Revision as of 20:59, 31 October 2019 by Aaron (Link correction.)
- The paper "Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance imaging" appears in NeuroImage. (doi) (PubMed)
- The paper "Why rankings of biomedical image analysis competitions should be interpreted with care" appears in the journal Nature Communications. (doi) (PubMed) (PMCID 6284017)
- IACL members win the 2018 ECE Pumpkin Carving Contest!!
- IACL members present papers at the 21st International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2018), Granada, Spain, September 16 - 20, 2018.
- Dr. A.D. Gomez presented "Quantifying Tensor Field Similarity With Global Distributions and Optimal Transport".
- Can Zhao presented "A Deep Learning based Anti-aliasing Self Super-resolution Algorithm for Magnetic Resonance Imaging".
- We also had presentations at several MICCAI workshops.
- Dr. A.D. Gomez presented "Quantitative validation of MRI-based motion estimation for brain impact biomechanics" at Computational Biomechanics for Medicine (CBM XIII).
- At Simulation and Synthesis in Medical Imaging (SASHIMI 2018), Blake Dewey presented "Deep Harmonization of Inconsistent MR Data for Consistent Volume Segmentation" and Yuta Hiasa presented "Crossmodality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data size".
- Dr. J.L. Prince presented "Shortcomings of Ventricle Segmentation Using Deep Convolutional Networks" at the Deep Learning Fails Workshop and also "Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGAN" at the 4th Workshop on Deep Learning in Medical Image Analysis (DLMIA 2018).
- In collaboration with Univ. of Pennsylvania, Dr. Min Chen presented "2D Modeling and Correction of Fan-beam Scan Geometry in OCT" at 5th Workshop on Ophthalmic Medical Image Analysis (MW-OMIA5). Dr. Chen also won the Best Poster prize at MW-OMIA5.
- The paper "Preoperative mapping of the supplementary motor area in brain tumor patients using resting-state fMRI with seed based analysis" appears in the American Journal of Neuroradiology. (doi) (PubMed)
- IACL members present papers at the International Symposium on Biomedical Imaging (ISBI 2018) meeting in Washington, DC, April 4 - 7, 2018.
- Can Zhao presented "Self Super-Resolution for Magnetic Resonance Images Using Deep Networks".
- Yihao Liu presented "Multi-Layer Fast Level Set Segmentation for Macular OCT".
|IACL at ISBI 2018|
|Can Zhao presenting her poster titled "Self Super-Resolution for Magnetic Resonance Images Using Deep Networks".||Yihao Liu presenting his poster titled "Multi-Layer Fast Level Set Segmentation for Macular OCT".|
- IACL members present papers at the SPIE Medical Imaging (SPIE-MI 2018) meeting in Houston, TX, February 10 - 15, 2018.
- Lianrui Zuo presented "Automatic outlier detection using hidden Markov model for cerebellar lobule segmentation".
- Muhan Shao presented "Multi-atlas segmentation of the hydrocephalus brain using an adaptive ventricles atlas".
- Jeffrey Glaister presented "Deformable model reconstruction of the subarachnoid space".
- Xiaokai Wang presented "A novel filtering approach for 3D harmonic phase analysis of tagged MRI"
- Other accepted papers at SPIE-MI 2018 coming from collaborations with IACL.
- With Sachin Goyal from IIT Bombay presented "Improving Self Super Resolution in Magnetic Resonance Images".
- With Aniket Tolpadi from Rice University "Inverse biomechanical modeling via machine learning and synthetic training data".
- With Sureerat Reaungamornrat from Mahidol University "Inter-scanner Variation Independent Descriptors for Constrained Diffeomorphic Demons Registration of Retinal OCT".
|IACL at SPIE 2018|
|Muhan Shao presenting her talk titled "Multi-atlas segmentation of the hydrocephalus brain using an adaptive ventricles atlas".|
|Jeffrey Glaister presenting his poster "Deformable model reconstruction of the subarachnoid space".||Aniket Tolpadi presenting his talk "Inverse biomechanical modeling via machine learning and synthetic training data".|