No abstract

In this work, we discuss epistemic uncertainty estimation obtained by Bayesian inference in diagnostic classifiers and show that the prediction uncertainty highly correlates with goodness of prediction. We train the ResNet-18 image classifier on a dataset of 84,484 optical coherence tomography scans showing four different retinal conditions. Dropout is added before every building block of ResNet, creating an approximation to a Bayesian classifier. Monte Carlo sampling is applied with dropout at test time for uncertainty estimation. In Monte Carlo experiments, multiple forward passes are performed to get a distribution of the class labels. The variance and the entropy of the distribution is used as metrics for uncertainty. Our results show strong correlation with ρ = 0.99 between prediction uncertainty and prediction error. Mean uncertainty of incorrectly diagnosed cases was significantly higher than mean uncertainty of correctly diagnosed cases. Modeling of the prediction uncertainty in computer-aided diagnosis with deep learning yields more reliable results and is therefore expected to increase patient safety. This will help to transfer such systems into clinical routine and to increase the acceptance of machine learning in diagnosis from the standpoint of physicians and patients.

Purpose: Robotic scrub nurses have the potential to become an attractive solution for the operating room. Surgical instrument detection is a fundamental task for these systems, which is the focus of this work. We address the detection of the complete surgery set for wisdom teeth extraction, and propose a data augmentation technique tailored for this task. Methods: Using a robotic scrub nurse system, we create a dataset of 369 unique multi-instrument images with manual annotations. We then propose the Mask-Based Object Insertion method, capable of automatically generating a large amount of synthetic images. By using both real and artificial data, different Mask R-CNN models are trained and evaluated. Results: Our experiments reveal that models trained on the synthetic data created with our method achieve comparable performance to that of models trained on real images. Moreover, we demonstrate that the combination of real and our artificial data can lead to a superior level of generalization. Conclusion: The proposed data augmentation technique is capable of dramatically reducing the labelling work required for training a deep-learning-based detection algorithm. A dataset for the complete instrument set for wisdom teeth extraction is made available for the scientific community, as well as the raw information required for the generation of the synthetic data (https://github.com/Jorebs/Deep-learning-based-instrument-detection-for-intra operative-robotic-assistance).

In microsurgery, lasers have emerged as precise tools for bone ablation. A challenge is automatic control of laser bone ablation with 4D optical coherence tomography (OCT). OCT as high resolution imaging modality provides volumetric images of tissue and foresees information of bone position and orientation (pose) as well as thickness. However, existing approaches for OCT based laser ablation control rely on external tracking systems or invasively ablated artificial landmarks for tracking the pose of the OCT probe relative to the tissue. This can be superseded by estimating the scene flow caused by relative movement between OCT-based laser ablation system and patient.Therefore, this paper deals with 2.5D scene flow estimation of volumetric OCT images for application in laser ablation. We present a semi-supervised convolutional neural network based tracking scheme for subsequent 3D OCT volumes and apply it to a realistic semi-synthetic data set of ex vivo human temporal bone specimen.The scene flow is estimated in a two-stage approach. In the first stage, 2D lateral scene flow is computed on census-transformed en-face arguments-of-maximum intensity projections. Subsequent to this, the projections are warped by predicted lateral flow and 1D depth flow is estimated. The neural network is trained semi-supervised by combining error to ground truth and the reconstruction error of warped images with assumptions of spatial flow smoothness. Quantitative evaluation reveals a mean endpoint error of (4.7 ± 3.5) voxel or (27.5 ± 20.5) µm for scene flow estimation caused by simulated relative movement between the OCT probe and bone. The scene flow estimation for 4D OCT enables its use for markerless tracking of mastoid bone structures for image guidance in general, and automated laser ablation control.

We evaluate two different methods for the integration of prediction uncertainty into diagnostic image classifiers to increase patient safety in deep learning 1 . In the first method, Monte Carlo sampling is applied with dropout at test time to get a posterior distribution of the class labels (Bayesian ResNet). The second method extends ResNet to a probabilistic approach by predicting the parameters of the posterior distribution and sampling the final result from it (Variational ResNet). The variance of the posterior is used as metric for uncertainty. Both methods are trained on a data set of optical coherence tomography scans showing four different retinal conditions. Our results shown that cases in which the classifier predicts incorrectly correlate with a higher uncertainty. Mean uncertainty of incorrectly diagnosed cases was between 4.6 and 8.1 times higher than mean uncertainty of correctly diagnosed cases. Modeling of the prediction uncertainty in computer-aided diagnosis with deep learning yields more reliable results and is anticipated to increase patient safety.

We present deformable unsupervised medical image registration using a randomly-initialized deep convolutional neural network (CNN) as regularization prior. Conventional registration methods predict a transformation by minimizing dissimilarities between an image pair. The minimization is usually regularized with manually engineered priors, which limits the potential of the registration. By learning transformation priors from a large dataset, CNNs have achieved great success in deformable registration. However, learned methods are restricted to domain-specific data and the required amounts of medical data are difficult to obtain. Our approach uses the idea of deep image priors to combine convolutional networks with conventional registration methods based on manually engineered priors. The proposed method is applied to brain MRI scans. We show that our approach registers image pairs with state-of-the-art accuracy by providing dense, pixel-wise correspondence maps. It does not rely on prior training and is therefore not limited to a specific image domain.

No abstract

Noise in speckle-prone optical coherence tomography tends to obfuscate important details necessary for medical diagnosis. In this paper, a denoising approach that preserves disease characteristics on retinal optical coherence tomography images in ophthalmology is presented. By combining a deep convolutional autoencoder with a priorly trained ResNet image classifier as regularizer, the perceptibility of delicate details is encouraged and only information-less background noise is filtered out. With our approach, higher peak signal-to-noise ratios with PSNR = 31.2 dB and higher classification accuracy of ACC = 85.0 % can be achieved for denoised images compared to state-of-the-art denoising with PSNR = 29.4 dB or ACC = 70.3 %, depending on the method. It is shown that regularized autoencoders are capable of denoising retinal OCT images without blurring details of diseases.