Finding novelty with uncertainty

  title={Finding novelty with uncertainty},
  author={Jacob C. Reinhold and Yufan He and Shizhong Han and Yunqiang Chen and Dashan Gao and Junghoon Lee and Jerry L Prince and Aaron Carass},
  booktitle={Medical Imaging: Image Processing},
Medical images are often used to detect and characterize pathology and disease; however, automatically identifying and segmenting pathology in medical images is challenging because the appearance of pathology across diseases varies widely. To address this challenge, we propose a Bayesian deep learning method that learns to translate healthy computed tomography images to magnetic resonance images and simultaneously calculates voxel-wise uncertainty. Since high uncertainty occurs in pathological… 

Figures from this paper

Validating Uncertainty in Medical Image Translation

This work investigates using dropout to estimate epistemic and aleatoric uncertainty in a CT-to-MR image translation task and shows that both types of uncertainty are captured, as defined, providing confidence in the output uncertainty estimates.



Unsupervised pathology detection in medical images using conditional variational autoencoders

Overall the presented approach is suitable for a rough pathology detection in medical images and can be successfully used as a preprocessing step to other image processing methods.

Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation

A 3D MS lesion segmentation CNN is developed, augmented to provide four different voxel-based uncertainty measures based on MC dropout, and the first exploration of multiple uncertainty estimates based on Monte Carlo (MC) dropout is presented in the context of deep networks for lesion detection and segmentation in medical images.

Unsupervised Lesion Detection in Brain CT using Bayesian Convolutional Autoencoders

This work explores the use of Bayesian autoencoders to learn the variability of healthy tissue and detect lesions as unlikely events under the normative model and results indicate that the method achieves best performance in detecting lesions caused by bleeding compared to baselines.

Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images

This work shows that deep spatial autoencoding models can be efficiently used to capture normal anatomical variability of entire 2D brain MR images and shows that constraints on the latent space and adversarial training can further improve the segmentation performance over standard deep representation learning.

Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

AnoGAN, a deep convolutional generative adversarial network is proposed to learn a manifold of normal anatomical variability, accompanying a novel anomaly scoring scheme based on the mapping from image space to a latent space.

Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement

Methods to characterise different components of uncertainty in medical image enhancement problems and demonstrate the ideas using diffusion MRI super-resolution to highlight three key benefits of uncertainty modelling for improving the safety of DL-based image enhancement systems.

Whole Brain Segmentation and Labeling from CT Using Synthetic MR Images

This paper presents a whole brain segmentation and labeling method for non-contrast CT images that first uses a fully convolutional network (FCN) to synthesize an MR image from a CT image and then uses the synthetic MR image in a standard pipeline for whole brainSegmentation and labeling.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Uncertainty in multitask learning: joint representations for probabilistic MR-only radiotherapy planning

A probabilistic multi-task network that estimates intrinsic uncertainty through a heteroscedastic noise model for spatially-adaptive task loss weighting and parameter uncertainty through approximate Bayesian inference, which allows sampling of multiple segmentations and synCTs that share their network representation is proposed.

Evaluating the Impact of Intensity Normalization on MR Image Synthesis

Seven different intensity normalization algorithms and three different synthesis methods are considered and evidence that suggests intensitynormalization is vital for successful deep learning-based MR image synthesis is shown.