Deep Volumetric Universal Lesion Detection using Light-Weight Pseudo 3D Convolution and Surface Point Regression

  title={Deep Volumetric Universal Lesion Detection using Light-Weight Pseudo 3D Convolution and Surface Point Regression},
  author={Jinzheng Cai and Ke Yan and Chi-Tung Cheng and Jing Xiao and C. Liao and Le Lu and Adam P. Harrison},
Identifying, measuring and reporting lesions accurately and comprehensively from patient CT scans are important yet time-consuming procedures for physicians. Computer-aided lesion/significant-findings detection techniques are at the core of medical imaging, which remain very challenging due to the tremendously large variability of lesion appearance, location and size distributions in 3D imaging. In this work, we propose a novel deep anchor-free one-stage volumetric lesion detector (VLD… Expand

Figures and Tables from this paper

Conditional Training with Bounding Map for Universal Lesion Detection
A BM- based conditional training for two-stage ULD, which can reduce positive vs. negative anchor imbalance via a BM-based conditioning (BMC) mechanism for anchor sampling instead of traditional IoU-based rule and adaptively compute size-adaptive BM (ABM) from lesion boundingbox, which is used for improving lesion localization accuracy via ABMsupervised segmentation. Expand
Recent advances and clinical applications of deep learning in medical image analysis
The latest progress and contributions of state-of-the-art unsupervised and semi-supervised deep learning in medical images are emphasized and summarized based on different application scenarios, including lesion classification, segmentation, detection, and image registration. Expand
Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images
Self-supervised Anatomical eMbedding is introduced, a pixel-level contrastive learning framework that generates semantic embeddings for each image pixel that describes its anatomical location or body part and outperforms supervised methods trained on 50 labeled images. Expand
A Flexible Three-Dimensional Hetero-phase Computed Tomography Hepatocellular Carcinoma (HCC) Detection Algorithm for Generalizable and Practical HCC Screening
  • Chi-Tung Cheng, Jinzheng Cai, +11 authors Adam P. Harrison
  • Computer Science
  • ArXiv
  • 2021
Hepatocellular carcinoma (HCC) can be potentially discovered from abdominal computed tomography (CT) studies under varied clinical scenarios, e.g., fully dynamic contrast enhanced (DCE) studies,Expand
Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies
This work presents deep lesion tracker (DLT), a deep learning approach that uses both appearance- and anatomical-based signals to incorporate anatomical constraints, and proposes an anatomical signal encoder, which prevents lesions being matched with visually similar but spurious regions. Expand


Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels
This work proposes a highly accurate and efficient one-stage lesion detector, by re-designing a RetinaNet to meet the particular challenges in medical imaging, and optimize the anchor configurations using a differential evolution search algorithm. Expand
Attentive CT Lesion Detection Using Deep Pyramid Inference with Multi-Scale Booster
A Multi-Scale Booster with channel and spatial attention integrated into the backbone Feature Pyramid Network (FPN) that performs superiorly against state-of-the-art approaches on lesion detection. Expand
Uldor: A Universal Lesion Detector For Ct Scans With Pseudo Masks And Hard Negative Example Mining
This work builds a Universal Lesion Detector (ULDor) based on Mask R-CNN, which is able to detect all different kinds of lesions from whole body parts and proposes a hard negative example mining strategy to reduce the false positives for improving the detection performance. Expand
Light-Weight Hybrid Convolutional Network for Liver Tumor Segmentation
The light-weight hybrid convolutional network (LW-HCN) is proposed to segment the liver and its tumors in CT volumes and has a encoder-decoder structure, in which 2D convolutions used at the bottom of the encoder decreases the complexity and 3D Convolutional networks used in other layers explore both spatial and temporal information. Expand
MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation
A multitask universal lesion analysis network (MULAN) for joint detection, tagging, and segmentation of lesions in a variety of body parts, which greatly extends existing work of single-task lesions analysis on specific body parts. Expand
DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning
Using DeepLesion, a universal lesion detector is trained that can find all types of lesions with one unified framework and achieves a sensitivity of 81.1% with five false positives per image. Expand
Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection
A novel method employing three-dimensional convolutional neural networks for false positive reduction in automated pulmonary nodule detection from volumetric computed tomography (CT) scans and a simple yet effective strategy to encode multilevel contextual information to meet the challenges coming with the large variations and hard mimics of pulmonary nodules. Expand
3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection
3D context enhanced region-based CNN (3DCE) is proposed to incorporate 3D context information efficiently by aggregating feature maps of 2D images to detect lesions from computed tomography scans. Expand
Reinventing 2D Convolutions for 3D Medical Images
This study proposes ACS (axial-coronal-sagittal) convolutions to perform natively 3D representation learning, while utilizing the pretrained weights from 2D counterparts, to bridge the gap between 2D and 3D convolution by reinventing the 2D convolutions. Expand
Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks
This paper introduces a deconvolutional structure to Faster Region-based Convolutional Neural Network (Faster R-CNN) for candidate detection on axial slices and proposes a novel pulmonary nodule detection approach based on DCNNs. Expand