Computer vision-based monitoring system for treating jaundice

Abstract

The invention relates to a computer-based jaundice monitoring system. The system adopts an image processing technology to monitor and detect jaundice of a patient. The system includes a camera for capturing images of a patient, a computing device for image processing and analysis, a local communication network for interconnecting system components, and a light panel integrated with the camera to provide phototherapy. A computing device identifies a skin area of a patient, analyzes primary colors within the skin area, detects yellow pigmentation indicative of jaundice, and generates a notification accordingly.

Description

Technical Field

[0001] The present invention relates to patient monitoring systems. More particularly, the present invention relates to a computer vision-based monitoring system for jaundice treatment. Background Art

[0002] Neonatal jaundice, a common disease in newborns, is caused by an excess of bilirubin, which causes yellowing of the skin and eyes. Recent studies have shown that it occurs widely, especially in low-income and middle-income countries. Risk factors such as premature birth and low birth weight are noted. Early detection and treatment are crucial to preventing serious consequences. Phototherapy using blue light is the standard treatment, but traditional systems have limitations. LED-based phototherapy is more cost-effective and efficient. Computer vision technology has become a promising solution for improving jaundice management, especially in resource-constrained environments. By using computer vision algorithms to analyze skin color, doctors and medical staff can accurately diagnose and monitor jaundice without relying on expensive equipment or professional training. This technology can also enable the development of low-cost, portable phototherapy lamps that can be easily deployed in areas where healthcare is limited. The present invention aims to improve healthcare solutions for newborns by providing affordable, available and effective phototherapy devices that can be used in low-resource settings. By combining phototherapy treatment with non-invasive skin color monitoring, the present invention has the potential to improve the accuracy and effectiveness of jaundice treatment and reduce the risks and complications associated with untreated jaundice.

[0003] Different patient monitoring systems are currently disclosed in the art. For example, Hashim et al. (2021) disclosed a neonatal jaundice detection system, which detects the skin area by converting the image into Lab color space and obtains the values ​​of the B channel and Cb channel, and compares these values ​​with predefined thresholds. If the value of the B channel or the Cb channel is less than the threshold, the diagnosis result is "Jaundice" and the baby needs phototherapy. Otherwise, the diagnosis result is "Normal".

[0004] KR101623167B1 discloses a monitoring system for newborns. The system includes a camera with a facial recognition module and a body recognition module. The system also includes a facial color recognition module that can recognize jaundice and operate an emergency module when jaundice is detected.

[0005] However, these patient monitoring systems do not disclose the patient monitoring system shown in the present invention. Summary of the invention

[0006] The object of the present invention is to provide a jaundice monitoring system.

[0007] Accordingly, the present invention provides a jaundice monitoring system based on computer vision, the system comprising:

[0008] a. a camera configured to capture an image of a patient;

[0009] b. A computing device in communication with the camera, the computing device being programmed to process the captured image, the processing comprising:

[0010] i. identifying the patient's skin area within the captured image,

[0011] ii. analyzing the dominant colors present in the patient's skin area,

[0012] iii. Determine the presence of yellow pigmentation based on the dominant color, and

[0013] iv. generating and transmitting a notification when yellow pigmentation is detected;

[0014] c. A light panel integrated with a camera for delivering light therapy to a patient; and

[0015] d. A local communication network that facilitates connectivity between the camera, computing device, and light panel. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A jaundice monitoring system based on computer vision according to a preferred embodiment of the present invention is shown;

[0017] Figure 2 A method of monitoring jaundice using a computer-based system according to a preferred embodiment of the present invention is shown. DETAILED DESCRIPTION

[0018] Figure 1 A computer vision-based jaundice monitoring system according to a preferred embodiment of the present invention is shown. The system includes a camera 100 configured to capture an image of a patient. A computing device 102 in communication with the camera 100 processes the captured image. Image processing includes identifying a skin region of the patient within the captured image. Next, the computing device 102 analyzes the dominant color present in the patient's skin region. Then, the presence of yellow pigmentation is determined based on the dominant color. Finally, upon determining yellow pigmentation, the computing device 102 generates and transmits a notification.

[0019] The system also includes a light panel 104 integrated with the camera 100. The light panel 104 provides light therapy to the patient.

[0020] Further, the system includes a local communication network 106 to facilitate connectivity between the camera 100, the computing device 102, and the light panel 104. Preferably, the local communication network 106 is a Wi-Fi network. Alternatively, the local communication network 106 is a Bluetooth network or other communication network technology available in the art.

[0021] In a preferred embodiment, computing device 102 sends a signal for controlling the intensity of light panel 104 based on the yellow pigmentation of the patient's skin.

[0022] In another further embodiment, the monitoring device 108 is further connected to the local communication network 106. The monitoring device 108 receives notifications and data from the computing device 102.

