Deep learning-based diagnosis of multi-subtype retroperitoneal soft tissue sarcomas

JIANG Yongjun; LI Hongling; RUAN Ping; CHEN Lu; LI Yanchun; HU Qing; XIE Gongxun; MENG Yunhe

doi:10.13471/j.cnki.acta.snus.ZR20240309

您当前的位置：

首页 >

文章列表页 >

Deep learning-based diagnosis of multi-subtype retroperitoneal soft tissue sarcomas

Research articles | 更新时间：2025-11-14

- Deep learning-based diagnosis of multi-subtype retroperitoneal soft tissue sarcomas
- Acta Scientiarum Naturalium Universitatis Sunyatseni Vol. 64, Issue 3, Pages: 156-164(2025)
- 作者机构：
  
  1.中山大学人工智能学院，广东珠海 519082
  2.佛山市中医院，广东佛山 528000
  3.广西中医药大学附属瑞康医院，广西南宁 530000
  4.宜昌市中心人民医院，湖北宜昌 443000
  5.湖南省人民医院，湖南长沙 410000
- 作者简介：
- 基金信息：
- DOI：10.13471/j.cnki.acta.snus.ZR20240309
  CLC： TP391
- Received：24 October 2024，
  
  Accepted：03 January 2025，
  
  Published Online：24 January 2025，
  
  Published：25 May 2025
- 稿件说明：
移动端阅览
姜永军,李红玲,阮萍等.基于深度学习的多亚型腹膜后软组织肉瘤诊断[J].中山大学学报(自然科学版)(中英文),2025,64(03):156-164.

JIANG Yongjun,LI Hongling,RUAN Ping,et al.Deep learning-based diagnosis of multi-subtype retroperitoneal soft tissue sarcomas[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2025,64(03):156-164.
姜永军,李红玲,阮萍等.基于深度学习的多亚型腹膜后软组织肉瘤诊断[J].中山大学学报(自然科学版)(中英文),2025,64(03):156-164. DOI： 10.13471/j.cnki.acta.snus.ZR20240309.

JIANG Yongjun,LI Hongling,RUAN Ping,et al.Deep learning-based diagnosis of multi-subtype retroperitoneal soft tissue sarcomas[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2025,64(03):156-164. DOI： 10.13471/j.cnki.acta.snus.ZR20240309.

摘要

在仅依赖组织病理图像且缺乏额外辅助检测的情况下，腹膜后软组织肉瘤小体积活检样本易导致观察者之间的判断差异，影响疾病亚型的整体诊断准确性。为了解决这一问题，从多中心收集了157张全切片图像（WSIs），涵盖去分化脂肪肉瘤、平滑肌肉瘤、恶性周围神经鞘瘤、未分化多形性肉瘤和高分化脂肪肉瘤五种疾病类别。基于上述WSIs，提出了基于单尺度图像与多尺度图像的两种模型集成方法，并利用ResNet18、EfficientNet B7和EfficientNet V2等深度学习模型进行训练。结果表明：两种模型集成方法均取得了较高的分类准确率，最佳模型在块级分析中达到82.27%的总体准确率，在全切片分析中达到80.95%。因此，所提方法能够有效辅助病理学家在临床实践中诊断腹膜后软组织肉瘤。

Abstract

In the absence of additional auxiliary tests and relying solely on histopathological images，small-volume biopsy samples of retroperitoneal soft tissue tumors often lead to interobserver variability，impacting the overall diagnostic accuracy of disease subtypes. To address this issue，157 whole-slide images（WSIs） were collected from multiple centers，encompassing five disease categories： dedifferentiated liposarcoma（DDLP），leiomyosarcoma（LMS），malignant peripheral nerve sheath tumor（MPNST），undifferentiated pleomorphic sarcoma（UPS），and well-differentiated liposarcoma（WDLP）. Based on these WSIs， two model ensemble methods were proposed： one based on single-scale images and the other on multi-scale images. Deep learning models，such as ResNet18，EfficientNet B7，and EfficientNet V2，were trained on the collected data. Results showed that both ensemble methods achieved high classification accuracy，with the best model achieving an overall accuracy of 82.27% in patch-level analysis and 80.95% in WSI-level analysis. Therefore，the proposed methods can effectively assist pathologists in the clinical diagnosis of retroperitoneal soft tissue tumors.

关键词

Keywords

references

ALMOND L ， TIROTTA F ， TATTERSALL H ， et al ， 2019 . Diagnostic accuracy of percutaneous biopsy in retroperitoneal sarcoma ［J］. Br J Surg ， 106 （ 4 ）： 395 - 403 .

ARUNACHALAM H B ， MISHRA R ， DAESCU O ， et al ， 2019 . Viable and necrotic tumor assessment from whole slide images of osteosarcoma using machine-learning and deep-learning models ［J］. PLoS One ， 14 （ 4 ）： 0210706 .

