This paper presents a new multimodal interventional radiology dataset, called PoCaP (Port Catheter Placement) Corpus.
In this work, we present a novel approach called Image Composition Canvas (ICC++) to compare and retrieve images having similar compositional elements.
Then, to align the source and target features and tackle the memory issue of the traditional contrastive loss, we propose the centroid-based contrastive learning (CCL) and a centroid norm regularizer (CNR) to optimize the contrastive pairs in both direction and magnitude.
Reliably detecting diseases using relevant biological information is crucial for real-world applicability of deep learning techniques in medical imaging.
In this work, we use for HSRS image classification a special class of deep neural networks, namely a Bayesian neural network (BNN).
This makes the algorithm applicable to run on embedded devices in real-time.
The best configuration detects LVOs with an AUC of 0. 91, LVOs in the ICA with an AUC of 0. 96, and in the MCA with 0. 91 while accurately predicting the affected side.
We validate our approach by using the CBIS-DDSM dataset for two classification tasks.
With iterative continual learning (i. e., the shared model revisits each center multiple times during training), the sensitivity is further improved to 0. 914, which is identical to the sensitivity using mixed data for training.
In the work at hand, we place the algorithm in a clinical context by evaluating the labeling and occlusion detection on stroke patients, where we have achieved labeling sensitivities comparable to other works between 92\,\% and 95\,\%.
This is potentially of high interest for the anonymization of pathological speech data.
Our results are among the first to show that disentangled speech representations can be used for automatic pathological speech intelligibility assessment, resulting in a reference speaker pair invariant method, applicable in scenarios with only few utterances available.
no code implementations • 7 Apr 2022 • Achim Schilling, William Sedley, Richard Gerum, Claus Metzner, Konstantin Tziridis, Andreas Maier, Holger Schulze, Fan-Gang Zeng, Karl J. Friston, Patrick Krauss
How is information processed in the brain during perception?
no code implementations • 6 Apr 2022 • Marc Aubreville, Nikolas Stathonikos, Christof A. Bertram, Robert Klopleisch, Natalie ter Hoeve, Francesco Ciompi, Frauke Wilm, Christian Marzahl, Taryn A. Donovan, Andreas Maier, Jack Breen, Nishant Ravikumar, Youjin Chung, Jinah Park, Ramin Nateghi, Fattaneh Pourakpour, Rutger H. J. Fick, Saima Ben Hadj, Mostafa Jahanifar, Nasir Rajpoot, Jakob Dexl, Thomas Wittenberg, Satoshi Kondo, Maxime W. Lafarge, Viktor H. Koelzer, Jingtang Liang, YuBo Wang, Xi Long, Jingxin Liu, Salar Razavi, April Khademi, Sen yang, Xiyue Wang, Mitko Veta, Katharina Breininger
The goal of the MICCAI MIDOG 2021 challenge has been to propose and evaluate methods that counter this domain shift and derive scanner-agnostic mitosis detection algorithms.
Compared to using Fbank features, XLSR-based features reduced WERs by 6. 8%, 22. 0%, and 7. 0% for the UASpeech, PC-GITA, and EasyCall corpus, respectively.
Collecting speech data is an important step in training speech recognition systems and other speech-based machine learning models.
no code implementations • • Lukas Folle, Sara Bayat, Arnd Kleyer, Filippo Fagni, Lorenz A Kapsner, Maja Schlereth, Timo Meinderink, Katharina Breininger, Koray Tacilar, Gerhard Krönke, Michael Uder, Michael Sticherling, Sebastian Bickelhaupt, Georg Schett, Andreas Maier, Frank Roemer, David Simon
AUROC was 75% for seropositive RA vs. PsA, 74% for seronegative RA vs. PsA and 67% for seropositive vs. seronegative RA.
Since the generation of high quality clinical training is a constant challenge, this study proposes to generate simulated X-ray images based on CT data sets combined with self-designed computer aided design (CAD) implants and make use of convolutional neural network (CNN) and vision transformer (ViT) for metal segmentation.
