Results for "Nassir Navab"

total 153took 0.13s
Towards Unsupervised Image Captioning with Shared Multimodal EmbeddingsAug 25 2019Understanding images without explicit supervision has become an important problem in computer vision. In this paper, we address image captioning by generating language descriptions of scenes without learning from annotated pairs of images and their captions. ... More
SUPRA: Open Source Software Defined Ultrasound Processing for Real-Time ApplicationsNov 16 2017May 10 2018Research in ultrasound imaging is limited in reproducibility by two factors: First, many existing ultrasound pipelines are protected by intellectual property, rendering exchange of code difficult. Second, most pipelines are implemented in special hardware, ... More
Object-Driven Multi-Layer Scene Decomposition From a Single ImageAug 26 2019We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation that arranges ... More
Adversarial Signal Denoising with encoder-decoder networksDec 20 2018In this work, we treat the task of signal denoising as distribution alignment between the clean and noisy signal. An adversarial encoder-decoder network is proposed for denoising signals, represented by a sequence of measurements. We rely on the signal's ... More
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' BlocksAug 23 2018In a wide range of semantic segmentation tasks, fully convolutional neural networks (F-CNNs) have been successfully leveraged to achieve state-of-the-art performance. Architectural innovations of F-CNNs have mainly been on improving spatial encoding or ... More
X-ray In-Depth Decomposition: Revealing The Latent StructuresDec 19 2016Mar 22 2017X-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 ... More
Learning Interpretable Features via Adversarially Robust OptimizationMay 09 2019Neural networks are proven to be remarkably successful for classification and diagnosis in medical applications. However, the ambiguity in the decision-making process and the interpretability of the learned features is a matter of concern. In this work, ... More
Semi-Supervised Deep Learning for Fully Convolutional NetworksMar 17 2017Jul 25 2017Deep 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. ... More
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image SegmentationJun 15 2016Convolutional Neural Networks (CNNs) have been recently employed to solve problems from both the computer vision and medical image analysis fields. Despite their popularity, most approaches are only able to process 2D images while most medical data used ... More
MelanoGANs: High Resolution Skin Lesion Synthesis with GANsApr 12 2018Generative Adversarial Networks (GANs) have been successfully used to synthesize realistically looking images of faces, scenery and even medical images. Unfortunately, they usually require large training datasets, which are often scarce in the medical ... More
Weakly-Supervised White and Grey Matter Segmentation in 3D Brain UltrasoundApr 10 2019Although the segmentation of brain structures in ultrasound helps initialize image based registration, assist brain shift compensation, and provides interventional decision support, the task of segmenting grey and white matter in cranial ultrasound is ... More
Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance PropagationAug 01 2019We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much one ... More
Few-Shot Meta-DenoisingJul 31 2019We study the problem of learning-based denoising where the training set contains just a handful of clean and noisy samples. A solution to mitigate the small training set issue is to train a denoising model with pairs of clean and synthesized noisy signals, ... More
Competition vs. Concatenation in Skip Connections of Fully Convolutional NetworksJul 20 2018Increased information sharing through short and long-range skip connections between layers in fully convolutional networks have demonstrated significant improvement in performance for semantic segmentation. In this paper, we propose Competitive Dense ... More
Alignment of the Virtual Scene to the Tracking Space of a Mixed Reality Head-Mounted DisplayMar 16 2017Mar 27 2019With the mounting global interest for optical see-through head-mounted displays (OST-HMDs) across medical, industrial and entertainment settings, many systems with different capabilities are rapidly entering the market. Despite such variety, they all ... More
Webly Supervised Learning for Skin Lesion ClassificationMar 31 2018May 31 2019Within medical imaging, manual curation of sufficient well-labeled samples is cost, time and scale-prohibitive. To improve the representativeness of the training dataset, for the first time, we present an approach to utilize large amounts of freely available ... More
A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point CloudsMar 19 2018This paper proposes a segmentation-free, automatic and efficient procedure to detect general geometric quadric forms in point clouds, where clutter and occlusions are inevitable. Our everyday world is dominated by man-made objects which are designed using ... More
