arXiv subjects

Alexander Schlaefer

Publications and source records attributed to Alexander Schlaefer.

At least 19 recordsLinked to original sources

arXiv2026

Predictive Multi-Landmark OCT Tracking for Increased Motion Robustness

Optical coherence tomography is a promising modality for markerless motion tracking due to its high spatial resolution and inherent depth perception. However, existing OCT-based tracking approaches are limited in terms of trackable velocity, particularly when multiple landmarks are tracked sequentially for 6D pose estimation. In this work, we present a predictive tracking approach that propagates positional updates between multiple tracked landmarks to obtain a global pose prediction. This enables more robust tracking under high velocities. Our results demonstrate RMSEs below 1 mm for velocities up to 100 mm/s and up to nine consecutively tracked landmarks, highlighting the potential of global motion propagation and prediction for improving the robustness of OCT-based tracking.

cs.CV↗

arXiv2026

Point Tracking in Surgery--The 2025 Surgical Tattoos in Infrared Challenge (STIRC2025)

Point tracking in surgery is crucial to enable applications in downstream tasks such as segmentation, 3D reconstruction, virtual tissue landmarking, autonomous probe-based scanning, and subtask autonomy. This paper introduces the 2025 iteration of a point tracking challenge to address this, wherein participants submit their algorithms for quantification. Their algorithms are evaluated using a dataset named surgical tattoos in infrared (STIR), with the challenge named the STIR Challenge 2025 (STIRC2025). The STIR Challenge 2025 comprises two quantitative components: accuracy and efficiency. The accuracy component tests the accuracy of algorithms on in vivo and ex vivo sequences. The efficiency component tests algorithm inference latency. The challenge was conducted as a part of MICCAI EndoVis 2025, and seven teams participated in this challenge. In this paper we summarize the challenge results and participant methods. The challenge dataset is available at: https://zenodo.org/records/20191078, and the code for baseline models and metrics calculation is available here: https://github.com/athaddius/STIRMetrics

cs.CV↗

arXiv2026

An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models

Surgical video understanding is a crucial prerequisite for advancing Computer-Assisted Surgery. While vision-language models (VLMs) have recently been applied to the surgical domain, existing surgical vision-language datasets lack in capturing and evaluating complex, interleaved spatial-temporal dynamics. Creating large scale datasets that accurately represent fine-grained spatial-temporal relationships in surgical videos is challenging due to costly manual annotations or error-prone generation using large language models. To address this gap, we introduce the SurgSTU-Pipeline, a deterministic generation pipeline featuring temporal and spatial continuity filtering to reliably create surgical datasets for fine-grained spatial-temporal multimodal understanding. Applying this pipeline to publicly available surgical datasets, we create the SurgSTU dataset, comprising 6711 video clips densely extended with 150k fine-grained spatial-temporal question-answer samples. Our comprehensive evaluation shows that while state-of-the-art generalist VLMs struggle in zero-shot settings, their spatial-temporal capabilities can be improved through in-context learning. A fine-tuned VLM on the SurgSTU training dataset achieves highest performance among all spatial-temporal tasks, validating the dataset's efficacy to improve spatial-temporal understanding of VLMs in surgical videos. The project is available here: https://lennart-maack.github.io/SurgSTU-project

cs.CV↗

arXiv2026

6D Robotic OCT Scanning of Curved Tissue Surfaces

Optical coherence tomography (OCT) is a non-invasive volumetric imaging modality with high spatial and temporal resolution. For imaging larger tissue structures, OCT probes need to be moved to scan the respective area. For handheld scanning, stitching of the acquired OCT volumes requires overlap to register the images. For robotic scanning and stitching, a typical approach is to restrict the motion to translations, as this avoids a full hand-eye calibration, which is complicated by the small field of view of most OCT probes. However, stitching by registration or by translational scanning are limited when curved tissue surfaces need to be scanned. We propose a marker for full six-dimensional hand-eye calibration of a robot mounted OCT probe. We show that the calibration results in highly repeatable estimates of the transformation. Moreover, we evaluate robotic scanning of two phantom surfaces to demonstrate that the proposed calibration allows for consistent scanning of large, curved tissue surfaces. As the proposed approach is not relying on image registration, it does not suffer from a potential accumulation of errors along a scan path. We also illustrate the improvement compared to conventional 3D-translational robotic scanning.

