AbstractAnaemia, a decrease in total concentration of haemoglobin (Hb) in blood, affects substantial percentage of the population worldwide. Currently, the gold standard for determining the Hb level is the invasive analysis of venous blood. Yet, more and more research groups demonstrate the possibility of non-invasive Hb assessment using white light imaging of tissue sites where Hb is the main chromophore, in particular, fingernails.

摘要贫血是血液中血红蛋白（Hb）总浓度的降低，影响全球相当大比例的人口。目前，确定Hb水平的金标准是静脉血的侵入性分析。然而，越来越多的研究小组证明了使用白光成像对Hb是主要发色团的组织部位，特别是指甲进行非侵入性Hb评估的可能性。

Despite the promising declarations, non-invasive Hb assessment via RGB-imaging is still poorly used in practice. The main reason is the difficulty in establishing the true accuracy of the methods presented in different works since they are tested on private datasets collected under different experimental conditions.

尽管有令人鼓舞的声明，但通过RGB成像进行的非侵入性Hb评估在实践中仍然很少使用。主要原因是难以确定不同作品中提出的方法的真实准确性，因为它们是在不同实验条件下收集的私有数据集上进行测试的。

Here we present an open dataset containing RGB images of skin and fingernails for patients with a known level of Hb, thus providing a single benchmark for researchers and engineers in the field, aimed at fostering translation of non-invasive imaging methods to the bedside..

在这里，我们提供了一个开放的数据集，其中包含已知Hb水平患者的皮肤和指甲RGB图像，从而为该领域的研究人员和工程师提供了一个单一的基准，旨在促进非侵入性成像方法向床边的转化。。

Background & SummaryOverview of data collection goalsHaemoglobin (Hb), the main protein in the human blood, is responsible for oxygen transport in the organism. The total Hb concentration in blood (hereinafter referred to as Hb level) is a significant clinical parameter. Anaemia, i.e. a decrease of the Hb level, affects approximately 29% of non-pregnant women, 38% of pregnant women and 43% of children1,2,3.

背景与总结数据收集目标概述血红蛋白（Hb）是人体血液中的主要蛋白质，负责生物体内的氧气运输。血液中的总Hb浓度（以下称为Hb水平）是一个重要的临床参数。贫血，即Hb水平下降，影响约29%的非孕妇，38%的孕妇和43%的儿童1,2,3。

Undiagnosed or improperly treated anaemia can lead to adverse outcomes for the newborns, increased risk of complications, and reduce quality of life4,5.The gold standard for Hb assessment is the invasive venous blood sampling followed by standard assays6. Such an analysis requires qualified personnel for biomaterial sampling, certified laboratory equipment, and, most important, it is costly, time-consuming, and hurtful for the patient6.

未确诊或治疗不当的贫血可导致新生儿不良后果，并发症风险增加，生活质量降低4,5。血红蛋白评估的金标准是有创静脉采血，然后进行标准检测6。这种分析需要合格的人员进行生物材料取样，认证的实验室设备，最重要的是，它对患者来说是昂贵的，耗时的，并且是有害的6。

Thus, non-invasive methods allowing for immediate and painless determination of the Hb level are of high demand.Since Hb is the dominant chromophore in the human organism, most of the suggested non-invasive methods for its assessment are based on the estimation of light attenuation in various tissues sites.

因此，允许立即无痛测定Hb水平的非侵入性方法具有很高的需求。由于Hb是人类生物体中的主要发色团，因此大多数建议的非侵入性评估方法都是基于对各种组织部位光衰减的估计。

The measured light attenuation is then calibrated according to the Hb level obtained using the reference (invasive) techniques. Generally, to achieve high accuracy of non-invasive Hb assessment, imaging is performed for the tissue sites where the impact of melanin, the skin pigment responsible for its brown colour, is negligible.

