SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching (2021-04-12T00:00:00.000000Z)

TL;DR

A 3D sphere representation-based center-points matching detection network (SCPM-Net) that is anchor-free and automatically predicts the position, radius, and offset of nodules without manual design of nodule/anchor parameters is proposed.

Authors

Dimitris N. Metaxas

3 papers

Jieneng Chen

5 papers

Guotai Wang

6 papers

Shaoting Zhang

7 papers

Xiangde Luo

4 papers

Tao Song

3 papers

Yinan Chen

2 papers

Kang Li

1 papers

TL;DR

Authors

References49 items

SANet: A Slice-Aware Network for Pulmonary Nodule Detection

CPM-Net: A 3D Center-Points Matching Network for Pulmonary Nodule Detection in CT Scans

CenterNet3D: An Anchor free Object Detector for Autonomous Driving

CircleNet: Anchor-free Detection with Circle Representation

SenseCare: a research platform for medical image informatics and interactive 3D visualization

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

A Two-Stage Convolutional Neural Networks for Lung Nodule Detection

Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

FreeAnchor: Learning to Match Anchors for Visual Object Detection

IoU Loss for 2D/3D Object Detection

NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation

Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels

Lung Nodule Detection with a 3D ConvNet via IoU Self-normalization and Maxout Unit

CenterNet: Keypoint Triplets for Object Detection

Objects as Points

Automatic Pulmonary Nodule Detection in CT Scans Using Convolutional Neural Networks Based on Maximum Intensity Projection

DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection

FCOS: Fully Convolutional One-Stage Object Detection

Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

Bottom-Up Object Detection by Grouping Extreme and Center Points

A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation

CornerNet: Detecting Objects as Paired Keypoints

Object Detection With Deep Learning: A Review

DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification

Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network

Squeeze-and-Excitation Networks

Automated Pulmonary Nodule Detection via 3D ConvNets with Online Sample Filtering and Hybrid-Loss Residual Learning

Focal Loss for Dense Object Detection

Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks

Guidelines for Management of Incidental Pulmonary Nodules Detected on CT Images: From the Fleischner Society 2017.

YOLO9000: Better, Faster, Stronger

Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge

Feature Pyramid Networks for Object Detection

UnitBox: An Advanced Object Detection Network

Training Region-Based Object Detectors with Online Hard Example Mining

SSD: Single Shot MultiBox Detector

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Microsoft COCO: Common Objects in Context

Measurements of digitized objects with fuzzy borders in 2D and 3D

IEEE Transactions on Neural Networks and Learning Systems

Cancer statistics, 2015

CA : A Cancer Journal for Clinicians

Medical Image Computing and Computer-Assisted Intervention

Cancer statistics

Edinburgh Research Explorer The PASCAL Visual Object Classes (VOC) Challenge

alleviate the gradient vanishing problem when there is not overlap between prediction and the ground truth

We present the ﬁrst attempt to represent the pulmonary nodule as a bounding sphere in 3D space

Field of Study

Journal Information

Name

Page

Volume