Browse Prior Art Database

Erythema and Wheal Detection From Thermal Images For Allergy Diagnosis

IP.com Disclosure Number: IPCOM000244506D
Publication Date: 2015-Dec-17
Document File: 5 page(s) / 260K

Publishing Venue

The IP.com Prior Art Database

Abstract

Skin prick test is a commonly used method for diagnosis of allergic diseases (e.g., pollen allergy, food allergy, etc.) in allergy clinics. The results of this test are erythema and wheal provoked on the skin where the test is applied. The sensitivity of the patient against a specific allergen is determined by the physical size of the wheal. The proposed method includes the following steps: 1) capturing a video feed from the test region; 2) detecting erythema region in the thermal video; 3) changing camera settings to automatically focus and zoom into the erythema region; 4) capturing an image from the zoomed region and segmenting the wheal from the captured image; 4) applying a perspective transformation for the camera calibration to estimate the physical wheal size.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 46% of the total text.

Page 01 of 5

Erythema and Wheal Detection From Thermal Images For Allergy Diagnosis

Skin prick test is a commonly used method for diagnosis of allergic diseases (e.g., pollen allergy, food allergy, etc.) in allergy clinics. The results of this test are erythema and wheal provoked on the skin where the test is applied. The sensitivity of the patient against a specific allergen is determined by the physical size of the wheal. The diameter of the wheal is typically measured by a nurse using a ruler. This manual method for measuring wheal size is a cumbersome process and prone to errors and inter-observer variations. The SPT results of a patient can be interpreted differently due to measurement errors and inter-observer variations of different medical personnel, which can easily cause inconsistencies in the diagnosis of the patient.

The proposed method includes the following steps: 1) capturing a video feed from the test region; 2) detecting erythema region in the thermal video; 3) changing camera settings to automatically focus and zoom into the erythema region; 4) capturing an image from the zoomed region and segmenting the wheal from the captured image; 4) applying a perspective transformation for the camera calibration to estimate the physical wheal size.

Although manual measurement of the wheal size is the most common method used in practice, several alternative techniques have been also proposed in the literature [1-6]. Majority of these techniques [5, 6] require marking the wheal boundaries with a pen and using an adhesive tape to transfer markings to a white paper. The size of the wheal is then measured from a scan of the marked paper using a third party software (e.g., Adobe Photoshop, Khoros, VisiQuest, Imagej etc.), which is time-consuming and require human intervention for manual delineation of the test region.

Methods that use images captured by visible light cameras also proposed for wheal segmentation and wheal size estimation [1-4]. Ref. [2], for example, proposes a semi- automated method that performs Fisher discriminant analysis on RGB color space for contrast enhancement and wheal detection. Refs. [1,4] propose fully automated unsupervised segmentation methods for wheal detection. The method in [4] performs wheal segmentation using HSV color space. This method first converts the captured RGB image to the HSV color space and performs the wheal detection on the Hue (H) channel. Similarly, method in [1], describes an unsupervised wheal segmentation algorithm by performing PCA on the Cb and Cr color channels.

Although visible light cameras are cheap and ubiquitous, wheal segmentation might sometimes be challenging from visible light images given the fact that they are captured in an uncontrolled clinic setting with varying illumination and skin color. Thermal cameras, even though being more expensive, can be robust to illumination and skin color variations.

FLIR recently released a thermal mobile imaging device (FLIR ONE) that can...