Methods: We trained a novel neural network on 3D articular bone shapes of hand joints of RA and PsA patients as well as HC.
We conclude that cognitive maps and neural network-based successor representations of structured knowledge provide a promising way to overcome some of the short comings of deep learning towards artificial general intelligence.
Methods: Given a set of image repetitions for a slice, a locally adaptive weighted averaging is proposed which aims to suppress the contribution of image regions affected by signal dropouts.
The experiments on patients' chest and head data demonstrate that learning perspective deformation using dual complementary views is also applicable in anatomical X-ray data, allowing accurate cardiothoracic ratio measurements in chest X-ray images and cephalometric analysis in synthetic cephalograms from cone-beam X-ray projections.
no code implementations • 8 Feb 2022 • Felix Denzinger, Michael Wels, Oliver Taubmann, Mehmet A. Gülsün, Max Schöbinger, Florian André, Sebastian J. Buss, Johannes Görich, Michael Sühling, Andreas Maier, Katharina Breininger
With coronary artery disease (CAD) persisting to be one of the leading causes of death worldwide, interest in supporting physicians with algorithms to speed up and improve diagnosis is high.
With the increasing number of online learning material in the web, search for specific content in lecture videos can be time consuming.
In this study, we investigated the impacts of training data diversity on the robustness of these networks by using multiple kinds of geometrical and natural simulated phantom structures.
This restricts the development of UDA methods for new domains.
Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging.
Neuromuscular diseases (NMDs) cause a significant burden for both healthcare systems and society.
1 code implementation • 25 Jan 2022 • Fabian Wagner, Mareike Thies, Mingxuan Gu, Yixing Huang, Sabrina Pechmann, Mayank Patwari, Stefan Ploner, Oliver Aust, Stefan Uderhardt, Georg Schett, Silke Christiansen, Andreas Maier
Due to the extremely low number of trainable parameters with well-defined effect, prediction reliance and data integrity is guaranteed at any time in the proposed pipelines, in contrast to most other deep learning-based denoising architectures.
We conclude that deep learning-supported analysis of non-invasive ultrasound images is a promising area of research to automatically extract cross-sectional wound size and depth information with potential value in monitoring response to therapy.
Learned iterative reconstruction algorithms for inverse problems offer the flexibility to combine analytical knowledge about the problem with modules learned from data.
no code implementations • 19 Jan 2022 • Mathias Öttl, Jana Mönius, Christian Marzahl, Matthias Rübner, Carol I. Geppert, Arndt Hartmann, Matthias W. Beckmann, Peter Fasching, Andreas Maier, Ramona Erber, Katharina Breininger
When evaluating the approaches on fully manually annotated images, we observe that the autoencoder-based superpixels achieve a 23% increase in boundary F1 score compared to the baseline SLIC superpixels.
In this report we want to present our method and results for the Carotid Artery Vessel Wall Segmentation Challenge.
Our method demonstrates the best registration performance on our and a public multi-modal dataset in comparison to competing methods.
no code implementations • 22 Dec 2021 • Yixing Huang, Christoph Bert, Philipp Sommer, Benjamin Frey, Udo Gaipl, Luitpold V. Distel, Thomas Weissmann, Michael Uder, Manuel A. Schmidt, Arnd Dörfler, Andreas Maier, Rainer Fietkau, Florian Putz
To improve brain metastasis detection performance with deep learning, a custom detection loss called volume-level sensitivity-specificity (VSS) is proposed, which rates individual metastasis detection sensitivity and specificity in (sub-)volume levels.
In the domain of medical image processing, medical device manufacturers protect their intellectual property in many cases by shipping only compiled software, i. e. binary code which can be executed but is difficult to be understood by a potential attacker.
