Segmentation of Lymph Nodes in Ultrasound Images using U-Net Convolutional Neural Networks and Gabor-based Anisotropic Diffusion

Abstract Objective Automated segmentation of lymph nodes (LNs) in ultrasound images is a challenging task mainly due to the presence of speckle noise and echogenic hila. In this paper, we propose a fully automatic and accurate method for LN segmentation in ultrasound. Methods The proposed segmentation method integrates diffusion-based despeckling, U-Net convolutional neural networks and morphological operations. Firstly, we suppress speckle noise and enhance lymph node edges using the Gabor-based anisotropic diffusion (GAD). Secondly, a modified U-Net model is proposed to segment LNs excluding echogenic hila. Finally, morphological operations are adopted to segment entire LNs by filling the regions of echogenic hila.Results A total of 531 lymph nodes from 526 patients were included to evaluate the proposed method. Quantitative metrics of segmentation performance, including the accuracy, sensitivity, specificity, Jaccard similarity and Dice coefficient, reached 0.934, 0.939, 0.937, 0.763 and 0.865, respectively.Conclusion The proposed method automatically and accurately segments LNs in ultrasound, which may assist artificially intelligent diagnosis of lymph node diseases.

Download Full-text

Segmentation of Lymph Nodes in Ultrasound Images Using U-Net Convolutional Neural Networks and Gabor-Based Anisotropic Diffusion

Journal of Medical and Biological Engineering ◽

10.1007/s40846-021-00670-8 ◽

2021 ◽

Author(s):

Haobo Chen ◽

Yuqun Wang ◽

Jie Shi ◽

Jingyu Xiong ◽

Jianwei Jiang ◽

...

Keyword(s):

Neural Networks ◽

Lymph Nodes ◽

Convolutional Neural Networks ◽

Anisotropic Diffusion ◽

Ultrasound Images

Download Full-text

Lymph node detection in MR Lymphography: false positive reduction using multi-view convolutional neural networks

PeerJ ◽

10.7717/peerj.8052 ◽

2019 ◽

Vol 7 ◽

pp. e8052

Author(s):

Oscar A. Debats ◽

Geert J.S. Litjens ◽

Henkjan J. Huisman

Keyword(s):

Prostate Cancer ◽

Neural Networks ◽

Lymph Node ◽

Lymph Nodes ◽

Convolutional Neural Networks ◽

False Positive ◽

Detection System ◽

False Positives ◽

Cad System ◽

Mr Lymphography

Purpose To investigate whether multi-view convolutional neural networks can improve a fully automated lymph node detection system for pelvic MR Lymphography (MRL) images of patients with prostate cancer. Methods A fully automated computer-aided detection (CAD) system had been previously developed to detect lymph nodes in MRL studies. The CAD system was extended with three types of 2D multi-view convolutional neural networks (CNN) aiming to reduce false positives (FP). A 2D multi-view CNN is an efficient approximation of a 3D CNN, and three types were evaluated: a 1-view, 3-view, and 9-view 2D CNN. The three deep learning CNN architectures were trained and configured on retrospective data of 240 prostate cancer patients that received MRL images as the standard of care between January 2008 and April 2010. The MRL used ferumoxtran-10 as a contrast agent and comprised at least two imaging sequences: a 3D T1-weighted and a 3D T2*-weighted sequence. A total of 5089 lymph nodes were annotated by two expert readers, reading in consensus. A first experiment compared the performance with and without CNNs and a second experiment compared the individual contribution of the 1-view, 3-view, or 9-view architecture to the performance. The performances were visually compared using free-receiver operating characteristic (FROC) analysis and statistically compared using partial area under the FROC curve analysis. Training and analysis were performed using bootstrapped FROC and 5-fold cross-validation. Results Adding multi-view CNNs significantly (p < 0.01) reduced false positive detections. The 3-view and 9-view CNN outperformed (p < 0.01) the 1-view CNN, reducing FP from 20.6 to 7.8/image at 80% sensitivity. Conclusion Multi-view convolutional neural networks significantly reduce false positives in a lymph node detection system for MRL images, and three orthogonal views are sufficient. At the achieved level of performance, CAD for MRL may help speed up finding lymph nodes and assessing them for potential metastatic involvement.

