arXiv subjects

Nassir Navab

Publications and source records attributed to Nassir Navab.

At least 559 records · Page 31Linked to original sources

arXiv2017

Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization

One-shot pose estimation for tasks such as body joint localization, camera pose estimation, and object tracking are generally noisy, and temporal filters have been extensively used for regularization. One of the most widely-used methods is the Kalman filter, which is both extremely simple and general. However, Kalman filters require a motion model and measurement model to be specified a priori, which burdens the modeler and simultaneously demands that we use explicit models that are often only crude approximations of reality. For example, in the pose-estimation tasks mentioned above, it is common to use motion models that assume constant velocity or constant acceleration, and we believe that these simplified representations are severely inhibitive. In this work, we propose to instead learn rich, dynamic representations of the motion and noise models. In particular, we propose learning these models from data using long short term memory, which allows representations that depend on all previous observations and all previous states. We evaluate our method using three of the most popular pose estimation tasks in computer vision, and in all cases we obtain state-of-the-art performance.

cs.CV↗

arXiv2017

Concurrent Segmentation and Localization for Tracking of Surgical Instruments

Real-time instrument tracking is a crucial requirement for various computer-assisted interventions. In order to overcome problems such as specular reflections and motion blur, we propose a novel method that takes advantage of the interdependency between localization and segmentation of the surgical tool. In particular, we reformulate the 2D instrument pose estimation as heatmap regression and thereby enable a concurrent, robust and near real-time regression of both tasks via deep learning. As demonstrated by our experimental results, this modeling leads to a significantly improved performance than directly regressing the tool position and allows our method to outperform the state of the art on a Retinal Microsurgery benchmark and the MICCAI EndoVis Challenge 2015.

cs.CV↗

arXiv2017

Semi-Supervised Deep Learning for Fully Convolutional Networks

Deep learning usually requires large amounts of labeled training data, but annotating data is costly and tedious. The framework of semi-supervised learning provides the means to use both labeled data and arbitrary amounts of unlabeled data for training. Recently, semi-supervised deep learning has been intensively studied for standard CNN architectures. However, Fully Convolutional Networks (FCNs) set the state-of-the-art for many image segmentation tasks. To the best of our knowledge, there is no existing semi-supervised learning method for such FCNs yet. We lift the concept of auxiliary manifold embedding for semi-supervised learning to FCNs with the help of Random Feature Embedding. In our experiments on the challenging task of MS Lesion Segmentation, we leverage the proposed framework for the purpose of domain adaptation and report substantial improvements over the baseline model.

cs.CV↗

arXiv2017

ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network

Optical coherence tomography (OCT) is used for non-invasive diagnosis of diabetic macular edema assessing the retinal layers. In this paper, we propose a new fully convolutional deep architecture, termed ReLayNet, for end-to-end segmentation of retinal layers and fluid masses in eye OCT scans. ReLayNet uses a contracting path of convolutional blocks (encoders) to learn a hierarchy of contextual features, followed by an expansive path of convolutional blocks (decoders) for semantic segmentation. ReLayNet is trained to optimize a joint loss function comprising of weighted logistic regression and Dice overlap loss. The framework is validated on a publicly available benchmark dataset with comparisons against five state-of-the-art segmentation methods including two deep learning based approaches to substantiate its effectiveness.

cs.CV↗

arXiv2017

Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data

Training deep fully convolutional neural networks (F-CNNs) for semantic image segmentation requires access to abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is very limited. We propose to automatically create auxiliary labels on initially unlabeled data with existing tools and to use them for pre-training. For the subsequent fine-tuning of the network with manually labeled data, we introduce error corrective boosting (ECB), which emphasizes parameter updates on classes with lower accuracy. Furthermore, we introduce SkipDeconv-Net (SD-Net), a new F-CNN architecture for brain segmentation that combines skip connections with the unpooling strategy for upsampling. The SD-Net addresses challenges of severe class imbalance and errors along boundaries. With application to whole-brain MRI T1 scan segmentation, we generate auxiliary labels on a large dataset with FreeSurfer and fine-tune on two datasets with manual annotations. Our results show that the inclusion of auxiliary labels and ECB yields significant improvements. SD-Net segments a 3D scan in 7 secs in comparison to 30 hours for the closest multi-atlas segmentation method, while reaching similar performance. It also outperforms the latest state-of-the-art F-CNN models.