Instead, we frame fault detection as more realistic unsupervised domain adaptation problem where we train on labelled data of one source PV plant and make predictions on another target plant.
In combating climate change, an effective demand-based energy supply operation of the district energy system (DES) for heating or cooling is indispensable.
Due to occurring metal artifacts, the quality of this evaluation heavily depends on the performance of so-called Metal Artifact Reduction methods (MAR).
1 code implementation • 3 Dec 2021 • Lukas Folle, Katharian Tkotz, Fasil Gadjimuradov, Lorenz Kapsner, Moritz Fabian, Sebastian Bickelhaupt, David Simon, Arnd Kleyer, Gerhard Krönke, Moritz Zaiß, Armin Nagel, Andreas Maier
This work paves the way for the prospective investigation of neural networks for super-resolution CEST MRI and, followingly, might lead to a earlier detection of the onset of rheumatic diseases.
Ranked #1 on Super-Resolution on CEST MRI
Training the EfficientNetB1 architecture on 100 data sets, the proposed augmentation scheme was able to raise the ROC AUC to 0. 85 from a baseline value of 0. 56 using no augmentation.
Annotating data, especially in the medical domain, requires expert knowledge and a lot of effort.
In this work, we propose DeepFilterNet, a two stage speech enhancement framework utilizing deep filtering.
no code implementations • 15 Sep 2021 • Celia Martin Vicario, Florian Kordon, Felix Denzinger, Jan Siad El Barbari, Maxim Privalov, Jochen Franke, Sarina Thomas, Lisa Kausch, Andreas Maier, Holger Kunze
The most important benefit of the MTL approach is that it is a single network for standard plane regression for all body regions with a reduced number of stored parameters.
no code implementations • 6 Sep 2021 • Seung Su Yoon, Elisabeth Preuhs, Michaela Schmidt, Christoph Forman, Teodora Chitiboi, Puneet Sharma, Juliano Lara Fernandes, Christoph Tillmanns, Jens Wetzl, Andreas Maier
The purpose of this work is to propose a fully automated framework that allows the detection of the right coronary artery (RCA) RP within CINE series.
While these areas can be easily identified from electroluminescense (EL) images, this is much harder for photoluminescence (PL) images.
Automatic coded audio quality assessment is an important task whose progress is hampered by the scarcity of human annotations, poor generalization to unseen codecs, bitrates, content-types, and a lack of flexibility of existing approaches.
For direct detection from distorted markers in reconstructed volumes, an efficient automatic marker detection method using two neural networks and a conventional circle detection algorithm is proposed.
1 code implementation • 19 Aug 2021 • Christian Marzahl, Jenny Hill, Jason Stayt, Dorothee Bienzle, Lutz Welker, Frauke Wilm, Jörn Voigt, Marc Aubreville, Andreas Maier, Robert Klopfleisch, Katharina Breininger, Christof A. Bertram
Pulmonary hemorrhage (P-Hem) occurs among multiple species and can have various causes.
In this article, we perform a review of the state-of-the-art of hybrid machine learning in medical imaging.
A refinement step using the classical optimization-based 2D/3D registration method applied in combination with Deep Learning-based techniques can provide the required accuracy.
1 code implementation • • Christian Marzahl, Frauke Wilm, Christine Kröger, Franz F Dressler, Lars Tharun, Sven Perner, Christof Bertram, Jörn Voigt, Robert Klopfleisch, Andreas Maier, Marc Aubreville, Katharina Breininger
The registration of whole slide images (WSIs) provides the basis for many subsequent processing steps in digital pathology.
In a first approach, image patches are sampled from this region and regression is based on morphological features encoded by a ResNet-based network.
As of recent generative adversarial networks have allowed for big leaps in the realism of generated images in diverse domains, not the least of which being handwritten text generation.
The algorithm is trained on DW liver data of 60 volunteers and evaluated on retrospectively and prospectively sub-sampled data of different anatomies and resolutions.
