Independent Validation of a Deep Learning nnU-Net Tool for Neuroblastoma Detection and Segmentation in MR Images
Cancers · 06.03.2023 · 15 (5) · 1622
DOI: 10.3390/cancers15051622 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancers, online erschienen am 06.03.2023. Verfasst von Diana Veiga-Canuto und 17 weiteren Autor:innen. Beteiligte Einrichtung: Grupo de Investigación Biomédica en Imagen, Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106 Torre A 7planta, 46026 …. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission, PRIMAGE.
Abstract (Originalsprache)
Objectives
To externally validate and assess the accuracy of a previously trained fully automatic nnU-Net CNN algorithm to identify and segment primary neuroblastoma tumors in MR images in a large children cohort.
Methods
An international multicenter, multivendor imaging repository of patients with neuroblastic tumors was used to validate the performance of a trained Machine Learning (ML) tool to identify and delineate primary neuroblastoma tumors. The dataset was heterogeneous and completely independent from the one used to train and tune the model, consisting of 300 children with neuroblastic tumors having 535 MR T2-weighted sequences (486 sequences at diagnosis and 49 after finalization of the first phase of chemotherapy). The automatic segmentation algorithm was based on a nnU-Net architecture developed within the PRIMAGE project. For comparison, the segmentation masks were manually edited by an expert radiologist, and the time for the manual editing was recorded. Different overlaps and spatial metrics were calculated to compare both masks.
Results
The median Dice Similarity Coefficient (DSC) was high 0.997; 0.944–1.000 (median; Q1–Q3). In 18 MR sequences (6%), the net was not able neither to identify nor segment the tumor. No differences were found regarding the MR magnetic field, type of T2 sequence, or tumor location. No significant differences in the performance of the net were found in patients with an MR performed after chemotherapy. The time for visual inspection of the generated masks was 7.9 ± 7.5 (mean ± Standard Deviation (SD)) seconds. Those cases where manual editing was needed (136 masks) required 124 ± 120 s.
Conclusions
The automatic CNN was able to locate and segment the primary tumor on the T2-weighted images in 94% of cases. There was an extremely high agreement between the automatic tool and the manually edited masks. This is the first study to validate an automatic segmentation model for neuroblastic tumor identification and segmentation with body MR images. The semi-automatic approach with minor manual editing of the deep learning segmentation increases the radiologist’s confidence in the solution with a minor workload for the radiologist.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Grupo de Investigación Biomédica en Imagen, Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106 Torre A 7planta, 46026 Valencia, Spain.
- Área Clínica de Imagen Médica, Hospital Universitario y Politécnico La Fe, Avenida Fernando Abril Martorell, 106 Torre A 7planta, 46026 Valencia, Spain.
- Quantitative Imaging Biomarkers in Medicine, QUIBIM SL, 46026 Valencia, Spain.
- Departamento de Estadística e Investigación Operativa Aplicadas y Calidad, Universitat Politècnica de València, Camí de Vera s/n, 46022 Valencia, Spain.
- Unidad de Oncohematología Pediátrica, Hospital Universitario y Politécnico La Fe, Avenida Fernando Abril Martorell, 106 Torre A 7planta, 46026 Valencia, Spain.
- St. Anna Children's Cancer Research Institute, Zimmermannplatz 10, 1090 Vienna, Austria.
ORCID-Profile: Diana Veiga-Canuto, Leonor Cerdà-Alberich, Ana Jiménez-Pastor, José Miguel Carot Sierra, Armando Gomis-Maya, Matías Fernández-Patón, Sabine Taschner-Mandl, Thorsten Simon, Emanuele Neri, Luis Martí-Bonmatí
Förderung
- European Commission
- PRIMAGE
Zitieren
APA
Veiga-Canuto, D., Cerdà-Alberich, L., Jiménez-Pastor, A., Carot Sierra, J. M., Gomis-Maya, A., Sangüesa-Nebot, C., Fernández-Patón, M., Martínez de Las Heras, B., Taschner-Mandl, S., Düster, V., Pötschger, U., Simon, T., Neri, E., Alberich-Bayarri, Á., Cañete, A., Hero, B., Ladenstein, R., & Martí-Bonmatí, L. (2023). Independent Validation of a Deep Learning nnU-Net Tool for Neuroblastoma Detection and Segmentation in MR Images. Cancers, 15(5), 1622. https://doi.org/10.3390/cancers15051622
Vancouver
Veiga-Canuto D, Cerdà-Alberich L, Jiménez-Pastor A, Carot Sierra JM, Gomis-Maya A, Sangüesa-Nebot C, et al. Independent Validation of a Deep Learning nnU-Net Tool for Neuroblastoma Detection and Segmentation in MR Images. Cancers. 2023;15(5):1622. doi:10.3390/cancers15051622
BibTeX
@article{VeigaCanuto2023,
author = {Veiga-Canuto, Diana and Cerdà-Alberich, Leonor and Jiménez-Pastor, Ana and Carot Sierra, José Miguel and Gomis-Maya, Armando and Sangüesa-Nebot, Cinta and Fernández-Patón, Matías and Martínez de Las Heras, Blanca and Taschner-Mandl, Sabine and Düster, Vanessa and Pötschger, Ulrike and Simon, Thorsten and Neri, Emanuele and Alberich-Bayarri, Ángel and Cañete, Adela and Hero, Barbara and Ladenstein, Ruth and Martí-Bonmatí, Luis},
title = {Independent Validation of a Deep Learning nnU-Net Tool for Neuroblastoma Detection and Segmentation in MR Images},
journal = {Cancers},
year = {2023},
volume = {15},
number = {5},
pages = {1622},
doi = {10.3390/cancers15051622}
}
EUVIMED