Artificial Intelligence in Medical Imaging

@article{bayquicknat2019,

title = {Bayesian QuickNAT: Model uncertainty in deep whole-brain segmentation for structure-wise quality control},

author = {Abhijit Guha Roy, Sailesh Conjeti, Nassir Navab, Christian Wachinger},

url = {https://www.sciencedirect.com/science/article/pii/S1053811919302319},

doi = {https://doi.org/10.1016/j.neuroimage.2019.03.042},

year  = {2019},

date = {2019-04-01},

urldate = {2019-04-01},

journal = {NeuroImage},

volume = {195},

abstract = {We introduce Bayesian QuickNAT for the automated quality control of whole-brain segmentation on MRI T1 scans. Next to the Bayesian fully convolutional neural network, we also present inherent measures of segmentation uncertainty that allow for quality control per brain structure. For estimating model uncertainty, we follow a Bayesian approach, wherein, Monte Carlo (MC) samples from the posterior distribution are generated by keeping the dropout layers active at test time. Entropy over the MC samples provides a voxel-wise model uncertainty map, whereas expectation over the MC predictions provides the final segmentation. Next to voxel-wise uncertainty, we introduce four metrics to quantify structure-wise uncertainty in segmentation for quality control. We report experiments on four out-of-sample datasets comprising of diverse age range, pathology and imaging artifacts. The proposed structure-wise uncertainty metrics are highly correlated with the Dice score estimated with manual annotation and therefore present an inherent measure of segmentation quality. In particular, the intersection over union over all the MC samples is a suitable proxy for the Dice score. In addition to quality control at scan-level, we propose to incorporate the structure-wise uncertainty as a measure of confidence to do reliable group analysis on large data repositories. We envisage that the introduced uncertainty metrics would help assess the fidelity of automated deep learning based segmentation methods for large-scale population studies, as they enable automated quality control and group analyses in processing large data repositories.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{roy2019braintorrent,

title = {Braintorrent: A peer-to-peer environment for decentralized federated learning},

author = {Abhijit Guha Roy and Shayan Siddiqui and Sebastian Pölsterl and Nassir Navab and Christian Wachinger},

url = {https://arxiv.org/abs/1905.06731},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

journal = {arXiv preprint arXiv:1905.06731},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{quicknat_neuroimage_agr,

title = {QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy},

author = {Abhijit Guha Roy and Sailesh Conjeti and Nassir Navab and Christian Wachinger},

url = {https://arxiv.org/abs/1801.04161},

year  = {2018},

date = {2018-11-23},

urldate = {2018-11-23},

journal = {NeuroImage},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger_2018_tmi,

title = {Keypoint Transfer for Fast Whole-Body Segmentation},

author = {C. Wachinger and M. Toews and G. Langs and W. Wells and P. Golland},

url = {http://ai-med.de/wp-content/uploads/2020/02/1806.087231.pdf},

year  = {2018},

date = {2018-09-13},

urldate = {2018-09-13},

journal = {IEEE Transactions on Medical Imaging},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{se_tmi_agr2018,

title = {Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks},

author = {Abhijit Guha Roy and Nassir Navab and Christian Wachinger},

url = {https://arxiv.org/abs/1808.08127},

year  = {2018},

date = {2018-08-17},

urldate = {2018-08-17},

journal = {IEEE Transactions on Medical Imaging},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2018longitudinal,

title = {A Longitudinal Imaging Genetics Study of Neuroanatomical Asymmetry in Alzheimer’s Disease},

author = {Wachinger, Christian and Nho, Kwangsik and Saykin, Andrew J and Reuter, Martin and Rieckmann, Anna},

url = {http://ai-med.de/wp-content/uploads/2020/02/1-s2.0-S0006322318314720-main1.pdf},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

journal = {Biological Psychiatry},

publisher = {Elsevier},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{becker2018gaussian,

title = {Gaussian process uncertainty in age estimation as a measure of brain abnormality},

author = {Gutierrez-Becker, Benjamin and Klein, Tassilo and Wachinger, Christian },

