Search Results for author: Alexander Schlaefer

Found 58 papers, 11 papers with code

Diffusion Models with Ensembled Structure-Based Anomaly Scoring for Unsupervised Anomaly Detection

1 code implementation21 Mar 2024 Finn Behrendt, Debayan Bhattacharya, Lennart Maack, Julia Krüger, Roland Opfer, Robin Mieling, Alexander Schlaefer

We demonstrate that this ensembling strategy can enhance the performance of DMs and mitigate the sensitivity to different kernel sizes across varying pathologies, highlighting its promise for brain MRI anomaly detection.

Segmentation SSIM +1

A Modified da Vinci Surgical Instrument for OCE based Elasticity Estimation with Deep Learning

no code implementations14 Mar 2024 Maximilian Neidhardt, Robin Mieling, Sarah Latus, Martin Fischer, Tobias Maurer, Alexander Schlaefer

We propose modifying a da~Vinci surgical instrument to realize optical coherence elastography (OCE) for quantitative elasticity estimation.

PolypNextLSTM: A lightweight and fast polyp video segmentation network using ConvNext and ConvLSTM

1 code implementation18 Feb 2024 Debayan Bhattacharya, Konrad Reuter, Finn Behrendt, Lennart Maack, Sarah Grube, Alexander Schlaefer

Our primary novelty lies in PolypNextLSTM, which stands out as the leanest in parameters and the fastest model, surpassing the performance of five state-of-the-art image and video-based deep learning models.

Segmentation Video Segmentation +1

Guided Reconstruction with Conditioned Diffusion Models for Unsupervised Anomaly Detection in Brain MRIs

1 code implementation7 Dec 2023 Finn Behrendt, Debayan Bhattacharya, Robin Mieling, Lennart Maack, Julia Krüger, Roland Opfer, Alexander Schlaefer

Using our proposed conditioning mechanism we can reduce the false-positive predictions and enable a more precise delineation of anomalies which significantly enhances the anomaly detection performance compared to established state-of-the-art approaches to unsupervised anomaly detection in brain MRI.

Anatomy Denoising +2

A systematic approach to deep learning-based nodule detection in chest radiographs

1 code implementation Nature Scientific Reports 2023 Finn Behrendt, Marcel Bengs, Debayan Bhattacharya, Julia Krüger, Roland Opfer, Alexander Schlaefer

We illustrate how this analysis and a combination of multiple architectures results in state-of-the-art performance for lung nodule detection, which is demonstrated by the proposed model winning the detection track of the Node21 competition.

Data Augmentation Lung Nodule Detection +3

Multiple Instance Ensembling For Paranasal Anomaly Classification In The Maxillary Sinus

no code implementations31 Mar 2023 Debayan Bhattacharya, Finn Behrendt, Benjamin Tobias Becker, Dirk Beyersdorff, Elina Petersen, Marvin Petersen, Bastian Cheng, Dennis Eggert, Christian Betz, Anna Sophie Hoffmann, Alexander Schlaefer

We demonstrate the feasibility of classifying anomalies in the MS. We propose a data enlarging strategy alongside a novel ensembling strategy that proves to be beneficial for paranasal anomaly classification in the MS.

Anomaly Classification Classification

Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRI

1 code implementation7 Mar 2023 Finn Behrendt, Debayan Bhattacharya, Julia Krüger, Roland Opfer, Alexander Schlaefer

The use of supervised deep learning techniques to detect pathologies in brain MRI scans can be challenging due to the diversity of brain anatomy and the need for annotated data sets.

Anatomy Unsupervised Anomaly Detection

Unsupervised Anomaly Detection of Paranasal Anomalies in the Maxillary Sinus

no code implementations1 Nov 2022 Debayan Bhattacharya, Finn Behrendt, Benjamin Tobias Becker, Dirk Beyersdorff, Elina Petersen, Marvin Petersen, Bastian Cheng, Dennis Eggert, Christian Betz, Anna Sophie Hoffmann, Alexander Schlaefer

However, experienced clinicians can segregate between normal samples (healthy maxillary sinus) and anomalous samples (anomalous maxillary sinus) after looking at a few normal samples.

Unsupervised Anomaly Detection

Supervised Contrastive Learning to Classify Paranasal Anomalies in the Maxillary Sinus

no code implementations5 Sep 2022 Debayan Bhattacharya, Benjamin Tobias Becker, Finn Behrendt, Marcel Bengs, Dirk Beyersdorff, Dennis Eggert, Elina Petersen, Florian Jansen, Marvin Petersen, Bastian Cheng, Christian Betz, Alexander Schlaefer, Anna Sophie Hoffmann

Particularly, we use a supervised contrastive loss that encourages embeddings of maxillary sinus volumes with and without anomaly to form two distinct clusters while the cross-entropy loss encourages the 3D CNN to maintain its discriminative ability.