[0023] Figure 2 A method for monitoring jaundice using a computer-based system according to a preferred embodiment of the present invention is shown. The method begins by capturing an image of a patient using a camera (step 200). A computing device in communication with the camera then processes the captured image (step 202). The process includes identifying a skin area of ​​the patient within the captured image (step 204). Preferably, the identification is performed by identifying pixels as skin using the following rule:

[0024] (i) R > 95 and G > 40 and B > 20 (1)

[0025] (ii)Max(R,G,B)-Min(R,G,B)>15

[0026] (iii)|RG|>15

[0027] (iv) R>G and R>B

[0028] Among them, R is the red channel, G is the green channel, and B is the blue channel.

[0029] The first rule defines the range of RGB values, the second rule describes the range of saturation, the third rule specifies the acceptable difference between the red and green channels, and the fourth rule requires that the red channel be larger than the green and blue channels. If all of these rules are met, the pixel is considered a skin pixel.

[0030] Next, the computing device analyzes the dominant color within the patient's skin area (step 206). This is done by k-means clustering.

[0031] The computing device then determines whether the primary color exhibits yellow pigmentation (step 208). The b* value of the color on the CIE L*a*b color space is used as a key variable. CIE L*a*b* is a device-independent 3D color space that can accurately measure and compare all perceptible colors expressed in three values ​​(L* for perceived lightness, a* and b* as chromaticity coordinates).

[0032] The yellowness score is determined by taking the weighted average of the normalized b* coordinate of the extracted primary skin color relative to a reference yellow point and a reference "normal" skin point. This is done to provide a more interpretable representation of the data for monitoring purposes. The formula is as follows:

[0033] Yellow score = ∑iwi(bi-bmin) / (bmax-bmin)

[0034] in:

[0035] - bi is the b* coordinate of the position of the extracted color i in the CIE L*a*b* color space;

[0036] -bmin is the b* coordinate of the reference normal skin pixel;

[0037] -bmax is the b* coordinate of the reference maximum yellow point;

[0038] - wi is the weight assigned to each extracted color i, determined by the number of pixels clustered around that color (how dominant that color is).

[0039] The computing device then generates a notification when yellow pigmentation is detected (step 210).

[0040] Furthermore, the computing device sends a signal for controlling the intensity of the light panel to deliver light therapy to the patient (step 212).

[0041] In a further embodiment of the invention, the computing device utilizes a machine learning algorithm to improve the accuracy of determining yellow pigmentation.

[0042] It is contemplated that the embodiments described herein extend to the individual elements and concepts described herein independently of other concepts, ideas or systems, and it is contemplated that embodiments include combinations of elements recorded anywhere in this application. It should be understood that the present invention is not limited to the embodiments described in detail herein with reference to the accompanying drawings. Therefore, many variations and modifications will be apparent to those skilled in the art. Illustrative embodiments such as those depicted relate to preferred forms, but are not limited to their constraints, and may be modified and substituted. Therefore, it is intended that the scope of the present invention is defined by the appended claims and their equivalents. Moreover, it is contemplated that features described individually or as part of an embodiment may be combined with other individually described features or parts of other embodiments, even if other features and embodiments do not mention the features. Therefore, the absence of a description of the combination should not prevent the inventor from claiming the right to such a combination.

Claims

1. A jaundice monitoring system based on computer vision, comprising: a. a camera configured to capture an image of a patient; b. A computing device in communication with the camera, the computing device being programmed to process the captured image, the processing comprising: i. identifying an area of ​​the patient's skin within said captured image, ii. analyzing the dominant colors present in the patient's skin area, iii. determining the presence of yellow pigmentation based on said primary color, and iv. generating and transmitting a notification when yellow pigmentation is detected; c. a light panel integrated with said camera for administering light therapy to said patient; and d. A local communication network that facilitates connectivity between the camera, the computing device, and the light panel.

2. The system of claim 1, further comprising a monitoring device connected to the local communication network, the monitoring device being configured to receive the notification and the patient data.

3. The system according to claim 1, wherein: The computing device utilizes a machine learning algorithm to improve the accuracy of determining yellow pigmentation.

4. The system according to claim 1, wherein: The local communication network is a wireless network using Wi-Fi or Bluetooth technology.

5. The system according to claim 1, wherein: The intensity of the light panel is adjustable to provide controlled light therapy to the patient.

6. A method of monitoring jaundice using a computer-based system comprising the steps of: a. Capturing an image of the patient using a camera; b. processing the captured image by a computing device in communication with the camera, the processing comprising: i. identifying an area of ​​the patient's skin within said captured image, ii. Analyze the dominant color in the patient's skin area, iii. determining whether the primary color exhibits yellow pigmentation indicative of jaundice, and iv. generating a notification when yellow pigmentation is detected; and c. Administering light therapy to the patient using a light panel integrated with the camera.

Images