Download Full-text

Endobronchial ultrasound-guided transbronchial needle aspiration for lung cancer staging: early experience in Brazil,

Jornal Brasileiro de Pneumologia ◽

10.1590/s1806-37132015000100004 ◽

2015 ◽

Vol 41 (1) ◽

pp. 23-30 ◽

Cited By ~ 5

Author(s):

Viviane Rossi Figueiredo ◽

Paulo Francisco Guerreiro Cardoso ◽

Márcia Jacomelli ◽

Sérgio Eduardo Demarzo ◽

Addy Lidvina Mejia Palomino ◽

...

Keyword(s):

Lung Cancer ◽

Lymph Node ◽

Lymph Nodes ◽

Cancer Staging ◽

Accurate Method ◽

Needle Aspiration ◽

Endobronchial Ultrasound ◽

Lymph Node Staging ◽

Ultrasound Guided ◽

Transbronchial Needle Aspiration

Objective: Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a minimally invasive, safe and accurate method for collecting samples from mediastinal and hilar lymph nodes. This study focused on the initial results obtained with EBUS-TBNA for lung cancer and lymph node staging at three teaching hospitals in Brazil. Methods: This was a retrospective analysis of patients diagnosed with lung cancer and submitted to EBUS-TBNA for mediastinal lymph node staging. The EBUS-TBNA procedures, which involved the use of an EBUS scope, an ultrasound processor, and a compatible, disposable 22 G needle, were performed while the patients were under general anesthesia. Results: Between January of 2011 and January of 2014, 149 patients underwent EBUS-TBNA for lymph node staging. The mean age was 66 ± 12 years, and 58% were male. A total of 407 lymph nodes were sampled by EBUS-TBNA. The most common types of lung neoplasm were adenocarcinoma (in 67%) and squamous cell carcinoma (in 24%). For lung cancer staging, EBUS-TBNA was found to have a sensitivity of 96%, a specificity of 100%, and a negative predictive value of 85%. Conclusions: We found EBUS-TBNA to be a safe and accurate method for lymph node staging in lung cancer patients.

Download Full-text

Vehicle Trajectory Estimation Based on Fusion of Visual Motion Features and Deep Learning

Sensors ◽

10.3390/s21237969 ◽

2021 ◽

Vol 21 (23) ◽

pp. 7969

Author(s):

Lianen Qu ◽

Matthew N. Dailey

Keyword(s):

Neural Networks ◽

Optical Flow ◽

Convolutional Neural Networks ◽

Situation Awareness ◽

Visual Motion ◽

Accurate Method ◽

Estimation Methods ◽

Single Type ◽

Global Localization ◽

Trajectory Estimation

Driver situation awareness is critical for safety. In this paper, we propose a fast, accurate method for obtaining real-time situation awareness using a single type of sensor: monocular cameras. The system tracks the host vehicle’s trajectory using sparse optical flow and tracks vehicles in the surrounding environment using convolutional neural networks. Optical flow is used to measure the linear and angular velocity of the host vehicle. The convolutional neural networks are used to measure target vehicles’ positions relative to the host vehicle using image-based detections. Finally, the system fuses host and target vehicle trajectories in the world coordinate system using the velocity of the host vehicle and the target vehicles’ relative positions with the aid of an Extended Kalman Filter (EKF). We implement and test our model quantitatively in simulation and qualitatively on real-world test video. The results show that the algorithm is superior to state-of-the-art sequential state estimation methods such as visual SLAM in performing accurate global localization and trajectory estimation for host and target vehicles.

Download Full-text