Based on a dataset of HR-pQCT volumes with MC measurements for 541 patients with arthritis, a segmentation network is trained.
Chest radiography is the most common radiographic examination performed in daily clinical practice for the detection of various heart and lung abnormalities.
Our approach is motivated by style transfer networks, whereas the "style" for an image is explicitly given in our case, as it is determined by the MR acquisition parameters our network is conditioned on.
Hypothesizing that the scanner device plays a decisive role in this effect, we evaluated the susceptibility of a standard mitosis detection approach to the domain shift introduced by using a different whole slide scanner.
Our verification system is able to identify whether two frontal chest X-ray images are from the same person with an AUC of 0. 9940 and a classification accuracy of 95. 55%.
The proposed method is based on adversarial learning and adapts network features between source and target domain in different spaces.
In this work, we propose to mitigate the class-imbalance between the calving front class and the non-calving front class by reformulating the segmentation problem into a pixel-wise regression task.
We perform a simulation study using real motion recorded with an optical tracking system.
A Magnetic Resonance Imaging (MRI) exam typically consists of the acquisition of multiple MR pulse sequences, which are required for a reliable diagnosis.
Moreover, we propose an improvement to the distance map-based binary cross-entropy (BCE) loss function.
First, a statistical human shape model of the human anatomy and second, a differentiable X-ray renderer.
We aim to address this gap by incorporating traditional methods in deep neural networks using known operator learning.
The utilization of computational photography becomes increasingly essential in the medical field.
Metal implants that are inserted into the patient's body during trauma interventions cause heavy artifacts in 3D X-ray acquisitions.
no code implementations • 22 Jan 2021 • Philipp Roser, Annette Birkhold, Alexander Preuhs, Christopher Syben, Lina Felsner, Elisabeth Hoppe, Norbert Strobel, Markus Korwarschik, Rebecca Fahrig, Andreas Maier
Algorithmic X-ray scatter compensation is a desirable technique in flat-panel X-ray imaging and cone-beam computed tomography.
Medical Physics Image and Video Processing
We evaluated our pipeline in a cross-validation setup with a fixed training set using a dataset of six equine WSIs of which four are partially annotated and used for training, and two fully annotated WSI are used for validation and testing.
However, to enable clinical research with the help of these algorithms, a software solution, which enables manual correction, comprehensive visual feedback and tissue analysis capabilities, is needed.
Supervised machine learning requires a large amount of labeled data to achieve proper test results.
An essential climate variable to determine the tidewater glacier status is the location of the calving front position and the separation of seasonal variability from long-term trends.
2 code implementations • 5 Jan 2021 • Christof A. Bertram, Taryn A. Donovan, Marco Tecilla, Florian Bartenschlager, Marco Fragoso, Frauke Wilm, Christian Marzahl, Katharina Breininger, Andreas Maier, Robert Klopfleisch, Marc Aubreville
For this study, we created the first open source data-set with 19, 983 annotations of BiNC and 1, 416 annotations of MuNC in 32 histological whole slide images of ccMCT.
Continuous protocols for cardiac magnetic resonance imaging enable sampling of the cardiac anatomy simultaneously resolved into cardiac phases.
In this paper, we propose a spatio-temporal multi-task learning approach to obtain a complete set of measurements quantifying cardiac LV morphology, regional-wall thickness (RWT), and additionally detecting the cardiac phase cycle (systole and diastole) for a given 3D Cine-magnetic resonance (MR) image sequence.
Large logarithmic corrections in $\hat s/p_t^2$ lead to substantial variations in the perturbative predictions for inclusive $W$-plus-dijet processes at the Large Hadron Collider.
High Energy Physics - Phenomenology
(2) To improve the already strong results further, we created a small dataset (ClassArch) consisting of ancient Greek vase paintings from the 6-5th century BCE with person and pose annotations.