然后根据使用参考（侵入性）技术获得的Hb水平校准测量的光衰减。通常，为了实现非侵入性Hb评估的高精度，对黑色素（负责其棕色的皮肤色素）的影响可忽略不计的组织部位进行成像。

The state-of-art results in non-invasive Hb assessment are summarized in Table 1.Table 1 The performance of non-invasive methods for the Hb level assessment.Full size tableThe first class of works report on the possibility of non-invasive Hb determination from the RGB images of the eye palpebral or bulbar .

表1总结了非侵入性Hb评估的最新结果。表1 Hb水平评估的非侵入性方法的性能。全尺寸表第一类工作报告了从眼睑或延髓的RGB图像进行非侵入性Hb测定的可能性。

PATIENT_ID – identification number of the patient in the dataset;

PATIENT\u ID–数据集中患者的识别号；

MEASUREMENT_DATE – hashed string corresponding to the measurement date;

MEASUREMENT\u DATE–对应于测量日期的散列字符串；

HB_LEVEL_GperL – the patient’s Hb level, determined using a certified haematology analyzer, in g/L.

HB\u LEVEL\u GperL–患者的HB水平，使用经认证的血液分析仪测定，单位为克/升。

NAIL_BOUNDING_BOXES– [[top1, left1, bottom1, right1], …, [top3, left3, bottom3, right3]] a list of lists of four integer values representing the coordinates of the upper left corner and lower right corner of the rectangle framing the patient’s nails in the image;

NAIL\u BOUNDING\u Box–[[top1，left1，bottom1，right1]，…，[top3，left3，bottom3，right3]]四个整数值的列表，表示图像中构成患者指甲的矩形左上角和右下角的坐标；

SKIN_BOUNDING_BOXES – [[top1, left1, bottom1, right1], …, [top3, left3, bottom3, right3]] a list of lists of four integer values representing the coordinates of the upper left corner and lower right corner of the rectangle framing the patient’s skin areas.

SKIN\u BOUNDING\u Box–[[top1，left1，bottom1，right1]，…，[top3，left3，bottom3，right3]]四个整数值的列表，表示构成患者皮肤区域的矩形左上角和右下角的坐标。

For the lists of coordinates of nails and skin areas of the finger, the following conventions are applicable. Index 1 always corresponds to the index finger, index 2 to the middle finger, index 3 to the ring finger of the measured hand (Fig. 1b).The ‘photo’ folder contains photographs taken for each patient.

对于指甲和手指皮肤区域的坐标列表，以下约定适用。食指1始终对应于食指，食指2对应于中指，食指3对应于被测手的无名指（图1b）。“照片”文件夹包含为每位患者拍摄的照片。

The files have the format ‘photo/{PATIENT_ID}.jpg’, for example, the file ‘photo/11.jpg’ corresponds to a patient with PATIENT_ID = 11 presented in ‘metadata.csv’ table.Technical ValidationBlood collection and reference method for determining Hb levelQuality of haemoglobin reference values is guaranteed by adhering to the standard protocols and guidelines for clinical blood sampling carried out by qualified medical personnel27,28.

。技术验证确定血红蛋白水平的血液采集和参考方法血红蛋白参考值的质量是通过遵守由合格医务人员进行的临床血液采样的标准方案和指南来保证的27,28。

Determination of the Hb level in venous blood was carried out using a certified haematological analyser in the ISO 15189:2012 standardized clinical diagnostic laboratory of the City Clinical Hospital No. 67 (Moscow, Russia).Assessment of the image qualityImaging was performed under fixed illumination conditions in an isolated box excluding external light.

在67号城市临床医院（俄罗斯莫斯科）的ISO 15189:2012标准化临床诊断实验室中，使用经认证的血液分析仪测定静脉血中的Hb水平。图像质量的评估成像是在固定照明条件下在不包括外部光线的隔离盒中进行的。

The exposure time and white balance on the camera were chosen so that the intensity of the reflected light in the areas corresponding to the nail and skin areas of the hand fell into the dynamic range of the camera, i.e., areas of interest corresponding to the nail plate and skin did not exhibit intensity values close to 255 or to zero.

