arXiv subjects

Martin Wagner

Publications and source records attributed to Martin Wagner.

At least 37 records · Page 2Linked to original sources

arXiv2021

Surgical Data Science -- from Concepts toward Clinical Translation

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process.

cs.CY↗

arXiv2021

Chameleons on Cloudlets: Elastic Edge Computing Through Microservice Variants

Common deployment models for Edge Computing are based on (composable) microservices that are offloaded to cloudlets. Runtime adaptations-in response to varying load, QoS fulfillment, mobility, etc.-are typically based on coarse-grained and costly management operations such as resource re-allocation or migration. The services themselves, however, remain non-adaptive, worsening the already limited elasticity of Edge Computing compared to Cloud Computing. Edge computing applications often have stringent requirements on the execution time but are flexible regarding the quality of a computation. The potential benefits of exploiting this trade-off remain untapped. This paper introduces the concept of adaptable microservices that provide alternative variants of specific functionalities. We define so-called service variants that differ w.r.t. the internal functioning of the service, manifested in different algorithms, parameters, and auxiliary data they use. Such variants allow fine-grained trade-offs between the QoS (e.g., a maximum tolerable execution time) and the quality of the computation. We integrate adaptable microservices into an Edge Computing framework, show the practical impact of service variants, and present a strategy for switching variants at runtime.

cs.DC↗

arXiv2021

Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Room

Image-based tracking of medical instruments is an integral part of surgical data science applications. Previous research has addressed the tasks of detecting, segmenting and tracking medical instruments based on laparoscopic video data. However, the proposed methods still tend to fail when applied to challenging images and do not generalize well to data they have not been trained on. This paper introduces the Heidelberg Colorectal (HeiCo) data set - the first publicly available data set enabling comprehensive benchmarking of medical instrument detection and segmentation algorithms with a specific emphasis on method robustness and generalization capabilities. Our data set comprises 30 laparoscopic videos and corresponding sensor data from medical devices in the operating room for three different types of laparoscopic surgery. Annotations include surgical phase labels for all video frames as well as information on instrument presence and corresponding instance-wise segmentation masks for surgical instruments (if any) in more than 10,000 individual frames. The data has successfully been used to organize international competitions within the Endoscopic Vision Challenges 2017 and 2019.

cs.CV↗

arXiv2020

Robust Medical Instrument Segmentation Challenge 2019

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).

cs.CV↗

arXiv2019

Robust and Efficient Power Flow Convergence with G-min Stepping Homotopy Method

Recent advances have shown that the circuit simulation algorithms that allow for solving highly nonlinear circuits of over one billion variables can be applicable to power system simulation and optimization problems through the use of an equivalent circuit formulation. It was demonstrated that large-scale (80k+ buses) power flow simulations can be robustly solved, independent of the initial starting point. In this paper, we extend the electronic circuit-based G-min stepping homotopy method to power flow simulations. Preliminary results indicate that the proposed algorithm results in significantly better simulation runtime performance when compared to existing homotopy methods.

eess.SP↗

arXiv2019

Prediction of laparoscopic procedure duration using unlabeled, multimodal sensor data

Purpose The course of surgical procedures is often unpredictable, making it difficult to estimate the duration of procedures beforehand. A context-aware method that analyses the workflow of an intervention online and automatically predicts the remaining duration would alleviate these problems. As basis for such an estimate, information regarding the current state of the intervention is required. Methods Today, the operating room contains a diverse range of sensors. During laparoscopic interventions, the endoscopic video stream is an ideal source of such information. Extracting quantitative information from the video is challenging though, due to its high dimensionality. Other surgical devices (e.g. insufflator, lights, etc.) provide data streams which are, in contrast to the video stream, more compact and easier to quantify. Though whether such streams offer sufficient information for estimating the duration of surgery is uncertain. Here, we propose and compare methods, based on convolutional neural networks, for continuously predicting the duration of laparoscopic interventions based on unlabeled data, such as from endoscopic images and surgical device streams. Results The methods are evaluated on 80 laparoscopic interventions of various types, for which surgical device data and the endoscopic video are available. Here the combined method performs best with an overall average error of 37% and an average halftime error of 28%. Conclusion In this paper, we present, to our knowledge, the first approach for online procedure duration prediction using unlabeled endoscopic video data and surgical device data in a laparoscopic setting. We also show that a method incorporating both vision and device data performs better than methods based only on vision, while methods only based on tool usage and surgical device data perform poorly, showing the importance of the visual channel.