url = {https://arxiv.org/pdf/1804.01296.pdf},

year  = {2018},

date = {2018-01-01},

journal = {NeuroImage},

publisher = {Elsevier},

abstract = {Multivariate regression models for age estimation are a powerful tool for assessing abnormal brain morphology associated to neuropathology. Age prediction models are built on cohorts of healthy subjects and are built to reflect normal aging patterns. The application of these multivariate models to diseased subjects usually results in high prediction errors, under the hypothesis that neuropathology presents a similar degenerative pattern as that of accelerated aging. In this work, we propose an alternative to the idea that pathology follows a similar trajectory than normal aging. Instead, we propose the use of metrics which measure deviations from the mean aging trajectory. We propose to measure these deviations using two different metrics: uncertainty in a Gaussian process regression model and a newly proposed age weighted uncertainty measure. Consequently, our approach assumes that pathologic brain patterns are different to those of normal aging. We present results for subjects with autism, mild cognitive impairment and Alzheimer's disease to highlight the versatility of the approach to different diseases and age ranges. We evaluate volume, thickness, and VBM features for quantifying brain morphology. Our evaluations are performed on a large number of images obtained from a variety of publicly available neuroimaging databases. Across all features, our uncertainty based measurements yield a better separation between diseased subjects and healthy individuals than the prediction error. Finally, we illustrate differences in the disease pattern to normal aging, supporting the application of uncertainty as a measure of neuropathology.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{gutierrez2017guidingb,

title = {Guiding Multimodal Registration with Learned Optimization Updates},

author = {Gutierrez-Becker, Benjamin and Mateus, Diana and Peter, Loic and Navab, Nassir},

url = {http://ai-med.de/wp-content/uploads/2017/06/MultimodalMedIA-1.pdf},

year  = {2017},

date = {2017-01-01},

journal = {Medical Image Analysis},

publisher = {Elsevier},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{riva20173d,

title = {3D intra-operative ultrasound and MR image guidance: pursuing an ultrasound-based management of brainshift to enhance neuronavigation},

author = {Riva, Marco and Hennersperger, Christoph and Milletari, Fausto and Katouzian, Amin and Pessina, Federico and Gutierrez-Becker, Benjamin and Castellano, Antonella and Navab, Nassir and Bello, Lorenzo},

year  = {2017},

date = {2017-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

pages = {1--15},

publisher = {Springer International Publishing},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2017deepnat,

title = {DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy},

author = {Wachinger, Christian and Reuter, Martin and Klein, Tassilo},

url = {https://arxiv.org/abs/1702.08192},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

journal = {NeuroImage},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{conjeti2016deep,

title = {Deep Residual Hashing},

author = {Conjeti, Sailesh and Guha Roy, Abhijit and Katouzian, Amin and Navab, Nassir},

year  = {2017},

date = {2017-01-01},

journal = {Accepted at MICCAI 2017},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{roy2017relaynet,

title = {ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network},

author = {Guha Roy, Abhijit and Conjeti, Sailesh and Karri, Sri Phani Krishna and Sheet, Debdoot and Katouzian, Amin and Wachinger, Christian and Navab, Nassir},

url = {https://arxiv.org/abs/1704.02161},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

journal = {Accepted at Biomedical Optics Express},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{roy2017error,

title = {Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data},

author = {Guha Roy, Abhijit and Conjeti, Sailesh and Sheet, Debdoot and Katouzian, Amin and Navab, Nassir and Wachinger, Christian},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

journal = {Accepted at MICCAI 2017},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2017does,

title = {Does the late positive component reflect successful reading acquisition? A longitudinal ERP study},

author = {Wachinger, Christian and Volkmer, Susanne and Bublath, Katharina and Bruder, Jennifer and Bartling, J{ü}rgen and Schulte-K{ö}rne, Gerd},

url = {http://ai-med.de/wp-content/uploads/2021/04/1-s2.0-S2213158217302565-main1-1.pdf},

year  = {2017},

date = {2017-01-01},

journal = {NeuroImage: Clinical},

publisher = {Elsevier},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2016domain,

title = {Domain adaptation for Alzheimer's disease diagnostics},

author = {Wachinger, Christian and Reuter, Martin},

year  = {2016},

date = {2016-01-01},

urldate = {2016-01-01},

journal = {NeuroImage},

publisher = {Academic Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2016efficient,

title = {Efficient Descriptor-Based Segmentation of Parotid Glands with Non-Local Means.},

author = {Wachinger, C and Brennan, M and Sharp, G and Golland, P},

year  = {2016},

date = {2016-01-01},

urldate = {2016-01-01},

journal = {IEEE transactions on bio-medical engineering},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2016whole,

title = {Whole-brain analysis reveals increased neuroanatomical asymmetries in dementia for hippocampus and amygdala},

author = {Wachinger, Christian and Salat, David H and Weiner, Michael and Reuter, Martin and Alzheimer’s Disease Neuroimaging Initiative and others},