选择相机上的曝光时间和白平衡，使得与指甲和手部皮肤区域相对应的区域中的反射光强度落入相机的动态范围，即，与指甲板和皮肤相对应的感兴趣区域没有显示出接近255或零的强度值。

The intensity histograms for all areas of interest corresponding to the nail and skin are shown in Fig. 3a,b.Fig. 3Intensity distributions in R, G and B channels of segmented regions of the nails (a) and finger skin (b) calculated for the whole dataset.Full size imageIllumination stabilityAdditionally, to control for illumination stability, the average int.

对应于指甲和皮肤的所有感兴趣区域的强度直方图如图3a，b所示。图3为整个数据集计算的指甲（a）和手指皮肤（b）分段区域的R，G和b通道中的强度分布。全尺寸图像照明稳定性另外，为了控制照明稳定性，平均int。

Code availability

代码可用性

All code for processing and building the model described in the Usage Notes section is available at https://github.com/biophotonics-msu/photo-haemoglobin.

有关处理和构建使用说明部分中描述的模型的所有代码，请访问https://github.com/biophotonics-msu/photo-haemoglobin.

ReferencesScott, S. P., Chen-Edinboro, L. P., Caulfield, L. E. & Murray-Kolb, L. E. The Impact of Anemia on Child Mortality: an updated review. Nutrients 6, 5915–5932 (2014).Article

参考文献Scott，S.P.，Chen Edinboro，L.P.，Caulfield，L.E。和Murray Kolb，L.E。贫血对儿童死亡率的影响：最新评论。营养素65915-5932（2014）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Stevens, G. A. et al. Global, regional, and national trends in haemoglobin concentration and prevalence of total and severe anaemia in children and pregnant and non-pregnant women for 1995–2011: a systematic analysis of population-representative data. The Lancet Global Health 1, e16–e25 (2013).Article .

Stevens，G.A.等人，《1995-2011年儿童、孕妇和非孕妇血红蛋白浓度和总贫血和严重贫血患病率的全球、区域和国家趋势：人口代表性数据的系统分析》。《柳叶刀》全球健康1，e16-e25（2013）。文章。

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Young, M. F. et al. Non-invasive hemoglobin measurement devices require refinement to match diagnostic performance with their high level of usability and acceptability. PLos One 16, e0254629 (2021).Article

。PLos One 16，e0254629（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Goonewardene, M., Shehata, M. & Hamad, A. Anaemia in pregnancy. Best practice & research Clin. obstetrics & gynaecology 26, 3–24 (2012).Article

Goonewardene，M.，Shehata，M。＆Hamad，A。妊娠期贫血。最佳实践与研究临床。妇产科26,3-24（2012）。文章

Google Scholar

谷歌学者

Haas, J. D. & Brownlie, T. Iron Deficiency and Reduced Work Capacity: A Critical Review of the Research to Determine a Causal Relationship. The J. nutrition 131, 676S–690S (2001).Article

Haas，J.D.＆Brownlie，T。缺铁和工作能力下降：对研究的批判性回顾，以确定因果关系。《营养学杂志》131676S-690S（2001）。文章

CAS

中科院

Google Scholar

谷歌学者

Karakochuk, C. D. et al. Measurement and interpretation of hemoglobin concentration in clinical and field settings: a narrative review. Annals of the new York Acad. Sci. 1450, 126–146 (2019).Article

Karakochuk，C.D.等人。临床和现场环境中血红蛋白浓度的测量和解释：叙述性综述。纽约Acad年鉴。科学。1450126-146（2019）。文章

ADS

广告

Google Scholar

谷歌学者

Suner, S. et al. Prediction of anemia and estimation of hemoglobin concentration using a smartphone camera. PLoS One 16, e0253495 (2021).Article

Suner，S.等人。使用智能手机摄像头预测贫血和估计血红蛋白浓度。PLoS One 16，e0253495（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Appiahene, P. et al. Conjunctival pallor dataset and benchmark for anemia detection in children. Medicine Nov. Technol. and Devices 18, 100244 (2023).Article