cs.CV↗

arXiv2019

Active Learning using Deep Bayesian Networks for Surgical Workflow Analysis

For many applications in the field of computer assisted surgery, such as providing the position of a tumor, specifying the most probable tool required next by the surgeon or determining the remaining duration of surgery, methods for surgical workflow analysis are a prerequisite. Often machine learning based approaches serve as basis for surgical workflow analysis. In general machine learning algorithms, such as convolutional neural networks (CNN), require large amounts of labeled data. While data is often available in abundance, many tasks in surgical workflow analysis need data annotated by domain experts, making it difficult to obtain a sufficient amount of annotations. The aim of using active learning to train a machine learning model is to reduce the annotation effort. Active learning methods determine which unlabeled data points would provide the most information according to some metric, such as prediction uncertainty. Experts will then be asked to only annotate these data points. The model is then retrained with the new data and used to select further data for annotation. Recently, active learning has been applied to CNN by means of Deep Bayesian Networks (DBN). These networks make it possible to assign uncertainties to predictions. In this paper, we present a DBN-based active learning approach adapted for image-based surgical workflow analysis task. Furthermore, by using a recurrent architecture, we extend this network to video-based surgical workflow analysis. We evaluate these approaches on the Cholec80 dataset by performing instrument presence detection and surgical phase segmentation. Here we are able to show that using a DBN-based active learning approach for selecting what data points to annotate next outperforms a baseline based on randomly selecting data points.

cs.CV↗

arXiv2018

Real-time image-based instrument classification for laparoscopic surgery

During laparoscopic surgery, context-aware assistance systems aim to alleviate some of the difficulties the surgeon faces. To ensure that the right information is provided at the right time, the current phase of the intervention has to be known. Real-time locating and classification the surgical tools currently in use are key components of both an activity-based phase recognition and assistance generation. In this paper, we present an image-based approach that detects and classifies tools during laparoscopic interventions in real-time. First, potential instrument bounding boxes are detected using a pixel-wise random forest segmentation. Each of these bounding boxes is then classified using a cascade of random forest. For this, multiple features, such as histograms over hue and saturation, gradients and SURF feature, are extracted from each detected bounding box. We evaluated our approach on five different videos from two different types of procedures. We distinguished between the four most common classes of instruments (LigaSure, atraumatic grasper, aspirator, clip applier) and background. Our method succesfully located up to 86% of all instruments respectively. On manually provided bounding boxes, we achieve a instrument type recognition rate of up to 58% and on automatically detected bounding boxes up to 49%. To our knowledge, this is the first approach that allows an image-based classification of surgical tools in a laparoscopic setting in real-time.

cs.CV↗

arXiv2018

Surgical Data Science: A Consensus Perspective

Surgical data science is a scientific discipline with the objective of improving the quality of interventional healthcare and its value through capturing, organization, analysis, and modeling of data. The goal of the 1st workshop on Surgical Data Science was to bring together researchers working on diverse topics in surgical data science in order to discuss existing challenges, potential standards and new research directions in the field. Inspired by current open space and think tank formats, it was organized in June 2016 in Heidelberg. While the first day of the workshop, which was dominated by interactive sessions, was open to the public, the second day was reserved for a board meeting on which the information gathered on the public day was processed by (1) discussing remaining open issues, (2) deriving a joint definition for surgical data science and (3) proposing potential strategies for advancing the field. This document summarizes the key findings.

cs.CY↗

arXiv2018

Comparative evaluation of instrument segmentation and tracking methods in minimally invasive surgery