cs.CV↗

arXiv2017

Segmentation of Intracranial Arterial Calcification with Deeply Supervised Residual Dropout Networks

Intracranial carotid artery calcification (ICAC) is a major risk factor for stroke, and might contribute to dementia and cognitive decline. Reliance on time-consuming manual annotation of ICAC hampers much demanded further research into the relationship between ICAC and neurological diseases. Automation of ICAC segmentation is therefore highly desirable, but difficult due to the proximity of the lesions to bony structures with a similar attenuation coefficient. In this paper, we propose a method for automatic segmentation of ICAC; the first to our knowledge. Our method is based on a 3D fully convolutional neural network that we extend with two regularization techniques. Firstly, we use deep supervision (hidden layers supervision) to encourage discriminative features in the hidden layers. Secondly, we augment the network with skip connections, as in the recently developed ResNet, and dropout layers, inserted in a way that skip connections circumvent them. We investigate the effect of skip connections and dropout. In addition, we propose a simple problem-specific modification of the network objective function that restricts the focus to the most important image regions and simplifies the optimization. We train and validate our model using 882 CT scans and test on 1,000. Our regularization techniques and objective improve the average Dice score by 7.1%, yielding an average Dice of 76.2% and 97.7% correlation between predicted ICAC volumes and manual annotations.

cs.CV↗

arXiv2017

Learning-based Surgical Workflow Detection from Intra-Operative Signals

A modern operating room (OR) provides a plethora of advanced medical devices. In order to better facilitate the information offered by them, they need to automatically react to the intra-operative context. To this end, the progress of the surgical workflow must be detected and interpreted, so that the current status can be given in machine-readable form. In this work, Random Forests (RF) and Hidden Markov Models (HMM) are compared and combined to detect the surgical workflow phase of a laparoscopic cholecystectomy. Various combinations of data were tested, from using only raw sensor data to filtered and augmented datasets. Achieved accuracies ranged from 64% to 72% for the RF approach, and from 80% to 82% for the combination of RF and HMM.

cs.LG↗

arXiv2017

CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction

Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for accurate and dense monocular reconstruction. We propose a method where CNN-predicted dense depth maps are naturally fused together with depth measurements obtained from direct monocular SLAM. Our fusion scheme privileges depth prediction in image locations where monocular SLAM approaches tend to fail, e.g. along low-textured regions, and vice-versa. We demonstrate the use of depth prediction for estimating the absolute scale of the reconstruction, hence overcoming one of the major limitations of monocular SLAM. Finally, we propose a framework to efficiently fuse semantic labels, obtained from a single frame, with dense SLAM, yielding semantically coherent scene reconstruction from a single view. Evaluation results on two benchmark datasets show the robustness and accuracy of our approach.

cs.CV↗

arXiv2017

Deep Residual Learning for Instrument Segmentation in Robotic Surgery

Detection, tracking, and pose estimation of surgical instruments are crucial tasks for computer assistance during minimally invasive robotic surgery. In the majority of cases, the first step is the automatic segmentation of surgical tools. Prior work has focused on binary segmentation, where the objective is to label every pixel in an image as tool or background. We improve upon previous work in two major ways. First, we leverage recent techniques such as deep residual learning and dilated convolutions to advance binary-segmentation performance. Second, we extend the approach to multi-class segmentation, which lets us segment different parts of the tool, in addition to background. We demonstrate the performance of this method on the MICCAI Endoscopic Vision Challenge Robotic Instruments dataset.