BENGIO Y ， COURVILLE A ， VINCENT P ， 2013 . Representation learning：A review and new perspectives ［J］. IEEE Trans Pattern Anal Mach Intell ， 35 （ 8 ）： 1798 - 1828 .

CUI M ， ZHANG D Y ， 2021 . Artificial intelligence and computational pathology ［J］. Lab Invest ， 101 （ 4 ）： 412 - 422 .

DROHAN A ， GRONCHI A ， 2023 . Next questions in the management of retroperitoneal sarcoma ［J］. Curr Opin Oncol ， 35 （ 4 ）： 301 - 308 .

FOERSCH S ， ECKSTEIN M ， WAGNER D C ， et al ， 2021 . Deep learning for diagnosis and survival prediction in soft tissue sarcoma ［J］. Ann Oncol ， 32 （ 9 ）： 1178 - 1187 .

HE K ， ZHANG X ， REN S ， et al ， 2016 . Deep residual learning for image recognition ［C］// IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas， NV， USA ： 770 - 778 .

LECUN Y ， BENGIO Y ， HINTON G ， 2015 . Deep learning ［J］. Nature ， 521 （ 7553 ）： 436 - 444 .

MACK T ， PURGINA B ， 2022 . Updates in pathology for retroperitoneal soft tissue sarcoma ［J］. Curr Oncol ， 29 （ 9 ）： 6400 - 6418 .

MARCOLINI A ， BUSSOLA N ， ARBITRIO E ， et al ， 2022 . Histolab：A python library for reproducible digital pathology preprocessing with automated testing ［J］. SoftwareX ， 20 ： 101237 .

MILEWSKI D ， JUNG H ， BROWN G T ， et al ， 2023 . Predicting molecular subtype and survival of rhabdomyosarcoma patients using deep learning of H&E images： A report from the children's oncology group ［J］. Clin Cancer Res ， 29 （ 2 ）： 364 - 378 .

MISHRA R ， DAESCU O ， LEAVEY P ， et al ， 2018 . Convolutional neural network for histopathological analysis of osteosarcoma ［J］. J Comput Biol ， 25 （ 3 ）： 313 - 325 .

TAN M ， LE Q ， 2019 . EfficientNet： Rethinking model scaling for convolutional neural networks ［C］// 36th International Conference on Machine Learning . Long Beach， CA， USA ： 6105 - 6114 .

TAN M ， LE Q ， 2021 . EfficientNet V2： Smaller models and faster training ［C］// 38th International Conference on Machine Learning . Graz，AT，Austria ： 10096 - 10106 .

TROJANI M ， CONTESSO G ， COINDRE J ， et al ， 1984 . Soft‐tissue sarcomas of adults； study of pathological prognostic variables and definition of a histopathological grading system ［J］. Int J Cancer ， 33 （ 1 ）： 37 - 42 .

van der LAAK J ， LITJENS G ， CIOMPI F ， 2021 . Deep learning in histopathology： The path to the clinic ［J］. Nat Med ， 27 （ 5 ）： 775 - 784 .

WOERL A C ， ECKSTEIN M ， GEIGER J ， et al ， 2020 . Deep learning predicts molecular subtype of muscle-invasive bladder cancer from conventional histopathological slides ［J］. Eur Urol ， 78 （ 2 ）： 256 - 264 .

YEUNG M C ， CHENG I S ， 2022 . Artificial intelligence significantly improves the diagnostic accuracy of deep myxoid soft tissue lesions in histology ［J］. Sci Rep ， 12 （ 1 ）： 6965 .

ZHANG H ， CISSE M ， DAUPHIN Y N ， et al ， 2018 . Mixup： Beyond empirical risk minimization ［EB/OL］. arxiv . 1710 . 09412 .

ZHAO Z ， CHEN X ， XU J ， et al ， 2023 . Whole exome sequencing of well-differentiated liposarcoma and dedifferentiated liposarcoma in older woman： A case report ［J］. Front Med ， 10 ： 1237246 .

Views

118

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Deep learning empowered beam management： State-of-the-art， challenges and opportunities

Semantic coding transmission method and application for industrial internet

Automatic detection of newly increased construction land based on deep learning and multi-source remote sensing data

Lattice Boltzmann method based on deep neural network

Related Author

JIANG Yongjun

LI Hongling

MENG Yunhe

XIE Gongxun

WANG Zhaocheng

MA Ke

NIU Kai

DONG Chao

Related Institution

Department of Electronic Engineering， Tsinghua University

School of Artificial Intelligence， Beijing University of Posts and Telecommunications

Peng Cheng Laboratory

The Key Laboratory of Universal Wireless Communications， Ministry of Education

School of Geographic Science and Planning， Sun Yat-sen University

Postal code：510275
Tel：020-84112585，84113223 Email：xuebaozr@mail.sysu.edu.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