AbstractAccurate detection and classification of lung malignancies are crucial for early diagnosis, treatment planning, and patient prognosis. Conventional histopathological analysis is time-consuming, limiting its clinical applicability. To address this, we present a dataset of 691 high-resolution (1200 × 1600 pixels) histopathological lung images, covering adenocarcinomas, squamous cell carcinomas, and normal tissues from 45 patients.

摘要准确检测和分类肺部恶性肿瘤对于早期诊断，治疗计划和患者预后至关重要。传统的组织病理学分析耗时，限制了其临床适用性。为了解决这个问题，我们提供了一个691个高分辨率（1200×1600像素）组织病理学肺图像的数据集，涵盖了45例患者的腺癌，鳞状细胞癌和正常组织。

These images are subdivided into three differentiation levels for both pathological types: well, moderately, and poorly differentiated, resulting in seven classes for classification. The dataset includes images at 20x and 40x magnification, reflecting real clinical diversity. We evaluated image classification using deep neural network and multiple instance learning approaches.

这些图像被细分为两种病理类型的三个分化水平：良好，中度和低分化，导致七类分类。该数据集包括放大20倍和40倍的图像，反映了真实的临床多样性。我们使用深度神经网络和多实例学习方法评估了图像分类。

Each method was used to classify images at 20x and 40x magnification into three superclasses. We achieved accuracies between 81% and 92%, depending on the method and resolution, demonstrating the dataset’s utility..

。根据方法和分辨率，我们实现了81%至92%的准确度，证明了数据集的实用性。。

Background & SummaryCancer is the second leading cause of death globally. In 2022, more than 20 million new cancer cases were reported, and approximately 9.7 million people succumbed to the disease worldwide. Lung cancer, with more than 2.5 million new cases diagnosed1, was the most lethal, accounting for 1.8 million deaths.

背景与总结癌症是全球第二大死亡原因。2022年，报告了2000多万新的癌症病例，全世界约有970万人死于这种疾病。肺癌是最致命的，诊断出250多万例新病例1，导致180万人死亡。

This staggering figure represents a fifth of all cancer deaths globally, significantly more than the second deadliest cancer, colon and rectum cancer, which caused almost 904,000 deaths in the same year, 20222.The high mortality rate of lung cancer is mainly due to late detection. Early diagnosis of lung cancer is key to survival.

这一惊人的数字占全球癌症死亡人数的五分之一，远远超过第二大致命癌症结肠癌和直肠癌，同年20222年，结肠癌和直肠癌导致近904000人死亡。肺癌的高死亡率主要是由于发现较晚。肺癌的早期诊断是生存的关键。

However, by the time symptoms become apparent, the disease has often spread, resulting in a low survival rate3. The 5-year survival rate for early-stage lung cancer can exceed 90%, while for patients diagnosed at a late stage, it can be less than 10%04. Smoking, identified as the leading risk factor by the American Cancer Society, is projected to account for 81% of lung cancer cases in 20235.Carcinomas, malignancies that develop from epithelial cells, are the most common type of malignancy in the lungs.

然而，当症状变得明显时，疾病经常扩散，导致生存率低3。早期肺癌的5年生存率可以超过90%，而对于晚期诊断的患者，其5年生存率可以低于10%。吸烟被美国癌症协会确定为主要危险因素，预计20235年将占肺癌病例的81%。癌症是由上皮细胞发展而来的恶性肿瘤，是肺部最常见的恶性肿瘤类型。

Carcinomas located in the lungs that originate there are referred to as primary lung carcinomas, distinguishing them from those that have spread to the lungs via metastasis. Primary lung carcinomas can be divided into two major histopathological types: small cell carcinoma and non-small cell carcinoma, with non-small cell carcinomas being the most frequent6.Non-small cell carcinoma can be classified into two main subtypes: adenocarcinomas and squamous cell carcinomas..