cs.CV↗

arXiv2017

X-ray In-Depth Decomposition: Revealing The Latent Structures

X-ray radiography is the most readily available imaging modality and has a broad range of applications that spans from diagnosis to intra-operative guidance in cardiac, orthopedics, and trauma procedures. Proper interpretation of the hidden and obscured anatomy in X-ray images remains a challenge and often requires high radiation dose and imaging from several perspectives. In this work, we aim at decomposing the conventional X-ray image into d X-ray components of independent, non-overlapped, clipped sub-volumes using deep learning approach. Despite the challenging aspects of modeling such a highly ill-posed problem, exciting and encouraging results are obtained paving the path for further contributions in this direction.

cs.CV↗

arXiv2017

Learning Robust Hash Codes for Multiple Instance Image Retrieval

In this paper, for the first time, we introduce a multiple instance (MI) deep hashing technique for learning discriminative hash codes with weak bag-level supervision suited for large-scale retrieval. We learn such hash codes by aggregating deeply learnt hierarchical representations across bag members through a dedicated MI pool layer. For better trainability and retrieval quality, we propose a two-pronged approach that includes robust optimization and training with an auxiliary single instance hashing arm which is down-regulated gradually. We pose retrieval for tumor assessment as an MI problem because tumors often coexist with benign masses and could exhibit complementary signatures when scanned from different anatomical views. Experimental validations on benchmark mammography and histology datasets demonstrate improved retrieval performance over the state-of-the-art methods.

cs.CV↗

arXiv2017

Quantitative Characterization of Components of Computer Assisted Interventions

Purpose: We propose a mathematical framework for quantitative analysis weighting the impact of heterogeneous components of a surgery. While multi-level approaches, surgical process modeling and other workflow analysis methods exist, this is to our knowledge the first quantitative approach. Methods: Inspired by the group decision making problem from the field of operational research, we define event impact factors, which combine independent and very diverse low-level functions. This allows us to rate surgical events by their importance. Results: We conducted surveys with 4 surgeons to determine the importance of roles, phases and their combinations within a laparoscopic cholecystectomy. Applying this data on a recorded surgery, we showed that it is possible to define a quantitative measure for deciding on acception or rejection of calls to different roles and at different phases of surgery. Conclusions: This methodology allows us to use components such as expertise and role of the surgical staff and other aspects of a given surgery in order to quantitatively analyze and evaluate events, actions, user interfaces or procedures.

cs.OH↗

arXiv2017

Surgical Data Science: Enabling Next-Generation Surgery

This paper introduces Surgical Data Science as an emerging scientific discipline. Key perspectives are based on discussions during an intensive two-day international interactive workshop that brought together leading researchers working in the related field of computer and robot assisted interventions. Our consensus opinion is that increasing access to large amounts of complex data, at scale, throughout the patient care process, complemented by advances in data science and machine learning techniques, has set the stage for a new generation of analytics that will support decision-making and quality improvement in interventional medicine. In this article, we provide a consensus definition for Surgical Data Science, identify associated challenges and opportunities and provide a roadmap for advancing the field.

cs.CY↗

arXiv2016

Cross-Modal Manifold Learning for Cross-modal Retrieval

This paper presents a new scalable algorithm for cross-modal similarity preserving retrieval in a learnt manifold space. Unlike existing approaches that compromise between preserving global and local geometries, the proposed technique respects both simultaneously during manifold alignment. The global topologies are maintained by recovering underlying mapping functions in the joint manifold space by deploying partially corresponding instances. The inter-, and intra-modality affinity matrices are then computed to reinforce original data skeleton using perturbed minimum spanning tree (pMST), and maximizing the affinity among similar cross-modal instances, respectively. The performance of proposed algorithm is evaluated upon two multimodal image datasets (coronary atherosclerosis histology and brain MRI) for two applications: classification, and regression. Our exhaustive validations and results demonstrate the superiority of our technique over comparative methods and its feasibility for improving computer-assisted diagnosis systems, where disease-specific complementary information shall be aggregated and interpreted across modalities to form the final decision.