cs.CV↗

arXiv2025

Distilling Expert Surgical Knowledge: How to train local surgical VLMs for anatomy explanation in Complete Mesocolic Excision

Recently, Vision Large Language Models (VLMs) have demonstrated high potential in computer-aided diagnosis and decision-support. However, current VLMs show deficits in domain specific surgical scene understanding, such as identifying and explaining anatomical landmarks during Complete Mesocolic Excision. Additionally, there is a need for locally deployable models to avoid patient data leakage to large VLMs, hosted outside the clinic. We propose a privacy-preserving framework to distill knowledge from large, general-purpose LLMs into an efficient, local VLM. We generate an expert-supervised dataset by prompting a teacher LLM without sensitive images, using only textual context and binary segmentation masks for spatial information. This dataset is used for Supervised Fine-Tuning (SFT) and subsequent Direct Preference Optimization (DPO) of the locally deployable VLM. Our evaluation confirms that finetuning VLMs with our generated datasets increases surgical domain knowledge compared to its base VLM by a large margin. Overall, this work validates a data-efficient and privacy-conforming way to train a surgical domain optimized, locally deployable VLM for surgical scene understanding.

cs.CV↗

arXiv2025

Automated Estimation of Anatomical Risk Metrics for Endoscopic Sinus Surgery Using Deep Learning

Endoscopic sinus surgery requires careful preoperative assessment of the skull base anatomy to minimize risks such as cerebrospinal fluid leakage. Anatomical risk scores like the Keros, Gera and Thailand-Malaysia-Singapore score offer a standardized approach but require time-consuming manual measurements on coronal CT or CBCT scans. We propose an automated deep learning pipeline that estimates these risk scores by localizing key anatomical landmarks via heatmap regression. We compare a direct approach to a specialized global-to-local learning strategy and find mean absolute errors on the relevant anatomical measurements of 0.506mm for the Keros, 4.516{\deg} for the Gera and 0.802mm / 0.777mm for the TMS classification.

cs.CV↗

arXiv2025

Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filters

Continuous electrocardiogram (ECG) monitoring via wearable devices is vital for early cardiovascular disease detection. However, deploying deep learning models on resource-constrained microcontrollers faces reliability challenges, particularly from Out-of-Distribution (OOD) pathologies and noise. Standard classifiers often yield high-confidence errors on such data. Existing OOD detection methods either neglect computational constraints or address noise and unseen classes separately. This paper investigates Unsupervised Anomaly Detection (UAD) as a lightweight, upstream filtering mechanism. We perform a Neural Architecture Search (NAS) on six UAD approaches, including Deep Support Vector Data Description (Deep SVDD), input reconstruction with (Variational-)Autoencoders (AE/VAE), Masked Anomaly Detection (MAD), Normalizing Flows (NFs) and Denoising Diffusion Probabilistic Models (DDPM) under strict hardware constraints ($\leq$512k parameters), suitable for microcontrollers. Evaluating on the PTB-XL and BUT QDB datasets, we demonstrate that a NAS-optimized Deep SVDD offers the superior Pareto efficiency between detection performance and model size. In a simulated deployment, this lightweight filter improves the accuracy of a diagnostic classifier by up to 21.0 percentage points, demonstrating that optimized UAD filters can safeguard ECG analysis on wearables.

cs.LG↗

arXiv2025

On-Device Inference versus Wireless Streaming: Energy-Efficient Multi-Modal Deep Learning for Wearable Cardiovascular Patches

Wearable cardiovascular sensor patches promise continuous, unobtrusive monitoring, but their tight energy, memory, and compute budgets make it unclear whether physiological signals should be analyzed on the device or streamed to the cloud for processing. We study this inference-versus-transmission trade-off for a resource-constrained patch that records synchronized electrocardiogram (ECG) and phonocardiogram (PCG) signals. We propose an end-to-end, multi-modal convolutional neural network (CNN) with early fusion that classifies the two modalities directly on the device, without hand-crafted features. Trained and validated on the PhysioNet/Computing in Cardiology Challenge 2016 dataset, the floating-point model attains an accuracy of 0.975, which is competitive with the best reported results. At the same time, it reduces the parameter count and computational cost by approximately three orders of magnitude. We deploy an 8-bit integer version of the model on a microcontroller with an integrated neural processing unit (NPU) and measure its inference energy. We also benchmark the energy required for Bluetooth Low Energy (BLE) communication on a representative evaluation kit across a range of payload sizes. NPU inference consumes approximately one-seventh of the energy required for CPU inference. For realistic per-second payloads, local inference is also several times more energy efficient than continuous raw-data streaming. These results show that on-device intelligence, rather than constant transmission, is the more energy-efficient basis for always-on wearable cardiovascular monitoring at the edge.

