Receptive Field Size as a Key Design Parameter for Ultrasound Image Segmentation with U-Net

Behboodi, Bahareh; Fortin, Maryse; Belasso, Clyde; Brooks, Rupert; Rivaz, Hassan

doi:10.1109/embc44109.2020.9175846

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep layer neurons have undergone more complicated calculations than shallow layer neurons, and the receptive field mapped on the original image is more extensive. Therefore, the extracted features are more abstract, and more detailed information is lost [25][26][27][28][29][30]. The first 52 layers in Darknet-53 are used for feature extraction, and the last layer is the output layer.…”

Section: Yolo V3 Backbonementioning

confidence: 99%

A Suspicious Multi-Object Detection and Recognition Method for Millimeter Wave SAR Security Inspection Images Based on Multi-Path Extraction Network

Yuan

Zhang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

There are several major challenges in detecting and recognizing multiple hidden objects from millimeter wave SAR security inspection images: inconsistent clarity of objects, similar objects, and complex background interference. To address these problems, a suspicious multi-object detection and recognition method based on the Multi-Path Extraction Network (MPEN) is proposed. In MPEN, You Only Look Once (YOLO) v3 is used as the base network, and then the Multi-Path Feature Pyramid (MPFP) module and modified residual block distribution are proposed. MPFP is designed to output the deep network feature layers separately. Then, to distinguish similar objects more easily, the residual block distribution is modified to improve the ability of the shallow network to capture details. To verify the effectiveness of the proposed method, the millimeter wave SAR images from the laboratory’s self-developed security inspection system are utilized in conducting research on multi-object detection and recognition. The detection rate (probability of detecting a target) and average false alarm (probability of error detection) rate of our method on the target are 94.6% and 14.6%, respectively. The mean Average Precision (mAP) of recognizing multi-object is 82.39%. Compared with YOLOv3, our method shows a better performance in detecting and recognizing similar targets.

show abstract

Section: Yolo V3 Backbonementioning

confidence: 99%

A Suspicious Multi-Object Detection and Recognition Method for Millimeter Wave SAR Security Inspection Images Based on Multi-Path Extraction Network

Yuan

Zhang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Modifying the receptive field to account for dataset-specific feature sizes has lead to increased performance in acoustic scene classification (Koutini et al, 2019), ultrasound image segmentation (Behboodi et al, 2020), and high-resolution TEM image denoising (Vincent et al, 2021). Specifically with TEM images, it has been suggested that the receptive field needs to account for the larger length scales of the features of interest (Horwath et al, 2020), and by increasing the receptive field accordingly, researchers were able to achieve much better denoising performance (Vincent et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Understanding the Influence of Receptive Field and Network Complexity in Neural Network-Guided TEM Image Analysis

Sytwu

Groschner

Scott

2022

Microscopy and Microanalysis

View full text Add to dashboard Cite

Trained neural networks are promising tools to analyze the ever-increasing amount of scientific image data, but it is unclear how to best customize these networks for the unique features in transmission electron micrographs. Here, we systematically examine how neural network architecture choices affect how neural networks segment, or pixel-wise separate, crystalline nanoparticles from amorphous background in transmission electron microscopy (TEM) images. We focus on decoupling the influence of receptive field, or the area of the input image that contributes to the output decision, from network complexity, which dictates the number of trainable parameters. For low-resolution TEM images which rely on amplitude contrast to distinguish nanoparticles from background, we find that the receptive field does not significantly influence segmentation performance. On the other hand, for high-resolution TEM images which rely on both amplitude and phase-contrast changes to identify nanoparticles, receptive field is an important parameter for increased performance, especially in images with minimal amplitude contrast. Rather than depending on atom or nanoparticle size, the ideal receptive field seems to be inversely correlated to the degree of nanoparticle contrast in the image. Our results provide insight and guidance as to how to adapt neural networks for applications with TEM datasets.

show abstract

A novel convolutional neural network for kidney ultrasound images segmentation

Chen

Yin

Dai

et al. 2022

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Receptive Field Size as a Key Design Parameter for Ultrasound Image Segmentation with U-Net

Cited by 4 publications

References 9 publications

A Suspicious Multi-Object Detection and Recognition Method for Millimeter Wave SAR Security Inspection Images Based on Multi-Path Extraction Network

A Suspicious Multi-Object Detection and Recognition Method for Millimeter Wave SAR Security Inspection Images Based on Multi-Path Extraction Network

Understanding the Influence of Receptive Field and Network Complexity in Neural Network-Guided TEM Image Analysis

A novel convolutional neural network for kidney ultrasound images segmentation

Contact Info

Product

Resources

About