Perceptual Embedding Consistency for Seamless Reconstruction of Tilewise Style TransferJun 03 2019Style transfer is a field with growing interest and use cases in deep learning. Recent work has shown Generative Adversarial Networks(GANs) can be used to create realistic images of virtually stained slide images in digital pathology with clinically validated ... More
An Octree-Based Approach towards Efficient Variational Range Data FusionAug 26 2016Volume-based reconstruction is usually expensive both in terms of memory consumption and runtime. Especially for sparse geometric structures, volumetric representations produce a huge computational overhead. We present an efficient way to fuse range data ... More
Hashmod: A Hashing Method for Scalable 3D Object DetectionJul 20 2016We present a scalable method for detecting objects and estimating their 3D poses in RGB-D data. To this end, we rely on an efficient representation of object views and employ hashing techniques to match these views against the input frame in a scalable ... More
Situation Assessment for Planning Lane Changes: Combining Recurrent Models and PredictionMay 17 2018One of the greatest challenges towards fully autonomous cars is the understanding of complex and dynamic scenes. Such understanding is needed for planning of maneuvers, especially those that are particularly frequent such as lane changes. While in recent ... More
Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality ControlNov 24 2018We 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 ... More
Semi-Supervised Few-Shot Learning with Local and Global ConsistencyMar 06 2019Learning from a few examples is a key characteristic of human intelligence that AI researchers have been excited about modeling. With the web-scale data being mostly unlabeled, few recent works showed that few-shot learning performance can be significantly ... More
Generalizability vs. Robustness: Adversarial Examples for Medical ImagingMar 23 2018In this paper, for the first time, we propose an evaluation method for deep learning models that assesses the performance of a model not only in an unseen test scenario, but also in extreme cases of noise, outliers and ambiguous input data. To this end, ... More
Generalizing multistain immunohistochemistry tissue segmentation using one-shot color deconvolution deep neural networksMay 17 2018Sep 22 2018A key challenge in cancer immunotherapy biomarker research is quantification of pattern changes in microscopic whole slide images of tumor biopsies. Different cell types tend to migrate into various tissue compartments and form variable distribution patterns. ... More
Fully Automatic Segmentation of 3D Brain Ultrasound: Learning from Coarse AnnotationsApr 18 2019Intra-operative ultrasound is an increasingly important imaging modality in neurosurgery. However, manual interaction with imaging data during the procedures, for example to select landmarks or perform segmentation, is difficult and can be time consuming. ... More
Initialize globally before acting locally: Enabling Landmark-free 3D US to MRI RegistrationJun 12 2018Registration of partial-view 3D US volumes with MRI data is influenced by initialization. The standard of practice is using extrinsic or intrinsic landmarks, which can be very tedious to obtain. To overcome the limitations of registration initialization, ... More
Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance PropagationAug 01 2019Aug 21 2019We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much one ... More
Webly Supervised Learning for Skin Lesion ClassificationMar 31 2018Within medical imaging, manual curation of sufficient well-labeled samples is cost, time and scale-prohibitive. To improve the representativeness of the training dataset, for the first time, we present an approach to utilize large amounts of freely available ... More
When Regression Meets Manifold Learning for Object Recognition and Pose EstimationMay 16 2018In this work, we propose a method for object recognition and pose estimation from depth images using convolutional neural networks. Previous methods addressing this problem rely on manifold learning to learn low dimensional viewpoint descriptors and employ ... More
An Uncertainty-Driven GCN Refinement Strategy for Organ SegmentationJun 05 2019Organ segmentation is an important pre-processing step in many computer assisted intervention and computer assisted diagnosis methods. In recent years, CNNs have dominated the state of the art in this task. Organ segmentation scenarios present a challenging ... More
Quantitative Characterization of Components of Computer Assisted InterventionsFeb 02 2017Purpose: 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 ... More
Deep Active ContoursJul 18 2016We propose a method for interactive boundary extraction which combines a deep, patch-based representation with an active contour framework. We train a class-specific convolutional neural network which predicts a vector pointing from the respective point ... More
Robust Optimization for Deep RegressionMay 25 2015Sep 22 2015Convolutional Neural Networks (ConvNets) have successfully contributed to improve the accuracy of regression-based methods for computer vision tasks such as human pose estimation, landmark localization, and object detection. The network optimization has ... More
