Back to Search
Start Over
Automated detection and segmentation of thoracic lymph nodes from CT using 3D foveal fully convolutional neural networks.
- Source :
-
BMC medical imaging [BMC Med Imaging] 2021 Apr 13; Vol. 21 (1), pp. 69. Date of Electronic Publication: 2021 Apr 13. - Publication Year :
- 2021
-
Abstract
- Background: In oncology, the correct determination of nodal metastatic disease is essential for patient management, as patient treatment and prognosis are closely linked to the stage of the disease. The aim of the study was to develop a tool for automatic 3D detection and segmentation of lymph nodes (LNs) in computed tomography (CT) scans of the thorax using a fully convolutional neural network based on 3D foveal patches.<br />Methods: The training dataset was collected from the Computed Tomography Lymph Nodes Collection of the Cancer Imaging Archive, containing 89 contrast-enhanced CT scans of the thorax. A total number of 4275 LNs was segmented semi-automatically by a radiologist, assessing the entire 3D volume of the LNs. Using this data, a fully convolutional neuronal network based on 3D foveal patches was trained with fourfold cross-validation. Testing was performed on an unseen dataset containing 15 contrast-enhanced CT scans of patients who were referred upon suspicion or for staging of bronchial carcinoma.<br />Results: The algorithm achieved a good overall performance with a total detection rate of 76.9% for enlarged LNs during fourfold cross-validation in the training dataset with 10.3 false-positives per volume and of 69.9% in the unseen testing dataset. In the training dataset a better detection rate was observed for enlarged LNs compared to smaller LNs, the detection rate for LNs with a short-axis diameter (SAD) ≥ 20 mm and SAD 5-10 mm being 91.6% and 62.2% (p < 0.001), respectively. Best detection rates were obtained for LNs located in Level 4R (83.6%) and Level 7 (80.4%).<br />Conclusions: The proposed 3D deep learning approach achieves an overall good performance in the automatic detection and segmentation of thoracic LNs and shows reasonable generalizability, yielding the potential to facilitate detection during routine clinical work and to enable radiomics research without observer-bias.
- Subjects :
- Adult
Aged
Axilla
Contrast Media administration & dosage
Datasets as Topic
Female
Humans
Lymphatic Metastasis diagnostic imaging
Male
Mediastinum
Middle Aged
Thorax
Carcinoma, Bronchogenic diagnostic imaging
Deep Learning
Lung Neoplasms diagnostic imaging
Lymph Nodes diagnostic imaging
Neural Networks, Computer
Tomography, X-Ray Computed methods
Subjects
Details
- Language :
- English
- ISSN :
- 1471-2342
- Volume :
- 21
- Issue :
- 1
- Database :
- MEDLINE
- Journal :
- BMC medical imaging
- Publication Type :
- Academic Journal
- Accession number :
- 33849483
- Full Text :
- https://doi.org/10.1186/s12880-021-00599-z