You are here

Article Text

Article menu
Download PDFPDF
Original research
Automatic CD30 scoring method for whole slide images of primary cutaneous CD30+ lymphoproliferative diseases
  1. Tingting Zheng1,
  2. Song Zheng2,3,4,
  3. Ke Wang1,
  4. Hao Quan1,
  5. Qun Bai1,
  6. Shuqin Li1,
  7. Ruiqun Qi2,3,4,
  8. Yue Zhao1,3,
  9. Xiaoyu Cui1,
  10. Xinghua Gao2,3,4
  1. 1 College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China
  2. 2 Department of Dermatology, The First Hospital of China Medical University, Shenyang, Liaoning, China
  3. 3 National and Local Joint Engineering Research Center of Immunodermatological Theranostics No, Heping District, Liaoning Province, China
  4. 4 NHC Key Laboratory of Immunodermatology, Heping District, Liaoning Province, China
  1. Correspondence to Dr Xiaoyu Cui, Northeastern University, Shenyang, Liaoning Province, China; cuixy{at}bmie.neu.edu.cn; Dr Yue Zhao; zhaoyue{at}bmie.neu.edu.cn; Dr Xinghua Gao; gaobarry{at}hotmail.com

Abstract

Aims Deep-learning methods for scoring biomarkers are an active research topic. However, the superior performance of many studies relies on large datasets collected from clinical samples. In addition, there are fewer studies on immunohistochemical marker assessment for dermatological diseases. Accordingly, we developed a method for scoring CD30 based on convolutional neural networks for a few primary cutaneous CD30+ lymphoproliferative disorders and used this method to evaluate other biomarkers.

Methods A multipatch spatial attention mechanism and conditional random field algorithm were used to fully fuse tumour tissue characteristics on immunohistochemical slides and alleviate the few sample feature deficits. We trained and tested 28 CD30+ immunohistochemical whole slide images (WSIs), evaluated them with a performance index, and compared them with the diagnoses of senior dermatologists. Finally, the model’s performance was further demonstrated on the publicly available Yale HER2 cohort.

Results Compared with the diagnoses by senior dermatologists, this method can better locate the tumour area and reduce the misdiagnosis rate. The prediction of CD3 and Ki-67 validated the model’s ability to identify other biomarkers.

Conclusions In this study, using a few immunohistochemical WSIs, our model can accurately identify CD30, CD3 and Ki-67 markers. In addition, the model could be applied to additional tumour identification tasks to aid pathologists in diagnosis and benefit clinical evaluation.

  • automation
  • image processing, computer-assisted
  • immunohistochemistry
  • pathology, surgical
  • biomarkers, tumor

Data availability statement

Data are available on reasonable request. Our Code is available at https://github.com/titizheng/MPSANet_BiomarkerScores. The Yale HER2 cohort dataset was obtained from SamanFarahmand's project (https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=119702524). As the use of this dataset is subject to critical review by the hospital, if other researchers require this dataset, they can contact the corresponding author of this paper.

https://doi.org/10.1136/jcp-2022-208344

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data are available on reasonable request. Our Code is available at https://github.com/titizheng/MPSANet_BiomarkerScores. The Yale HER2 cohort dataset was obtained from SamanFarahmand's project (https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=119702524). As the use of this dataset is subject to critical review by the hospital, if other researchers require this dataset, they can contact the corresponding author of this paper.

    View Full Text

    Footnotes

    • Handling editor Runjan Chetty.

    • TZ and SZ contributed equally.

    • Contributors XC is the guarantor of this study. TZ wrote the manuscript and developed the network together with the assistance of KW; SZ annotated all the WSIs and evaluated the model results; HQ, QB and SL provided additional guidance on the network design part of the project; RQ and XG assisted in the annotation of all the WSIs data and guided on clinical and pathology related matters; RQ, XG, YZ and XC provided financial and laboratory equipment support.

    • Funding Supported by the National Nature Science Foundation of China (U1908206), 'Double hundred project' major scientific and technological achievements transformation project (Z19-4-010), Key research and development program of Liaoning Province (2019JH8/10300003),The Fundamental Research Funds for the Central Universities (N2219001), Ningbo Science and Technology Major Project (2021Z027).

    • Competing interests None declared.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.