An improved hair removal algorithm for dermoscopy images

被引:2
作者
Barin, Sezin [1 ]
Gueraksin, Guer Emre [2 ]
机构
[1] Afyon Kocatepe Univ, Engn Fac, Biomed Engn Dept, Afyonkarahisar, Turkiye
[2] Afyon Kocatepe Univ, Engn Fac, Comp Engn Dept, Afyonkarahisar, Turkiye
关键词
Image processing; Skin cancer; Hair removal algorithm; Deep learning; SQUAMOUS-CELL CARCINOMA;
D O I
10.1007/s11042-023-15936-3
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Dermoscopy is commonly used for diagnosing skin cancer in its early stages. However, hair structures in dermoscopy images can negatively affect diagnosis. A proposed algorithm based on conventional image processing methods removes hair structures from these images. Removing hair structures is crucial for constructing accurate computer-aided diagnosis systems for skin cancer. To eliminate hair structures from dermoscopy images, a hair removal algorithm based on conventional image processing methods has been proposed in this study. The proposed algorithm was compared to the existing hair removal algorithms in literature and tested on the ISIC2018 dataset using the AlexNet architecture. The effects on computer-aided systems were assessed by training on images with and without hair. Results show that the algorithm performs well in removing hairs compared to previous studies and improves classification performance. Upon comparison with other literature studies, the recommended algorithm has exhibited consistently high performance, usually ranking among the top two performers in the rank analysis. Additionally, the integration of the suggested algorithm has led to improvements in the performance metrics of the AlexNet architecture, with increases of 0.9% in accuracy, 1.4% in sensitivity, 0.6% in specificity, and 1.06 in F1 score. The performance of the suggested algorithm indicates its potential as a practical and effective tool in clinical settings.
引用
收藏
页码:8931 / 8953
页数:23
相关论文
共 46 条
[31]  
Model MA, 2001, CYTOMETRY, V44, P309, DOI 10.1002/1097-0320(20010801)44:4<309::AID-CYTO1122>3.0.CO
[32]  
2-3
[33]   THRESHOLD SELECTION METHOD FROM GRAY-LEVEL HISTOGRAMS [J].
OTSU, N .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1979, 9 (01) :62-66
[34]   Dermoscopic skin lesion image segmentation based on Local Binary Pattern Clustering: Comparative study [J].
Pereira, Pedro M. M. ;
Fonseca-Pinto, Rui ;
Paiva, Rui Pedro ;
Assuncao, Pedro A. A. ;
Tavora, Luis M. N. ;
Thomaz, Lucas A. ;
Faria, Sergio M. M. .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2020, 59
[35]   Hair Removal Combining Saliency, Shape and Color [J].
Ramella, Giuliana .
APPLIED SCIENCES-BASEL, 2021, 11 (01) :1-26
[36]   Flat-field correction technique for digital detectors [J].
Seibert, JA ;
Boone, JM ;
Lindfors, KK .
PHYSICS OF MEDICAL IMAGING, 1998, 3336 :348-354
[37]   Cancer statistics, 2019 [J].
Siegel, Rebecca L. ;
Miller, Kimberly D. ;
Jemal, Ahmedin .
CA-A CANCER JOURNAL FOR CLINICIANS, 2019, 69 (01) :7-34
[38]   State of the art in non-invasive imaging of cutaneous melanoma [J].
Smith, Louise ;
MacNeil, Sheila .
SKIN RESEARCH AND TECHNOLOGY, 2011, 17 (03) :257-269
[39]   Comparison of Image Quality Measurements in Threshold Determination of Most Popular Gradient Based Edge Detection Algorithms Based on Particle Swarm Optimization [J].
Suzme, Nurgul Ozmen ;
Guraksin, Gur Emre .
ARTIFICIAL INTELLIGENCE AND APPLIED MATHEMATICS IN ENGINEERING PROBLEMS, 2020, 43 :171-181
[40]   An effective hair removal algorithm for dermoscopy images [J].
Toossi, Mohammad Taghi Bahreyni ;
Pourreza, Hamid Reza ;
Zare, Hoda ;
Sigari, Mohamad-Hoseyn ;
Layegh, Pouran ;
Azimi, Abbas .
SKIN RESEARCH AND TECHNOLOGY, 2013, 19 (03) :230-235