Identification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristics

Abstract The axillary lymph node status remains an important prognostic factor in breast cancer, and nodal staging using sentinel lymph node biopsy (SLNB) is routine. Randomized clinical trials provide evidence supporting de-escalation of axillary surgery and omission of SLNB in patients at low risk...

Full description

Saved in:
Bibliographic Details
Main Authors: Daqu Zhang, Miriam Svensson, Patrik Edén, Looket Dihge
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-78040-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850062299055783936
author Daqu Zhang
Miriam Svensson
Patrik Edén
Looket Dihge
author_facet Daqu Zhang
Miriam Svensson
Patrik Edén
Looket Dihge
author_sort Daqu Zhang
collection DOAJ
description Abstract The axillary lymph node status remains an important prognostic factor in breast cancer, and nodal staging using sentinel lymph node biopsy (SLNB) is routine. Randomized clinical trials provide evidence supporting de-escalation of axillary surgery and omission of SLNB in patients at low risk. However, identifying sentinel lymph node macrometastases (macro-SLNMs) is crucial for planning treatment tailored to the individual patient. This study is the first to explore the capacity of deep learning (DL) models to identify macro-SLNMs based on preoperative clinicopathological characteristics. We trained and validated five multivariable models using a population-based cohort of 18,185 patients. DL models outperform logistic regression, with Transformer showing the strongest results, under the constraint that the sensitivity is no less than 90%, reflecting the sensitivity of SLNB. This highlights the feasibility of noninvasive macro-SLNM prediction using DL. Feature importance analysis revealed that patients with similar characteristics exhibited different nodal status predictions, indicating the need for additional predictors for further improvement.
format Article
id doaj-art-75ac2e84a7b143b286e6edf1cb6334fd
institution DOAJ
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-75ac2e84a7b143b286e6edf1cb6334fd2025-08-20T02:49:58ZengNature PortfolioScientific Reports2045-23222024-11-0114111510.1038/s41598-024-78040-yIdentification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristicsDaqu Zhang0Miriam Svensson1Patrik Edén2Looket Dihge3Division of Computational Science for Health and Environment, Center for Environmental and Climate Science, Lund UniversityDepartment of Clinical Sciences Lund, Division of Surgery, Lund UniversityDivision of Computational Science for Health and Environment, Center for Environmental and Climate Science, Lund UniversityDepartment of Clinical Sciences Lund, Division of Surgery, Lund UniversityAbstract The axillary lymph node status remains an important prognostic factor in breast cancer, and nodal staging using sentinel lymph node biopsy (SLNB) is routine. Randomized clinical trials provide evidence supporting de-escalation of axillary surgery and omission of SLNB in patients at low risk. However, identifying sentinel lymph node macrometastases (macro-SLNMs) is crucial for planning treatment tailored to the individual patient. This study is the first to explore the capacity of deep learning (DL) models to identify macro-SLNMs based on preoperative clinicopathological characteristics. We trained and validated five multivariable models using a population-based cohort of 18,185 patients. DL models outperform logistic regression, with Transformer showing the strongest results, under the constraint that the sensitivity is no less than 90%, reflecting the sensitivity of SLNB. This highlights the feasibility of noninvasive macro-SLNM prediction using DL. Feature importance analysis revealed that patients with similar characteristics exhibited different nodal status predictions, indicating the need for additional predictors for further improvement.https://doi.org/10.1038/s41598-024-78040-yBreast cancerLymphatic metastasisSentinel lymph nodeDeep learningClinical decision support
spellingShingle Daqu Zhang
Miriam Svensson
Patrik Edén
Looket Dihge
Identification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristics
Scientific Reports
Breast cancer
Lymphatic metastasis
Sentinel lymph node
Deep learning
Clinical decision support
title Identification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristics
title_full Identification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristics
title_fullStr Identification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristics
title_full_unstemmed Identification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristics
title_short Identification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristics
title_sort identification of sentinel lymph node macrometastasis in breast cancer by deep learning based on clinicopathological characteristics
topic Breast cancer
Lymphatic metastasis
Sentinel lymph node
Deep learning
Clinical decision support
url https://doi.org/10.1038/s41598-024-78040-y
work_keys_str_mv AT daquzhang identificationofsentinellymphnodemacrometastasisinbreastcancerbydeeplearningbasedonclinicopathologicalcharacteristics
AT miriamsvensson identificationofsentinellymphnodemacrometastasisinbreastcancerbydeeplearningbasedonclinicopathologicalcharacteristics
AT patrikeden identificationofsentinellymphnodemacrometastasisinbreastcancerbydeeplearningbasedonclinicopathologicalcharacteristics
AT looketdihge identificationofsentinellymphnodemacrometastasisinbreastcancerbydeeplearningbasedonclinicopathologicalcharacteristics