• Home
  • Search
  • Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features
  • Open Access IconOpen Access
  • Cite Icon81
  • https://doi.org/10.1088/1361-6560/ab326aCopy DOI Icon

Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

To predict lung nodule malignancy with a high sensitivity and specificity for low dose CT (LDCT) lung cancer screening, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine HF, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM). We then trained 3D CNNs modified from three 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract the CNN features learned at the output layer. For each 3D CNN, the CNN features combined with the 29 HF were used as the input for the support vector machine (SVM) coupled with the sequential forward feature selection (SFS) method to select the optimal feature subset and construct the classifiers. The fusion algorithm takes full advantage of the HF and the highest level CNN features learned at the output layer. It can overcome the disadvantage of the HF that may not fully reflect the unique characteristics of a particular lesion by combining the intrinsic CNN features. Meanwhile, it also alleviates the requirement of a large scale annotated dataset for the CNNs based on the complementary of HF. The patient cohort includes 431 malignant nodules and 795 benign nodules extracted from the LIDC/IDRI database. For each investigated CNN architecture, the proposed fusion algorithm achieved the highest AUC, accuracy, sensitivity, and specificity scores among all competitive classification models.

Similar Papers
  • Research Article
  • Citations139

Learning deep features to recognise speech emotion using merged deep CNN

  • Aug 01, 2018
  • IET Signal Processing
  • Jianfeng Zhao +2
  • PDF
  • Research Article
  • Citations3

Enhancement of ELDA Tracker Based on CNN Features and Adaptive Model Update

  • Apr 15, 2016
  • Sensors (Basel, Switzerland)
  • Changxin Gao +3
  • Conference Article
  • Citations16

Visual Sentiment Prediction by Merging Hand-Craft and CNN Features

  • Aug 01, 2018
  • Wang Fengjiao +1
  • Research Article
  • Citations6

A FUSION OF HAND-CRAFTED FEATURES AND DEEP NEURAL NETWORK FOR INDOOR SCENE CLASSIFICATION

  • Apr 30, 2023
  • Malaysian Journal of Computer Science
  • Basavaraj S Anami +1
  • Research Article
  • Citations1

Visual tracking with complementary deep feature optimization

  • Aug 27, 2018
  • Journal of Electronic Imaging
  • Wei Wang +2
  • Conference Article

Computerized determination scheme for histological classification of masses on breast ultrasonographic images using combination of CNN features and morphologic features

  • May 22, 2020
  • Shinya Kunieda +2
  • Research Article
  • Citations222

Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs

  • Oct 12, 2018
  • Computers in Biology and Medicine
  • Yu Gu +8
  • Conference Article
  • Citations11

Feature extraction of protein secondary structure using 2D convolutional neural network

  • Oct 01, 2016
  • Yihui Liu +2
  • Conference Article
  • Citations12

An Attention-based Hybrid 2D/3D CNN-LSTM for Human Action Recognition

  • Jan 25, 2022
  • Khaled Bayoudh +2
  • Conference Article
  • Citations2501

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?

  • Jun 01, 2018
  • Kensho Hara +2
  • Research Article
  • Citations32

Automated classification of nasal polyps in endoscopy video-frames using handcrafted and CNN features

  • Jun 13, 2022
  • Computers in Biology and Medicine
  • Betul Ay +4
  • Research Article
  • Citations338

Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high resolution oblique aerial images, and multiple-kernel-learning

  • Mar 09, 2017
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Anand Vetrivel +4
  • Research Article
  • Citations115

Stacking ensemble learning models for daily runoff prediction using 1D and 2D CNNs

  • Dec 24, 2022
  • Expert Systems with Applications
  • Yutong Xie +5
  • Research Article
  • Citations27

Integrating the Reconstructed Scattering Center Feature Maps With Deep CNN Feature Maps for Automatic SAR Target Recognition

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Jinsong Zhang +3
  • Conference Article
  • Citations263

Effective semantic pixel labelling with convolutional networks and Conditional Random Fields

  • Jun 01, 2015
  • Sakrapee Paisitkriangkrai +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.