Anomaly Classification Contrastive Learning

Data-Efficient Vision Transformers for Multi-Label Disease Classification on Chest Radiographs

no code implementations17 Aug 2022 Finn Behrendt, Debayan Bhattacharya, Julia Krüger, Roland Opfer, Alexander Schlaefer

Our results show that while the performance between ViTs and CNNs is on par with a small benefit for ViTs, DeiTs outperform the former if a reasonably large data set is available for training.

Multi-Label Classification

Unsupervised Anomaly Detection in 3D Brain MRI using Deep Learning with impured training data

no code implementations12 Apr 2022 Finn Behrendt, Marcel Bengs, Frederik Rogge, Julia Krüger, Roland Opfer, Alexander Schlaefer

Overall, we highlight the importance of clean data sets for UAD in brain MRI and demonstrate an approach for detecting falsely labeled data directly during training.

Unsupervised Anomaly Detection

Ultrasound Shear Wave Elasticity Imaging with Spatio-Temporal Deep Learning

no code implementations11 Apr 2022 Maximilian Neidhardt, Marcel Bengs, Sarah Latus, Stefan Gerlach, Christian J. Cyron, Johanna Sprenger, Alexander Schlaefer

The results show that our approach can estimate elastic properties on a pixelwise basis with a mean absolute error of 5. 01+-4. 37 kPa.

Modeling R$^3$ Needle Steering in Uppaal

no code implementations18 Mar 2022 Sascha Lehmann, Antje Rogalla, Maximilian Neidhardt, Anton Reinecke, Alexander Schlaefer, Sibylle Schupp

Medical cyber-physical systems are safety-critical, and as such, require ongoing verification of their correct behavior, as system failure during run time may cause severe (or even fatal) personal damage.

Posterior temperature optimized Bayesian models for inverse problems in medical imaging

1 code implementation2 Feb 2022 Max-Heinrich Laves, Malte Tölle, Alexander Schlaefer, Sandy Engelhardt

In POTOBIM, we optimize both the parameters of the prior distribution and the posterior temperature with respect to reconstruction accuracy using Bayesian optimization with Gaussian process regression.

Bayesian Optimization Image Denoising +1

Unsupervised Anomaly Detection in 3D Brain MRI using Deep Learning with Multi-Task Brain Age Prediction

no code implementations31 Jan 2022 Marcel Bengs, Finn Behrendt, Max-Heinrich Laves, Julia Krüger, Roland Opfer, Alexander Schlaefer

We analyze the value of age information during training, as an additional anomaly score, and systematically study several architecture concepts.

Anatomy Lesion Detection +1

Online Strategy Synthesis for Safe and Optimized Control of Steerable Needles

no code implementations25 Oct 2021 Sascha Lehmann, Antje Rogalla, Maximilian Neidhardt, Alexander Schlaefer, Sibylle Schupp

Autonomous systems are often applied in uncertain environments, which require prospective action planning and retrospective data evaluation for future planning to ensure safe operation.

Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning

no code implementations14 Sep 2021 Marcel Bengs, Satish Pant, Michael Bockmayr, Ulrich Schüller, Alexander Schlaefer

Our top-performing method achieves the AUC-ROC value of 90. 90\% compared to 84. 53\% using the previous approach with smaller input tiles.

Classification Transfer Learning

Medulloblastoma Tumor Classification using Deep Transfer Learning with Multi-Scale EfficientNets

no code implementations10 Sep 2021 Marcel Bengs, Michael Bockmayr, Ulrich Schüller, Alexander Schlaefer

In this work, we propose an end-to-end MB tumor classification and explore transfer learning with various input sizes and matching network dimensions.

Transfer Learning

Spectral-Spatial Recurrent-Convolutional Networks for In-Vivo Hyperspectral Tumor Type Classification

no code implementations2 Jul 2020 Marcel Bengs, Nils Gessert, Wiebke Laffers, Dennis Eggert, Stephan Westermann, Nina A. Mueller, Andreas O. H. Gerstner, Christian Betz, Alexander Schlaefer

We analyze the value of using multiple hyperspectral bands compared to conventional RGB images and we study several machine learning models' ability to make use of the additional spectral information.

General Classification

Deep learning with 4D spatio-temporal data representations for OCT-based force estimation

1 code implementation20 May 2020 Nils Gessert, Marcel Bengs, Matthias Schlüter, Alexander Schlaefer

Moreover, optical coherence tomography (OCT) and deep learning have been used for estimating forces based on deformation observed in volumetric image data.

Spatio-spectral deep learning methods for in-vivo hyperspectral laryngeal cancer detection

no code implementations21 Apr 2020 Marcel Bengs, Stephan Westermann, Nils Gessert, Dennis Eggert, Andreas O. H. Gerstner, Nina A. Mueller, Christian Betz, Wiebke Laffers, Alexander Schlaefer

A recent study has shown that hyperspectral imaging (HSI) can be used for non-invasive detection of head and neck tumors, as precancerous or cancerous lesions show specific spectral signatures that distinguish them from healthy tissue.

