Cargando…
A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes
Malignant lateral lymph nodes (LLNs) in low, locally advanced rectal cancer can cause (ipsi-lateral) local recurrences ((L)LR). Accurate identification is, therefore, essential. This study explored LLN features to create an artificial intelligence prediction model, estimating the risk of (L)LR. This...
Autores principales: | , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10572128/ https://www.ncbi.nlm.nih.gov/pubmed/37835842 http://dx.doi.org/10.3390/diagnostics13193099 |
_version_ | 1785120162023735296 |
---|---|
author | Sluckin, Tania C. Hekhuis, Marije Kol, Sabrine Q. Nederend, Joost Horsthuis, Karin Beets-Tan, Regina G. H. Beets, Geerard L. Burger, Jacobus W. A. Tuynman, Jurriaan B. Rutten, Harm J. T. Kusters, Miranda Benson, Sean |
author_facet | Sluckin, Tania C. Hekhuis, Marije Kol, Sabrine Q. Nederend, Joost Horsthuis, Karin Beets-Tan, Regina G. H. Beets, Geerard L. Burger, Jacobus W. A. Tuynman, Jurriaan B. Rutten, Harm J. T. Kusters, Miranda Benson, Sean |
author_sort | Sluckin, Tania C. |
collection | PubMed |
description | Malignant lateral lymph nodes (LLNs) in low, locally advanced rectal cancer can cause (ipsi-lateral) local recurrences ((L)LR). Accurate identification is, therefore, essential. This study explored LLN features to create an artificial intelligence prediction model, estimating the risk of (L)LR. This retrospective multicentre cohort study examined 196 patients diagnosed with rectal cancer between 2008 and 2020 from three tertiary centres in the Netherlands. Primary and restaging T2W magnetic resonance imaging and clinical features were used. Visible LLNs were segmented and used for a multi-channel convolutional neural network. A deep learning model was developed and trained for the prediction of (L)LR according to malignant LLNs. Combined imaging and clinical features resulted in AUCs of 0.78 and 0.80 for LR and LLR, respectively. The sensitivity and specificity were 85.7% and 67.6%, respectively. Class activation map explainability methods were applied and consistently identified the same high-risk regions with structural similarity indices ranging from 0.772–0.930. This model resulted in good predictive value for (L)LR rates and can form the basis of future auto-segmentation programs to assist in the identification of high-risk patients and the development of risk stratification models. |
format | Online Article Text |
id | pubmed-10572128 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-105721282023-10-14 A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes Sluckin, Tania C. Hekhuis, Marije Kol, Sabrine Q. Nederend, Joost Horsthuis, Karin Beets-Tan, Regina G. H. Beets, Geerard L. Burger, Jacobus W. A. Tuynman, Jurriaan B. Rutten, Harm J. T. Kusters, Miranda Benson, Sean Diagnostics (Basel) Article Malignant lateral lymph nodes (LLNs) in low, locally advanced rectal cancer can cause (ipsi-lateral) local recurrences ((L)LR). Accurate identification is, therefore, essential. This study explored LLN features to create an artificial intelligence prediction model, estimating the risk of (L)LR. This retrospective multicentre cohort study examined 196 patients diagnosed with rectal cancer between 2008 and 2020 from three tertiary centres in the Netherlands. Primary and restaging T2W magnetic resonance imaging and clinical features were used. Visible LLNs were segmented and used for a multi-channel convolutional neural network. A deep learning model was developed and trained for the prediction of (L)LR according to malignant LLNs. Combined imaging and clinical features resulted in AUCs of 0.78 and 0.80 for LR and LLR, respectively. The sensitivity and specificity were 85.7% and 67.6%, respectively. Class activation map explainability methods were applied and consistently identified the same high-risk regions with structural similarity indices ranging from 0.772–0.930. This model resulted in good predictive value for (L)LR rates and can form the basis of future auto-segmentation programs to assist in the identification of high-risk patients and the development of risk stratification models. MDPI 2023-09-29 /pmc/articles/PMC10572128/ /pubmed/37835842 http://dx.doi.org/10.3390/diagnostics13193099 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Sluckin, Tania C. Hekhuis, Marije Kol, Sabrine Q. Nederend, Joost Horsthuis, Karin Beets-Tan, Regina G. H. Beets, Geerard L. Burger, Jacobus W. A. Tuynman, Jurriaan B. Rutten, Harm J. T. Kusters, Miranda Benson, Sean A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes |
title | A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes |
title_full | A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes |
title_fullStr | A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes |
title_full_unstemmed | A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes |
title_short | A Deep Learning Framework with Explainability for the Prediction of Lateral Locoregional Recurrences in Rectal Cancer Patients with Suspicious Lateral Lymph Nodes |
title_sort | deep learning framework with explainability for the prediction of lateral locoregional recurrences in rectal cancer patients with suspicious lateral lymph nodes |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10572128/ https://www.ncbi.nlm.nih.gov/pubmed/37835842 http://dx.doi.org/10.3390/diagnostics13193099 |
work_keys_str_mv | AT sluckintaniac adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT hekhuismarije adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT kolsabrineq adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT nederendjoost adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT horsthuiskarin adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT beetstanreginagh adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT beetsgeerardl adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT burgerjacobuswa adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT tuynmanjurriaanb adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT ruttenharmjt adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT kustersmiranda adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT bensonsean adeeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT sluckintaniac deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT hekhuismarije deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT kolsabrineq deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT nederendjoost deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT horsthuiskarin deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT beetstanreginagh deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT beetsgeerardl deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT burgerjacobuswa deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT tuynmanjurriaanb deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT ruttenharmjt deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT kustersmiranda deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes AT bensonsean deeplearningframeworkwithexplainabilityforthepredictionoflaterallocoregionalrecurrencesinrectalcancerpatientswithsuspiciouslaterallymphnodes |