• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.436-442
• /
• 2017

A novel method of Skin lesion segmentation based on the combination of Texture and Neural Network is proposed in this paper. This paper combines the textures of different pixels in the skin images in order to increase the performance of lesion segmentation. For segmenting skin lesions, a two-step process is done. First, automatic border detection is performed to separate the lesion from the background skin. This begins by identifying the features that represent the lesion border clearly by the process of Texture analysis. In the second step, the obtained features are given as input towards the Recurrent Echo state neural networks in order to obtain the segmented skin lesion region. The proposed algorithm is trained and tested for 862 skin lesion images in order to evaluate the accuracy of segmentation. Overall accuracy of the proposed method is compared with existing algorithms. An average accuracy of 98.8% for segmenting skin lesion images has been obtained.

• Journal of Korean Neurosurgical Society
• /
• v.54 no.3
• /
• pp.225-231
• /
• 2013

Objective : Spinal dysraphism defects span wide spectrum. Wound dehiscence is a common postoperative complication, and is a challenge in the current management of cerebrospinal fluid (CSF) leaks and wound healing. The purpose of this study is to evaluate the risks of CSF-related morbidity in the surgical treatment of spinal dysraphism. Methods : Ten patients with spinal dysraphism were included in this retrospective study. The median age of the cohort was 4.8 months. To assess the risk of CSF morbidity, we measured the skin lesion area and the percentage of the skin lesion area relative to the back surface for each patient. We then analyzed the relationship between morbidity and the measured skin lesion area or related factors. Results : The overall median skin lesion area was 36.2 $cm^2$ (n=10). The percentage of the skin lesion area relative to the back surface ranged from 0.6% to 18.1%. During surgical reconstruction, 4 patients required subsequent operations to repair CSF morbidity. The comparison of the mean area of skin lesions between the CSF morbidity group and the non-CSF morbidity group was statistically significant (average volume skin lesion of $64.4{\pm}32.5cm^2$ versus $27.7{\pm}27.8cm^2$, p<0.05). CSF morbidity tended to occur either when the skin lesion area was up to 44.2 $cm^2$ or there was preexisting fibrosis before revision with an accompanying broad-based dural defect. Conclusion : Measuring the lesion area, including the skin, dura, and related surgical parameters, offers useful information for predicting wound challenges and selecting appropriate reconstructive surgery methods.

• Archives of Craniofacial Surgery
• /
• v.17 no.2
• /
• pp.86-89
• /
• 2016

Despite the fact that benign skin lesions can undergo malignant transformation, the necessity and timing of the surgical resection have yet to be established. In this study, we analyse three cases of benign-appearing skin lesions, which were found to be carcinomatous on histologic examination and review the literature regarding the importance of prophylactic removal of benign-appearing skin lesion. The first and second cases were female patients wishing for cosmetic surgery. The first patient had a benign-appearing lesion on dorsum nasi, and the second patient had an inconspicuous lesion right along the right nasolabial fold. The third patient was a middle-aged male with a pigmented lesion on the left cheek, who presented to the clinic only after having met the operating surgeon through an acquaintance outside the hospital setting. All of the lesions were suspected to be of benign nature and were excised for cosmesis only. However, histologic examination of these lesions showed that the first two tumors were basal cell carcinoma with the last tumor being squamouse cell carcinoma. Thus, it is considered that removal of benign like skin lesion will result in good prognosis of patients scheduled to undergo other surgery.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.533-540
• /
• 2022

Specialists diagnose skin cancer using a dermatoscopy to detect skin cancer as early as possible, but it is difficult to determine accurate skin lesions because skin lesions have various shapes. Recently, the skin lesion segmentation method using deep learning, which has shown high performance, has a problem in segmenting skin lesions because the boundary between healthy skin and skin lesions is not clear. To solve these issues, the proposed method constructs a transformer block to effectively segment the skin lesion, and constructs an edge decoder for each layer of the network to segment the skin lesion in detail. Experiment results have shown that the proposed method achieves a performance improvement of 0.041 ~ 0.071 for Dic Coefficient and 0.062 ~ 0.112 for Jaccard Index, compared with the previous method.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.31 no.1
• /
• pp.59-64
• /
• 2017

Scutellaria baicalensis Georgi is one of major herbs used to treat patients with skin diseases diagnosed by wind-heat syndrome. This study was designed to investigate the effects of Scutellaria baicalensis Extract (SBE) on skin lesion of Contact dermatitis (CD) in mice. We investigated the effects of SBE on skin thickness, skin lesions, erythema index and melanin index in vivo. The effects on body weights and spleen/body weight ratio were also investigated in mice with CD induced by topical application of 1-Fluoro-2,4-dinitrofluorobenzene (DNFB). In our results, topical application of SBE lowered skin thickness significantly. In addition, SBE ameliorated skin lesions such as erythema, exudate and petechia in mice with CD. SBE also inhibited erythema index elevated by DNFB significantly. finally, SBE did not affect body weight and spleen/body weight ratio. In conclusion, these data imply that SBE can ameliorate skin lesion of CD such as erythema, exudate and petechia, and be used to treat CD patients with relative safety.

