U-Det: A Modified U-Net architecture with bidirectional feature network for lung nodule segmentation (2020-03-20T00:00:00.000000Z)

TL;DR

U-Det, a resource-efficient model architecture, which is an end to end deep learning approach to solve the task at hand, incorporates a Bi-FPN (bidirectional feature network) between the encoder and decoder and uses Mish activation function and class weights of masks to enhance segmentation efficiency.

Abstract

Early diagnosis and analysis of lung cancer involve a precise and efficient lung nodule segmentation in computed tomography (CT) images. However, the anonymous shapes, visual features, and surroundings of the nodule in the CT image pose a challenging problem to the robust segmentation of the lung nodules. This article proposes U-Det, a resource-efficient model architecture, which is an end to end deep learning approach to solve the task at hand. It incorporates a Bi-FPN (bidirectional feature network) between the encoder and decoder. Furthermore, it uses Mish activation function and class weights of masks to enhance segmentation efficiency. The proposed model is extensively trained and evaluated on the publicly available LUNA-16 dataset consisting of 1186 lung nodules. The U-Det architecture outperforms the existing U-Net model with the Dice similarity coefficient (DSC) of 82.82% and achieves results comparable to human experts.

Authors

Nikhil Varma Keetha

1 papers

P. SamsonAnoshBabu

1 papers

Chandra Sekhara Rao Annavarapu

1 papers

TL;DR

Abstract

Authors

References58 items

EfficientDet: Scalable and Efficient Object Detection

Mish: A Self Regularized Non-Monotonic Neural Activation Function

A survey on Image Data Augmentation for Deep Learning

Dual-branch residual network for lung nodule segmentation

Fine-grained lung nodule segmentation with pyramid deconvolutional neural network

A new effective and powerful medical image segmentation algorithm based on optimum path snakes

Data augmentation for improving deep learning in image classification problem

Capsules for Object Segmentation

3D multi-view convolutional neural networks for lung nodule classification

Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis

A multi-view deep convolutional neural networks for lung nodule segmentation

Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation

Lung nodule segmentation using deep learned prior based graph cut

Semi-automatic 3D lung nodule segmentation in CT using dynamic programming

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

Automatic Approach for Lung Segmentation with Juxta-Pleural Nodules from Thoracic CT Based on Contour Tracing and Correction

Hessian based approaches for 3D lung nodule segmentation

Segmentation of lung nodule in CT data using active contour model and Fuzzy C-mean clustering

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

A neural network approach to lung nodule segmentation

Automatic detection of large pulmonary solid nodules in thoracic CT images.

U-Net: Convolutional Networks for Biomedical Image Segmentation

Brain tumor segmentation with Deep Neural Networks

Adam: A Method for Stochastic Optimization

Fully convolutional networks for semantic segmentation

Dropout Rademacher complexity of deep neural networks

Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images

A Novel Approach for Lung Nodules Segmentation in Chest CT Using Level Sets

Computer Aided Diagnosis Using Multilevel Image Features on Large-Scale Evaluation

Automated Segmentation Refinement of Small Lung Nodules in CT Scans by Local Shape Analysis

Lung imaging and computer-aided diagnosis

Effective 3D object detection and regression using probabilistic segmentation features in CT images

The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans.

Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models

Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels

Stratified learning of local anatomical context for lung nodules in CT images

Computer-aided diagnosis of lung nodules on CT scans: ROC study of its effect on radiologists' performance.

A large-scale evaluation of automatic pulmonary nodule detection in chest CT using local image features and k-nearest-neighbour classification

Automatic lung segmentation from thoracic computed tomography scans using a hybrid approach with error detection.

Accurate polyp segmentation for 3D CT colongraphy using multi-staged probabilistic binary learning and compositional model

Segmentation of Pulmonary Nodules in Thoracic CT Scans: A Region Growing Approach

Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans

Guidelines for management of small pulmonary nodules detected on CT scans: a statement from the Fleischner Society.

Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical CT images

An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision

Active contours without edges

Mish: A Self Regularized Non-Monotonic Activation Function

Ground-glass nodule segmentation in chest CT images using asymmetric multi-phase deformable model and pulmonary vessel removal

Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification

Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II

Automated tissue segmentation of MR brain images in the presence of white matter lesions

Cancer statistics, 2016

CA : A Cancer Journal for Clinicians

Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping

Cancer statistics

Série Scientifique Scientific Series No Unbiased Estimator of the Variance of K-fold Cross-validation No Unbiased Estimator of the Variance of K-fold Cross-validation

The proposed U-Det model uses a bidirectional feature network, which functions as a feature enricher, integrating multi-scale feature fusion for efﬁcient feature extraction

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names