For organ-specific AEC, a preliminary CT reconstruction is necessary to estimate organ shapes for dose optimization, where only a few projections are allowed for real-time reconstruction.
no code implementations • 4 Dec 2020 • Frauke Wilm, Christof A. Bertram, Christian Marzahl, Alexander Bartel, Taryn A. Donovan, Charles-Antoine Assenmacher, Kathrin Becker, Mark Bennett, Sarah Corner, Brieuc Cossic, Daniela Denk, Martina Dettwiler, Beatriz Garcia Gonzalez, Corinne Gurtner, Annika Lehmbecker, Sophie Merz, Stephanie Plog, Anja Schmidt, Rebecca C. Smedley, Marco Tecilla, Tuddow Thaiwong, Katharina Breininger, Matti Kiupel, Andreas Maier, Robert Klopfleisch, Marc Aubreville
Density of mitotic figures in histologic sections is a prognostically relevant characteristic for many tumours.
no code implementations • 20 Nov 2020 • Leonid Mill, David Wolff, Nele Gerrits, Patrick Philipp, Lasse Kling, Florian Vollnhals, Andrew Ignatenko, Christian Jaremenko, Yixing Huang, Olivier De Castro, Jean-Nicolas Audinot, Inge Nelissen, Tom Wirtz, Andreas Maier, Silke Christiansen
Nanoparticles occur in various environments as a consequence of man-made processes, which raises concerns about their impact on the environment and human health.
Visual inspection of solar modules is an important monitoring facility in photovoltaic power plants.
no code implementations • 29 Oct 2020 • Lennart Husvogt, Stefan B. Ploner, Siyu Chen, Daniel Stromer, Julia Schottenhamml, A. Yasin Alibhai, Eric Moult, Nadia K. Waheed, James G. Fujimoto, Andreas Maier
Optical coherence tomography angiography (OCTA) is a novel and clinically promising imaging modality to image retinal and sub-retinal vasculature.
In this work we first formulate this reconstruction problem in terms of a system matrix and weighting part.
In particular, we investigate the performance of large-scale retrieval of historical document fragments in terms of style and writer identification.
no code implementations • 5 Oct 2020 • Felix Denzinger, Michael Wels, Katharina Breininger, Mehmet A. Gülsün, Max Schöbinger, Florian André, Sebastian Buß, Johannes Görich, Michael Sühling, Andreas Maier
Coronary CT angiography (CCTA) has established its role as a non-invasive modality for the diagnosis of coronary artery disease (CAD).
1 code implementation • 30 Sep 2020 • Mathis Hoffmann, Claudia Buerhop-Lutz, Luca Reeb, Tobias Pickel, Thilo Winkler, Bernd Doll, Tobias Würfl, Ian Marius Peters, Christoph Brabec, Andreas Maier, Vincent Christlein
However, knowledge of the power at maximum power point is important as well, since drops in the power of a single module can affect the performance of an entire string.
The training set consists of data produced by a computational model of cardiac electrophysiology on a large cohort of synthetically generated geometries of ischemic hearts.
The method trained on conventional cephalograms can be directly applied to landmark detection in the synthetic cephalograms, achieving 93. 0% and 80. 7% successful detection rate in 4 mm precision range for synthetic cephalograms from 3D volumes and 2D projections respectively.
These compositions are useful in analyzing the interactions in an image to study artists and their artworks.
We achieved a mean F1-score of 0. 791 on the test set and of up to 0. 696 on a human breast cancer dataset.
Due to the multiple imperfections during the signal acquisition, Electrocardiogram (ECG) datasets are typically contaminated with numerous types of noise, like salt and pepper and baseline drift.
We propose to adjust the C-arm CBCT source trajectory during the scan to optimize reconstruction quality with respect to a certain task, i. e. verification of screw placement.
However, because of the limited availability of scans containing nodules and the subtle properties of nodules in CXRs, state-of-the-art methods do not perform well on nodule classification.