CFCM: Segmentation via Coarse to Fine Context MemoryJun 04 2018Recent neural-network-based architectures for image segmentation make extensive usage of feature forwarding mechanisms to integrate information from multiple scales. Although yielding good results, even deeper architectures and alternative methods for ... More
Collaboration Analysis Using Deep LearningApr 17 2019The analysis of the collaborative learning process is one of the growing fields of education research, which has many different analytic solutions. In this paper, we provided a new solution to improve automated collaborative learning analyses using deep ... More
Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric FitsJan 04 2019We present a novel and effective method for detecting 3D primitives in cluttered, unorganized point clouds, without axillary segmentation or type specification. We consider the quadric surfaces for encapsulating the basic building blocks of our environments ... More
Redefining Ultrasound Compounding: Computational SonographyNov 05 2018Freehand three-dimensional ultrasound (3D-US) has gained considerable interest in research, but even today suffers from its high inter-operator variability in clinical practice. The high variability mainly arises from tracking inaccuracies as well as ... More
Incremental Adversarial Learning for Optimal Path PlanningSep 25 2018Path planning plays an essential role in many areas of robotics. Various planning techniques have been presented, either focusing on learning a specific task from demonstrations or retrieving trajectories by optimizing for hand-crafted cost functions ... More
Multi-scale Microaneurysms Segmentation Using Embedding Triplet LossApr 18 2019Deep learning techniques are recently being used in fundus image analysis and diabetic retinopathy detection. Microaneurysms are an important indicator of diabetic retinopathy progression. We introduce a two-stage deep learning approach for microaneurysms ... More
Cross-Modal Manifold Learning for Cross-modal RetrievalDec 19 2016This 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 ... More
Learning Robust Hash Codes for Multiple Instance Image RetrievalMar 16 2017In 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 ... More
Deep Residual HashingDec 16 2016Hashing 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 ... More
CNN-SLAM: Real-time dense monocular SLAM with learned depth predictionApr 11 2017Given 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 ... More
Deep Residual Learning for Instrument Segmentation in Robotic SurgeryMar 24 2017Detection, 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 ... More
Deep Model-Based 6D Pose Refinement in RGBOct 07 2018We present a novel approach for model-based 6D pose refinement in color data. Building on the established idea of contour-based pose tracking, we teach a deep neural network to predict a translational and rotational update. At the core, we propose a new ... More
SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againNov 27 2017We present a novel method for detecting 3D model instances and estimating their 6D poses from RGB data in a single shot. To this end, we extend the popular SSD paradigm to cover the full 6D pose space and train on synthetic model data only. Our approach ... More
A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural NetworksJun 24 2016Over the last decade, Convolutional Neural Networks (CNN) saw a tremendous surge in performance. However, understanding what a network has learned still proves to be a challenging task. To remedy this unsatisfactory situation, a number of groups have ... More
Deeper Depth Prediction with Fully Convolutional Residual NetworksJun 01 2016Sep 19 2016This paper addresses the problem of estimating the depth map of a scene given a single RGB image. We propose a fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and depth maps. In ... More
Weakly-Supervised White and Grey Matter Segmentation in 3D Brain UltrasoundApr 10 2019Apr 11 2019Although the segmentation of brain structures in ultrasound helps initialize image based registration, assist brain shift compensation, and provides interventional decision support, the task of segmenting grey and white matter in cranial ultrasound is ... More
Adversarial Joint Image and Pose Distribution Learning for Camera Pose Regression and RefinementMar 15 2019In this paper we present a deep-learning based framework for direct camera pose regression and refinement using RGB information only. For this aim we introduce a novel framework for camera pose estimation, that regresses the camera pose as well as offers ... More
Multi Layered-Parallel Graph Convolutional Network (ML-PGCN) for Disease PredictionApr 28 2018Structural data from Electronic Health Records as complementary information to imaging data for disease prediction. We incorporate novel weighting layer into the Graph Convolutional Networks, which weights every element of structural data by exploring ... More