起源于肺部的癌被称为原发性肺癌，将其与通过转移扩散到肺部的癌区分开。原发性肺癌可分为两种主要的组织病理学类型：小细胞癌和非小细胞癌，其中非小细胞癌最常见6。非小细胞癌可分为两种主要亚型：腺癌和鳞状细胞癌。。

Adenocarcinomas: These tumors exhibit microscopic glandular-related tissue cytology, tissue architecture, and/or gland-related products.

。

Squamous Cell Carcinomas: These tumors are characterized by observable traits of squamous differentiation, such as intercellular bridges, keratinization, and the formation of squamous pearls6.

鳞状细胞癌：这些肿瘤的特征是鳞状分化的可观察特征，例如细胞间桥，角化和鳞状珍珠的形成6。

Additionally, there are other less common types of non-small cell carcinoma, such as large cell carcinoma, adenosquamous carcinoma, and sarcomatoid carcinoma, each with its own unique histological features and clinical behaviors that may influence treatment strategies and prognosis.Distinguishing the histological types of lung carcinomas is crucial in the era of personalized medicine, as each tumor type can be associated with different genetic alterations within the tumor itself.

此外，还有其他不太常见的非小细胞癌类型，例如大细胞癌，腺鳞癌和肉瘤样癌，每种癌都有其独特的组织学特征和临床行为，可能会影响治疗策略和预后。。

These genetic changes, in turn, are related to targeted therapies aimed at those specific mutations, improving the medium and long-term prognosis7.Histopathological images, microscopic images of tissue samples, play a crucial role in medical diagnosis and research. They offer valuable insights into the appearance and structure of cells and tissues, enabling pathologists to accurately identify and classify diseases8.

反过来，这些遗传变化与针对这些特定突变的靶向治疗有关，从而改善了中长期预后7。组织病理学图像，组织样本的显微图像在医学诊断和研究中起着至关重要的作用。它们为细胞和组织的外观和结构提供了有价值的见解，使病理学家能够准确识别和分类疾病8。

However, manual analysis of these images is time-consuming and prone to human error9. Therefore, histopathological image datasets, collections of labeled histopathological images, are essential for developing and training image analysis algorithms. These datasets provide researchers with a large and diverse set of images, facilitating the creation of artificial intelligence (AI) models that can accurately classify and diagnose diseases, thereby assisting human experts in their tasks.The field of AI is expanding rapidly, with new applications emerging daily, particularly in the medical sector10.

然而，手动分析这些图像很耗时，并且容易出现人为错误9。因此，组织病理学图像数据集，即标记的组织病理学图像的集合，对于开发和训练图像分析算法至关重要。这些数据集为研究人员提供了大量多样的图像，有助于创建能够准确分类和诊断疾病的人工智能（AI）模型，从而帮助人类专家完成任务。人工智能领域正在迅速扩大，每天都有新的应用出现，特别是在医学领域10。

One promising application is in diagnostics, where AI can enhance both diagnostic accuracy and efficiency. AI can improve the early detection and diagnosis of lung cancer, potentially leading to better patient outcomes11.To develop AI algorithms using lung histopathology images, several popul.

一个有前途的应用是在诊断中，人工智能可以提高诊断的准确性和效率。AI可以改善肺癌的早期发现和诊断，可能会导致更好的患者结果11。为了开发使用肺组织病理学图像的AI算法，一些popul。

1.

1.

Well-differentiated: Tumors primarily exhibiting a lepidic pattern, with no high-grade components or less than 20% high-grade features (such as solid, micropapillary, or complex glandular patterns).

高分化：肿瘤主要表现为鳞状模式，没有高级成分或少于20%的高级特征（如实体，微乳头或复杂的腺体模式）。

2.

2.

Moderately differentiated adenocarcinoma: Tumors mainly showing acinar or papillary patterns, with less than 20% high-grade features.

中分化腺癌：肿瘤主要表现为腺泡或乳头状，高度特征不到20%。

3.