In classification, notarial instruments are distinguished from other documents, while the notary sign is separated from the certificate in the segmentation task.
We show that a re-ranking step based on k-reciprocal nearest neighbor relationships is advantageous for writer identification, even if only a few samples per writer are available.
To date, some datasets on mitotic figures are available and were used for development of promising deep learning-based algorithms.
Denoising of clinical CT images is an active area for deep learning research.
In our proposed multi-stage algorithm, these signals are transformed to the global coordinate system of the CT scan and applied for motion compensation during reconstruction.
no code implementations • 8 Jul 2020 • Philipp Roser, Xia Zhong, Annette Birkhold, Alexander Preuhs, Christopher Syben, Elisabeth Hoppe, Norbert Strobel, Markus Kowarschik, Rebecca Fahrig, Andreas Maier
Here, we propose a novel approach combining conventional techniques with learning-based methods to simultaneously estimate the forward-scatter reaching the detector as well as the back-scatter affecting the patient skin dose.
To this end, we train a siamese triplet network to predict the reprojection error (RPE) for the complete acquisition as well as an approximate distribution of the RPE along the single views from the reconstructed volume in a multi-task learning approach.
For example, for truncated data, DCR achieves a mean root-mean-square error of 24 HU and a mean structure similarity index of 0. 999 inside the field-of-view for different patients in the noisy case, while the state-of-the-art U-Net method achieves 55 HU and 0. 995 respectively for these two metrics.
In this work, partial convolution is applied for projection inpainting, which only relies on valid pixels values.
2 code implementations • 30 Apr 2020 • Christian Marzahl, Marc Aubreville, Christof A. Bertram, Jennifer Maier, Christian Bergler, Christine Kröger, Jörn Voigt, Katharina Breininger, Robert Klopfleisch, Andreas Maier
In many research areas, scientific progress is accelerated by multidisciplinary access to image data and their interdisciplinary annotation.
no code implementations • 26 Apr 2020 • Zhaohan Xiong, Qing Xia, Zhiqiang Hu, Ning Huang, Cheng Bian, Yefeng Zheng, Sulaiman Vesal, Nishant Ravikumar, Andreas Maier, Xin Yang, Pheng-Ann Heng, Dong Ni, Caizi Li, Qianqian Tong, Weixin Si, Elodie Puybareau, Younes Khoudli, Thierry Geraud, Chen Chen, Wenjia Bai, Daniel Rueckert, Lingchao Xu, Xiahai Zhuang, Xinzhe Luo, Shuman Jia, Maxime Sermesant, Yashu Liu, Kuanquan Wang, Davide Borra, Alessandro Masci, Cristiana Corsi, Coen de Vente, Mitko Veta, Rashed Karim, Chandrakanth Jayachandran Preetha, Sandy Engelhardt, Menyun Qiao, Yuanyuan Wang, Qian Tao, Marta Nunez-Garcia, Oscar Camara, Nicolo Savioli, Pablo Lamata, Jichao Zhao
Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) widely used for visualizing diseased cardiac structures, is a crucial first step for clinical diagnosis and treatment.
1 code implementation • 13 Apr 2020 • Christian Marzahl, Christof A. Bertram, Marc Aubreville, Anne Petrick, Kristina Weiler, Agnes C. Gläsel, Marco Fragoso, Sophie Merz, Florian Bartenschlager, Judith Hoppe, Alina Langenhagen, Anne Jasensky, Jörn Voigt, Robert Klopfleisch, Andreas Maier
However, a significant percentage of the deliberately introduced false labels was not identified by the experts.
Human-Computer Interaction Image and Video Processing
We present experiments and analysis on three different models and show that the model trained on domain related data gives the best performance for recognizing character.
Then, a method for online handwriting synthesis is used to produce a new realistic-looking text primed with the online input sequence.
In this study, we investigate the impact of various data augmentation algorithms, e. g., oversampling, Gaussian Mixture Models (GMMs) and Generative Adversarial Networks (GANs), on solving the class imbalance problem.
