Global-Leading Research and Education in Brain and Cognitive engineering KOREA UNIVERSITY To understand the structure and the key principles of high-order information processing by which brains work,
and to implement these in artificial systems that interact intelligently with real world

Research Highlight

Research
Prof. Heung-Il Suk's paper accepted in Neural Networks
Author Administrator (IP: *.152.74.116) Date 2019-03-07 14:10 Views 344
원본사진보기

Prof. Heung-Il Suk's research paper, 'Multi-Scale Gradual Integration CNN for False Positive Reduction in Pulmonary Nodule Detection' was accepted in Neural Networks.

 

Title: Multi-Scale Gradual Integration CNN for False Positive Reduction in Pulmonary Nodule Detection


Abstract: Lung cancer is a global and dangerous disease, and its early detection is crucial for reducing the risks of mortality. In this regard, it has been of great interest in developing a computer-aided system for pulmonary nodules detection as early as possible on thoracic CT scans. In general, a nodule detection system involves two steps: (i) candidate nodule detection at a high sensitivity, which captures many false positives and (ii) false positive reduction from candidates. However, due to the high variation of nodule morphological characteristics and the possibility of mistaking them for neighboring organs, candidate nodule detection remains a challenge. In this study, we propose a novel Multi-scale Gradual Integration Convolutional Neural Network (MGI-CNN), designed with three main strategies: (1) to use multi-scale inputs with different levels of contextual information, (2) to use abstract information inherent in different input scales with gradual integration, and (3) to learn multi-stream feature integration in an end-to-end manner. To verify the efficacy of the proposed network, we conducted exhaustive experiments on the LUNA16 challenge datasets by comparing the performance of the proposed method with state-of-the-art methods in the literature. On two candidate subsets of the LUNA16 dataset, i.e., V1 and V2, our method achieved an average CPM of 0.908 (V1) and 0.942(V2), outperforming comparable methods by a large margin. Our MGI-CNN is implemented in Python using TensorFlow and the source code is available from https://github.com/ku-milab/MGICNN.

 


File 5c7c9ab2df292.gif(10.9K)


Research
Prof. Heung-Il Suk's paper accepted in NeuroImage
Prof. Heung-Il Suk's paper accepted in NeuroImage
Prof. Heung-Il Suk's research paper, 'Toward an Interpretable Alzheimer's Disease Diagnostic Model with Regional Abnormality Representation via Deep Learning' was accepted in NeuroImage.  Title: Toward an Interpretable Alzheimer's Disease Diagnostic Model with Regional Abnormality Representation via Deep Learning  Abstract: In this paper, we propose a novel method for magnetic resonance imaging based Alzheimer's disease (…

2019-08-20

Prof.Jae-Ho Han’s paper accepted in IEEE Transactions on Image Processing
Prof.Jae-Ho Han’s paper accepted in IEEE Transactions on Image Processing
Prof. Jae-Ho Han’s new research on `Deep Neural Network Regression for Automated Retinal Layer Segmentation in Optical Coherence Tomography Images` was accepted in IEEE Transactions on Image Processing.  Title: Deep Neural Network Regression for Automated Retinal Layer Segmentation in Optical Coherence Tomography ImagesAbstract: Segmenting the retinal layers in optical coherence tomography (OCT) images helps to quantify the …

2019-07-24

Prof. Seong-Whan Lee's paper accepted in IEEE Transactions on Intelligent Transportation Systems
Prof. Seong-Whan Lee's paper accepted in IEEE Transactions on Intelligent Transp…
Prof. Seong-Whan Lee's new research, Coarse-to-Fine Deep Learning of Continuous Pedestrian Orientation Based on Spatial Co-occurrence Feature was accepted in IEEE Transactions on Intelligent Transportation Systems. Title: 'Coarse-to-Fine Deep Learning of Continuous Pedestrian Orientation Based on Spatial Co-occurrence Feature Abstract: The continuous orientation estimation of a moving pedestrian is a crucial issue in auto…

