Detecting Scatteredly-Distributed, Small, andCritically Important Objects in 3D OncologyImaging via Decision Stratification

Finding and identifying scatteredly-distributed, small, and critically important objects in 3D oncology images is very challenging. We focus on the detection and segmentation of oncology-significant (or suspicious cancer metastasized) lymph nodes (OSLNs), which has not been studied before as a computational task. Determining and delineating the spread of OSLNs is essential in defining the corresponding resection/irradiating regions for the downstream workflows of surgical resection and radiotherapy of various cancers. For patients who are treated with radiotherapy, this task is performed by experienced radiation oncologists that involves high-level reasoning on whether LNs are metastasized, which is subject to high inter-observer variations. In this work, we propose a divide-and-conquer decision stratification approach that divides OSLNs into tumor-proximal and tumor-distal categories. This is motivated by the observation that each category has its own different underlying distributions in appearance, size and other characteristics. Two separate detection-by-segmentation networks are trained per category and fused. To further reduce false positives (FP), we present a novel global-local network (GLNet) that combines high-level lesion characteristics with features learned from localized 3D image patches. Our method is evaluated on a dataset of 141 esophageal cancer patients with PET and CT modalities (the largest to-date). Our results significantly improve the recall from $45\%$ to $67\%$ at $3$ FPs per patient as compared to previous state-of-the-art methods. The highest achieved OSLN recall of $0.828$ is clinically relevant and valuable.

• Publication year

  2020

• Venue

  arXiv.org

• Publication date

  2020-05-27

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  arXiv 2005.13705
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning From Radiology Reports and Label Ontology

  2019influential reference
• Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities

  2019cited by this paper
• Semantic segmentation and detection of mediastinal lymph nodes and anatomical structures in CT data for lung cancer staging

  2019cited by this paper
• Deep High-Resolution Representation Learning for Human Pose Estimation

  2019cited by this paper
• MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation

  2019influential reference
• On the Variance of the Adaptive Learning Rate and Beyond

  2019cited by this paper
• Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels

  2019cited by this paper
• MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection

  2019cited by this paper
• Accurate Esophageal Gross Tumor Volume Segmentation in PET/CT using Two-Stream Chained 3D Deep Network Fusion

  2019influential reference
• Tumor co-segmentation in PET/CT using multi-modality fully convolutional neural network

  2018cited by this paper
• 3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection

  2018cited by this paper
• Dense volumetric detection and segmentation of mediastinal lymph nodes in chest CT images

  2018cited by this paper
• Automated Whole-Body Bone Lesion Detection for Multiple Myeloma on 68Ga-Pentixafor PET/CT Imaging Using Deep Learning Methods

  2018cited by this paper
• DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning

  2018influential reference
• Clinical Practice in PET/CT for the Management of Head and Neck Squamous Cell Cancer.

  2017influential reference
• Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks

  2017cited by this paper
• Progressive and Multi-path Holistically Nested Neural Networks for Pathological Lung Segmentation from CT Images

  2017cited by this paper
• Mask R-CNN

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

  2017cited by this paper
• Squeeze-and-Excitation Networks

  2017cited by this paper
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

  2016cited by this paper
• Mediastinal lymph node detection and station mapping on chest CT using spatial priors and random forest.

  2016cited by this paper
• Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique.

  2016cited by this paper
• Automatic Lymph Node Cluster Segmentation Using Holistically-Nested Neural Networks and Structured Optimization in CT Images

  2016cited by this paper
• Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks

  2016cited by this paper
• Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin

  2016cited by this paper
• Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation

  2015influential reference
• Fast R-CNN

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

  2015cited by this paper
• A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations

  2014influential reference
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Lymph node detection and segmentation in chest CT data using discriminative learning and a spatial prior

  2013cited by this paper
• Automatic Detection and Segmentation of Lymph Nodes From CT Data

  2012cited by this paper
• Evaluation of lymph nodes with RECIST 1.1.

  2009cited by this paper
• New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1).

  2009cited by this paper
• Automated Extraction of Lymph Nodes from 3-D Abdominal CT Images Using 3-D Minimum Directional Difference Filter

  2007cited by this paper
• A prospective study to evaluate the impact of FDG-PET on CT-based radiotherapy treatment planning for oesophageal cancer.

  2006cited by this paper
• A Linear Time Algorithm for Computing Exact Euclidean Distance Transforms of Binary Images in Arbitrary Dimensions

  2003cited by this paper
• Low attenuation nodal metastases in testicular carcinoma.

  1983cited by this paper

• From Slices to Sequences: Autoregressive Tracking Transformer for Cohesive and Consistent 3D Lymph Node Detection in CT Scans

  2025cites this paper
• Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformer

  2024cites this paper
• A Gradient Mapping Guided Explainable Deep Neural Network for Extracapsular Extension Identification in 3D Head and Neck Cancer Computed Tomography Images

  2022cites this paper
• Integrating features from lymph node stations for metastatic lymph node detection

  2022influential citation
• Global-Local attention network with multi-task uncertainty loss for abnormal lymph node detection in MR images

  2022cites this paper
• Towards automated organs at risk and target volumes contouring: Defining precision radiation therapy in the modern era

  2022cites this paper
• Lymph Node Gross Tumor Volume Detection in Oncology Imaging via Relationship Learning Using Graph Neural Network

  2020cites this paper
• Learning From Multiple Datasets With Heterogeneous and Partial Labels for Universal Lesion Detection in CT

  2020cites this paper
• DeepTarget: Gross tumor and clinical target volume segmentation in esophageal cancer radiotherapy

  2020cites this paper
• Lymph Node Gross Tumor Volume Detection and Segmentation via Distance-based Gating using 3D CT/PET Imaging in Radiotherapy

  2020cites this paper