3.

Poorly differentiated adenocarcinoma: Tumors that have 20% or more high-grade features.

低分化腺癌：具有20%或更多高级特征的肿瘤。

Pulmonary squamous cell carcinoma has also traditionally been divided into well differentiated, moderately differentiated, and poorly differentiated, similar to squamous cell carcinomas of other organ systems. The degree of differentiation is generally dependent on a combination of features, such as the presence or absence of keratinization and intercellular bridges, as well as cellular pleomorphism and mitotic activity22.

肺鳞状细胞癌传统上也分为高分化，中分化和低分化，类似于其他器官系统的鳞状细胞癌。分化程度通常取决于特征的组合，例如角化和细胞间桥的存在与否，以及细胞多形性和有丝分裂活性22。

Following these guidelines, squamous cell carcinoma has been divided into the following three categories:.

根据这些指南，鳞状细胞癌分为以下三类：。

1.

1.

Well differentiated: These tumors exhibit keratinization, such as keratin pearls and intercellular bridges. They typically grow in sheets or nests, with polygonal cells that have round to oval nuclei, vesicular features, and eosinophilic cytoplasm. Additionally, mitotic figures and focal areas of hemorrhage or necrosis may be present..

。它们通常以片状或巢状生长，多边形细胞具有圆形至椭圆形的细胞核，水泡特征和嗜酸性细胞质。此外，可能存在有丝分裂图和出血或坏死的病灶区域。。

2.

2.

Moderately differentiated: These tumors show increased cytologic atypia and mitotic activity. Although keratinization and intercellular bridges are still present, they are less prominent compared to well-differentiated tumors. Moreover, areas of hemorrhage or necrosis are more common.

中度分化：这些肿瘤显示出增加的细胞学异型性和有丝分裂活性。尽管仍然存在角化和细胞间桥，但与分化良好的肿瘤相比，它们不太突出。此外，出血或坏死区域更常见。

3.

3.

Poorly differentiated: These tumors grow in sheets and are often unrecognizable as squamous type without immunohistochemistry. They display significant cellular pleomorphism, high mitotic activity, and extensive areas of necrosis.

低分化：这些肿瘤呈片状生长，通常在没有免疫组织化学的情况下无法识别为鳞状细胞。它们表现出明显的细胞多形性，高有丝分裂活性和广泛的坏死区域。

Figure 1 shows adenocarcinoma samples, Fig. 2 displays squamous cell carcinoma samples at varying levels of differentiation and resolution. Figure 3 presents images of normal lung tissue at two different resolution.Fig. 1Images displaying adenocarcinoma at varying levels of differentiation and resolution.Full size imageFig.

图1显示了腺癌样本，图2显示了不同分化程度和分辨率的鳞状细胞癌样本。。图1显示不同分化程度和分辨率的腺癌的图像。全尺寸图像图。

2Images displaying squamous cell carcinoma at varying levels of differentiation and resolution.Full size imageFig. 3Normal lung images at different resolution.Full size imageEthics approvalThe study was conducted according to the guidelines of the Declaration of Helsinki and approved by the Ethical Committee of the Hospital Clínico Universitario de Valladolid (CEIm Área de Salud Valladolid Este) under project PI 23–3167.

2以不同的分化和分辨率显示鳞状细胞癌的图像。。3不同分辨率的正常肺部图像。全尺寸影像伦理学批准该研究是根据《赫尔辛基宣言》的指导方针进行的，并得到瓦拉多利德克利尼科大学医院伦理委员会（CEImÁrea de Salud Valladolid Este）在PI 23-3167项目下的批准。

The committee waived participant consent given data anonymization and approved open publication of the data.Data RecordsThe dataset is available at figshare23. It consists of 691 images from 45 patients, with each image having a resolution of 1200 × 1600 pixels and stored in .jpg format. These images are captured at either 20x or 40x magnification levels and are categorized into seven classes (see Table 1).

