Evaluating deep learning methods in detecting and segmenting different sizes of brain metastases on 3D post-contrast T1-weighted images
| Autor: | Eli Gibson, Yue Cao, Siqi Liu, Youngjin Yoo, James M. Balter, Thomas J. Re, Ceccaldi Pascal |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Image fusion
medicine.medical_specialty medicine.diagnostic_test Recall business.industry Deep learning Magnetic resonance imaging Image segmentation medicine.disease 030218 nuclear medicine & medical imaging Lesion 03 medical and health sciences 0302 clinical medicine 030220 oncology & carcinogenesis medicine Radiology Nuclear Medicine and imaging Segmentation Radiology Artificial intelligence medicine.symptom Ultrasonic Imaging and Tomography business Brain metastasis |
| Zdroj: | J Med Imaging (Bellingham) |
| ISSN: | 2329-4302 |
| DOI: | 10.1117/1.jmi.8.3.037001 |
| Popis: | Purpose: We investigate the impact of various deep-learning-based methods for detecting and segmenting metastases with different lesion volume sizes on 3D brain MR images. Approach: A 2.5D U-Net and a 3D U-Net were selected. We also evaluated weak learner fusion of the prediction features generated by the 2.5D and the 3D networks. A 3D fully convolutional one-stage (FCOS) detector was selected as a representative of bounding-box regression-based detection methods. A total of 422 3D post-contrast T1-weighted scans from patients with brain metastases were used. Performances were analyzed based on lesion volume, total metastatic volume per patient, and number of lesions per patient. Results: The performance of detection of the 2.5D and 3D U-Net methods had recall of [Formula: see text] and precision of [Formula: see text] for lesion volume [Formula: see text] but deteriorated as metastasis size decreased below [Formula: see text] to 0.58 to 0.74 in recall and 0.16 to 0.25 in precision. Compared the two U-Nets for detection capability, high precision was achieved by the 2.5D network, but high recall was achieved by the 3D network for all lesion sizes. The weak learner fusion achieved a balanced performance between the 2.5D and 3D U-Nets; particularly, it increased precision to 0.83 for lesion volumes of 0.1 to [Formula: see text] but decreased recall to 0.59. The 3D FCOS detector did not outperform the U-Net methods in detecting either the small or large metastases presumably because of the limited data size. Conclusions: Our study provides the performances of four deep learning methods in relationship to lesion size, total metastasis volume, and number of lesions per patient, providing insight into further development of the deep learning networks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|