Intraoperative segmentation and tracking of minimally invasive instruments is a prerequisite for computer- and robotic-assisted surgery. Since additional hardware like tracking systems or the robot encoders are cumbersome and lack accuracy, surgical vision is evolving as promising techniques to segment and track the instruments using only the endoscopic images. However, what is missing so far are common image data sets for consistent evaluation and benchmarking of algorithms against each other. The paper presents a comparative validation study of different vision-based methods for instrument segmentation and tracking in the context of robotic as well as conventional laparoscopic surgery. The contribution of the paper is twofold: we introduce a comprehensive validation data set that was provided to the study participants and present the results of the comparative validation study. Based on the results of the validation study, we arrive at the conclusion that modern deep learning approaches outperform other methods in instrument segmentation tasks, but the results are still not perfect. Furthermore, we show that merging results from different methods actually significantly increases accuracy in comparison to the best stand-alone method. On the other hand, the results of the instrument tracking task show that this is still an open challenge, especially during challenging scenarios in conventional laparoscopic surgery.

cs.CV↗

arXiv2018

Exploiting the potential of unlabeled endoscopic video data with self-supervised learning

Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to the breakthrough successes of deep learning-based solutions for automatic image annotation, the availability of reference annotations for algorithm training is becoming a major bottleneck in the field. The purpose of this paper was to investigate the concept of self-supervised learning to address this issue. Our approach is guided by the hypothesis that unlabeled video data can be used to learn a representation of the target domain that boosts the performance of state-of-the-art machine learning algorithms when used for pre-training. Core of the method is an auxiliary task based on raw endoscopic video data of the target domain that is used to initialize the convolutional neural network (CNN) for the target task. In this paper, we propose the re-colorization of medical images with a generative adversarial network (GAN)-based architecture as auxiliary task. A variant of the method involves a second pre-training step based on labeled data for the target task from a related domain. We validate both variants using medical instrument segmentation as target task. The proposed approach can be used to radically reduce the manual annotation effort involved in training CNNs. Compared to the baseline approach of generating annotated data from scratch, our method decreases exploratively the number of labeled images by up to 75% without sacrificing performance. Our method also outperforms alternative methods for CNN pre-training, such as pre-training on publicly available non-medical or medical data using the target task (in this instance: segmentation). As it makes efficient use of available (non-)public and (un-)labeled data, the approach has the potential to become a valuable tool for CNN (pre-)training.

cs.CV↗

arXiv2017

Artifact Free Transient Near-Field Nanoscopy

We report on the first implementation of ultrafast near field nanoscopy carried out with the transient pseudoheterodyne detection method (Tr-pHD). This method is well suited for efficient and artifact free pump-probe scattering-type near-field optical microscopy with nanometer scale resolution. The Tr-pHD technique is critically compared to other data acquisition methods and found to offer significant advantages. Experimental evidence for the advantages of Tr-pHD is provided in the Near-IR frequency range. Crucial factors involved in achieving proper performance of the Tr-pHD method with pulsed laser sources are analyzed and detailed in this work. We applied this novel method to time-resolved and spatially resolved studies of the photo-induced effects in the insulator-to-metal transition system vanadium dioxide with nanometer scale resolution.

cond-mat.mes-hall↗

arXiv2017

What does it all mean? Capturing Semantics of Surgical Data and Algorithms with Ontologies

Every year approximately 234 million major surgeries are performed, leading to plentiful, highly diverse data. This is accompanied by a matching number of novel algorithms for the surgical domain. To garner all benefits of surgical data science it is necessary to have an unambiguous, shared understanding of algorithms and data. This includes inputs and outputs of algorithms and thus their function, but also the semantic content, i.e. meaning of data such as patient parameters. We therefore propose the establishment of a new ontology for data and algorithms in surgical data science. Such an ontology can be used to provide common data sets for the community, encouraging sharing of knowledge and comparison of algorithms on common data. We hold that this is a necessary foundation towards new methods for applications such as semantic-based content retrieval and similarity measures and that it is overall vital for the future of surgical data science.

cs.CY↗

arXiv2017

Unsupervised temporal context learning using convolutional neural networks for laparoscopic workflow analysis