To this end, we apply normalized Lp normalization to aggregate the activation maps into single scores for classification.
To improve monaural speech enhancement in noisy environments, we propose CLCNet, a framework based on complex valued linear coding.
no code implementations • 12 Jan 2020 • Siming Bayer, Ute Spiske, Jie Luo, Tobias Geimer, William M. Wells III, Martin Ostermeier, Rebecca Fahrig, Arya Nabavi, Christoph Bert, Ilker Eyupoglo, Andreas Maier
For a wide range of clinical applications, such as adaptive treatment planning or intraoperative image update, feature-based deformable registration (FDR) approaches are widely employed because of their simplicity and low computational complexity.
Particularly, the U-Net, the state-of-the-art neural network in biomedical imaging, is trained from synthetic ellipsoid data and multi-category data to reduce artifacts in filtered back-projection (FBP) reconstruction images.
Thus, we used image features and their variation over time to predict coil damage.
The other data level uses matrices which represent the overall coil condition and feeds a different neural network.
Chronic obstructive pulmonary disease (COPD) is a lung disease that is not fully reversible and one of the leading causes of morbidity and mortality in the world.
In this work, we propose an imitation learning framework for the registration of 2D color funduscopic images for a wide range of applications such as disease monitoring, image stitching and super-resolution.
Analysing coronary artery plaque segments with respect to their functional significance and therefore their influence to patient management in a non-invasive setup is an important subject of current research.
A second approach is based on deep learning and relies on centerline extraction as sole prerequisite.
In this study, we propose a deep learning method based on Convolutional Neural Networks (CNNs) for mammogram denoising to improve the image quality.
This competition investigates the performance of large-scale retrieval of historical document images based on writing style.
With a simple one-class problem, the classification of tuberculosis, we measure the performance on a clean evaluation set when training with label-corrupt data.
no code implementations • 3 Dec 2019 • Jennifer Maier, Luis Carlos Rivera Monroy, Christopher Syben, Yejin Jeon, Jang-Hwan Choi, Mary Elizabeth Hall, Marc Levenston, Garry Gold, Rebecca Fahrig, Andreas Maier
Analyzing knee cartilage thickness and strain under load can help to further the understanding of the effects of diseases like Osteoarthritis.
To adapt the backprojection operation accordingly, a motion estimation strategy is necessary.
We were able to show that domain adversarial training considerably improves accuracy when applying mitotic figure classification learned from the canine on the human data sets (up to +12. 8% in accuracy) and is thus a helpful method to transfer knowledge from existing data sets to new tissue types and species.
Additionally, a weighting scheme in the loss computation that favors high-frequency structures is proposed to focus on the important details and contours in projection imaging.
In medical imaging, this lack of comprehensibility of the results is a sensitive issue.
As such, it is end-to-end trainable, circumvents the use of hand-crafted and potentially complex algorithms, and mitigates error propagation.
Results show that for retinal vessel segmentation on DRIVE database, U-Net does not degenerate until surprisingly acute conditions: one level, one filter in convolutional layers, and one training sample.
Diagnostic stroke imaging with C-arm cone-beam computed tomography (CBCT) enables reduction of time-to-therapy for endovascular procedures.
Metal artifacts in computed tomography (CT) arise from a mismatch between physics of image formation and idealized assumptions during tomographic reconstruction.
Magnetic Resonance Fingerprinting (MRF) is an imaging technique acquiring unique time signals for different tissues.
Nevertheless, publications introducing novel interactive segmentation systems (ISS) often lack an objective comparison of HCI aspects.
We first train an encoder-decoder CNN on T2-weighted and balanced-Steady State Free Precession (bSSFP) MR images with pixel-level annotation and fine-tune the same network with a limited number of Late Gadolinium Enhanced-MR (LGE-MR) subjects, to adapt the domain features.