Appiahene，P。等人。结膜苍白数据集和儿童贫血检测基准。医学11月技术。和设备18100244（2023）。文章

Google Scholar

谷歌学者

Chen, Y., Zhong, K., Zhu, Y. & Sun, Q. Two-stage hemoglobin prediction based on prior causality. Front. in public health 10, 1079389 (2022).Article

Chen，Y.，Zhong，K.，Zhu，Y。＆Sun，Q。基于先验因果关系的两阶段血红蛋白预测。正面。公共卫生101079389（2022）。文章

Google Scholar

谷歌学者

Dimauro, G., Camporeale, M. G., Dipalma, A., Guarini, A. & Maglietta, R. Anaemia detection based on sclera and blood vessel colour estimation. Biomed. Signal Process. Control 81, 104489 (2023).Article

Dimauro，G.，Camporeale，M.G.，Dipalma，A.，Guarini，A。＆Maglietta，R。基于巩膜和血管颜色估计的贫血检测。生物医学。信号处理。控制81104489（2023）。文章

Google Scholar

谷歌学者

Suner, S., McMurdy, J., Jay, G. & Crawford, G. Digital imaging, spectroscopy, and liquid crystals in a hand-held, non-invasive device to determine hemoglobin concentration. J. Soc. for Inf. Displ. 15, 399–407 (2007).Article

Suner，S.，McMurdy，J.，Jay，G。＆Crawford，G。手持式非侵入性设备中的数字成像，光谱和液晶，以确定血红蛋白浓度。J、 信息显示Soc。15399-407（2007）。文章

CAS

中科院

Google Scholar

谷歌学者

Dimauro, G. et al. An intelligent non-invasive system for automated diagnosis of anemia exploiting a novel dataset. Artif.l Intell. Medicine 136, 102477 (2023).Article

Dimauro，G.等人。一种利用新型数据集自动诊断贫血的智能非侵入性系统。人工智能。医学136102477（2023）。文章

Google Scholar

谷歌学者

Collings, S. et al. Non-Invasive Detection of Anaemia Using Digital Photographs of the Conjunctiva. PLoS One 11, e0153286 (2016).Article

Collings，S.等人。使用结膜数码照片无创检测贫血。PLoS One 11，e0153286（2016）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Park, S. M. et al. mHealth spectroscopy of blood hemoglobin with spectral super-resolution. Optica 7, 563–573 (2020).Article

Park，S.M.等人。具有光谱超分辨率的血液血红蛋白的mHealth光谱。Optica 7563–573（2020）。文章

ADS

广告

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Mitani, A. et al. Detection of anaemia from retinal fundus images via deeplearning. Nat. biomedical engineering 4, 18–27 (2020).Article

。Nat.生物医学工程4，18-27（2020）。文章

Google Scholar

谷歌学者

Zhao, X. et al. Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images. Front. Cell Dev. Biol. 10 (2022).Babenko, B. et al. A deep learning model for novel systemic biomarkers in photographs of the external eye: a retrospective study.

赵，X。等。基于深度学习的血红蛋白浓度预测和使用超宽视野眼底图像进行贫血筛查。正面。细胞开发生物学。10（2022年）。Babenko，B.等人，《外眼照片中新型系统生物标志物的深度学习模型：回顾性研究》。

The Lancet Digit. Heal. 5, e257–e264 (2023).Article .

柳叶刀数字。治愈。5，e257–e264（2023）。文章。

CAS

中科院

Google Scholar

谷歌学者

Causey, M. W. et al. Validation of noninvasive hemoglobin measurements using the Masimo Radical-7 SpHb Station. The Am. journal surgery 201, 592–598 (2011).Article

Causey，M.W.等人。使用Masimo Radical-7 SpHb站验证无创血红蛋白测量。《美国外科杂志》201592-598（2011）。文章

CAS

中科院

Google Scholar

谷歌学者

Honnef, G. et al. Evaluation of the usefulness of non-invasive serum haemoglobin measurement in a perioperative setting in a prospective observational study. Sci. Reports 12, 9065 (2022).ADS

