人工智能在乳房外Paget病病理诊断及鉴别中的应用

朱一维; 吴哲; 陈星材; 粘永健; 罗娜; 张恋; 吴毅; 翟志芳

doi:10.16016/j.2097-0927.202401014

您当前的位置：

首页 >

文章列表页 >

人工智能在乳房外Paget病病理诊断及鉴别中的应用

生物医学工程 | 更新时间：2026-01-09

- 人工智能在乳房外Paget病病理诊断及鉴别中的应用
- Application of artificial intelligence in histopathologic diagnosis and differentiation of extramammary Paget's disease
- 陆军军医大学学报 2024年46卷第16期页码：1897-1905
- 作者机构：
  
  1.400038 重庆，陆军军医大学(第三军医大学)第一附属医院皮肤科
  2.400038 重庆，陆军军医大学(第三军医大学)生物医学工程与影像医学系数字医学教研室
  3.401120 重庆，重庆医科大学附属第三医院皮肤科
- 作者简介：
  
  [ 吴毅，E-mail：wuy1979@tmmu.edu.cn WU Yi, E-mail: wuy1979@tmmu.edu.cn
  [ 翟志芳，E-mail：zhaizf1004@163.com ZHAI Zhifang, E-mail: zhaizf1004@163.com
- 基金信息：
  
  重庆市技术创新与应用发展专项重点项目(CSTB2022TIAD-KPX0181);作者贡献声明朱一维：收集整理病理图像，标注病理图像，参与AI模型训练，撰写文章；吴哲：指导及参与图像标注，主要负责AI模型训练，对文章部分内容撰写提供重要建议；陈星材、粘永健：参与AI模型训练，对文章修改提出重要建议；罗娜：参与收集整理病理图像，对文章修改提出重要建议；张恋：病理切片制作，指导扫描WSI图像；吴毅：主要负责AI模型部分的构思、设计、数据分析，修改和审核论文；翟志芳：主要负责病理图像数据部分的构思、设计、样本获取，修改和审核论文
- DOI：10.16016/j.2097-0927.202401014
  中图分类号： R319;R730.4;R739.5
- 收稿：2024-01-04，
  
  修回：2024-03-03，
  
  纸质出版：2024-08-30
- 稿件说明：
移动端阅览
朱一维, 吴哲, 陈星材, 等. 人工智能在乳房外Paget病病理诊断及鉴别中的应用[J]. 陆军军医大学学报, 2024,46(16):1897-1905.

Yiwei ZHU, Zhe WU, Xingcai CHEN, et al. Application of artificial intelligence in histopathologic diagnosis and differentiation of extramammary Paget's disease[J]. Journal of Army Medical University, 2024, 46(16): 1897-1905.
朱一维, 吴哲, 陈星材, 等. 人工智能在乳房外Paget病病理诊断及鉴别中的应用[J]. 陆军军医大学学报, 2024,46(16):1897-1905. DOI： 10.16016/j.2097-0927.202401014.

Yiwei ZHU, Zhe WU, Xingcai CHEN, et al. Application of artificial intelligence in histopathologic diagnosis and differentiation of extramammary Paget's disease[J]. Journal of Army Medical University, 2024, 46(16): 1897-1905. DOI： 10.16016/j.2097-0927.202401014.

摘要

目的

建立乳房外Paget病(extramammary Paget’s disease，EMPD) 组织病理诊断的人工智能(artificial intelligence

AI)诊断模型，并评价其对EMPD诊断及鉴别诊断的效能。

方法

收集2003年9月至2023年2月于陆军军医大学第一附属医院皮肤科就诊并行皮肤组织活检术，且病理明确诊断为EMPD、Bowen病、皮肤鳞状细胞癌(squamous cell carcinoma

SCC)以及表皮增生肥厚为主要病理特征的非肿瘤性皮肤病患者的病理资料。以EMPD为主要研究对象，与Bowen病、SCC以及非肿瘤性皮肤病病理图像进行鉴别，通过ResNet101、DenseNet121深度学习神经网络对4种疾病的组织病理进行分类诊断并评价模型效能。

结果

ResNet101诊断模型诊断EMPD、Bowen病、SCC及非肿瘤性皮肤病的20倍组织病理图像的AUC值分别为0.97、0.98、1.00、0.96，准确度为(0.925±0.011)；40倍组织病理图像AUC值分别为1.00、0.99、1.00、0.97，准确度为(0.943±0.017)。DenseNet121诊断模型诊断EMPD、Bowen病、SCC及非肿瘤性皮肤病的20倍组织病理图像的AUC值分别为0.98、0.95、0.99、1.00，准确度为(0.912±0.034)；40倍组织病理图像AUC值分别为0.99、0.96、1.00、1.00，准确度为(0.971±0.012)。表示分类诊断模型能够将EMPD与Bowen病、SCC及非肿瘤性皮肤病等的低倍组织病理图像进行有效区分。ResNet101计算量为786.6 M、参数量为4.5 M，DensNet121计算量为289.7 M、参数量为0.8 M。

