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

Abstract

Automatic diagnosing lung cancer from Computed Tomography (CT) scans involves two steps: detect all suspicious lesions (pulmonary nodules) and evaluate the whole-lung/pulmonary malignancy. Currently, there are many studies about the first step, but few about the second step. Since the existence of nodule does not definitely indicate cancer, and the morphology of nodule has a complicated relationship with cancer, the diagnosis of lung cancer demands careful investigations on every suspicious nodule and integration of information of all nodules. We propose a 3D deep neural network to solve this problem. The model consists of two modules. The first one is a 3D region proposal network for nodule detection, which outputs all suspicious nodules for a subject. The second one selects the top five nodules based on the detection confidence, evaluates their cancer probabilities and combines them with a leaky noisy-or gate to obtain the probability of lung cancer for the subject. The two modules share the same backbone network, a modified U-net. The over-fitting caused by the shortage of training data is alleviated by training the two modules alternately. The proposed model won the first place in the Data Science Bowl 2017 competition. The code has been made publicly available.

arXiv comment12 pages, 9 figures

References in corpus (8)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A Survey on Deep Learning in Medical Image Analysis
• Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge
• Revisiting Multiple Instance Neural Networks
• YOLO9000: Better, Faster, Stronger
• Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
• Unsupervised Learning of Noisy-Or Bayesian Networks

Cited by in corpus (39)

• Attention U-Net: Learning Where to Look for the Pancreas
• Recent advances and clinical applications of deep learning in medical image analysis
• SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching
• A Deep Learning System That Generates Quantitative CT Reports for Diagnosing Pulmonary Tuberculosis
• DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification
• A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data
• Interpretative Computer-aided Lung Cancer Diagnosis: from Radiology Analysis to Malignancy Evaluation
• Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers
• Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guiding
• Stabilized Medical Image Attacks
• DeepEM: Deep 3D ConvNets With EM For Weakly Supervised Pulmonary Nodule Detection
• NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation
• Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets
• Distanced LSTM: Time-Distanced Gates in Long Short-Term Memory Models for Lung Cancer Detection
• FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
• 3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection
• Deep Learning on Point Clouds for False Positive Reduction at Nodule Detection in Chest CT Scans
• Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention
• A new semi-supervised self-training method for lung cancer prediction
• Technical Report: Quality Assessment Tool for Machine Learning with Clinical CT
• 3D Aggregated Faster R-CNN for General Lesion Detection
• DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection
• Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
• Attentive CT Lesion Detection Using Deep Pyramid Inference with Multi-Scale Booster
• Internal-transfer Weighting of Multi-task Learning for Lung Cancer Detection
• SSMD: Semi-Supervised Medical Image Detection with Adaptive Consistency and Heterogeneous Perturbation
• Deep Learning for Automated Medical Image Analysis
• Lung Cancer Detection using Co-learning from Chest CT Images and Clinical Demographics
• Survey of the Detection and Classification of Pulmonary Lesions via CT and X-Ray
• Region-Manipulated Fusion Networks for Pancreatitis Recognition
• Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs
• Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective
• Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition
• Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network
• Primary Tumor Origin Classification of Lung Nodules in Spectral CT using Transfer Learning
• PGD-UNet: A Position-Guided Deformable Network for Simultaneous Segmentation of Organs and Tumors
• Deep Multi-task Prediction of Lung Cancer and Cancer-free Progression from Censored Heterogenous Clinical Imaging
• Exploring Instance-Level Uncertainty for Medical Detection
• Deep Multi-path Network Integrating Incomplete Biomarker and Chest CT Data for Evaluating Lung Cancer Risk