Skip to main content

ORIGINAL RESEARCH article

Front. Med.
Sec. Pathology
Volume 11 - 2024 | doi: 10.3389/fmed.2024.1418013
This article is part of the Research Topic Translational Digital Pathology to Enable Precision Oncology View all articles

Deep learning model shows pathologist-level detection of sentinel node metastasis of melanoma and intra-nodal nevi on whole slide images

Provisionally accepted
Jan Siarov Jan Siarov 1,2Angelica Siarov Angelica Siarov 1Darshan Kumar Darshan Kumar 3John Paoli John Paoli 4,5Johan Mölne Johan Mölne 1,2Noora Neittaanmäki Noora Neittaanmäki 1,2*
  • 1 Department of Clinical Pathology and Genetics, Sahlgrenska University Hospital, Gothenburg, Sweden
  • 2 Department of Laboratory Medicine,Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
  • 3 Aiforia Technologies Oy, Helsinki, Finland
  • 4 Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
  • 5 Department of Dermatology and Venereology, Sahlgrenska University Hospital, Gothenburg, Sweden

The final, formatted version of the article will be published soon.

    The presence of nodal metastasis (NM) in sentinel node biopsies (SNB) is a crucial part in melanoma staging. Further, an intra-nodal nevus (INN) may be misclassified as NM. There is high discordance in assessing SNB positivity which may lead to false staging. The use of digital whole slide imaging enables the implementation of artificial intelligence (AI) in digital pathology.We assessed the capability of AI in detection of NM and INN in SNBs.: In total, 485 hematoxylin and eosin whole slide images (WSIs) including NM and INN from 196 SNBs were collected and divided into training (279 WSIs), validation (89 WSIs) and test sets (117 WSIs). The deep learning model was trained with 5,956 manual pixelwise annotations. The test set was assessed by the AI and three blinded dermatopathologists. Immunohistochemistry served as the reference standard. Results: The AI model showed excellent performance with an area under the curve receiver operating characteristic (AUC) of 0.965 for detection of NM. For comparison, AUC for NM detection among the dermatopathologists varied between 0.94 and 0.98. For detection of INN, AUC was lower for both AI (0.781) and the dermatopathologists (range 0.63-0.79). Discussion: To conclude, the deep learning AI model showed excellent accuracy in detection of NM and dermatopathologist-level performance in detection of both NM and INN. Importantly, the AI model showed potential in differentiating between these two entities. Further validation is still warranted.

    Keywords: deep learning, artificial intelligence, digital pathology, Dermatopathology, Sentinel node biopsy, nodal melanoma metastasis, intra-nodal nevus Deep learning, intra-nodal nevus

    Received: 15 Apr 2024; Accepted: 29 Jul 2024.

    Copyright: © 2024 Siarov, Siarov, Kumar, Paoli, Mölne and Neittaanmäki. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Noora Neittaanmäki, Department of Clinical Pathology and Genetics, Sahlgrenska University Hospital, Gothenburg, Sweden

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.