结论

本研究建立的组织病理图像人工智能诊断模型对EMPD的诊断及鉴别诊断具有较高效能，并推荐DenseNet121为皮肤病理图片的诊断模型。

Abstract

Objective

To establish an artificial intelligence (AI) diagnostic model for the histopathologic diagnosis of extramammary Paget's disease (EMPD) and to evaluate its efficiency for the diagnosis and differential diagnosis of EMPD.

Methods

All non-tumor skin disease patients who underwent skin tissue biopsy in Department of Dermatology of First Affiliated Hospital of Army Medical University from September 2003 to February 2023 were recruited

and their pathological data were collected

including EMPD

Bowen's disease (BD)

squamous cell carcinoma (SCC)

and epidermal hyperplasia and hypertrophy. With EMPD as the main research subject

the histopathological images of BD

SCC

and non-tumor skin diseases were included in the study. The histopathological data of 4 types of diseases was classified and diagnosed by ResNet101 and DenseNet121 deep learning neural networks

and the performance of these models was evaluated.

Results

The AUC values of the ResNet101 diagnostic model for the diagnosis of EMPD

SCC and non-tumor skin diseases on the images at ×20 magnification were 0.97

0.98

1.00 and 0.96

respectively

with an accuracy of 0.925±0.011

while the AUC values on the images at ×40 magnification were 1.00

0.99

1.00 and 0.97

respectively

with an accuracy of 0.943±0.017. The AUC values of the DenseNet121 diagnostic model for the diagnosis of 4 diseases on the images at ×20 magnification were 0.98

0.95

0.99 and 1.00

respectively

with an accuracy of 0.912±0.034

while the AUC values on the images at ×40 magnification were 0.99

0.96

1.00 and 1.00

respectively

with an accuracy of 0.971±0.012. Our results indicated that the histopathologic diagnostic model could effectively differentiate EMPD from BD

SCC and non-tumor skin diseases at low power magnification. The FLPOs of ResNet101 was 786.6 M

and the parameter was 4.5 M; The FLPOs of DensNet121 was 289.7 M

and the parameter was 0.8M.

Conclusion

Our AI diagnostic model is of good effectiveness in the diagnosis and differential diagnosis of EMPD. DenseNet121 is recommended as the dermatopathological diagnostic model of this study.

关键词

Keywords

references

ITO T, KAKU-ITO Y, FURUE M. The diagnosis and management of extramammary Paget's disease[J]. Expert Rev Anticancer Ther, 2018, 18(6): 543-553. DOI: 10.1080/14737140.2018.1457955.

ASEL M, LEBOEUF N R. Extramammary Paget's disease[J]. Hematol Oncol Clin North Am, 2019, 33(1): 73-85. DOI: 10.1016/j.hoc.2018.09.003.

WILLIAM D, TIMOTHY G, DIRK M, et al. Andrews' diseases of the skin: clinical dermatology[M]. Beijing: Science Press, 2019.

郑闪, 孙丰龙, 张慧娟, 等. 人工智能在肿瘤组织病理学的研究现状[J]. 中华肿瘤杂志, 2018, 40(12): 885-889. DOI: 10.3760/cma.j.issn.0253-3766.2018.12.002.

ZHENG S, SUN F L, ZHANG H J, et al . Current applications of artificial intelligence in tumor histopathology[J ] . Chin J Oncol, 2018, 40(12): 885-889. DOI: 10.3760/cma.j.issn.0253-3766.2018.12.002.

HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507. DOI: 10.1126/science.1127647.

赵佩. 人工智能技术在临床医疗诊断中的应用及发展[J]. 中国新通信, 2019, 21(22): 90-91. DOI: 10.3969/j.issn.1673-4866.2019.22.077.

ZHAO P. Application and development of artificial intelligence technology in clinical medical diagnosis[J]. China New Telecommun, 2019, 21(22): 90-91. DOI: 10.3969/j.issn.1673-4866.2019.22.077.

BHATTI K M, KHANZADA Z S, KUZMAN M, et al . Diagnostic performance of artificial intelligence-based models for the detection of early esophageal cancers in Barret's esophagus: a meta-analysis of patient-based studies[J ] . Cureus , 2021, 13(6): e15447. DOI: 10.7759/cureus.15447.