cs.LG↗

arXiv2025

Deep Learning for High Speed Optical Coherence Elastography with a Fiber Scanning Endoscope

Tissue stiffness is related to soft tissue pathologies and can be assessed through palpation or via clinical imaging systems, e.g., ultrasound or magnetic resonance imaging. Typically, the image based approaches are not suitable during interventions, particularly for minimally invasive surgery. To this end, we present a miniaturized fiber scanning endoscope for fast and localized elastography. Moreover, we propose a deep learning based signal processing pipeline to account for the intricate data and the need for real-time estimates. Our elasticity estimation approach is based on imaging complex and diffuse wave fields that encompass multiple wave frequencies and propagate in various directions. We optimize the probe design to enable different scan patterns. To maximize temporal sampling while maintaining three-dimensional information we define a scan pattern in a conical shape with a temporal frequency of 5.05 kHz. To efficiently process the image sequences of complex wave fields we consider a spatio-temporal deep learning network. We train the network in an end-to-end fashion on measurements from phantoms representing multiple elasticities. The network is used to obtain localized and robust elasticity estimates, allowing to create elasticity maps in real-time. For 2D scanning, our approach results in a mean absolute error of 6.31+-5.76 kPa compared to 11.33+-12.78 kPa for conventional phase tracking. For scanning without estimating the wave direction, the novel 3D method reduces the error to 4.48+-3.63 kPa compared to 19.75+-21.82 kPa for the conventional 2D method. Finally, we demonstrate feasibility of elasticity estimates in ex-vivo porcine tissue.

eess.SP↗

arXiv2025

A Digital Twin for Robotic Post Mortem Tissue Sampling using Virtual Reality

Studying tissue samples obtained during autopsies is the gold standard when diagnosing the cause of death and for understanding disease pathophysiology. Recently, the interest in post mortem minimally invasive biopsies has grown which is a less destructive approach in comparison to an open autopsy and reduces the risk of infection. While manual biopsies under ultrasound guidance are more widely performed, robotic post mortem biopsies have been recently proposed. This approach can further reduce the risk of infection for physicians. However, planning of the procedure and control of the robot need to be efficient and usable. We explore a virtual reality setup with a digital twin to realize fully remote planning and control of robotic post mortem biopsies. The setup is evaluated with forensic pathologists in a usability study for three interaction methods. Furthermore, we evaluate clinical feasibility and evaluate the system with three human cadavers. Overall, 132 needle insertions were performed with an off-axis needle placement error of 5.30+-3.25 mm. Tissue samples were successfully biopsied and histopathologically verified. Users reported a very intuitive needle placement approach, indicating that the system is a promising, precise, and low-risk alternative to conventional approaches.

cs.RO↗

arXiv2025

Tracking Any Point Methods for Markerless 3D Tissue Tracking in Endoscopic Stereo Images

Minimally invasive surgery presents challenges such as dynamic tissue motion and a limited field of view. Accurate tissue tracking has the potential to support surgical guidance, improve safety by helping avoid damage to sensitive structures, and enable context-aware robotic assistance during complex procedures. In this work, we propose a novel method for markerless 3D tissue tracking by leveraging 2D Tracking Any Point (TAP) networks. Our method combines two CoTracker models, one for temporal tracking and one for stereo matching, to estimate 3D motion from stereo endoscopic images. We evaluate the system using a clinical laparoscopic setup and a robotic arm simulating tissue motion, with experiments conducted on a synthetic 3D-printed phantom and a chicken tissue phantom. Tracking on the chicken tissue phantom yielded more reliable results, with Euclidean distance errors as low as 1.1 mm at a velocity of 10 mm/s. These findings highlight the potential of TAP-based models for accurate, markerless 3D tracking in challenging surgical scenarios.

