There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

/pdf/the-multimodal-brain-tumor-image-segmentation-benchmark-2gfraj98dk.pdf

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Medical image registration is an important task in medical image processing. It refers to the process of aligning data sets, possibly from different modalities (e.g., magnetic resonance and computed tomography), different time points (e.g., follow-up scans), and/or different subjects (in case of population studies). A large number of methods for image registration are described in the literature. Unfortunately, there is not one method that works for all applications. We have therefore developed elastix, a publicly available computer program for intensity-based medical image registration. The software consists of a collection of algorithms that are commonly used to solve medical image registration problems. The modular design of elastix allows the user to quickly configure, test, and compare different registration methods for a specific application. The command-line interface enables automated processing of large numbers of data sets, by means of scripting. The usage of elastix for comparing different registration methods is illustrated with three example experiments, in which individual components of the registration method are varied.

elastix : A Toolbox for Intensity-Based Medical Image Registration

Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image analysis and quantification in many applications, the design of respective specialized solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We developed nnU-Net, a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task. The key design choices in this process are modeled as a set of fixed parameters, interdependent rules and empirical decisions. Without manual intervention, nnU-Net surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international biomedical segmentation competitions. We make nnU-Net publicly available as an out-of-the-box tool, rendering state-of-the-art segmentation accessible to a broad audience by requiring neither expert knowledge nor computing resources beyond standard network training.

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

Ductal carcinoma in situ (DCIS) of the breast represents a heterogeneous group of neoplastic lesions in the breast ducts. The goal for management of DCIS is to prevent the development of invasive breast cancer. This manuscript focuses on the NCCN Guidelines Panel recommendations for the workup, primary treatment, risk reduction strategies, and surveillance specific to DCIS.

https://www.unitypoint.org/desmoines/filesimages/Cancer%20Education/Oncology%20Nursing%20Conference/2015/2014%20NCCN%20Clin%20Pract%20Guidelines%20Male%20Sex%20Dysf.pdf

Clinical practice guidelines in oncology

Phantoms for surgical training are able to mimic cutting and suturing properties and patient-individual shape of organs, but lack a realistic visual appearance that captures the heterogeneity of surgical scenes. In order to overcome this in endoscopic approaches, hyperrealistic concepts have been proposed to be used in an augmented reality-setting, which are based on deep image-to-image transformation methods. Such concepts are able to generate realistic representations of phantoms learned from real intraoperative endoscopic sequences.

/pdf/abstract-generative-adversarial-networks-for-stereoscopic-2mkaykiqz9.pdf

Abstract: Generative Adversarial Networks for Stereoscopic Hyperrealism in Surgical Training.

Das Standardvorgehen bei der Behandlung von Calcaneusfrakturen ist eine Osteosynthese. Mit Hilfe der intraoperativen Bildgebung wie dem mobilen C-Bogen CT kann der Chirurg das Repositionsergebnis noch im Operationssaal verifizieren und wenn notig korrigieren. Die Mobilitat des C-Bogen CT hat jedoch zur Folge, dass Informationen uber die Orientierung des Patienten zum Gerat verloren gehen. Dadurch kann keine Standard-Ausrichtung der dreidimensionalen Daten an die Anatomie erfolgen. Eine manuelle Einstellung des Volumendatensatzes durch den Chirurgen ist damit unabdingbar. Dies ist ein zeitaufwendiger Schritt und kann bei einer unprazisen Einstellung zu Fehlern bei der Beurteilung der Daten fuhren. In diesem Paper stellen wir zwei automatische Methoden zur Einstellung der Standard-Ebenen auf mobilen C-Bogen CT Daten vor. Die automatischen Methoden rekonstruieren die Standard-Ebenen in zwei Schritten: als Erstes werden SURF-Keypoints (2D und neu eingefuhrte Pseudo-3D-Punkte) fur das Bildvolumen berechnet, in einem zweiten Schritt wird eine Atlas-Punktwolke auf diese Merkmale registriert und die Parameter der Standard-Ebenen transformiert. Die Genauigkeit unserer Methoden wurde an 51 klinischen mobilen C-Bogen CT Bildern mit manuell eingestellten Standard-Ebenen evaluiert. Die Referenzdaten wurden von drei Chirurgen mit unterschiedlichem Erfahrungsstand erstellt. Die durchschnittlich benotigte Zeit der Experten (46 s) unterscheidet sich von der des fortgeschrittenen Benutzers (55 s) um neun Sekunden. Die Berechnungszeit des 2D-Surf Ansatzes betragt 10 Sekunden und liefert bei 88% der Ebenen der Referenzdaten eine korrkte Einstellung. Der Pseudo-3D Ansatz liefert die besten Ergebnisse mit einer Genauigkeit von 91% und einer Berechnungszeit von nur 8 Sekunden.

