Biophotonics-Riga最新文献

Deep learning model deploying on embedded skin cancer diagnostic device 在嵌入式皮肤癌诊断设备上部署深度学习模型

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2582108

D. Bļizņuks, E. Cibulska, A. Bondarenko, Y. Chizhov, I. Lihacova

{"title":"Deep learning model deploying on embedded skin cancer diagnostic device","authors":"D. Bļizņuks, E. Cibulska, A. Bondarenko, Y. Chizhov, I. Lihacova","doi":"10.1117/12.2582108","DOIUrl":"https://doi.org/10.1117/12.2582108","url":null,"abstract":"The number of research papers, where neural networks are applied in medical image analysis is growing. There is a proof that Convolutional Neural Networks (CNN) are able to differentiate skin cancer from nevi with greater accuracy than experienced specialists on average (sensitivity 82% and 73% accordingly).1 Team's latest research2 allows achieving even greater accuracy, by using specific narrow-band illumination. Nevertheless, the overall probability of early skin cancer detection depends on the availability of diagnostic tools. If screening tools will be available to a high number of general practices, the chance of disease detection will increase. The previous research3 shows that scalable cloud service is able to process a high number of users. After a certain number of users, the overall cost of the system, including cloud processing expenses and cost of high computational power portable device, might be higher if compared to an on-premises solution, where each device is capable of diagnosing without Internet access. It might be cheaper to equip devices with additional neural processing unit (NPU) and exclude cloud processing. Another option is to make screening available by using the newest smartphones that are equipped with NPU.4 The problem of using the NPU is that they are limited in storage space, accuracy, and features. Therefore, a full-size CNN model should be adapted and minimized to fit in a limited NPU. Research reviews existing CNN optimization methods and proposes the most accurate for skin cancer diagnostics. The paper evaluates CNN prediction losses when the model's elements’ precision is reduced from 32 bits to 8 and rounded to integer values.","PeriodicalId":283327,"journal":{"name":"Biophotonics-Riga","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131571015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Endoscopes for internal organs cancer diagnostics based on television and multispectral methods of image processing 基于电视和多光谱图像处理方法的内部器官内窥镜癌症诊断

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2581738

K. Zaichenko, B. Gurevich

{"title":"Endoscopes for internal organs cancer diagnostics based on television and multispectral methods of image processing","authors":"K. Zaichenko, B. Gurevich","doi":"10.1117/12.2581738","DOIUrl":"https://doi.org/10.1117/12.2581738","url":null,"abstract":"Endoscopes are applied widely for diagnostics of different diseases of internal organs. However, simultaneous transmission of spectral and spatial information by means of even the most perfect endoscopes meets significant obstacles. A new kind of endoscope has been proposed in this paper, in which the image of internal organ is transmitted not only by video camera but also some certain fragments of the image are transmitted by the image transmitter based on fiber optics. This composition provides elimination of the information losses which are connected with three-colored principle of television image transmission. Additional spectral information increases the reliability of diagnoses made on the base of data presented by endoscope. The structural circuit of the proposed endoscope has been considered and discussed. The most common area of practical application of this endoscope is internal organs oncology diagnostics. In order to perform such diagnostics, some preliminary investigations are required because the reflection spectra of human tissues defeated by the cancer cells, are not yet known. Such hybrid endoscope can be used in gastroscopy, bronchoscopy, colonoscopy, laparoscopy, and all other similar areas. The principle of multispectral processing which is used in fiber-optics-based sensors provides obtaining of maximum possible spectral information in addition to high spatial resolution provided by RGB camera.","PeriodicalId":283327,"journal":{"name":"Biophotonics-Riga","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131170247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Challenges of automatic processing of large amount of skin lesion multispectral data 大量皮肤病变多光谱数据自动处理的挑战

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2582049

I. Lihacova, E. Cibulska, A. Lihachev, M. Lange, E. V. Plorina, D. Bļizņuks, A. Derjabo, N. Kiss

{"title":"Challenges of automatic processing of large amount of skin lesion multispectral data","authors":"I. Lihacova, E. Cibulska, A. Lihachev, M. Lange, E. V. Plorina, D. Bļizņuks, A. Derjabo, N. Kiss","doi":"10.1117/12.2582049","DOIUrl":"https://doi.org/10.1117/12.2582049","url":null,"abstract":"This work will describe the challenges involved in setting up automatic processing for a large differentiated data set. In this study, a multispectral (skin diffuse reflection images using 526nm (green), 663nm (red), and 964nm (infrared) illumination and autofluorescence (AF) image using 405 nm excitation) data set with 756 lesions (3024 images) was processed. Previously, using MATLAB software, finding markers, correctly segmenting images with dark edges and image alignment were the main causes of the problems in automatic data processing. To improve automatic processing and eliminate the use of licensed software, the latter was substituted with the open source Python environment. For more precise segmentation of skin markers and skin lesions, as well for image alignment, the processing of artificial neural networks was utilized. The resulting processing method solves most of the issues of the MATLAB script. However, for even more accurate results, it is necessary to provide more accurate ground-truth segmentation masks and generate more input data to increase the training image database by using data augmentation.","PeriodicalId":283327,"journal":{"name":"Biophotonics-Riga","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116797566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Optimization of information presentation process by multispectral processing systems of biological objects images 生物目标图像多光谱处理系统的信息呈现过程优化

