Improving Computer-aided Detection using Convolutional Neural Networks and Random View Aggregation

Abstract

Automated computer-aided detection (CADe) in medical imaging has been an important tool in clinical practice and research. State-of-the-art methods often show high sensitivities but at the cost of high false-positives (FP) per patient rates. We design a two-tiered coarse-to-fine cascade framework that first operates a candidate generation system at sensitivities of $\sim$100% but at high FP levels. By leveraging existing CAD systems, coordinates of regions or volumes of interest (ROI or VOI) for lesion candidates are generated in this step and function as input for a second tier, which is our focus in this study. In this second stage, we generate $N$ 2D (two-dimensional) or 2.5D views via sampling through scale transformations, random translations and rotations with respect to each ROI's centroid coordinates. These random views are used to train deep convolutional neural network (ConvNet) classifiers. In testing, the trained ConvNets are employed to assign class (e.g., lesion, pathology) probabilities for a new set of $N$ random views that are then averaged at each ROI to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. The methods are evaluated on three different data sets with different numbers of patients: 59 patients for sclerotic metastases detection, 176 patients for lymph node detection, and 1,186 patients for colonic polyp detection. Experimental results show the ability of ConvNets to generalize well to different medical imaging CADe applications and scale elegantly to various data sets. Our proposed methods improve CADe performance markedly in all cases. CADe sensitivities improved from 57% to 70%, from 43% to 77% and from 58% to 75% at 3 FPs per patient for sclerotic metastases, lymph nodes and colonic polyps, respectively.

2D vs 2.5D vs 3D inputs and comparison to other standard classifiers such as SVM have been addressed by more experimentation and two completely new sections and figures. Results and Discussions have been updated accordingly

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Improving neural networks by preventing co-adaptation of feature detectors
• Two-Stream Convolutional Networks for Action Recognition in Videos
• How transferable are features in deep neural networks?
• One weird trick for parallelizing convolutional neural networks

Cited by in corpus (55)

• A Survey on Deep Learning in Medical Image Analysis
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• Recent advances and clinical applications of deep learning in medical image analysis
• Applications of Deep Learning and Reinforcement Learning to Biological Data
• CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
• Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method
• DeepPap: Deep Convolutional Networks for Cervical Cell Classification
• Automatic Classification of Cancerous Tissue in Laserendomicroscopy Images of the Oral Cavity using Deep Learning
• Models Genesis
• Generative Adversarial Network for Medical Images (MI-GAN)
• Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images
• Semantic Segmentation of Pathological Lung Tissue with Dilated Fully Convolutional Networks
• Predicting Lung Nodule Malignancies by Combining Deep Convolutional Neural Network and Handcrafted Features
• Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation
• Convolutional Invasion and Expansion Networks for Tumor Growth Prediction
• Multiple Sclerosis Lesion Segmentation from Brain MRI via Fully Convolutional Neural Networks
• Deep Model with Siamese Network for Viability and Necrosis Tumor Assessment in Osteosarcoma
• Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
• Learning protein conformational space by enforcing physics with convolutions and latent interpolations
• Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts
• A Deep Learning Approach for Pose Estimation from Volumetric OCT Data
• Deep learning in radiology: an overview of the concepts and a survey of the state of the art
• Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection
• Deep convolutional networks for automated detection of posterior-element fractures on spine CT
• Image Segmentation and Classification for Sickle Cell Disease using Deformable U-Net
• Deep Learning in Bioinformatics
• DeepHealth: Review and challenges of artificial intelligence in health informatics
• ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks
• Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding
• Spatial Aggregation of Holistically-Nested Convolutional Neural Networks for Automated Pancreas Localization and Segmentation
• Recurrent Convolutional Networks for Pulmonary Nodule Detection in CT Imaging
• Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database
• Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection
• A CADe System for Gliomas in Brain MRI using Convolutional Neural Networks
• Generative Adversarial U-Net for Domain-free Medical Image Augmentation
• Learning from Multiple Datasets with Heterogeneous and Partial Labels for Universal Lesion Detection in CT
• Tango: A Deep Neural Network Benchmark Suite for Various Accelerators
• Detecting Scatteredly-Distributed, Small, andCritically Important Objects in 3D OncologyImaging via Decision Stratification
• Deep Learning for Breast Cancer Classification: Enhanced Tangent Function
• Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets
• 3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection
• A Feature Transfer Enabled Multi-Task Deep Learning Model on Medical Imaging
• Integrating features from lymph node stations for metastatic lymph node detection
• Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
• Lymph Node Gross Tumor Volume Detection in Oncology Imaging via Relationship Learning Using Graph Neural Network
• Automatic Assessment of Full Left Ventricular Coverage in Cardiac Cine Magnetic Resonance Imaging with Fisher-Discriminative 3D CNN
• Lymph Node Gross Tumor Volume Detection and Segmentation via Distance-based Gating using 3D CT/PET Imaging in Radiotherapy
• ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
• AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging: Towards Radiophenomics
• Multi-Scale Gradual Integration CNN for False Positive Reduction in Pulmonary Nodule Detection
• Discovery Radiomics for Pathologically-Proven Computed Tomography Lung Cancer Prediction
• Feature2Mass: Visual Feature Processing in Latent Space for Realistic Labeled Mass Generation
• RTEX: A novel methodology for Ranking, Tagging, and Explanatory diagnostic captioning of radiography exams
• Random smooth gray value transformations for cross modality learning with gray value invariant networks