Honnef，G.等人在一项前瞻性观察性研究中评估围手术期无创血清血红蛋白测量的有用性。科学。报告129065（2022）。广告

CAS

中科院

Google Scholar

谷歌学者

Shamah Levy, T. et al. Validation of Masimo Pronto 7 and HemoCue 201 for hemoglobin determination in children from 1 to 5 years of age. PloS one 12, e0170990 (2017).Article

Shamah Levy，T.等人验证Masimo Pronto 7和HemoCue 201用于1至5岁儿童血红蛋白测定。PloS one 12，e0170990（2017）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Shah, N., Osea, E. A. & Martinez, G. J. Accuracy of noninvasive hemoglobin and invasive point-of-care hemoglobin testing compared with a laboratory analyzer. Int. journal of laboratory hematology 36, 56–61 (2014).Article

Shah，N.，Osea，E.A。和Martinez，G.J。与实验室分析仪相比，无创血红蛋白和有创即时血红蛋白检测的准确性。Int.《实验室血液学杂志》36,56-61（2014）。文章

CAS

中科院

Google Scholar

谷歌学者

Hornedo-González, K. D. et al. Non-invasive hemoglobin estimation for preoperative anemia screening. Transfusion 63, 315–322 (2023).Article

Hornedo-González，K.D.等人。术前贫血筛查的无创血红蛋白估计。输血63315-322（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Baulig, W., Seifert, B., Spahn, D. R. & Theusinger, O. M. Accuracy of non-invasive continuous total hemoglobin measurement by Pulse CO-Oximetry in severe traumatized and surgical bleeding patients. J. clinical monitoring computing 31, 177–185 (2017).Article

Baulig，W.，Seifert，B.，Spahn，D.R。＆Theusinger，O.M。通过脉冲CO血氧仪在严重创伤和手术出血患者中无创连续总血红蛋白测量的准确性。J、 临床监测计算31177-185（2017）。文章

Google Scholar

谷歌学者

Yang, S. et al. Trends of Hemoglobin Oximetry: Do They Help Predict Blood Transfusion During Trauma Patient Resuscitation? Anesth. & Analg. 122 (2016).R G. Mannino et al. Clinical and real-world evaluation of a “fingernail selfie” smartphone app for non-invasive, individually-personalized estimation of blood hemoglobin levels.

Yang，S.等人。血红蛋白血氧仪的趋势：它们是否有助于预测创伤患者复苏期间的输血？麻醉和分析。122（2016）。R G.Mannino等人，“指甲自拍”智能手机应用程序的临床和现实评估，用于无创，个性化估计血红蛋白水平。

medRxiv 2022-12 (2022).Wu, Y., Tanaka, T. & Akimoto, M. Utilization of individual typology angle (ITA) and hue angle in the measurement of skin color on images. Bioimages 28, 1–8 (2020)..

medRxiv 2022-12（2022）。Wu，Y.，Tanaka，T。＆Akimoto，M。利用个体类型学角度（ITA）和色调角度测量图像上的肤色。生物图像28,1-8（2020）。。

Google Scholar

谷歌学者

Clinical and Laboratory Standards Institute. Collection of diagnostic venous blood specimens. (Clinical and Laboratory Standards Institute 2017).Lima-Oliveira, G., Lippi, G., Salvagno, G. L., Picheth, G. & Guidi, G. C. Laboratory diagnostics and quality of blood collection. J. medical biochemistry 34, 288 (2015).Article .

临床和实验室标准研究所。收集诊断性静脉血标本。。Lima Oliveira，G.，Lippi，G.，Salvagno，G.L.，Picheth，G。＆Guidi，G.C。实验室诊断和血液采集质量。J、 医学生物化学34288（2015）。文章。

Google Scholar

谷歌学者

Yakimov, B. et al Dataset of human skin and fingernails images for non-invasive haemoglobin level assessment. figshare https://doi.org/10.6084/m9.figshare.c.6760179 (2024).Hrynaszkiewicz, I., Norton, M. L., Vickers, A. J. & Altman, D. G. Preparing raw clinical data for publication: guidance for journal editors, authors, and peer reviewers.

