Quantifying alopecia for clinical use

 

Quantifying alopecia areata in real time is an ongoing challenge for clinicians and investigators. Although a few scoring systems exist, they can be cumbersome. Our goal is to build a quantitative system that is reproducible, standardized, and simple to use.

Commonly used alopecia severity scales usually rely on having clinicians individuate areas of hair loss and compare their locations and/or sizes in order to map the hair loss appearance to a score, such as overall percent alopecia. To standardize this process, we developed a computational tool that takes standardized photographs of patients’ scalps and returns an overall percent hair loss as output without any user input. Scores are computed from hair density information extracted automatically at every point of the patient’s scalp.

 

Quantifying Alopecia

TRICHY: interface for alopecia monitoring

Rethinking Alopecia Scores – Automating Hair Loss Labels for Universally Scoring Alopecia from Images [JAMA Derm 2022] [Project Page]

 

 

 

 

How many pixels needed

Photographing Alopecia: How Many Pixels Are Needed for Clinical Evaluation?

Determining the minimum image resolution needed for clinical assessment is crucial for computational efficiency, image standardization, and storage needs alleviation. In this paper, we explore the image resolution requirements for the assessment of alopecia by analyzing how clinicians detect the presence of characteristics needed to quantify the disorder in the clinic.

 
 
Head Geometry

Adapting SALT guidelines for the pediatric population: standardizing image capture for pediatric patients

The Severity of Alopecia Tool (SALT), and its updated SALT II (ALODEX) scoring systems are designed for adults. To quantify alopecia on pediatric patients and, more importantly to follow their progression over time, we adapted the SALT guidelines to account for the changing head geometry of children as their heads grow. [PedsDerm2017]

References

 

  1. A. Bayramova, T. Mane, L. Castelo-Soccio, T. Ogunleye, S. Taylor, E. Bernardis, Photographing Alopecia: How Many Pixels are Needed?, J Digital Imaging, Oct. 2020.     
  2. E. Bernardis, L. Castelo-Soccio, Quantifying Alopecia Areata via Texture Analysis to Automate the SALT Score Computation, JIDSP 2018.
  3. E. Bernardis, L. Castelo-Soccio, Pediatric severity of alopecia tool, Pediatric Dermatology, 2017. 
  4. Gudobba C, Mane T, Bayramova A, Rodriguez N, Castelo-Soccio L, Ogunleye TA, Taylor SC, Cotsarelis G, Bernardis E, Automating Hair Loss Labels for Universally Scoring Alopecia from Images – Rethinking Alopecia Scores, JAMA Dermatology, 2022.