Computer-assisted surgery (CAS) aims to provide the surgeon with the right type of assistance at the right moment. Such assistance systems are especially relevant in laparoscopic surgery, where CAS can alleviate some of the drawbacks that surgeons incur. For many assistance functions, e.g. displaying the location of a tumor at the appropriate time or suggesting what instruments to prepare next, analyzing the surgical workflow is a prerequisite. Since laparoscopic interventions are performed via endoscope, the video signal is an obvious sensor modality to rely on for workflow analysis. Image-based workflow analysis tasks in laparoscopy, such as phase recognition, skill assessment, video indexing or automatic annotation, require a temporal distinction between video frames. Generally computer vision based methods that generalize from previously seen data are used. For training such methods, large amounts of annotated data are necessary. Annotating surgical data requires expert knowledge, therefore collecting a sufficient amount of data is difficult, time-consuming and not always feasible. In this paper, we address this problem by presenting an unsupervised method for training a convolutional neural network (CNN) to differentiate between laparoscopic video frames on a temporal basis. We extract video frames at regular intervals from 324 unlabeled laparoscopic interventions, resulting in a dataset of approximately 2.2 million images. From this dataset, we extract image pairs from the same video and train a CNN to determine their temporal order. To solve this problem, the CNN has to extract features that are relevant for comprehending laparoscopic workflow. Furthermore, we demonstrate that such a CNN can be adapted for surgical workflow segmentation. We performed image-based workflow segmentation on a publicly available dataset of 7 cholecystectomies and 9 colorectal interventions.

cs.CV↗

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↗

arXiv2017

Hydrodynamic Swarming of Thermally Active Dimeric Colloids

Self-propelled phoretic colloids have recently emerged as a promising avenue for the design of artificial swimmers. These swimmers combine purely phoretic interactions with intricate hydrodynamics which critically depend on the swimmer shape. Thermophobic dimer shaped colloids are here investigated by means of hydrodynamic simulations, from the single particle motion to their collective behavior. The combination of phoretic repulsion with hydrodynamic lateral attraction favors the formation of planar moving clusters. The resulting hydrodynamic assembly in flattened swarms is therefore very specific to these dimeric active colloids.

cond-mat.soft↗

arXiv2015

Graphene-Based Platform for Infrared Near-Field Nanospectroscopy of Water and Biological Materials in an Aqueous Environment

Scattering scanning near-field optical microscopy (s-SNOM) has emerged as a powerful nanoscale spectroscopic tool capable of characterizing individual biomacromolecules and molecular materials. However, applications of scattering-based near-field techniques in the infrared (IR) to native biosystems still await a solution of how to implement the required aqueous environment. In this work, we demonstrate an IR-compatible liquid cell architecture that enables near-field imaging and nanospectroscopy by taking advantage of the unique properties of graphene. Large-area graphene acts as an impermeable monolayer barrier that allows for nano-IR inspection of underlying molecular materials in liquid. Here, we use s-SNOM to investigate the tobacco mosaic virus (TMV) in water underneath graphene. We resolve individual virus particles and register the amide I and II bands of TMV at ca. 1520 and 1660 cm$^{-1}$, respectively, using nanoscale Fourier transform infrared spectroscopy (nano-FTIR). We verify the presence of water in the graphene liquid cell by identifying a spectral feature associated with water absorption at 1610 cm$^{-1}$.

cond-mat.mes-hall↗

arXiv2015

Phase transition in bulk single crystals and thin films of VO2 by nano-infrared spectroscopy and imaging

We have systematically studied a variety of vanadium dioxide (VO2) crystalline forms, including bulk single crystals and oriented thin films, using infrared (IR) near-field spectroscopic imaging techniques. By measuring the IR spectroscopic responses of electrons and phonons in VO2 with sub-grain-size spatial resolution (~20 nm), we show that epitaxial strain in VO2 thin films not only triggers spontaneous local phase separations but also leads to intermediate electronic and lattice states that are intrinsically different from those found in bulk. Generalized rules of strain and symmetry dependent mesoscopic phase inhomogeneity are also discussed. These results set the stage for a comprehensive understanding of complex energy landscapes that may not be readily determined by macroscopic approaches.

cond-mat.str-el↗