Yakimov，B。等人用于非侵入性血红蛋白水平评估的人类皮肤和指甲图像数据集。figshare公司https://doi.org/10.6084/m9.figshare.c.6760179（2024年）。Hrynaszkiewicz，I.，Norton，M.L.，Vickers，A.J。＆Altman，D.G。准备原始临床数据以供出版：期刊编辑，作者和同行评论者指南。

Bmj 340 (2010).Hernandez-Andres, J., Lee, R. L. & Romero, J. Calculating correlated color temperatures across the entire gamut of daylight and skylight chromaticities. Appl. optics 38, 5703–5709 (1999).Article .

Bmj 340（2010）。Hernandez-Andres，J.，Lee，R.L。和Romero，J。计算日光和天光色度整个色域的相关色温。应用。光学385703–5709（1999）。文章。

ADS

广告

CAS

中科院

Google Scholar

谷歌学者

Schindelin, J. et al. Fiji: an open-source platform for biological-image analysis. Nat. Methods 9, 676–682 (2012).Article

Schindelin，J。等人。斐济：生物图像分析的开源平台。《自然方法》9676-682（2012）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Zou, H. & Hastie, T. Regularization and Variable Selection Via the Elastic Net. J. Royal Stat. Soc. Ser. B: Stat. Methodol. 67, 301–320 (2005).Article

Zou，H。＆Hastie，T。通过弹性网进行正则化和变量选择。J、 皇家统计局。B： 统计方法。67301-320（2005）。文章

MathSciNet

MathSciNet

Google Scholar

谷歌学者

Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. machine learning research 12, 2825 (2011).MathSciNet

Pedregosa，F.等人，《Scikit learn：Python中的机器学习》。J、 机器学习研究122825（2011）。数学网

Google Scholar

谷歌学者

Mannino, R. G. et al. Smartphone app for non-invasive detection of anemia using only patient-sourced photos. Nat. Communications 9, 4924 (2018).Article

Mannino，R.G.等人。智能手机应用程序，仅使用患者来源的照片进行无创性贫血检测。《自然通讯》94924（2018）。文章

ADS

广告

Google Scholar

谷歌学者

Yılmaz, H., Kızılateş, B. S., Shaaban, F. & Karataş, Z. R. A novel combined deep learning methodology to non-invasively estimate hemoglobin levels in blood with high accuracy. Med. Eng.g & Phys. 108, 103891 (2022).Article

Yılmaz，H.，Kızılateş，B.S.，Shaaban，F。＆Karataş，z.R。一种新颖的深度学习方法，可以无创地高精度估计血液中的血红蛋白水平。医学工程与物理。108103891（2022）。文章

Google Scholar

谷歌学者

Das, S. et al. Smartphone-based non-invasive haemoglobin level estimation by analyzing nail pallor. Biomed.l Signal Process. and Control 85, 104959 (2023).Article

Das，S.等人。通过分析指甲苍白，基于智能手机的无创血红蛋白水平估计。生物医学l信号过程。和控制85104959（2023）。文章

Google Scholar

谷歌学者

Das, S., Kesarwani, A., Kisku, D. R. & Dalui, M. Non-invasive Haemoglobin Estimation by Observing Nail Color: A PCA based Approach. In 2022 IEEE 6th Conference on Information and Communication Technology (CICT), 1–5 (2022).Ahmed, S. & Habib, M. A. Automatic Region of Interest Extraction from Finger Nail Images for Measuring Blood Hemoglobin Level.

Das，S.，Kesarwani，A.，Kisku，D.R。＆Dalui，M。通过观察指甲颜色进行无创血红蛋白估计：基于PCA的方法。2022年IEEE第六届信息和通信技术会议（CICT），1-5（2022）。Ahmed，S.＆Habib，M.A。从指甲图像中自动提取感兴趣区域以测量血液血红蛋白水平。

In 2021 International Conference on Electronics, Communications and Information Technology (ICECIT), 1–4 (IEEE, 2021).Asare, J. W., Appiahene, P., Donkoh, E. T. & Dimauro, G. Iron deficiency anemia detection using machine learning models: A comparative study of fingernails, palm and conjunctiva of the eye images.