Robustness of deep learning methods for limited angle tomography is challenged by two major factors: a) due to insufficient training data the network may not generalize well to unseen data; b) deep learning methods are sensitive to noise.
2 code implementations • 12 Aug 2019 • Christian Marzahl, Marc Aubreville, Christof A. Bertram, Jason Stayt, Anne-Katherine Jasensky, Florian Bartenschlager, Marco Fragoso-Garcia, Ann K. Barton, Svenja Elsemann, Samir Jabari, Jens Krauth, Prathmesh Madhu, Jörn Voigt, Jenny Hill, Robert Klopfleisch, Andreas Maier
Additionally, we evaluated object detection methods on a novel data set of 17 completely annotated cytology whole slide images (WSI) containing 78, 047 hemosiderophages.
A deep multi-task stacked hourglass network is trained on 149 conventional lateral X-ray images to jointly localize two femoral landmarks, to predict a region of interest for the posterior femoral cortex tangent line, and to perform semantic segmentation of the femur, patella, tibia, and fibula with adaptive task complexity weighting.
We start with a high-performance U-Net and show by step-by-step conversion that we are able to divide the network into modules of known operators.
Although the acquisition is highly accelerated, the state-of-the-art reconstruction suffers from long computation times: Template matching methods are used to find the most similar signal to the measured one by comparing it to pre-simulated signals of possible parameter combinations in a discretized dictionary.
Recently, autoregressive deep generative models such as WaveNet and SampleRNN have been used as speech vocoders to scale up the perceptual quality of the reconstructed signals without increasing the coding rate.
Automatic segmentation of organs-at-risk (OAR) in computed tomography (CT) is an essential part of planning effective treatment strategies to combat lung and esophageal cancer.
Chest X-ray (CXR) is the most common X-ray examination performed in daily clinical practice for the diagnosis of various heart and lung abnormalities.
Tissue loss in the hippocampi has been heavily correlated with the progression of Alzheimer's Disease (AD).
Squamous Cell Carcinoma (SCC) is the most common cancer type of the epithelium and is often detected at a late stage.
1 code implementation • 12 Feb 2019 • Marc Aubreville, Christof A. Bertram, Christian Marzahl, Corinne Gurtner, Martina Dettwiler, Anja Schmidt, Florian Bartenschlager, Sophie Merz, Marco Fragoso, Olivia Kershaw, Robert Klopfleisch, Andreas Maier
Manual count of mitotic figures, which is determined in the tumor region with the highest mitotic activity, is a key parameter of most tumor grading schemes.
For both approaches, the CNN performs a segmentation of the WSI to assess mitotic activity.
This paper tries to give a gentle introduction to deep learning in medical image processing, proceeding from theoretical foundations to applications.
One interesting result is that top-performing methods on simulated data may be surpassed by others on real data.
This underlines the need for an accurate and automatic approach to skin lesion segmentation.
We employ a 3D fully convolutional network, with dilated convolutions in the lowest level of the network, and residual connections between encoder blocks to incorporate local and global knowledge.
This approach opens the way towards implementation of direct user feedback in deep learning and is applicable for a wide range of application.
The results demonstrate that the proposed method is superior to ray-by-ray interpolation and is able to deliver sharper images using the same amount of parallel-beam input projections which is crucial for interventional applications.
Both approaches are trained on 1, 968 cells extracted from high resolution EL intensity images of mono- and polycrystalline PV modules.
1 code implementation • 28 Jun 2018 • Maximilian Seitzer, Guang Yang, Jo Schlemper, Ozan Oktay, Tobias Würfl, Vincent Christlein, Tom Wong, Raad Mohiaddin, David Firmin, Jennifer Keegan, Daniel Rueckert, Andreas Maier
In addition, we introduce a semantic interpretability score, measuring the visibility of the region of interest in both ground truth and reconstructed images, which allows us to objectively quantify the usefulness of the image quality