Evaluation of Automated Measurement of Hair Density Using Deep Neural Networks

Kim, Minki; Kang, Sunwon; Lee, Byoung-Dai

doi:10.3390/s22020650

Cited by 18 publications

(21 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further validate the performance of the ResNet-101 model over other alternatives, we conducted a benchmark comparison with other models (EfficientDet and YOLOv4) reported in [ 21 ] which were similarly applied to hair follicle detection classification in Table 2 . ResNet-50 showed better performance as compared to EfficientDet; however, it underperformed as compared to YOLOv4.…”

Section: Resultsmentioning

confidence: 99%

“…On the other hand, ResNet-101 showed superior performance compared to all other models compared. Our method used a circular shape to mask the region of interest (ROI) to train the model, which is different from the rectangular ROI employed in [ 21 ]. This could have been the reason for the higher mAP values of ResNet-101 compared to other models because it more closely resembles the shape of actual hair follicles which might improve the Intersection over Union (IoU).…”

Section: Resultsmentioning

confidence: 99%

“…Further, a support vector machine (SVM) and a k-nearest neighbor (KNN) were utilized to train a machine learning model to classify healthy and hair loss conditions [ 20 ]. The feasibility of automating the process of hair density assessment was tested by measuring the number of hairs from hair follicles and their type using deep learning-based object detection as well as other methods [ 21 ], such as VGG-16 [ 22 ], EfficientDet [ 23 ], YOLOv4 [ 24 ], and DetectoRS [ 25 ]. The common shortcomings of these approaches are prevalent false detections on the number of hairs, inaccuracy in detecting hair follicles, and lacking entire scalp-level hair loss severity estimation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hair Follicle Classification and Hair Loss Severity Estimation Using Mask R-CNN

Kim

Kwon²,

et al. 2022

J. Imaging

View full text Add to dashboard Cite

Early and accurate detection of scalp hair loss is imperative to provide timely and effective treatment plans to halt further progression and save medical costs. Many techniques have been developed leveraging deep learning to automate the hair loss detection process. However, the accuracy and robustness of assessing hair loss severity still remain a challenge and barrier for transitioning such a technique into practice. The presented work proposes an efficient and accurate algorithm to classify hair follicles and estimate hair loss severity, which was implemented and validated using a multitask deep learning method via a Mask R-CNN framework. A microscopic image of the scalp was resized, augmented, then processed through pre-trained ResNet models for feature extraction. The key features considered in this study concerning hair loss severity include the number of hair follicles, the thickness of the hair, and the number of hairs in each hair follicle. Based on these key features, labeling of hair follicles (healthy, normal, and severe) were performed on the images collected from 10 men in varying stages of hair loss. More specifically, Mask R-CNN was applied for instance segmentation of the hair follicle region and to classify the hair follicle state into three categories, following the labeling convention (healthy, normal and severe). Based on the state of each hair follicle captured from a single image, an estimation of hair loss severity was determined for that particular region of the scalp, namely local hair loss severity index (P), and by combining P of multiple images taken and processed from different parts of the scalp, we constructed the hair loss severity estimation (Pavg) and visualized in a heatmap to illustrate the overall hair loss type and condition. The proposed hair follicle classification and hair loss severity estimation using Mask R-CNN demonstrated a more efficient and accurate algorithm compared to other methods previously used, enhancing the classification accuracy by 4 to 15%. This performance supports its potential for use in clinical settings to enhance the accuracy and efficiency of current hair loss diagnosis and prognosis techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hair Follicle Classification and Hair Loss Severity Estimation Using Mask R-CNN

Kim

Kwon²,

et al. 2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…This would improve the trustworthiness of the trained model and address the issue of models fitting too well. The accuracy of hair density measurement (HDM) was investigated in this study utilizing deep learning to locate objects, and it was discovered that HDM could be performed automatically 25 . One thousand four hundred Red, Blue, and Green photos of balding men's scalps were utilized for training and testing.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The accuracy of hair density measurement (HDM) was investigated in this study utilizing deep learning to locate objects, and it was discovered that HDM could be performed automatically. 25 One thousand four hundred Red, Blue, and Green photos of balding men's scalps were utilized for training and testing. Images of hair follicles and the information about their location and kind depending on the quantity of hairs shown were provided.…”

Section: Literature Reviewmentioning

confidence: 99%

Leveraging deep neural networks to uncover unprecedented levels of precision in the diagnosis of hair and scalp disorders

Chowdhury,

Sultan,

Jahan

et al. 2024

Skin Research and Technology

View full text Add to dashboard Cite

BackgroundHair and scalp disorders present a significant challenge in dermatology due to their clinical diversity and overlapping symptoms, often leading to misdiagnoses. Traditional diagnostic methods rely heavily on clinical expertise and are limited by subjectivity and accessibility, necessitating more advanced and accessible diagnostic tools. Artificial intelligence (AI) and deep learning offer a promising solution for more accurate and efficient diagnosis.MethodsThe research employs a modified Xception model incorporating ReLU activation, dense layers, global average pooling, regularization and dropout layers. This deep learning approach is evaluated against existing models like VGG19, Inception, ResNet, and DenseNet for its efficacy in accurately diagnosing various hair and scalp disorders.ResultsThe model achieved a 92% accuracy rate, significantly outperforming the comparative models, with accuracies ranging from 50% to 80%. Explainable AI techniques like Gradient‐weighted Class Activation Mapping (Grad‐CAM) and Saliency Map provided deeper insights into the model's decision‐making process.ConclusionThis study emphasizes the potential of AI in dermatology, particularly in accurately diagnosing hair and scalp disorders. The superior accuracy and interpretability of the model represents a significant advancement in dermatological diagnostics, promising more reliable and accessible diagnostic methods.

show abstract