2021年国际电子、通信和信息技术会议（ICECIT），1-4（IEEE，2021）。Asare，J.W.，Appiahene，P.，Donkoh，E.T。和Dimauro，G。使用机器学习模型检测缺铁性贫血：指甲，手掌和眼图像结膜的比较研究。

Eng. Reports 5, e12667 (2023).Article .

工程报告5，e12667（2023）。文章。

CAS

中科院

Google Scholar

谷歌学者

Download referencesAcknowledgementsThis research was funded by grant from the Moscow government (research project № 2212-19/22). The publication of this manuscript was sponsored by the Moscow Center for Innovative Technologies in Healthcare. Research was performed according to Academic leadership program Priority 2030 proposed by Federal State Autonomous Educational Institution of Higher Education I.M.

下载参考文献致谢本研究由莫斯科政府资助（研究项目编号2212-19/22）。这份手稿的出版是由莫斯科医疗保健创新技术中心赞助的。这项研究是根据美国联邦州立自治高等教育学院（I.M.）提出的学术领导力计划优先权2030进行的。

Sechenov First Moscow State Medical University of the Ministry of Health of the Russian Federation (Sechenov University) and Development Program of the Interdisciplinary Scientific and Educational Schools of Lomonosov Moscow State University “Photonic and Quantum Technologies. Digital medicine”.Author informationAuthors and AffiliationsFaculty of Physics, M.V.Lomonosov Moscow State University, 1-2 Leninskie Gory, 119234, Moscow, RussiaBoris Yakimov, Kirill Buiankin, Ilia Bardadin, Oleg Pavlov & Evgeny ShirshinLaboratory of Clinical Biophotonics, Biomedical Science and Technology Park, Sechenov First Moscow State Medical University, Trubetskaya 8, Moscow, 119048, RussiaBoris Yakimov, Georgy Denisenko & Evgeny ShirshinMoscow State Budgetary Institution of Healthcare “L.A.

俄罗斯联邦卫生部第一莫斯科国立医科大学（塞切诺夫大学）和洛莫诺索夫莫斯科国立大学跨学科科学和教育学院的发展计划“光子和量子技术。数字医学”。作者信息作者和附属机构M.V.Lomonosov莫斯科国立大学物理学院，1-2 Leninskie Gory，119234，莫斯科，RussiaBoris Yakimov，Kirill Buiankin，Ilia Bardadin，Oleg Pavlov＆Evgeny Shirshin临床生物光子学实验室，生物医学科学与技术园，Sechenov第一莫斯科国立医科大学，特鲁贝茨卡亚8，莫斯科，119048，RussiaBoris Yakimov，Georgy Denisenko＆Evgeny Shirshin莫斯科国家医疗保健预算机构“L.A。

Vorohobov City Clinical Hospital No. 67 MHD”, Moscow, Salama Adil str., 2/44, 123423, RussiaBoris Yakimov, Alexey Yuriev, Lyudmila Pankratieva, Alexander Pukhov & Andrey ShkodaMedeum LLC, Vysokovoltny proezd 1/20, Moscow, 127566, RussiaYuliya ShitovaAuthorsBoris YakimovView author publicationsYou can also search for this author in.