cs.CV↗

arXiv2016

Deep Residual Hashing

Hashing aims at generating highly compact similarity preserving code words which are well suited for large-scale image retrieval tasks. Most existing hashing methods first encode the images as a vector of hand-crafted features followed by a separate binarization step to generate hash codes. This two-stage process may produce sub-optimal encoding. In this paper, for the first time, we propose a deep architecture for supervised hashing through residual learning, termed Deep Residual Hashing (DRH), for an end-to-end simultaneous representation learning and hash coding. The DRH model constitutes four key elements: (1) a sub-network with multiple stacked residual blocks; (2) hashing layer for binarization; (3) supervised retrieval loss function based on neighbourhood component analysis for similarity preserving embedding; and (4) hashing related losses and regularisation to control the quantization error and improve the quality of hash coding. We present results of extensive experiments on a large public chest x-ray image database with co-morbidities and discuss the outcome showing substantial improvements over the latest state-of-the art methods.

cs.CV↗

arXiv2016

Exploring Non-Reversing Magic Mirrors for Screen-Based Augmented Reality Systems

Screen-based Augmented Reality (AR) systems can be built as a window into the real world as often done in mobile AR applications or using the Magic Mirror metaphor, where users can see themselves with augmented graphics on a large display. Such Magic Mirror systems have been used in digital clothing environments to create virtual dressing rooms, to teach human anatomy, and for collaborative design tasks. The term Magic Mirror implies that the display shows the users enantiomorph, i.e. the mirror image, such that the system mimics a real-world physical mirror. However, the question arises whether one should design a traditional mirror, or instead display the true mirror image by means of a non-reversing mirror? This is an intriguing perceptual question, as the image one observes in a mirror is not a real view, as it would be seen by an external observer, but a reflection, i.e. a front-to-back reversed image. In this paper, we discuss the perceptual differences between these two mirror visualization concepts and present a first comparative study in the context of Magic Mirror anatomy teaching. We investigate the ability of users to identify the correct placement of virtual anatomical structures in our screen-based AR system for two conditions: a regular mirror and a non-reversing mirror setup. The results of our study indicate that the latter is more suitable for applications where previously acquired domain-specific knowledge plays an important role. The lessons learned open up new research directions in the fields of user interfaces and interaction in non-reversing mirror environments and could impact the implementation of general screen-based AR systems in other domains.

cs.HC↗

arXiv2016

An Efficient Training Algorithm for Kernel Survival Support Vector Machines

Survival analysis is a fundamental tool in medical research to identify predictors of adverse events and develop systems for clinical decision support. In order to leverage large amounts of patient data, efficient optimisation routines are paramount. We propose an efficient training algorithm for the kernel survival support vector machine (SSVM). We directly optimise the primal objective function and employ truncated Newton optimisation and order statistic trees to significantly lower computational costs compared to previous training algorithms, which require $O(n^4)$ space and $O(p n^6)$ time for datasets with $n$ samples and $p$ features. Our results demonstrate that our proposed optimisation scheme allows analysing data of a much larger scale with no loss in prediction performance. Experiments on synthetic and 5 real-world datasets show that our technique outperforms existing kernel SSVM formulations if the amount of right censoring is high ($\geq85\%$), and performs comparably otherwise.

cs.LG↗

arXiv2016

Hands-Free Segmentation of Medical Volumes via Binary Inputs

We propose a novel hands-free method to interactively segment 3D medical volumes. In our scenario, a human user progressively segments an organ by answering a series of questions of the form "Is this voxel inside the object to segment?". At each iteration, the chosen question is defined as the one halving a set of candidate segmentations given the answered questions. For a quick and efficient exploration, these segmentations are sampled according to the Metropolis-Hastings algorithm. Our sampling technique relies on a combination of relaxed shape prior, learnt probability map and consistency with previous answers. We demonstrate the potential of our strategy on a prostate segmentation MRI dataset. Through the study of failure cases with synthetic examples, we demonstrate the adaptation potential of our method. We also show that our method outperforms two intuitive baselines: one based on random questions, the other one being the thresholded probability map.

cs.CV↗