TY - JOUR
T1 - Automatic segmentation for magnetic resonance imaging guided individual elective lymph node irradiation in head and neck cancer patients
AU - Reinders, Floris C.J.
AU - Savenije, Mark H.F.
AU - de Ridder, Mischa
AU - Maspero, Matteo
AU - Doornaert, Patricia A.H.
AU - Terhaard, Chris H.J.
AU - Raaijmakers, Cornelis P.J.
AU - Zakeri, Kaveh
AU - Lee, Nancy Y.
AU - Aliotta, Eric
AU - Rangnekar, Aneesh
AU - Veeraraghavan, Harini
AU - Philippens, Marielle E.P.
N1 - Publisher Copyright:
© 2024 The Authors
PY - 2024/10
Y1 - 2024/10
N2 - Background and purpose: In head and neck squamous cell carcinoma (HNSCC) patients, the radiation dose to nearby organs at risk can be reduced by restricting elective neck irradiation from lymph node levels to individual lymph nodes. However, manual delineation of every individual lymph node is time-consuming and error prone. Therefore, automatic magnetic resonance imaging (MRI) segmentation of individual lymph nodes was developed and tested using a convolutional neural network (CNN). Materials and methods: In 50 HNSCC patients (UMC-Utrecht), individual lymph nodes located in lymph node levels Ib-II-III-IV-V were manually segmented on MRI by consensus of two experts, obtaining ground truth segmentations. A 3D CNN (nnU-Net) was trained on 40 patients and tested on 10. Evaluation metrics were Dice Similarity Coefficient (DSC), recall, precision, and F1-score. The segmentations of the CNN was compared to segmentations of two observers. Transfer learning was used with 20 additional patients to re-train and test the CNN in another medical center. Results: nnU-Net produced automatic segmentations of elective lymph nodes with median DSC: 0.72, recall: 0.76, precision: 0.78, and F1-score: 0.78. The CNN had higher recall compared to both observers (p = 0.002). No difference in evaluation scores of the networks in both medical centers was found after re-training with 5 or 10 patients. Conclusion: nnU-Net was able to automatically segment individual lymph nodes on MRI. The detection rate of lymph nodes using nnU-Net was higher than manual segmentations. Re-training nnU-Net was required to successfully transfer the network to the other medical center.
AB - Background and purpose: In head and neck squamous cell carcinoma (HNSCC) patients, the radiation dose to nearby organs at risk can be reduced by restricting elective neck irradiation from lymph node levels to individual lymph nodes. However, manual delineation of every individual lymph node is time-consuming and error prone. Therefore, automatic magnetic resonance imaging (MRI) segmentation of individual lymph nodes was developed and tested using a convolutional neural network (CNN). Materials and methods: In 50 HNSCC patients (UMC-Utrecht), individual lymph nodes located in lymph node levels Ib-II-III-IV-V were manually segmented on MRI by consensus of two experts, obtaining ground truth segmentations. A 3D CNN (nnU-Net) was trained on 40 patients and tested on 10. Evaluation metrics were Dice Similarity Coefficient (DSC), recall, precision, and F1-score. The segmentations of the CNN was compared to segmentations of two observers. Transfer learning was used with 20 additional patients to re-train and test the CNN in another medical center. Results: nnU-Net produced automatic segmentations of elective lymph nodes with median DSC: 0.72, recall: 0.76, precision: 0.78, and F1-score: 0.78. The CNN had higher recall compared to both observers (p = 0.002). No difference in evaluation scores of the networks in both medical centers was found after re-training with 5 or 10 patients. Conclusion: nnU-Net was able to automatically segment individual lymph nodes on MRI. The detection rate of lymph nodes using nnU-Net was higher than manual segmentations. Re-training nnU-Net was required to successfully transfer the network to the other medical center.
KW - Artificial intelligence
KW - Deep learning
KW - Elective neck irradiation
KW - Lymph nodes
KW - Magnetic resonance imaging
KW - Radiotherapy
KW - Squamous cell carcinoma of head and neck
UR - http://www.scopus.com/inward/record.url?scp=85206936267&partnerID=8YFLogxK
U2 - 10.1016/j.phro.2024.100655
DO - 10.1016/j.phro.2024.100655
M3 - Article
C2 - 39502445
AN - SCOPUS:85206936267
SN - 2405-6316
VL - 32
JO - Physics and Imaging in Radiation Oncology
JF - Physics and Imaging in Radiation Oncology
M1 - 100655
ER -