ISLAM M M, POLY T N, WALTHER B A, et al . Deep learning for the diagnosis of esophageal cancer in endoscopic images: a systematic review and meta-analysis[J ] . Cancers, 2022, 14(23): 5996. DOI: 10.3390/cancers14235996.

ZHANG D, JIANG F, YIN R, et al . A review of the role of the S-detect computer-aided diagnostic ultrasound system in the evaluation of benign and malignant breast and thyroid masses[J ] . Med Sci Monit, 2021, 27: e931957. DOI: 10.12659/MSM.931957.

PEEK N, COMBI C, MARIN R, et al . Thirty years of artificial intelligence in medicine (AIME) conferences: a review of research themes[J ] . Artif Intell Med, 2015, 65(1): 61-73. DOI: 10.1016/j.artmed.2015.07.003.

CALONJE E, BRENN T, LAZAR A, et al . McKee's pathology of the skin with clinical correlations[M ] . Philadelphia: Elsevier Saunders, 2011.

HE K M, ZHANG X Y, REN S Q, et al . Deep residual learning for image recognition[C ] //2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770-778. DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ..

HUANG G, LIU Z, VAN DER MAATEN L, et al . Densely connected convolutional networks[C ] //2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 2261-2269. DOI: 10.1109/CVPR.2017.243 http://dx.doi.org/10.1109/CVPR.2017.243 ..

SELVARAJU R R, COGSWELL M, DAS A, et al . Grad-CAM: visual explanations from deep networks via gradient-based localization[C ] //2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017: 618-626. DOI: 10.1109/ICCV.2017.74 http://dx.doi.org/10.1109/ICCV.2017.74 ..

KANG Z, ZHU Y, ZHANG Q A, et al . Methylation and expression analysis of mismatch repair genes in extramammary Paget's disease[J ] . J Eur Acad Dermatol Venereol, 2019, 33(5): 874-879. DOI: 10.1111/jdv.15404.

朱一维, 张恋, 顾洪芝, 等. 乳房外Paget病135例临床及组织病理学特征分析[J]. 中国皮肤性病学杂志, 2024, 38(2): 171-176. DOI: 10.13735/j.cjdv.1001-7089.202308056.

ZHU Y W, ZHANG L, GU H Z, et al . Analysis on the clinical and histopathological characteristic s of 135 patients with extramammary Paget's disease[J ] . Chin J Dermatovenereol, 2024, 38(2): 171-176. DOI: 10.13735/j.cjdv.1001-7089.202308056.

ACS B, RANTALAINEN M, HARTMAN J. Artificial intelligence as the next step towards precision pathology[J]. J Intern Med, 2020, 288(1): 62-81. DOI: 10.1111/joim.13030.

陈虎艳, 李晓鹏, 李乔, 等. 鲍温病和脂溢性角化人工智能病理诊断模型的建立和评估[J]. 第二军医大学学报, 2021, 42(3): 243-248. DOI: 10.16781/j.0258-879x.2021.03.0243.

CHEN H Y, LI X P, LI Q, et al . Establishment and evaluation of an artificial intelligence model in pathological diagnosis of Bowen's disease and seborrheic keratosis[J ] . Acad J Second Mil Med Univ, 2021, 42(3): 243-248. DOI: 10.16781/j.0258-879x.2021.03.0243.

AREVALO J, CRUZ-ROA A, ARIAS V, et al . An unsupervised feature learning framework for basal cell carcinoma image analysis[J ] . Artif Intell Med, 2015, 64(2): 131-145. DOI: 10.1016/j.artmed.2015.04.004.

JIANG Y Q, XIONG J H, LI H Y, et al . Recognizing basal cell carcinoma on smartphone-captured digital histopathology images with a deep neural network[J ] . Br J Dermatol, 2020, 182(3): 754-762. DOI: 10.1111/bjd.18026.

HEKLER A, UTIKAL J S, ENK A H, et al . Pathologist-level classification of histopathological melanoma images with deep neural networks[J ] . Eur J Cancer, 2019, 115: 79-83. DOI: 10.1016/j.ejca.2019.04.021.

WU H, CHEN H Y, WANG X C, et al . Development and validation of an artificial intelligence-based image classification method for pathological diagnosis in patients with extramammary Paget's disease[J ] . Front Oncol, 2021, 11: 810909. DOI: 10.3389/fonc.2021.810909.

浏览量

124

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用支持向量机预测重症监护室患者死亡风险的研究

鼻咽癌放疗临床靶区人工智能勾画模型的训练及验证研究

人工智能在临床领域的研究进展及前景展望

研精覃思，见微知著——人工智能开启精准病理诊断新时代

肝硬化伴自发性细菌性腹膜炎的诊断模型研究及验证