Robust End-to-End Focal Liver Lesion Detection Using Unregistered Multiphase Computed Tomography Images (2021-12-02T00:00:00.000000Z)

TL;DR

Evaluation on a large-scale dataset with 280 patients confirmed that the proposed method outperformed previous state-of-the-art methods and significantly reduced the performance degradation for detecting FLLs using misaligned multiphase CT images.

Abstract

The computer-aided diagnosis of focal liver lesions (FLLs) can help improve workflow and enable correct diagnoses; FLL detection is the first step in such a computer-aided diagnosis. Despite the recent success of deep-learning-based approaches in detecting FLLs, current methods are not sufficiently robust for assessing misaligned multiphase data. By introducing an attention-guided multiphase alignment in feature space, this study presents a fully automated, end-to-end learning framework for detecting FLLs from multiphase computed tomography (CT) images. Our method is robust to misaligned multiphase images owing to its complete learning-based approach, which reduces the sensitivity of the model’s performance to the quality of registration and enables a standalone deployment of the model in clinical practice. Evaluation on a large-scale dataset with 280 patients confirmed that our method outperformed previous state-of-the-art methods and significantly reduced the performance degradation for detecting FLLs using misaligned multiphase CT images. The robustness of the proposed method can enhance the clinical adoption of the deep-learning-based computer-aided detection system.

Authors

Sungroh Yoon

5 papers

Eunji Kim

2 papers

Sang-gil Lee

2 papers

TL;DR

Abstract

Authors

References62 items

Automatic Segmentation of Liver Tumor in Multiphase CT Images by Mask R-CNN

Multi-Stream Scale-Insensitive Convolutional and Recurrent Neural Networks for Liver Tumor Detection in Dynamic Ct Images

Image-and-Spatial Transformer Networks for Structure-Guided Image Registration

Unsupervised Deformable Image Registration Using Cycle-Consistent CNN

Multi-Scale Self-Guided Attention for Medical Image Segmentation

Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels

IEEE Transactions on Emerging Topics in Computational Intelligence

Attention Residual Learning for Skin Lesion Classification

The Liver Tumor Segmentation Benchmark (LiTS)

Deformable ConvNets V2: More Deformable, Better Results

Large Scale GAN Training for High Fidelity Natural Image Synthesis

Combining Convolutional and Recurrent Neural Networks for Classification of Focal Liver Lesions in Multi-phase CT Images

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images

Liver Lesion Detection from Weakly-labeled Multi-phase CT Volumes with a Grouped Single Shot MultiBox Detector

DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes

Self-Attention Generative Adversarial Networks

Abdominal multi-organ segmentation with organ-attention networks and statistical fusion

Attention U-Net: Learning Where to Look for the Pancreas

An Unsupervised Learning Model for Deformable Medical Image Registration

PixelLink: Detecting Scene Text via Instance Segmentation

AASLD guidelines for the treatment of hepatocellular carcinoma

Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions

Focal Loss for Dense Object Detection

Neuroscience-Inspired Artificial Intelligence

Asia–Pacific clinical practice guidelines on the management of hepatocellular carcinoma: a 2017 update

Attention is All you Need

ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases

Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method

Deformable Convolutional Networks

Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks

Real-Time Detection and Localisation of Fetal Standard Scan Planes in 2D Freehand Ultrasound

Feature Pyramid Networks for Object Detection

Fully Convolutional Network for Liver Segmentation and Lesions Detection

Patch-Based Discrete Registration of Clinical Brain Images

Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields

SimpleElastix: A User-Friendly, Multi-lingual Library for Medical Image Registration

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

Automatic Segmentation of Liver Tumor in CT Images with Deep Convolutional Neural Networks

Non-rigid image registration with anatomical structure constraint for assessing locoregional therapy of hepatocellular carcinoma

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

CT and MR imaging diagnosis and staging of hepatocellular carcinoma: part II. Extracellular agents, hepatobiliary agents, and ancillary imaging features.

Sequence to Sequence Learning with Neural Networks

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet classification with deep convolutional neural networks

Learning Task-Optimal Registration Cost Functions for Localizing Cytoarchitecture and Function in the Cerebral Cortex

Hepatocarcinogenesis: multistep changes of drainage vessels at CT during arterial portography and hepatic arteriography--radiologic-pathologic correlation.

Dense image registration through MRFs and efficient linear programming

A fast diffeomorphic image registration algorithm

Graph Cuts and Efficient N-D Image Segmentation

Detecting hepatic lesions: the added utility of CT liver window settings.

Measures of the Amount of Ecologic Association Between Species

classiﬁcation and localization of common thorax diseases

Epidemiology of HCC: Consider the population

EASL-EORTC clinical practice guidelines: management of hepatocellular carcinoma.

European Association for the Study of the Liver

The openCV library

is with the Department of Radiology, Seoul National University College of Medicine, Seoul 03080, Korea, and also with the Department

Lee received the dual B.S. degree in elec

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names