委员会放弃了参与者同意的匿名数据，并批准了数据的公开发布。数据记录该数据集可在figshare23上获得。它由来自45位患者的691张图像组成，每张图像的分辨率为1200×1600像素，并以.jpg格式存储。这些图像以20倍或40倍的放大倍数拍摄，分为七类（见表1）。

An accompanying.csv file links each image to the associated patient ID. All patients have been anonymized, and the file includes an identifier to match images from the same patient.Table 1 The dataset comprises three classes: adenocarcinoma (aca), squamous cell carcinoma (scc), and normal (nor).Full size tableTechnical ValidationIn this section, we present two baseline methods for classifying the dataset into the three major superclasses.

附带的.csv文件将每个图像链接到相关的患者ID。所有患者都是匿名的，该文件包含一个标识符，以匹配来自同一患者的图像。。全尺寸表技术验证在本节中，我们介绍了两种基线方法，用于将数据集分类为三个主要的超类。

First, a classic approach was employed where images were resized, and a deep neural network (DNN) was trained. The second method involves a multiple instance learning (MIL) strategy, where patche.

。第二种方法涉及多实例学习（MIL）策略，其中patche。

Code availability

代码可用性

Code to reproduce the DNN baseline is available at https://github.com/jorgediosdado/LungHist700.

复制DNN基线的代码可在https://github.com/jorgediosdado/LungHist700.

ReferencesBray, F. et al. Global cancer statistics 2022: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians 74, 229–263, https://doi.org/10.3322/caac.21834 (2024).Article

ReferencesBray，F。等人，《2022年全球癌症统计：全球癌症协会对185个国家36种癌症的全球发病率和死亡率的估计》。CA：临床医生癌症杂志74229-263，https://doi.org/10.3322/caac.21834（2024年）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Cancer. https://www.who.int/news-room/fact-sheets/detail/cancer available online (Accessed in October 2023).Sullivan, F. M. et al. Earlier diagnosis of lung cancer in a randomised trial of an autoantibody blood test followed by imaging. European Respiratory Journal 57, https://doi.org/10.1183/13993003.00670-2020 (2021).Ning, J.

癌症。https://www.who.int/news-room/fact-sheets/detail/cancer在线提供（2023年10月访问）。Sullivan，F.M.等人在一项随机试验中对肺癌的早期诊断进行了自身抗体血液检测，然后进行了成像。欧洲呼吸杂志57，https://doi.org/10.1183/13993003.00670-2020（2021年）。宁，J。

et al. Early diagnosis of lung cancer: which is the optimal choice. Aging (Albany NY) 13, 6214, https://doi.org/10.18632/aging.202504 (2021).Article .

肺癌的早期诊断：哪种是最佳选择。老龄化（纽约州奥尔巴尼）136214，https://doi.org/10.18632/aging.202504（2021年）。文章。

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Siegel, R. L., Miller, K. D., Wagle, N. S. & Jemal, A. Cancer statistics, 2023. Ca Cancer J Clin 73, 17–48, https://doi.org/10.3322/caac.21763 (2023).Article

Siegel，R.L.，Miller，K.D.，Wagle，N.S。和Jemal，A。癌症统计，2023年。Ca癌症J临床73,17-48，https://doi.org/10.3322/caac.21763（2023年）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Kumar, V., Abbas, A., Aster, J. C. & Deyrup, A. T. Robbins & Kumar Basic Pathology (Elsevier Health Sciences, 2022).Rodak, O., Peris-Díaz, M. D., Olbromski, M., Podhorska-Okołó, M. & Dzięgiel, P. Current landscape of non-small cell lung cancer: Epidemiology, histological classification, targeted therapies, and immunotherapy.