Scene Coordinate and Correspondence Learning for Image-Based LocalizationMay 22 2018Jul 26 2018Scene coordinate regression has become an essential part of current camera re-localization methods. Different versions, such as regression forests and deep learning methods, have been successfully applied to estimate the corresponding camera pose given ... More
Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose EstimationJul 20 2016We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting. For regression, we employ a convolutional auto-encoder that has been trained on a large collection of random local patches. During ... More
Peeking Behind Objects: Layered Depth Prediction from a Single ImageJul 23 2018While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of depth prediction in augmented and virtual reality applications, ... More
Fully-Convolutional Point Networks for Large-Scale Point CloudsAug 21 2018This work proposes a general-purpose, fully-convolutional network architecture for efficiently processing large-scale 3D data. One striking characteristic of our approach is its ability to process unorganized 3D representations such as point clouds as ... More
QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of NeuroanatomyJan 12 2018Nov 24 2018Whole brain segmentation from structural magnetic resonance imaging (MRI) is a prerequisite for most morphological analyses, but is computationally intense and can therefore delay the availability of image markers after scan acquisition. We introduce ... More
RIO: 3D Object Instance Re-Localization in Changing Indoor EnvironmentsAug 16 2019In this work, we introduce the task of 3D object instance re-localization (RIO): given one or multiple objects in an RGB-D scan, we want to estimate their corresponding 6DoF poses in another 3D scan of the same environment taken at a later point in time. ... More
Learning Interpretable Disentangled Representations using Adversarial VAEsApr 17 2019Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a more compact ... More
Grasp Type Estimation for Myoelectric Prostheses using Point Cloud Feature LearningAug 07 2019Prosthetic hands can help people with limb difference to return to their life routines. Commercial prostheses, however have several limitations in providing an acceptable dexterity. We approach these limitations by augmenting the prosthetic hands with ... More
Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR ImagesApr 12 2018Reliably modeling normality and differentiating abnormal appearances from normal cases is a very appealing approach for detecting pathologies in medical images. A plethora of such unsupervised anomaly detection approaches has been made in the medical ... More
Learning in an Uncertain World: Representing Ambiguity Through Multiple HypothesesDec 01 2016Many prediction tasks contain uncertainty. In the case of next-frame or future prediction the uncertainty is inherent in the task itself, as it is impossible to foretell what exactly is going to happen in the future. Another source of uncertainty or ambiguity ... More
Towards MRI-Based Autonomous Robotic US Acquisitions: A First Feasibility StudyJul 28 2016Robotic ultrasound has the potential to assist and guide physicians during interventions. In this work, we present a set of methods and a workflow to enable autonomous MRI-guided ultrasound acquisitions. Our approach uses a structured-light 3D scanner ... More
`Project & Excite' Modules for Segmentation of Volumetric Medical ScansJun 11 2019Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for image segmentation in medical imaging. Recently, squeeze and excitation (SE) modules and variations thereof have been introduced to recalibrate feature maps channel- ... More
GANs for Medical Image AnalysisSep 13 2018Dec 21 2018Generative Adversarial Networks (GANs) and their extensions have carved open many exciting ways to tackle well known and challenging medical image analysis problems such as medical image de-noising, reconstruction, segmentation, data simulation, detection ... More
Markerless Inside-Out Tracking for Interventional ApplicationsApr 05 2018Jun 12 2018Tracking of rotation and translation of medical instruments plays a substantial role in many modern interventions. Traditional external optical tracking systems are often subject to line-of-sight issues, in particular when the region of interest is difficult ... More
Exploring Non-Reversing Magic Mirrors for Screen-Based Augmented Reality SystemsNov 10 2016Screen-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 ... More
Hands-Free Segmentation of Medical Volumes via Binary InputsSep 20 2016We 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, ... More
Adaptive image-feature learning for disease classification using inductive graph networksMay 08 2019Recently, Geometric Deep Learning (GDL) has been introduced as a novel and versatile framework for computer-aided disease classification. GDL uses patient meta-information such as age and gender to model patient cohort relations in a graph structure. ... More
BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated LearningMay 16 2019Access to sufficient annotated data is a common challenge in training deep neural networks on medical images. As annotating data is expensive and time-consuming, it is difficult for an individual medical center to reach large enough sample sizes to build ... More
Multi-scale Microaneurysms Segmentation Using Embedding Triplet LossApr 18 2019Aug 14 2019Deep learning techniques are recently being used in fundus image analysis and diabetic retinopathy detection. Microaneurysms are an important indicator of diabetic retinopathy progression. We introduce a two-stage deep learning approach for microaneurysms ... More
End-to-End Learning-Based Ultrasound ReconstructionApr 09 2019Ultrasound imaging is caught between the quest for the highest image quality, and the necessity for clinical usability. Our contribution is two-fold: First, we propose a novel fully convolutional neural network for ultrasound reconstruction. Second, a ... More
A Deep Metric for Multimodal RegistrationSep 17 2016Multimodal registration is a challenging problem in medical imaging due the high variability of tissue appearance under different imaging modalities. The crucial component here is the choice of the right similarity measure. We make a step towards a general ... More
The TUM LapChole dataset for the M2CAI 2016 workflow challengeOct 28 2016In this technical report we present our collected dataset of laparoscopic cholecystectomies (LapChole). Laparoscopic videos of a total of 20 surgeries were recorded and annotated with surgical phase labels, of which 15 were randomly pre-determined as ... More
Deep Learning Under the Microscope: Improving the Interpretability of Medical Imaging Neural NetworksApr 05 2019In this paper, we propose a novel interpretation method tailored to histological Whole Slide Image (WSI) processing. A Deep Neural Network (DNN), inspired by Bag-of-Features models is equipped with a Multiple Instance Learning (MIL) branch and trained ... More
3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain SegmentationApr 05 2019Model architectures have been dramatically increasing in size, improving performance at the cost of resource requirements. In this paper we propose 3DQ, a ternary quantization method, applied for the first time to 3D Fully Convolutional Neural Networks ... More
Concurrent Segmentation and Localization for Tracking of Surgical InstrumentsMar 30 2017Aug 01 2017Real-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 ... More
Adaptive Image-Feature Learning for Disease Classification Using Inductive Graph NetworksMay 08 2019Aug 19 2019Recently, Geometric Deep Learning (GDL) has been introduced as a novel and versatile framework for computer-aided disease classification. GDL uses patient meta-information such as age and gender to model patient cohort relations in a graph structure. ... More
Learning in an Uncertain World: Representing Ambiguity Through Multiple HypothesesDec 01 2016Aug 22 2017Many prediction tasks contain uncertainty. In some cases, uncertainty is inherent in the task itself. In future prediction, for example, many distinct outcomes are equally valid. In other cases, uncertainty arises from the way data is labeled. For example, ... More
Multi-modal Graph Fusion for Inductive Disease Classification in Incomplete DatasetsMay 08 2019Clinical diagnostic decision making and population-based studies often rely on multi-modal data which is noisy and incomplete. Recently, several works proposed geometric deep learning approaches to solve disease classification, by modeling patients as ... More
DeepDRR -- A Catalyst for Machine Learning in Fluoroscopy-guided ProceduresMar 22 2018Machine learning-based approaches outperform competing methods in most disciplines relevant to diagnostic radiology. Interventional radiology, however, has not yet benefited substantially from the advent of deep learning, in particular because of two ... More
Attention-based Lane Change PredictionMar 04 2019Lane change prediction of surrounding vehicles is a key building block of path planning. The focus has been on increasing the accuracy of prediction by posing it purely as a function estimation problem at the cost of model understandability. However, ... More
3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain SegmentationApr 05 2019Apr 16 2019Model architectures have been dramatically increasing in size, improving performance at the cost of resource requirements. In this paper we propose 3DQ, a ternary quantization method, applied for the first time to 3D Fully Convolutional Neural Networks ... More
SynNet: Structure-Preserving Fully Convolutional Networks for Medical Image SynthesisJun 29 2018Cross modal image syntheses is gaining significant interests for its ability to estimate target images of a different modality from a given set of source images,like estimating MR to MR, MR to CT, CT to PET etc, without the need for an actual acquisition.Though ... More
Exploring Non-Reversing Magic Mirrors for Screen-Based Augmented Reality SystemsNov 10 2016Dec 07 2016Screen-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 ... More