Vorohobov City Clinical Hospital No.67 MHD”，莫斯科，萨拉马·阿迪尔街，2/44123423，俄罗斯鲍里斯·亚基莫夫，亚历克赛·尤里耶夫，柳德米拉·潘克拉蒂耶娃，亚历山大·普霍夫和安德烈·什科达梅德姆有限责任公司，Vysokovoltny proezd 1/20，莫斯科，127566，RussiaYuliya ShitovaAuthorsBoris YakimovView作者出版物你也可以在中搜索这位作者。

PubMed Google ScholarKirill BuiankinView author publicationsYou can also search for this author in

PubMed Google ScholarKirill BuiankinView作者出版物您也可以在

PubMed Google ScholarGeorgy DenisenkoView author publicationsYou can also search for this author in

PubMed谷歌学术期刊DenisenkoView作者出版物您也可以在

PubMed Google ScholarIlia BardadinView author publicationsYou can also search for this author in

PubMed Google ScholarIlia BardadinView作者出版物您也可以在

PubMed Google ScholarOleg PavlovView author publicationsYou can also search for this author in

PubMed Google ScholarolegPavloview作者出版物您也可以在

PubMed Google ScholarYuliya ShitovaView author publicationsYou can also search for this author in

PubMed Google ScholarYuliya ShitovaView作者出版物您也可以在

PubMed Google ScholarAlexey YurievView author publicationsYou can also search for this author in

PubMed Google ScholarAlexey YurievView作者出版物您也可以在

PubMed Google ScholarLyudmila PankratievaView author publicationsYou can also search for this author in

PubMed Google ScholarAlexander PukhovView author publicationsYou can also search for this author in

PubMed Google ScholarAlexander PukhovView作者出版物您也可以在

PubMed Google ScholarAndrey ShkodaView author publicationsYou can also search for this author in

PubMed Google ScholarandreyShkodaview作者出版物您也可以在

PubMed Google ScholarEvgeny ShirshinView author publicationsYou can also search for this author in

PubMed谷歌学术评论ShirshinView作者出版物您也可以在

PubMed Google ScholarContributionsB.Y., A.S. and E.S. – research design, B.Y., K.B., G.D., I.B. – data collection; I.B. – data preparation and segmentation; Y.S. – full data anonymization; O.P., A.P., L.P. and A.Y. – data curation and validation; B.Y. and E.S. – manuscript draft; all authors revised and corrected the manuscript.Corresponding authorsCorrespondence to.

PubMed谷歌学术贡献b。Y、 ，A.S.和E.S.–研究设计，B.Y.，K.B.，G.D.，I.B.–数据收集；一、 B.–数据准备和分割；Y、 S.–完全数据匿名化；O、 P.，A.P.，L.P.和A.Y.–数据管理和验证；B、 Y.和E.S.–手稿草稿；所有作者都修改并更正了手稿。通讯作者通讯。

Boris Yakimov or Evgeny Shirshin.Ethics declarations

Boris Yakimov或Evgeny Shirshin。道德宣言

Competing interests

相互竞争的利益

The authors declare no competing interests.

作者声明没有利益冲突。

Additional informationPublisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Rights and permissions

。权限和权限

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material.

开放获取本文是根据知识共享署名非商业性NoDerivatives 4.0国际许可证授权的，该许可证允许以任何媒介或格式进行任何非商业性使用，共享，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出您是否修改了许可材料。

You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

根据本许可证，您无权共享源自本文或其部分的改编材料。本文中的图像或其他第三方材料包含在文章的知识共享许可证中，除非该材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by-nc-nd/4.0/..

Reprints and permissionsAbout this articleCite this articleYakimov, B., Buiankin, K., Denisenko, G. et al. Dataset of human skin and fingernails images for non-invasive haemoglobin level assessment.

转载和许可本文引用本文Yakimov，B.，Buiankin，K.，Denisenko，G。等人。用于非侵入性血红蛋白水平评估的人体皮肤和指甲图像数据集。

Sci Data 11, 1070 (2024). https://doi.org/10.1038/s41597-024-03895-9Download citationReceived: 07 August 2023Accepted: 19 September 2024Published: 02 October 2024DOI: https://doi.org/10.1038/s41597-024-03895-9Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

Sci数据111070（2024）。https://doi.org/10.1038/s41597-024-03895-9Download引文接收日期：2023年8月7日接收日期：2024年9月19日发布日期：2024年10月2日OI：https://doi.org/10.1038/s41597-024-03895-9Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供