Kumar，V.，Abbas，A.，Aster，J.C.＆Deyrup，A.T.Robbins＆Kumar Basic Pathology（Elsevier Health Sciences，2022）。Rodak，O.，Peris-Díaz，M.D.，Olbromski，M.，Podhorska-Okołó，M。＆Dzięgiel，P。非小细胞肺癌的现状：流行病学，组织学分类，靶向治疗和免疫治疗。

Cancers 13, https://doi.org/10.3390/cancers13184705 (2021).Mukhopadhyay, S. et al. Whole slide imaging versus microscopy for primary diagnosis in surgical pathology: A multicenter blinded randomized noninferiority study of 1992 cases (pivotal study. The American Journal of Surgical Pathology 42, 39–52, https://doi.org/10.1097/PAS.0000000000000948 (2018).Article .

癌症13，https://doi.org/10.3390/cancers13184705（2021年）。Mukhopadhyay，S.等人，《手术病理学初步诊断的全幻灯片成像与显微镜检查：1992例病例的多中心盲法随机非劣效性研究》（关键研究，《美国外科病理学杂志》42,39-52，https://doi.org/10.1097/PAS.0000000000000948（2018年）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Peck, M., Moffatt, D., Latham, B. & Badrick, T. Review of diagnostic error in anatomical pathology and the role and value of second opinions in error prevention. Journal of Clinical Pathology 71, jclinpath–2018, https://doi.org/10.1136/jclinpath-2018-205226 (2018).Article

Peck，M.，Moffatt，D.，Latham，B。＆Badrick，T。回顾解剖病理学中的诊断错误以及第二意见在错误预防中的作用和价值。临床病理学杂志71，jclinpath–2018，https://doi.org/10.1136/jclinpath-2018-205226（2018年）。文章

Google Scholar

谷歌学者

Esteva, A. et al. A guide to deep learning in healthcare. Nature medicine 25, 24–29, https://doi.org/10.1038/s41591-018-0316-z (2019).Article

Esteva，A.等人，《医疗保健深度学习指南》。自然医学25,24-29，https://doi.org/10.1038/s41591-018-0316-z（2019年）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Khodabakhshi, Z. et al. Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass ct radiomics signature. Computers in biology and medicine 136, 104752, https://doi.org/10.1016/j.compbiomed.2021.104752 (2021).Article

Khodabakhshi，Z。等。使用高维多项式多类ct放射组学特征的非小细胞肺癌组织病理学亚型表型。生物与医学计算机136104752，https://doi.org/10.1016/j.compbiomed.2021.104752（2021年）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Collisson, E. A. et al. Comprehensive molecular profiling of lung adenocarcinoma. Nature 511, 543–550, https://doi.org/10.1038/nature13385 (2014).Article

Collisson，E.A。等。肺腺癌的综合分子谱分析。自然511543-550，https://doi.org/10.1038/nature13385（2014年）。文章

ADS

广告

CAS

中科院

Google Scholar

谷歌学者

Kirk, S. et al. The cancer genome atlas lung squamous cell carcinoma collection (tcga-lusc) (version 4) [data set]. The Cancer Imaging Archive https://doi.org/10.7937/K9/TCIA.2016.TYGKKFMQ (2016).Borkowski, A. A. et al. Lung and colon cancer histopathological image dataset (lc25000), https://doi.org/10.48550/arXiv.1912.12142 (2019).Mehmood, S.

Kirk，S.等人，《癌症基因组图谱-肺鳞状细胞癌收集》（tcga lusc）（第4版）[数据集]。癌症影像档案https://doi.org/10.7937/K9/TCIA.2016.TYGKKFMQ（2016年）。Borkowski，A.A.等人，肺癌和结肠癌组织病理学图像数据集（lc25000），https://doi.org/10.48550/arXiv.1912.12142（2019年）。梅穆德，S。

et al. Malignancy detection in lung and colon histopathology images using transfer learning with class selective image processing. IEEE Access 10, 25657–25668, https://doi.org/10.1109/ACCESS.2022.3150924 (2022).Article .