• Archives of Plastic Surgery
• /
• v.33 no.6
• /
• pp.748-752
• /
• 2006

Purpose:Circular skin lesions between 10 and 35 mm in diameter generate problems often. Direct closure of the lesion risks excessive wound tension or wound dehiscence. Skin grafts heal slowly and often remain unsightly. Traditional skin flaps have a limited role. We treated this circular medium-sized skin lesion(10 - 35 mm sized) by reducing opposed multilobed(ROM) flap. Methods: ROM flap involves a series of semicircular lobes extending both cephalic and caudal from the defect. Direction of the semicircular multilobed flap is set parallel to relaxed skin tension line(RSTL) to minimize scar formation. First semicircle is drawn 60% in diameter of the defect. Second semicircles are drawn at the cephalic and caudal aspects of the original semicircles. These semicircles are 60% in diameter of the first semicircle. Additional semicircles are repeatedly drawn until the tension of skin flaps becomes free. ROM flap has a length-to-base ratio of 0.5 resulting in lower theoretical risk of end flap necrosis than a random pattern flap with a large ratio. The technique involves lobes most distant from the primary defect being transposed in turn closer to the defect. Results: The ROM flap reduces skin tension concerns, lowers the risk of flap necrosis and allows for quicker and more aesthetic healing. Results were generally good and major complications, such as dehiscence, infection, or delayed healing, did not occur. Conclusion: ROM flap repair allows the plastic surgeon an additional option when faced with a circular medium-sized skin lesion.

• Archives of Plastic Surgery
• /
• v.41 no.5
• /
• pp.500-504
• /
• 2014

Background Skin cancer is the most prevalent cancer by organ type and referral accuracy is vital for diagnosis and management. The British Association of Dermatologists (BAD) and literature highlight the importance of accurate skin lesion examination, diagnosis and educationally-relevant studies. Methods We undertook a review of the relevant literature, a national audit of skin lesion description standards and a study of speciality training influences on these descriptions. Questionnaires (n=200), with pictures of a circular and an oval lesion, were distributed to UK dermatology/plastic surgery consultants and speciality trainees (ST), general practitioners (GP), and medical students (MS). The following variables were analysed against a pre-defined 95% inclusion accuracy standard: site, shape, size, skin/colour, and presence of associated scars. Results There were 250 lesion descriptions provided by 125 consultants, STs, GPs, and MSs. Inclusion accuracy was greatest for consultants over STs (80% vs. 68%; P<0.001), GPs (57%) and MSs (46%) (P<0.0001), for STs over GPs (P<0.010) and MSs (P<0.0001) and for GPs over MSs (P<0.010), all falling below audit standard. Size description accuracy sub-analysis according to circular/oval dimensions was as follows: consultants (94%), GPs (80%), STs (73%), MSs (37%), with the most common error implying a quadrilateral shape (66%). Addressing BAD guidelines and published requirements for more empirical performance data to improve teaching methods, we performed a national audit and studied skin lesion descriptions. To improve diagnostic and referral accuracy for patients, healthcare professionals must strive towards accuracy (a circle is not a square). Conclusions We provide supportive evidence that increased speciality training improves this process and propose that greater focus is placed on such training early on during medical training, and maintained throughout clinical practice.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2826-2840
• /
• 2018

Traditional methods based active contours or region merging are powerless in processing images with blurring border or hair occlusion. In this paper, a structure based convolutional neural networks is proposed to solve segmentation of skin lesion image. The structure mainly consists of two networks which are segmentation net and discrimination net. The segmentation net is designed based U-net that used to generate the mask of lesion, while the discrimination net is designed with only convolutional layers that used to determine whether input image is from ground truth labels or generated images. Images were obtained from "Skin Lesion Analysis Toward Melanoma Detection" challenge which was hosted by ISBI 2016 conference. We achieved segmentation average accuracy of 0.97, dice coefficient of 0.94 and Jaccard index of 0.89 which outperform the other existed state-of-the-art segmentation networks, including winner of ISBI 2016 challenge for skin melanoma segmentation.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• Korean Journal of Veterinary Service
• /
• v.17 no.3
• /
• pp.167-173
• /
• 1994

This study were performed to distribution of dermatophytes isolated from pet dogs in Pusan area and pathogenicity of the isolates. During the period from March 1993. to April 1994, 201 pet dogs of house breeding were examined. The result of obtained were summarized as followes； 1. Isolation rate of dermatophytes were 4.7%(7/149) in no lesion and 23.1%(12/52) in lesion of dog's skin. 2. According to breeding conditions, isolation rate of dermatophytes were 1) 3.8% in no lesion and indoor breeding, 2) 16.7% in lesion and indoor breeding, 3) 13.5% no lesion and outdoor breeding, and 4) 37.5% in lesion and outdoor bleeding. 3. Among the 201 Pet dogs, 16 strains of M. cams(84.2%), 1 of M. gypseum(5.3%), and 2 of T. mentagrophytes (10.5%) were isolated. 4. For Pathogenicity test, one strain of each M. canis, M, gypseum, T. mentagrophytes isolated from skin lesions were inoculated to the skin of the posterior back of guinea pigs. All of dermatophytes tested were induced skin lesions. Among them, M. cams and T. mentagrophytes were more virulent than M. gypseum.