Showing papers by "Ivo Wolf published in 2018"

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Abstract: Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the “Automatic Cardiac Diagnosis Challenge” dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies. In the wake of the 2017 MICCAI-ACDC challenge, we report results from deep learning methods provided by nine research groups for the segmentation task and four groups for the classification task. Results show that the best methods faithfully reproduce the expert analysis, leading to a mean value of 0.97 correlation score for the automatic extraction of clinical indices and an accuracy of 0.96 for automatic diagnosis. These results clearly open the door to highly accurate and fully automatic analysis of cardiac CMRI. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for new submissions.

Improving Surgical Training Phantoms by Hyperrealism: Deep Unpaired Image-to-Image Translation from Real Surgeries

Abstract: Current ‘dry lab’ surgical phantom simulators are a valuable tool for surgeons which allows them to improve their dexterity and skill with surgical instruments. These phantoms mimic the haptic and shape of organs of interest, but lack a realistic visual appearance. In this work, we present an innovative application in which representations learned from real intraoperative endoscopic sequences are transferred to a surgical phantom scenario. The term hyperrealism is introduced in this field, which we regard as a novel subform of surgical augmented reality for approaches that involve real-time object transfigurations. For related tasks in the computer vision community, unpaired cycle-consistent Generative Adversarial Networks (GANs) have shown excellent results on still RGB images. Though, application of this approach to continuous video frames can result in flickering, which turned out to be especially prominent for this application. Therefore, we propose an extension of cycle-consistent GANs, named tempCycleGAN, to improve temporal consistency. The novel method is evaluated on captures of a silicone phantom for training endoscopic reconstructive mitral valve procedures. Synthesized videos show highly realistic results with regard to (1) replacement of the silicone appearance of the phantom valve by intraoperative tissue texture, while (2) explicitly keeping crucial features in the scene, such as instruments, sutures and prostheses. Compared to the original CycleGAN approach, tempCycleGAN efficiently removes flickering between frames. The overall approach is expected to change the future design of surgical training simulators since the generated sequences clearly demonstrate the feasibility to enable a considerably more realistic training experience for minimally-invasive procedures.

AutoCellSeg: robust automatic colony forming unit (CFU)/cell analysis using adaptive image segmentation and easy-to-use post-editing techniques.

Abstract: In biological assays, automated cell/colony segmentation and counting is imperative owing to huge image sets. Problems occurring due to drifting image acquisition conditions, background noise and high variation in colony features in experiments demand a user-friendly, adaptive and robust image processing/analysis method. We present AutoCellSeg (based on MATLAB) that implements a supervised automatic and robust image segmentation method. AutoCellSeg utilizes multi-thresholding aided by a feedback-based watershed algorithm taking segmentation plausibility criteria into account. It is usable in different operation modes and intuitively enables the user to select object features interactively for supervised image segmentation method. It allows the user to correct results with a graphical interface. This publicly available tool outperforms tools like OpenCFU and CellProfiler in terms of accuracy and provides many additional useful features for end-users.

Elastic Mitral Valve Silicone Replica Made from 3D-Printable Molds Offer Advanced Surgical Training

Abstract: Reconstructive mitral valve surgeries are demanding cardiac surgeries that are conducted in the mid-age of a surgical career at the earliest. Receiving years of training in patients is required to gain the experiences and skills necessary for surgical success. On top of that, the number of such surgeries is limited per hospital, therefore other means of training should be offered to facilitate a steep learning curve. Within the scope of this work, we equipped an existing physical simulator with patient-specific flexible replica of the mitral valve. We developed software to automatically produce a 3D-printable casting mold for silicone material, as this mimics properties of the valve tissue in terms of stitching and cutting. We show the feasibility of the approach and the usefulness of these models is evaluated by an experienced cardiac surgeon, successfully conducting reconstructive surgery on pathological silicone valves.

Improving Surgical Training Phantoms by Hyperrealism: Deep Unpaired Image-to-Image Translation from Real Surgeries

Abstract: Current `dry lab' surgical phantom simulators are a valuable tool for surgeons which allows them to improve their dexterity and skill with surgical instruments. These phantoms mimic the haptic and shape of organs of interest, but lack a realistic visual appearance. In this work, we present an innovative application in which representations learned from real intraoperative endoscopic sequences are transferred to a surgical phantom scenario. The term hyperrealism is introduced in this field, which we regard as a novel subform of surgical augmented reality for approaches that involve real-time object transfigurations. For related tasks in the computer vision community, unpaired cycle-consistent Generative Adversarial Networks (GANs) have shown excellent results on still RGB images. Though, application of this approach to continuous video frames can result in flickering, which turned out to be especially prominent for this application. Therefore, we propose an extension of cycle-consistent GANs, named tempCycleGAN, to improve temporal consistency.The novel method is evaluated on captures of a silicone phantom for training endoscopic reconstructive mitral valve procedures. Synthesized videos show highly realistic results with regard to 1) replacement of the silicone appearance of the phantom valve by intraoperative tissue texture, while 2) explicitly keeping crucial features in the scene, such as instruments, sutures and prostheses. Compared to the original CycleGAN approach, tempCycleGAN efficiently removes flickering between frames. The overall approach is expected to change the future design of surgical training simulators since the generated sequences clearly demonstrate the feasibility to enable a considerably more realistic training experience for minimally-invasive procedures.