Atlasbasierte feature-registrierung zur automatischen Einstellung der Standardebenen bei mobilen C-Bogen CT-daten

Purpose: The development of machine learning models for surgical workflow and instrument recognition from temporal data represents a challenging task due to the complex nature of surgical workflows. In particular, the imbalanced distribution of data is one of the major challenges in the domain of surgical workflow recognition. In order to obtain meaningful results, careful partitioning of data into training, validation, and test sets, as well as the selection of suitable evaluation metrics are crucial. Methods: In this work, we present an openly available web-based application that enables interactive exploration of dataset partitions. The proposed visual framework facilitates the assessment of dataset splits for surgical workflow recognition, especially with regard to identifying sub-optimal dataset splits. Currently, it supports visualization of surgical phase and instrument annotations. Results: In order to validate the dedicated interactive visualizations, we use a dataset split of the Cholec80 dataset. This dataset split was specifically selected to reflect a case of strong data imbalance. Using our software, we were able to identify phases, phase transitions, and combinations of surgical instruments that were not represented in one of the sets. Conclusion: In order to obtain meaningful results in highly unbalanced class distributions, special care should be taken with respect to the selection of an appropriate split. Interactive data visualization represents a promising approach for the assessment of machine learning datasets. The source code is available at https://github.com/Cardio-AI/endovis-ml

Surgical Phase and Instrument Recognition: How to identify appropriate Dataset Splits

Die Registrierung von zweidimensionalen, intraoperativen Bilddaten mit praoperativ ermittelten, dreidimensionalen Volumendaten ist eine bekannte Problemstellung mit vielfaltigen Anwendungen. Die Anforderung, beispielsweise bei intraoperativer Eingriffsunterstutzung moglichst schnell Ergebnisse vorliegen zu haben, legt eine hochparallelisierte Implementierung der dazu notigen Algorithmen nahe. In diesem Paper wird ein kostengunstiges Verfahren auf Basis von GPGPU-Programmierung mit dem CUDA-Framework beschrieben. Um die Vergleichbarkeit der Umsetzung zu ermoglichen, wird das Registrierungsverfahren unter Verwendung eines Referenzdatensatzes mit bekannten Aufnahmeparametern evaluiert.

Parallelisierung intensitätsbasierter 2D/3D-Registrierung mit CUDA

In diesem Beitrag stellen wir ein Nachverarbeitungsverfahren vor, das dynamische Genauigkeitsuntersuchungen von Positions- und Winkelmessungen zweier den gleichen Raum beschreibender, nicht interferierender Tracking-Systeme ermoglicht. Bei gemeinsamer zeitlicher Taktung der Messungen eignet sich unsere Vorgehensweise daruber hinaus zur Realisierung eines hybriden Tracking-Systems.

Ivo Wolf

Papers

Abstract: Generative Adversarial Networks for Stereoscopic Hyperrealism in Surgical Training.

Atlasbasierte feature-registrierung zur automatischen Einstellung der Standardebenen bei mobilen C-Bogen CT-daten

Surgical Phase and Instrument Recognition: How to identify appropriate Dataset Splits

Parallelisierung intensitätsbasierter 2D/3D-Registrierung mit CUDA

Ein Verfahren zur Genauigkeitsanalyse magnetischen Trackings