2019-05-02

Prof. Heung-Il Suk's paper accepted in Neural Networks
Prof. Heung-Il Suk's paper accepted in Neural Networks
Prof. Heung-Il Suk's research paper, 'Multi-Scale Gradual Integration CNN for False Positive Reduction in Pulmonary Nodule Detection' was accepted in Neural Networks.   Title: Multi-Scale Gradual Integration CNN for False Positive Reduction in Pulmonary Nodule Detection Abstract: Lung cancer is a global and dangerous disease, and its early detection is crucial for reducing the risks of mortality. In this regard, it has been o…

2019-03-07

Prof. Christian Wallraven's paper accepted in IEEE Transactions on Visualization and Computer Graphics
Prof. Christian Wallraven's paper accepted in IEEE Transactions on Visualization…
Prof. Christian Wallraven's research paper, 'You or me? Personality Traits Predict Sacrificial Decisions in an Accident Situation' was accepted in IEEE Transactions on Visualization and Computer Graphics. Title : You or me? Personality Traits Predict Sacrificial Decisions in an Accident SituationAbstract : Emergency situations during car driving sometimes force the driver to make a sudden decision. Predicting these decisions will have i…

2019-03-04

Prof. Dong-Joo Kim's paper accepted in Journal of Neurosurgery
Prof. Dong-Joo Kim's paper accepted in Journal of Neurosurgery
Prof. Dong-Joo Kim's research paper, Artifact removal from neurophysiological signals: impact on intracranial and arterial pressure monitoring in traumatic brain injury was accepted in Journal of Neurosurgery. Title: Artifact removal from neurophysiological signals: impact on intracranial and arterial pressure monitoring in traumatic brain injury Abstract:OBJECTIVE Monitoring intracranial and arterial blood pressure (ICP and ABP, r…

2019-02-28

Prof. Dong-Joo Kim's paper accepted in Journal of Neurosurgery
Prof. Dong-Joo Kim's paper accepted in Journal of Neurosurgery
Prof. Dong-Joo Kim's research paper, Novel index for predicting mortality during the first 24 hours after traumatic brain injury was accepted in Journal of Neurosurgery.Title: Novel index for predicting mortality during the first 24 hours after traumatic brain injuryAbstract:OBJECTIVE Failure of cerebral autoregulation and subsequent hypoperfusion is common during the acute phase of traumatic brain injury (TBI). The cerebrovascular pres…

2019-02-28

Prof. Dong-Joo Kim's paper accepted in Journal of Neurosurgery
Prof. Dong-Joo Kim's paper accepted in Journal of Neurosurgery
Prof. Dong-Joo Kim's research paper , Changes in the gray and white matter of patients with ischemic-edematous insults after traumatic brain injury was accepted in Journal of Neurosurgery. Title: Changes in the gray and white matter of patients with ischemic-edematous insults after traumatic brain injury Abstract:OBJECTIVE Gray matter (GM) and white matter (WM) are vulnerable to ischemic-edematous insults after traumatic brain…

2019-02-28

Prof. Dong-Joo Kim's paper accepted in Information Sciences
Prof. Dong-Joo Kim's paper accepted in Information Sciences
Prof. Dong-Joo Kim's research paper, Automated artifact elimination of physiological signals using a deep belief network: An application for continuously measured arterial blood pressure waveformswas accepted in Information Sciences. Title: Automated artifact elimination of physiological signals using a deep belief network: An application for continuously measured arterial blood pressure waveforms Abstract:Artifacts in physiological sig…

2019-02-28

Prof. Christian Wallraven's paper accepted in Neuroimage
Prof. Christian Wallraven's paper accepted in Neuroimage
Prof. Christian Wallraven's research paper, Manipulating and decoding subjective gaming experience during active gameplay: a multivariate, whole-brain analysis was accepted in NeuroImage.Title: Manipulating and decoding subjective gaming experience during active gameplay: a multivariate, whole-brain analysisAbstract: A large number of perceptual and cognitive processes are instantiated during active gameplay, culminating in what is term…

2018-12-11

1 2 3 4 5 6 7 8