等人。使用转移学习和类选择性图像处理在肺和结肠组织病理学图像中检测恶性肿瘤。IEEE Access 1025657–25668，https://doi.org/10.1109/ACCESS.2022.3150924（2022年）。文章。

Google Scholar

谷歌学者

Mangal, S., Chaurasia, A. & Khajanchi, A. Convolution neural networks for diagnosing colon and lung cancer histopathological images, https://doi.org/10.48550/arXiv.2009.03878 (2020).Masud, M., Sikder, N., Nahid, A.-A., Bairagi, A. K. & AlZain, M. A. A machine learning approach to diagnosing lung and colon cancer using a deep learning-based classification framework.

Mangal，S.，Chaurasia，A。和Khajanchi，A。用于诊断结肠癌和肺癌组织病理学图像的卷积神经网络，https://doi.org/10.48550/arXiv.2009.03878（2020年）。Masud，M.，Sikder，N.，Nahid，A.-A.，Bairagi，A.K。＆AlZain，M.A。使用基于深度学习的分类框架诊断肺癌和结肠癌的机器学习方法。

Sensors 21, 748, https://doi.org/10.3390/s21030748 (2021).Article .

传感器21748，https://doi.org/10.3390/s21030748（2021年）。文章。

ADS

广告

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Al-Jabbar, M., Alshahrani, M., Senan, E. M. & Ahmed, I. A. Histopathological analysis for detecting lung and colon cancer malignancies using hybrid systems with fused features. Bioengineering 10, 383, https://doi.org/10.3390/bioengineering10030383 (2023).Article

Al-Jabbar，M.，Alshahrani，M.，Senan，E.M。＆Ahmed，I.A。使用具有融合特征的混合系统检测肺癌和结肠癌恶性肿瘤的组织病理学分析。生物工程10383，https://doi.org/10.3390/bioengineering10030383（2023年）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Hatuwal, B. K. & Thapa, H. C. Lung cancer detection using convolutional neural network on histopathological images. International Journal of Computer Trends and Technology 68, 21–24, https://doi.org/10.14445/22312803/IJCTT-V68I10P104 (2020).Article

Hatuwal，B.K。＆Thapa，H.C。在组织病理学图像上使用卷积神经网络检测肺癌。国际计算机趋势与技术杂志68,21-24，https://doi.org/10.14445/22312803/IJCTT-V68I10P104（2020年）。文章

Google Scholar

谷歌学者

Moreira, A. L. et al. A grading system for invasive pulmonary adenocarcinoma: a proposal from the international association for the study of lung cancer pathology committee. Journal of Thoracic Oncology 15, 1599–1610, https://doi.org/10.1016/j.jtho.2020.06.001 (2020).Article

Moreira，A.L.等人，《浸润性肺腺癌的分级系统：国际肺癌病理学研究协会的提案》。胸肿瘤学杂志151599-1610，https://doi.org/10.1016/j.jtho.2020.06.001（2020年）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Schneider, F. et al. Protocol for the examination of resection specimens from patients with primary non-small cell carcinoma, small cell carcinoma, or carcinoid tumor of the lung. Arch Pathol Lab Med 133, 1552–1559, https://doi.org/10.5858/133.10.1552 (2009).Article

Schneider，F.等人，《检查原发性非小细胞癌、小细胞癌或肺类癌患者切除标本的方案》。Arch Pathol实验室医学1331552-1559，https://doi.org/10.5858/133.10.1552（2009年）。文章

Google Scholar

谷歌学者

Weissferdt, A. Diagnostic Thoracic Pathology (Springer, 2020).Diosdado, J., Gilabert, P., Santi, S. & Borrego, H. Lunghist700: A dataset of histological images for deep learning in pulmonary pathology. figshare https://doi.org/10.6084/m9.figshare.25459174 (2024).Vaswani, A. et al. Attention is all you need.

