A precise automatic system for the hair assessment in hair-care diagnosis applications

Hair-to-Hair Trichoscopy: An Objective Method to Assess Effectiveness of Botulinum Toxin in a Clinical Trial for Androgenetic Alopecia

Introduction

Androgenetic alopecia (AGA) is the most common alopecia affecting both genders leading to a potential decrease in quality of life and self-esteem. A current concern in trichology is how to accurately measure clinical response in both daily medical practice and academic research. Hair-to-hair (H2H)-matching technology™ has recently emerged as a technique to evaluate variations in follicular units, hair shaft number, and thickness. This study aimed to describe the methodology employed in a clinical trial using this technology to test the efficacy of botulinum toxin (BT) for male AGA.

Methods

This pilot study is a triple-blind, randomized, split scalp, placebo-controlled clinical trial. Patients enrolled were submitted to injections half of the scalp with 50 IU of BT and the other half with 1 mL of normal saline as a control. The trial involved three visits (weeks 0, 12, and 24) and 8 global clinical photographs followed by H2H-matching trichoscopy were captured before the injections at each visit. Paired t test analysis was employed for matched pairs of the following parameters: total hair count, the total number of terminal hair strands, average shaft thickness, and the number of hairs lost or gained during each visit. Then, the software compared the differences between the two sides (BT vs. placebo) per scalp zone and a long time.

Conclusion

The combination of manually corrected image processing, follicular map, and H2H-matching technology™ appears to be the most precise way to evaluate changes in hair count and thickness over time. The design is reproducible and can help other researchers and dermatologists in their clinical practice to obtain reliable results in similar scientific research.

Efficiency of Hair Detection in Hair-to-Hair Matched Trichoscopy

Introduction

Precise evaluation of changes in hair count is crucial for monitoring progression of hair loss and the effects of treatment. The focus of this study is the comparison of the various examination and assessment techniques in terms of the precision of hair count change observed in trichoscopy images.

Methods

Controlled hair extraction of the same scalp spot was used to simulate hair loss, and the different examination techniques were performed to detect this change. The investigators who performed the counting were blinded.

Results

For trichoscopy images, the average error in determining the terminal hair count change (relative to total hair count) was 9 ± 1% for automatic assessment with manual correction and 0.4 ± 0.2% for hair-to-hair matched images. For phototrichogram, the automatic measurement results were found to deviate from truth on average by 12 ± 2%. The manually corrected hair count results were much closer to the truth with average deviation at the level of 7 ± 1%. The hair-to-hair matched results corresponded to approximately 0.6 ± 0.3% average discrepancy.

Conclusion

Combination of manually corrected image processing, follicular mapping, and hair-to-hair matching appears to be the most precise way of evaluating the change in hair count over time. These novel techniques should be considered valuable, especially in research and clinical trials.

Evaluation of Automated Measurement of Hair Density Using Deep Neural Networks

Recently, deep learning has been employed in medical image analysis for several clinical imaging methods, such as X-ray, computed tomography, magnetic resonance imaging, and pathological tissue imaging, and excellent performance has been reported. With the development of these methods, deep learning technologies have rapidly evolved in the healthcare industry related to hair loss. Hair density measurement (HDM) is a process used for detecting the severity of hair loss by counting the number of hairs present in the occipital donor region for transplantation. HDM is a typical object detection and classification problem that could benefit from deep learning. This study analyzed the accuracy of HDM by applying deep learning technology for object detection and reports the feasibility of automating HDM. The dataset for training and evaluation comprised 4492 enlarged hair scalp RGB images obtained from male hair-loss patients and the corresponding annotation data that contained the location information of the hair follicles present in the image and follicle-type information according to the number of hairs. EfficientDet, YOLOv4, and DetectoRS were used as object detection algorithms for performance comparison. The experimental results indicated that YOLOv4 had the best performance, with a mean average precision of 58.67.

Development and qualification of a machine learning algorithm for automated hair counting

OBJECTIVE

Determining the amount of hair on the scalp has always been an important metric of patient satisfaction for hair growth and hair retention technologies. While simple in concept, this measurement is a difficult, resource intensive task for the dermatologist and the research scientist. Specifically, counting and measuring hair in phototrichogram images is very time consuming and labour intensive. Due to cost, often only a fraction of available images is manually analysed. There is a need for an automated method that can significantly increase speed and throughput while reducing the cost of counting and measuring hair in phototrichogram images.

METHODS

Recent advances in machine learning and deep convolutional neural networks (deep learning) have led to a revolution in the analysis of image, video, speech, text and other sensor data. Image diagnostics have seen remarkable improvements with completely automated methods outperforming both human experts and human-engineered analysis methods. Deep learning methods can also provide speed and cost benefits. To enable use of a deep learning, we created a data set of 288 manually annotated phototrichogram images with marked location and length of each hair (the training dataset). We designed a custom neural network architecture and custom image processing algorithms to best utilize the available training data and to maximize performance for hair counting and length measurement. The performance of the algorithm was qualified by comparing hair count and length measurements to an independent ground truth method, the semi-manual Canfield's Hair Metrix method.

RESULTS

Leveraging deep neural networks, we have developed capability to apply machine learning to reduce the time needed to acquire data from phototrichograms of patients' scalp from months to seconds. Our algorithm enables fast and fully automated hair counting and length measurement. The algorithm shows high agreement with human manually assisted analysis (ground truth).

CONCLUSIONS

We have trained and deployed an algorithm utilizing this technology and have demonstrated the reproducibility, accuracy and speed of this algorithm that, once deployed, requires little to no recurring cost or manual intervention for its operation. The method allows fast analysis of large number of images, reducing study cost and significantly reducing study analysis time.

Classification Framework for Healthy Hairs and Alopecia Areata: A Machine Learning (ML) Approach

Alopecia areata is defined as an autoimmune disorder that results in hair loss. The latest worldwide statistics have exhibited that alopecia areata has a prevalence of 1 in 1000 and has an incidence of 2%. Machine learning techniques have demonstrated potential in different areas of dermatology and may play a significant role in classifying alopecia areata for better prediction and diagnosis. We propose a framework pertaining to the classification of healthy hairs and alopecia areata. We used 200 images of healthy hairs from the Figaro1k dataset and 68 hair images of alopecia areata from the Dermnet dataset to undergo image preprocessing including enhancement and segmentation. This was followed by feature extraction including texture, shape, and color. Two classification techniques, i.e., support vector machine (SVM) and k-nearest neighbor (KNN), are then applied to train a machine learning model with 70% of the images. The remaining image set was used for the testing phase. With a 10-fold cross-validation, the reported accuracies of SVM and KNN are 91.4% and 88.9%, respectively. Paired sample T-test showed significant differences between the two accuracies with a p < 0.001. SVM generated higher accuracy (91.4%) as compared to KNN (88.9%). The findings of our study demonstrate potential for better prediction in the field of dermatology.

How good is artificial intelligence (AI) at solving hairy problems? A review of AI applications in hair restoration and hair disorders

Artificial intelligence (AI) applications in medicine are rapidly evolving. Deep learning diagnostic models that can accurately classify skin lesions have been developed. New AI applications are also starting to emerge in the hair restoration field. The objective was to review the current and future clinical applications of AI in hair restoration and hair disorder diagnosis. Current AI applications in hair restoration include fully automated systems for hair detection and hair growth measurement. New deep learning-based systems have been proposed for scalp diagnosis and automated hair loss measurements, including devices that can be used for self-diagnosis. Hair restoration experts should recognize the potential benefits and limitations of these emerging technologies as they become more readily available to both clinicians and patients.