year  = {2016},

date = {2016-01-01},

urldate = {2016-01-01},

journal = {Brain},

volume = {139},

number = {12},

pages = {3253--3266},

publisher = {Oxford University Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{conjeti2016supervised,

title = {Supervised domain adaptation of decision forests: Transfer of models trained in vitro for in vivo intravascular ultrasound tissue characterization},

author = {Conjeti, Sailesh and Katouzian, Amin and Guha Roy, Abhijit and Peter, Lo{"i}c and Sheet, Debdoot and Carlier, St{'e}phane and Laine, Andrew and Navab, Nassir},

year  = {2016},

date = {2016-01-01},

journal = {Medical image analysis},

volume = {32},

pages = {1--17},

publisher = {Elsevier},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{conjeti2016domain,

title = {Domain Adapted Model for In Vivo Intravascular Ultrasound Tissue Characterization},

author = {Conjeti, S and Guha Roy, A and Sheet, D and Carlier, S and Syeda-Mahmood, T and Navab, N and Katouzian, A},

year  = {2016},

date = {2016-01-01},

journal = {Computing and Visualization for Intravascular Imaging and Computer-Assisted Stenting},

pages = {157},

publisher = {Academic Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2015multi,

title = {Multi-modal robust inverse-consistent linear registration},

author = {Wachinger, Christian and Golland, Polina and Magnain, Caroline and Fischl, Bruce and Reuter, Martin},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

journal = {Human brain mapping},

volume = {36},

number = {4},

pages = {1365--1380},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2015brainprint,

title = {BrainPrint: A discriminative characterization of brain morphology},

author = {Wachinger, Christian and Golland, Polina and Kremen, William and Fischl, Bruce and Reuter, Martin and Alzheimer's Disease Neuroimaging Initiative and others},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

journal = {NeuroImage},

volume = {109},

pages = {232--248},

publisher = {Academic Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bron2015standardized,

title = {Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge},

author = {Bron, Esther E and Smits, Marion and van der Flier, Wiesje M and Vrenken, Hugo and Barkhof, Frederik and Scheltens, Philip and Papma, Janne M and Steketee, Rebecca ME and Orellana, Carolina M{'e}ndez and Meijboom, Rozanna and others},

year  = {2015},

date = {2015-01-01},

journal = {NeuroImage},

volume = {111},

pages = {562--579},

publisher = {Academic Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2015diverse,

title = {Diverse Landmark Sampling from Determinantal Point Processes for Scalable Manifold Learning},

author = {Wachinger, Christian and Golland, Polina},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

journal = {arXiv preprint arXiv:1503.03506},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2015sampling,

title = {Sampling from determinantal point processes for scalable manifold learning},

author = {Wachinger, Christian and Golland, Polina},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

journal = {Information Processing in Medical Imaging. Lecture Notes in Computer Science, Springer},

pages = {687--698},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2015countour,

title = {Countour-Driven Atlas-Based Segmenation},

author = {Wachinger, Christian and Fritscher, Karl and Sharp, Greg and Golland, Polina},

year  = {2015},

date = {2015-01-01},

urldate = {2015-01-01},

journal = {Transactions on medical imaging},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{magnain2014blockface,

title = {Blockface histology with optical coherence tomography: A comparison with Nissl staining},

author = {Magnain, Caroline and Augustinack, Jean C and Reuter, Martin and Wachinger, Christian and Frosch, Matthew P and Ragan, Timothy and Akkin, Taner and Wedeen, Van J and Boas, David A and Fischl, Bruce},

year  = {2014},

date = {2014-01-01},

urldate = {2014-01-01},

journal = {NeuroImage},

volume = {84},

pages = {524--533},

publisher = {Academic Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{gutierrez2013automatic,

title = {Automatic segmentation of the fetal cerebellum on ultrasound volumes, using a 3D statistical shape model},

author = {Gutierrez-Becker, Benjamin and Cosio, Fernando Arambula and Huerta, Mario E Guzman and Benavides-Serralde, Jesus Andres and Camargo-Marin, Lisbeth and Medina Banuelos, Veronica} journal={Medical & biological engineering & computing},

year  = {2013},

date = {2013-01-01},

volume = {51},

number = {9},

pages = {1021--1030},

publisher = {Springer Berlin Heidelberg},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wachinger2013simultaneous,

title = {Simultaneous registration of multiple images: similarity metrics and efficient optimization},

author = {Wachinger, Christian and Navab, Nassir},

year  = {2013},

date = {2013-01-01},

urldate = {2013-01-01},

journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on},

volume = {35},

number = {5},

pages = {1221--1233},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}