A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study
Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a cornerstone in minimally invasive thoracic lymph node sampling. In lung cancer staging, precise assessment of lymph node position is crucial for clinical decision-making. This study aimed to demonstrate a new deep lear...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/1/10 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588299373379584 |
|---|---|
| author | Øyvind Ervik Mia Rødde Erlend Fagertun Hofstad Ingrid Tveten Thomas Langø Håkon O. Leira Tore Amundsen Hanne Sorger |
| author_facet | Øyvind Ervik Mia Rødde Erlend Fagertun Hofstad Ingrid Tveten Thomas Langø Håkon O. Leira Tore Amundsen Hanne Sorger |
| author_sort | Øyvind Ervik |
| collection | DOAJ |
| description | Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a cornerstone in minimally invasive thoracic lymph node sampling. In lung cancer staging, precise assessment of lymph node position is crucial for clinical decision-making. This study aimed to demonstrate a new deep learning method to classify thoracic lymph nodes based on their anatomical location using EBUS images. Bronchoscopists labeled lymph node stations in real-time according to the Mountain Dressler nomenclature. EBUS images were then used to train and test a deep neural network (DNN) model, with intraoperative labels as ground truth. In total, 28,134 EBUS images were acquired from 56 patients. The model achieved an overall classification accuracy of 59.5 ± 5.2%. The highest precision, sensitivity, and F1 score were observed in station 4L, 77.6 ± 13.1%, 77.6 ± 15.4%, and 77.6 ± 15.4%, respectively. The lowest precision, sensitivity, and F1 score were observed in station 10L. The average processing and prediction time for a sequence of ten images was 0.65 ± 0.04 s, demonstrating the feasibility of real-time applications. In conclusion, the new DNN-based model could be used to classify lymph node stations from EBUS images. The method performance was promising with a potential for clinical use. |
| format | Article |
| id | doaj-art-b12927b642d9449d92b24919a3858d60 |
| institution | Kabale University |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-b12927b642d9449d92b24919a3858d602025-01-24T13:36:15ZengMDPI AGJournal of Imaging2313-433X2025-01-011111010.3390/jimaging11010010A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept StudyØyvind Ervik0Mia Rødde1Erlend Fagertun Hofstad2Ingrid Tveten3Thomas Langø4Håkon O. Leira5Tore Amundsen6Hanne Sorger7Clinic of Medicine, Nord-Trøndelag Hospital Trust, Levanger Hospital, 7601 Levanger, NorwayDepartment of Health Research, SINTEF Digital, 7034 Trondheim, NorwayDepartment of Health Research, SINTEF Digital, 7034 Trondheim, NorwayDepartment of Health Research, SINTEF Digital, 7034 Trondheim, NorwayDepartment of Health Research, SINTEF Digital, 7034 Trondheim, NorwayDepartment of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, 7030 Trondheim, NorwayDepartment of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, 7030 Trondheim, NorwayClinic of Medicine, Nord-Trøndelag Hospital Trust, Levanger Hospital, 7601 Levanger, NorwayEndobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a cornerstone in minimally invasive thoracic lymph node sampling. In lung cancer staging, precise assessment of lymph node position is crucial for clinical decision-making. This study aimed to demonstrate a new deep learning method to classify thoracic lymph nodes based on their anatomical location using EBUS images. Bronchoscopists labeled lymph node stations in real-time according to the Mountain Dressler nomenclature. EBUS images were then used to train and test a deep neural network (DNN) model, with intraoperative labels as ground truth. In total, 28,134 EBUS images were acquired from 56 patients. The model achieved an overall classification accuracy of 59.5 ± 5.2%. The highest precision, sensitivity, and F1 score were observed in station 4L, 77.6 ± 13.1%, 77.6 ± 15.4%, and 77.6 ± 15.4%, respectively. The lowest precision, sensitivity, and F1 score were observed in station 10L. The average processing and prediction time for a sequence of ten images was 0.65 ± 0.04 s, demonstrating the feasibility of real-time applications. In conclusion, the new DNN-based model could be used to classify lymph node stations from EBUS images. The method performance was promising with a potential for clinical use.https://www.mdpi.com/2313-433X/11/1/10endobronchial ultrasoundAI-augmented EBUSdeep learningdeep neural networkslymph node classificationlymph node staging |
| spellingShingle | Øyvind Ervik Mia Rødde Erlend Fagertun Hofstad Ingrid Tveten Thomas Langø Håkon O. Leira Tore Amundsen Hanne Sorger A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study Journal of Imaging endobronchial ultrasound AI-augmented EBUS deep learning deep neural networks lymph node classification lymph node staging |
| title | A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study |
| title_full | A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study |
| title_fullStr | A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study |
| title_full_unstemmed | A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study |
| title_short | A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study |
| title_sort | new deep learning based method for automated identification of thoracic lymph node stations in endobronchial ultrasound ebus a proof of concept study |
| topic | endobronchial ultrasound AI-augmented EBUS deep learning deep neural networks lymph node classification lymph node staging |
| url | https://www.mdpi.com/2313-433X/11/1/10 |
| work_keys_str_mv | AT øyvindervik anewdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT miarødde anewdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT erlendfagertunhofstad anewdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT ingridtveten anewdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT thomaslangø anewdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT hakonoleira anewdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT toreamundsen anewdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT hannesorger anewdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT øyvindervik newdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT miarødde newdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT erlendfagertunhofstad newdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT ingridtveten newdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT thomaslangø newdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT hakonoleira newdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT toreamundsen newdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy AT hannesorger newdeeplearningbasedmethodforautomatedidentificationofthoraciclymphnodestationsinendobronchialultrasoundebusaproofofconceptstudy |