Psoriasis is a chronic skin disease affecting approximately 125 million people worldwide. Currently, dermatologists monitor changes of psoriasis by clinical evaluation or by measuring psoriasis severity scores over time which lead to Subjective management of this condition. The goal of this paper is to develop a reliable assessment system to quantitatively assess the changes of erythema and intensity of scaling of psoriatic lesions.
A smartphone deployable mobile application is presented that uses the smartphone camera and cloud-based image processing to analyze physiological characteristics of psoriasis lesions, identify the type and stage of the scaling and erythema. The application targets to automatically evaluate Psoriasis Area Severity Index (PASI) by measuring the severity and extent of psoriasis. The mobile application performs the following core functions: 1) it captures text information from user input to create a profile in a HIPAA compliant database. 2) It captures an image of the skin with psoriasis as well as image-related information entered by the user. 3) The application color correct the image based on environmental lighting condition using calibration process including calibration procedure by capturing Macbeth ColorChecker image. 4) The color-corrected image will be transmitted to a cloud-based engine for image processing. In cloud, first, the algorithm removes the non-skin background to ensure the psoriasis segmentation is only applied to the skin regions. Then, the psoriasis segmentation algorithm estimates the erythema and scaling boundary regions of lesion.
We analyzed 10 images of psoriasis images captured by cellphone, determined PASI score for each subject during our pilot study, and correlated it with changes in severity scores given by dermatologists. The success of this work allows smartphone application for psoriasis severity assessment in a long-term treatment.
This project introduces a new smartphone mobile medical application that utilizes cloud-based image processing to measure and characterize acne lesions. The application uses image segmentation and image analysis to measure erythema regions and compare them to known physiological characteristics to identify lesion type and stage. It then predicts the time when the lesion will heal, the “Vanishing Point”. The system can update and refine its prediction of the vanishing point as additional images of actual lesion progression are captured on subsequent days. Data from 40 subjects are analyzed for classification accuracy.
A deployable mobile medical application is presented that employs a smartphone camera, patient input, internet connectivity, and cloud-based image processing techniques to document and analyze physiological characteristics of hands in osteoarthritis (OA) patients. The application performs digital image processing that spatially calibrates the image, locates hand fiduciary features, and quantifies hand features to identify abnormal distal and proximal interphalangeal joints. The algorithm determines the finger centerlines and joint coordinates. From these anatomical fiduciary points, it measures the width of fingers, location and size of joints, and finger joint angulation. The diagnostically relevant features measured by the mobile application can be applied to current diagnostic protocols such as the American College of Rheumatology (ACR) criteria for OA. Based on the results from a pilot study, the mobile application was modified to include interactive user guidance built into the smartphone. This app makes improvements on the algorithm that validate the image quality and makes the algorithm less dependent on precise capture conditions. Based on clinical feedback, a web-based portal and dashboard for advanced analysis was developed and presented. Clinicians, researchers, and patients can use this to explore relationships between pain, treatment, environmental parameters, and lifestyle factors.