Spatio-Temporal Deep Learning Methods for Motion Estimation Using 4D OCT Image Data

no code implementations21 Apr 2020 Marcel Bengs, Nils Gessert, Matthias Schlüter, Alexander Schlaefer

For this purpose, we design and evaluate several 3D and 4D deep learning methods and we propose a new deep learning approach.

Motion Estimation

A Deep Learning Approach for Motion Forecasting Using 4D OCT Data

no code implementations MIDL 2019 Marcel Bengs, Nils Gessert, Alexander Schlaefer

We propose 4D spatio-temporal deep learning for end-to-end motion forecasting and estimation using a stream of OCT volumes.

Motion Compensation Motion Estimation +3

4D Deep Learning for Multiple Sclerosis Lesion Activity Segmentation

no code implementations20 Apr 2020 Nils Gessert, Marcel Bengs, Julia Krüger, Roland Opfer, Ann-Christin Ostwaldt, Praveena Manogaran, Sven Schippling, Alexander Schlaefer

While deep learning methods for single-scan lesion segmentation are common, deep learning approaches for lesion activity have only been proposed recently.

Lesion Segmentation Segmentation

Learning Preference-Based Similarities from Face Images using Siamese Multi-Task CNNs

no code implementations25 Jan 2020 Nils Gessert, Alexander Schlaefer

The ground-truth for the similarity matching scores is determined by a test that aims to capture users' preferences, interests, and attitude that are relevant for forming romantic relationships.

Melanoma detection with electrical impedance spectroscopy and dermoscopy using joint deep learning models

no code implementations6 Nov 2019 Nils Gessert, Marcel Bengs, Alexander Schlaefer

As a result, we propose a recurrent model with state-max-pooling which automatically learns the relevance of different EIS measurements.

BIG-bench Machine Learning Lesion Classification

Spatio-Temporal Deep Learning Models for Tip Force Estimation During Needle Insertion

no code implementations22 May 2019 Nils Gessert, Torben Priegnitz, Thore Saathoff, Sven-Thomas Antoni, David Meyer, Moritz Franz Hamann, Klaus-Peter Jünemann, Christoph Otte, Alexander Schlaefer

Our novel convGRU-CNN architecture results in the lowest mean absolute error of 1. 59 +- 1. 3 mN and a cross-correlation coefficient of 0. 9997, and clearly outperforms the other methods.

Deep Transfer Learning Methods for Colon Cancer Classification in Confocal Laser Microscopy Images

no code implementations20 May 2019 Nils Gessert, Marcel Bengs, Lukas Wittig, Daniel Drömann, Tobias Keck, Alexander Schlaefer, David B. Ellebrecht

For feedback during interventions, real-time in-vivo imaging with confocal laser microscopy has been proposed for differentiation of benign and malignant tissue by manual expert evaluation.

General Classification Image Classification +1

Efficient Neural Architecture Search on Low-Dimensional Data for OCT Image Segmentation

no code implementations7 May 2019 Nils Gessert, Alexander Schlaefer

We propose an efficient approach for NAS in the context of medical, image-based deep learning problems by searching for architectures on low-dimensional data which are subsequently transferred to high-dimensional data.

Image Segmentation Neural Architecture Search +1

Endoscopic vs. volumetric OCT imaging of mastoid bone structure for pose estimation in minimally invasive cochlear implant surgery

no code implementations19 Jan 2019 Max-Heinrich Laves, Sarah Latus, Jan Bergmeier, Tobias Ortmaier, Lüder A. Kahrs, Alexander Schlaefer

The resulting volumentric images provide additional information on the shape of caveties in the bone structure, which will be useful for image-to-patient registration and to estimate the drill trajectory.

Pose Estimation

Two-path 3D CNNs for calibration of system parameters for OCT-based motion compensation

no code implementations22 Oct 2018 Nils Gessert, Martin Gromniak, Matthias Schlüter, Alexander Schlaefer

Optical coherence tomography (OCT) is an imaging modality which is used in interventions due to its high spatial resolution of few micrometers and its temporal resolution of potentially several hundred volumes per second.

Motion Compensation

Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting

2 code implementations5 Aug 2018 Nils Gessert, Thilo Sentker, Frederic Madesta, Rüdiger Schmitz, Helge Kniep, Ivo Baltruschat, René Werner, Alexander Schlaefer

We identify heavy class imbalance as a key problem for this challenge and consider multiple balancing approaches such as loss weighting and balanced batch sampling.

Meta-Learning

Force Estimation from OCT Volumes using 3D CNNs

no code implementations26 Apr 2018 Nils Gessert, Jens Beringhoff, Christoph Otte, Alexander Schlaefer

Our novel Siamese 3D CNN architecture outperforms single-path methods that achieve a mean average error of 11. 59 +- 6. 7 mN.

Friction

A Deep Learning Approach for Pose Estimation from Volumetric OCT Data

no code implementations10 Mar 2018 Nils Gessert, Matthias Schlüter, Alexander Schlaefer

We use this setup to provide an in-depth analysis on deep learning-based pose estimation from volumes.

Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.