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2581743

K. Zaichenko, B. Gurevich

引用次数: 0

Objective noninvasive monitoring of laser tattoo removal in a human volunteer: a proof of principle study 目的:无创监测激光纹身去除在人类志愿者:一个证明的原则研究

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2582137

N. Verdel, B. Majaron

{"title":"Objective noninvasive monitoring of laser tattoo removal in a human volunteer: a proof of principle study","authors":"N. Verdel, B. Majaron","doi":"10.1117/12.2582137","DOIUrl":"https://doi.org/10.1117/12.2582137","url":null,"abstract":"We explore the potential for noninvasive monitoring of laser tattoo removal treatment by adapting a recently introduced methodology for quantitative assessment of structure and composition of human skin in vivo.1 The approach combines diffuse reflectance spectroscopy in visible part of the spectrum with pulsed photothermal radiometry, involving timeresolved measurements of mid-infrared emission after irradiation with a millisecond laser pulse. The experimental data are fitted simultaneously with the respective predictions of a dedicated numerical model of light and heat transport in tattooed skin. For this purpose we apply a three-layer optical model of skin, consisting of epidermis, upper dermis, and lower dermis which includes the tattoo ink. This proof of principle study involved one healthy volunteer undergoing tattoo removal treatment. One half of the tattoo was treated with 5 ns pulses from a commercial Nd:YAG laser (StarWalker® MaQX, Fotona) at radiant exposure of 3 J/cm2, and the other half with much shorter, \"picosecond\" pulses at the same wavelength and 1.3 J/cm2. Measurements were performed before and 8 weeks after the first treatment session, as well as 20 weeks after the second treatment. The results show a significant reduction of the ink content and an increase of the subsurface depth of the tattoo layer over the course of treatment with both lasers, in agreement with gradual fading of the tattoo.","PeriodicalId":283327,"journal":{"name":"Biophotonics-Riga","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130435647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Study of As and Tl high-frequency electrodeless lamps for Zeeman absorption spectroscopy 用于塞曼吸收光谱的As和Tl高频无极灯研究

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2580856

N. Zorina, A. Skudra, G. Revalde, A. Abola

引用次数: 1

Photoplethysmographic waves and their detailed pulse interval distribution analysis on Poincare plots before and after the sauna exposures 桑拿前后的光容积脉搏波及其脉冲间隔在庞加莱图上的详细分布分析

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2582204

M. Huotari, Kari Määttä, J. Röning

引用次数: 0

Improved biomedical imaging over a wide spectral range from UV to THz towards multimodality 改进生物医学成像在从紫外到太赫兹向多模态的宽光谱范围

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2584999

L. M. Oliveira, K. Zaytsev, V. Tuchin

引用次数: 6

Selection of erythema index and image sampling method for the objective erythema estimation in dogs with atopic dermatitis 特应性皮炎犬红斑指数的选择及图像采样方法的客观估计

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2581997

B. Cugmas, Daira Viskere, E. Struc, J. Spigulis

{"title":"Selection of erythema index and image sampling method for the objective erythema estimation in dogs with atopic dermatitis","authors":"B. Cugmas, Daira Viskere, E. Struc, J. Spigulis","doi":"10.1117/12.2581997","DOIUrl":"https://doi.org/10.1117/12.2581997","url":null,"abstract":"Canine atopic dermatitis (CAD) is a common inflammatory and pruritic skin disease associated with allergy to exogenous allergens. The regular monitoring of skin lesions is essential to execute the anti-allergic therapy successfully. Erythema is one of the most important CAD-related lesions since it represents acute skin inflammation. Previously, we studied two optical systems (i.e., multispectral and dermatoscopic devices), which could objectively estimate erythema severity. However, we did not investigate, which image sampling method for selecting erythema-representing pixels and erythema index (EI) are correlated with the visual erythema assessment the most. In this paper, we tested three image sampling methods and four EIs for erythema severity estimation in 43 dogs. We discovered that all studied sampling methods and EIs were strongly correlated (r> 0.58) with the visual CADESI-4-based erythema severity assessment. However, the highest average Spearman’s correlations coefficient r of 0.77 was achieved when the average pixel value from the two small squared image sections without the hair and pigment was considered. On the other hand, EI, which was calculated from all three RGB values, achieved the highest r of 0.78. In this study, we identified a reliable image sampling method and erythema index (EI), which are well correlated with the visual erythema estimation.","PeriodicalId":283327,"journal":{"name":"Biophotonics-Riga","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128508363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Remote photoplethysmography device with adaptive illumination for skin microcirculation assessment 用于皮肤微循环评估的自适应照明远程光容积脉搏仪

Biophotonics-Riga Pub Date : 2020-10-28 DOI: 10.1117/12.2581933

E. Kviesis-Kipge, U. Rubins

引用次数: 1