ISBI 2018

153 papers
The 2018 International Symposium on Biomedical Imaging (ISBI) featured 181 papers focusing on advancements in volumetric reconstruction and automated segmentation. Key research directions included slice-to-volume reconstruction for fetal MRI and dynamic imaging, as well as 3D reconstruction from unposed 2D projections. Methodological trends highlighted the use of adversarial learning for skin lesion and nuclei segmentation, alongside 2D convolutional models designed for anisotropic medical imaging. Notable work addressed technical challenges in structural reconstruction, such as counteracting depth-dependent signal loss and managing non-uniform orientation distributions. Research also explored real-time intraoperative scene reconstruction and the refinement of segmentation masks through morphological operations. Prolific contributors to this edition included Tianming Liu, Dinggang Shen, and Li Shen. The proceedings reflected a growing emphasis on integrating simulation data for patient-specific modeling and utilizing intracranial electrical stimulation mapping within diffusion tractography. Other significant topics included 3D ab initio modeling in cryo-EM and the development of cascade networks for volumetric medical image segmentation.

Top Research Directions

Research directions most represented by ISBI 2018 papers.

Overcoming Volumetric Context Loss in Medical Vision Models 4
Cross-Modality Generalization in Medical Artificial Intelligence 2
Hybrid Local Global Image Segmentation 1
Correspondence Free Shape Analysis via Geometric Measures 1
Preserving Motion Boundaries in Dense Flow Estimation 1
Joint Image Synthesis and Semantic Segmentation 1
Reducing Redundant Feature Computation in Patch Based Inference 1
The Performance Gap Between Unsupervised and Supervised Learning 1
Morphological and Geometric Refinement of Segmentation Masks 1
Spatial Patch Parallelism for Distributed Image Processing 1
Self-Supervised Measurement Splitting for Signal Reconstruction 1
Depth Dependent Signal Attenuation in Volumetric Imaging 1
Isotropic Resolution Restoration for 3D Microscopy 1
Local Adaptive Thresholding for Robust Image Segmentation 1
Orthogonal Multi View Fusion for Volumetric Imaging 1

Top Authors

AuthorPapers
Dinggang Shen7
Tianming Liu7
Xintao Hu5
Jeffrey A Fessler4
Le Lu4
Andrew P. King3
Ghassan Hamarneh3
Guido Gerig3
J. Alison Noble3
James s Duncan3
Lei Guo3
Lei Wang3
Li Shen3
Luping Zhou3
Michael Unser3
Nicha C Dvornek3
Ronald M. Summers3
Aaron Carass2
Andrew J. Reader2
Aristeidis Sotiras2

Impactful Papers

Papers from ISBI 2018 that shaped research clusters.

Foundational

Influential

Papers

Title
Model-based optimal design of a magnetic nanoparticle tomographic imaging setup
Model-dependent uncertainty estimation of medical image segmentation
Modeling resting state fMRI data via longitudinal supervised stochastic coordinate coding
Modeling task fMRI data via mixture of deep expert networks
MRI slice stacking using manifold alignment and wave kernel signatures
Multi-component deformable models coupled with 2D-3D U-Net for automated probabilistic segmentation of cardiac walls and blood
Multi-layer fast level set segmentation for macular OCT
Multi-modality feature selection with adaptive similarity learning for classification of Alzheimer's disease
Multiple incomplete views clustering via non-negative matrix factorization with its application in Alzheimer's disease analysis
Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures
Non-Euclidean, convolutional learning on cortical brain surfaces
Non-rigid image registration using self-supervised fully convolutional networks without training data
Nuclei instance segmentation with dual contour-enhanced adversarial network
Ocular disease detection from multiple informatics domains
PET-MR respiratory signal estimation using semi-supervised manifold alignment
Phaseless diffraction tomography with regularized beam propagation
Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning
Prediction of Pivotal response treatment outcome with task fMRI using random forest and variable selection
Quantification of cardiac bull's-eye map based on principal strain analysis for myocardial wall motion assessment in stress echocardiography
Rapid annotation of 3D medical imaging datasets using registration-based interpolation and adaptive slice selection
Real-time automatic fetal brain extraction in fetal MRI by deep learning
Regionally discriminative multivariate statistical mapping
Region of interest X-ray computed tomography via corrected back projection
Regularized multi-label fast marching and application to whole-body image segmentation
Retinal vascular topology estimation via dominant sets clustering
Scale-bundle spline-based non-rigid registration for handling fissures
Scoliosis screening and monitoring using self contained ultrasound and neural networks
SEGMENT3D: A web-based application for collaborative segmentation of 3D images used in the shoot apical meristem
Segmentation-by-detection: A cascade network for volumetric medical image segmentation
Segmentation of cell nuclei using intensity-based model fitting and sequential convex programming
Self-Attention Equipped Graph Convolutions for Disease Prediction
Self-learning to detect and segment cysts in lung CT images without manual annotation
Self super-resolution for magnetic resonance images using deep networks
Semi-supervised learning for pelvic MR image segmentation based on multi-task residual fully convolutional networks
Semi-supervised learning with generative adversarial networks for chest X-ray classification with ability of data domain adaptation
Shape analysis and tracking of migrating macrophages
SIPID: A deep learning framework for sinogram interpolation and image denoising in low-dose CT reconstruction
SonoEyeNet: Standardized fetal ultrasound plane detection informed by eye tracking
Spatially variant PSF modeling in confocal macroscopy
Spatial temporal GRU convnets for vision-based real time epileptic seizure detection
Staingan: Stain Style Transfer for Digital Histological Images
Stain normalization of histopathology images using generative adversarial networks
Statistical disease mapping for heterogeneous neuroimaging studies
Statistically-constrained robust diffeomorphic registration
The candidate multi-cut for cell segmentation
Topographical reconstructions from monocular optical colonoscopy images via deep learning
Tracking diaphragm and chest wall movement on cine-MRI
Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data
Tumor segmentation via multi-modality joint dictionary learning
Understanding anatomy classification through attentive response maps

« prev Page 3/4 next »