digital photographs publicly available on the internet. The techniques can include outputting the output diagnosis.

Claims (9)

1 . A system for diagnosing Lyme disease comprising at least one processor that executes instructions to perform operations comprising:

obtaining, by a smart phone camera, a digital photo of a skin lesion;

providing the digital photo to a deep learning convolutional neural network, whereby an output diagnosis is provided, wherein the output diagnosis is one of Lymes or not Lymes, wherein the deep learning convolutional neural network is trained using a training corpus comprising a plurality of digital training images annotated according to one of a plurality of training image diagnoses, wherein the plurality of training image diagnoses comprise at least one Lyme disease type diagnosis, normal skin, and at least one non-Lyme skin lesion type diagnosis, wherein the plurality of digital training images comprise a plurality of Lyme disease skin lesion training images depicting simple erythema migrans skin lesions and diffuse erythema migrans skin lesions, a plurality of normal skin training images, and a plurality of non-Lyme skin lesion training images depicting non-Lyme skin lesions, wherein the at least one non-Lyme skin lesion type comprises herpes zoster, wherein the at least one non-Lyme skin lesion type further comprises Tinea corporis , and wherein the plurality of digital training images comprise multiple digital photographs publicly available on the internet; and

outputting in electronic format the output diagnosis.

2 . The system of claim 1 , wherein the providing comprises providing to the smart phone, and wherein the outputting comprises outputting by the smart phone.

3 . The system of claim 2 , wherein the obtaining, the providing, and the outputting comprise obtaining by, providing to, and outputting by an app executing on the smart phone.

4 . The system of claim 1 wherein the multiple digital photographs publicly available on the internet are obtained using a search engine and search terms comprising: erythema migrans, lyme, and bullseye rash.

5 . The system of claim 1 , wherein the multiple digital photographs publicly available on the internet are obtained without patient consent.

6 . The system of claim 1 , wherein the obtaining, the providing, and the outputting are performed by a server computer communicatively coupled to the internet.