Weissferdt，A。诊断性胸部病理学（Springer，2020）。Diosdado，J.，Gilabert，P.，Santi，S。＆Borrego，H。Lunghist700：用于肺部病理学深度学习的组织学图像数据集。figshare公司https://doi.org/10.6084/m9.figshare.25459174（2024年）。Vaswani，A。等人。注意力是你所需要的。

Advances in neural information processing systems 30 (2017).Buslaev, A. et al. Albumentations: Fast and flexible image augmentations. Information 11, https://doi.org/10.3390/info11020125 (2020).Selvaraju, R. R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), https://doi.org/10.1007/s11263-019-01228-7 (2017).Download referencesAcknowledgementsThis work has been partially funded by 2021 SGR 01104 and FPU20/01090 grant.Author informationAuthors and AffiliationsDept.

神经信息处理系统的进展30（2017）。Buslaev，A。等人。专辑：快速灵活的图像增强。信息11，https://doi.org/10.3390/info11020125（2020年）。Selvaraju，R.R.等人，Grad cam：通过基于梯度的定位从深度网络进行视觉解释。在IEEE国际计算机视觉会议论文集（ICCV）中，https://doi.org/10.1007/s11263-019-01228-7（2017年）。下载参考文献致谢这项工作已由2021 SGR 01104和FPU20/01090赠款部分资助。。

de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, SpainJorge Diosdado, Pere Gilabert & Santi SeguíHospital Clínico Universitario de Valladolid, Valladolid, SpainHenar BorregoAuthorsJorge DiosdadoView author publicationsYou can also search for this author in.

Jorge Diosdado，\ Pere Gilabert\ Santi SeguíHospital Clínico Universitario de Valladolid，Valladolide，Espain巴塞罗那大学数学与信息学系Henar Borrego作者Jorge DiosdadoView作者出版物您也可以在中搜索此作者。

PubMed Google ScholarPere GilabertView author publicationsYou can also search for this author in

PubMed Google ScholarPere GilabertView作者出版物您也可以在

PubMed Google ScholarSanti SeguíView author publicationsYou can also search for this author in

PubMed Google ScholarSanti SeguíView作者出版物您也可以在

PubMed Google ScholarHenar BorregoView author publicationsYou can also search for this author in

PubMed Google ScholarContributionsJ.D. and H.B. conceived the experiments, collected and processed the data. J.D. and P.G. conducted the experiments and wrote the manuscript. All authors reviewed the manuscript.Corresponding authorCorrespondence to

PubMed谷歌学术贡献。D、 H.B.构思了实验，收集并处理了数据。J、 D.和P.G.进行了实验并撰写了手稿。所有作者都审阅了手稿。对应作者对应

Jorge Diosdado.Ethics declarations

豪尔赫·迪奥斯达多。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 4.0 International License, which permits use, sharing, adaptation, 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 changes were made.

开放获取本文是根据知识共享署名4.0国际许可证授权的，该许可证允许以任何媒体或格式使用，共享，改编，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，并指出是否进行了更改。

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.

。如果材料未包含在文章的知识共享许可证中，并且您的预期用途未被法律法规允许或超出允许的用途，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/4.0/..

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

Reprints and permissionsAbout this articleCite this articleDiosdado, J., Gilabert, P., Seguí, S. et al. LungHist700: A dataset of histological images for deep learning in pulmonary pathology.

转载和许可本文引用本文Diosdado，J.，Gilabert，P.，Seguí，S。et al。LungHist700：用于肺部病理学深度学习的组织学图像数据集。

Sci Data 11, 1088 (2024). https://doi.org/10.1038/s41597-024-03944-3Download citationReceived: 25 March 2024Accepted: 30 September 2024Published: 05 October 2024DOI: https://doi.org/10.1038/s41597-024-03944-3Share 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.

。https://doi.org/10.1038/s41597-024-03944-3Download引文接收日期：2024年3月25日接受日期：2024年9月30日发布日期：2024年10月5日OI：https://doi.org/10.1038/s41597-024-03944-3Share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