LumiPath - Towards Real-time Physically-based Rendering on Embedded DevicesMar 09 2019As the computational power of toady's devices increases, real-time physically-based rendering becomes possible, and is rapidly gaining attention across a variety of domains. These include gaming, where physically-based rendering enhances immersion and ... More
Attention-based Lane Change PredictionMar 04 2019Mar 07 2019Lane change prediction of surrounding vehicles is a key building block of path planning. The focus has been on increasing the accuracy of prediction by posing it purely as a function estimation problem at the cost of model understandability. However, ... More
The speaker-independent lipreading play-off; a survey of lipreading machinesOct 24 2018Lipreading is a difficult gesture classification task. One problem in computer lipreading is speaker-independence. Speaker-independence means to achieve the same accuracy on test speakers not included in the training set as speakers within the training ... More
Machine learning-based colon deformation estimation method for colonoscope trackingJun 08 2018This paper presents a colon deformation estimation method, which can be used to estimate colon deformations during colonoscope insertions. Colonoscope tracking or navigation system that navigates a physician to polyp positions during a colonoscope insertion ... More
The TUM LapChole dataset for the M2CAI 2016 workflow challengeOct 28 2016Aug 31 2017In this technical report we present our collected dataset of laparoscopic cholecystectomies (LapChole). Laparoscopic videos of a total of 20 surgeries were recorded and annotated with surgical phase labels, of which 15 were randomly pre-determined as ... More
Guide Me: Interacting with Deep NetworksMar 30 2018Interaction and collaboration between humans and intelligent machines has become increasingly important as machine learning methods move into real-world applications that involve end users. While much prior work lies at the intersection of natural language ... More
Image to Images Translation for Multi-Task Organ Segmentation and Bone Suppression in Chest X-Ray RadiographyJun 24 2019Chest X-ray radiography is one of the earliest medical imaging technologies and remains one of the most widely-used for the diagnosis, screening and treatment follow up of diseases related to lungs and heart. The literature in this field of research reports ... More
'Squeeze & Excite' Guided Few-Shot Segmentation of Volumetric ImagesFeb 04 2019Deep neural networks enable highly accurate image segmentation, but require large amounts of manually annotated data for supervised training. Few-shot learning aims to address this shortcoming by learning a new class from a few annotated support examples. ... More
`Project & Excite' Modules for Segmentation of Volumetric Medical ScansJun 11 2019Jun 12 2019Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for image segmentation in medical imaging. Recently, squeeze and excitation (SE) modules and variations thereof have been introduced to recalibrate feature maps channel- ... More
Domain-Specific Priors and Meta Learning for Low-shot First-Person Action RecognitionJul 22 2019The lack of large-scale real datasets with annotationsmakes transfer learning a necessity for video activity under-standing. Within this scope, we aim at developing an effec-tive method for low-shot transfer learning for first-personaction classification. ... More
Augmented Reality-based Feedback for Technician-in-the-loop C-arm RepositioningJun 22 2018Interventional C-arm imaging is crucial to percutaneous orthopedic procedures as it enables the surgeon to monitor the progress of surgery on the anatomy level. Minimally invasive interventions require repeated acquisition of X-ray images from different ... More
Towards an Interactive and Interpretable CAD System to Support Proximal Femur Fracture ClassificationFeb 04 2019Fractures of the proximal femur represent a critical entity in the western world, particularly with the growing elderly population. Such fractures result in high morbidity and mortality, reflecting a significant health and economic impact on our society. ... More
Mitosis Detection in Intestinal Crypt Images with Hough Forest and Conditional Random FieldsAug 26 2016Intestinal enteroendocrine cells secrete hormones that are vital for the regulation of glucose metabolism but their differentiation from intestinal stem cells is not fully understood. Asymmetric stem cell divisions have been linked to intestinal stem ... More
On-the-fly Augmented Reality for Orthopaedic Surgery Using a Multi-Modal FiducialJan 04 2018Fluoroscopic X-ray guidance is a cornerstone for percutaneous orthopaedic surgical procedures. However, two-dimensional observations of the three-dimensional anatomy suffer from the effects of projective simplification. Consequently, many X-ray images ... More
Closing the Calibration Loop: An Inside-out-tracking Paradigm for Augmented Reality in Orthopedic SurgeryMar 22 2018In percutaneous orthopedic interventions the surgeon attempts to reduce and fixate fractures in bony structures. The complexity of these interventions arises when the surgeon performs the challenging task of navigating surgical tools percutaneously only ... More