cs.CV↗

arXiv2025

Robust Tracking with Particle Filtering for Fluorescent Cardiac Imaging

Intraoperative fluorescent cardiac imaging enables quality control following coronary bypass grafting surgery. We can estimate local quantitative indicators, such as cardiac perfusion, by tracking local feature points. However, heart motion and significant fluctuations in image characteristics caused by vessel structural enrichment limit traditional tracking methods. We propose a particle filtering tracker based on cyclicconsistency checks to robustly track particles sampled to follow target landmarks. Our method tracks 117 targets simultaneously at 25.4 fps, allowing real-time estimates during interventions. It achieves a tracking error of (5.00 +/- 0.22 px) and outperforms other deep learning trackers (22.3 +/- 1.1 px) and conventional trackers (58.1 +/- 27.1 px).

cs.CV↗

arXiv2025

Do We Need Pre-Processing for Deep Learning Based Ultrasound Shear Wave Elastography?

Estimating the elasticity of soft tissue can provide useful information for various diagnostic applications. Ultrasound shear wave elastography offers a non-invasive approach. However, its generalizability and standardization across different systems and processing pipelines remain limited. Considering the influence of image processing on ultrasound based diagnostics, recent literature has discussed the impact of different image processing steps on reliable and reproducible elasticity analysis. In this work, we investigate the need of ultrasound pre-processing steps for deep learning-based ultrasound shear wave elastography. We evaluate the performance of a 3D convolutional neural network in predicting shear wave velocities from spatio-temporal ultrasound images, studying different degrees of pre-processing on the input images, ranging from fully beamformed and filtered ultrasound images to raw radiofrequency data. We compare the predictions from our deep learning approach to a conventional time-of-flight method across four gelatin phantoms with different elasticity levels. Our results demonstrate statistically significant differences in the predicted shear wave velocity among all elasticity groups, regardless of the degree of pre-processing. Although pre-processing slightly improves performance metrics, our results show that the deep learning approach can reliably differentiate between elasticity groups using raw, unprocessed radiofrequency data. These results show that deep learning-based approaches could reduce the need for and the bias of traditional ultrasound pre-processing steps in ultrasound shear wave elastography, enabling faster and more reliable clinical elasticity assessments.

eess.IV↗

arXiv2025

A Mobile Robotic Approach to Autonomous Surface Scanning in Legal Medicine

Purpose: Comprehensive legal medicine documentation includes both an internal but also an external examination of the corpse. Typically, this documentation is conducted manually during conventional autopsy. A systematic digital documentation would be desirable, especially for the external examination of wounds, which is becoming more relevant for legal medicine analysis. For this purpose, RGB surface scanning has been introduced. While a manual full surface scan using a handheld camera is timeconsuming and operator dependent, floor or ceiling mounted robotic systems require substantial space and a dedicated room. Hence, we consider whether a mobile robotic system can be used for external documentation. Methods: We develop a mobile robotic system that enables full-body RGB-D surface scanning. Our work includes a detailed configuration space analysis to identify the environmental parameters that need to be considered to successfully perform a surface scan. We validate our findings through an experimental study in the lab and demonstrate the system's application in a legal medicine environment. Results: Our configuration space analysis shows that a good trade-off between coverage and time is reached with three robot base positions, leading to a coverage of 94.96 %. Experiments validate the effectiveness of the system in accurately capturing body surface geometry with an average surface coverage of 96.90 +- 3.16 % and 92.45 +- 1.43 % for a body phantom and actual corpses, respectively. Conclusion: This work demonstrates the potential of a mobile robotic system to automate RGB-D surface scanning in legal medicine, complementing the use of post-mortem CT scans for inner documentation. Our results indicate that the proposed system can contribute to more efficient and autonomous legal medicine documentation, reducing the need for manual intervention.

cs.RO↗

arXiv2024

Leveraging the Mahalanobis Distance to enhance Unsupervised Brain MRI Anomaly Detection

Unsupervised Anomaly Detection (UAD) methods rely on healthy data distributions to identify anomalies as outliers. In brain MRI, a common approach is reconstruction-based UAD, where generative models reconstruct healthy brain MRIs, and anomalies are detected as deviations between input and reconstruction. However, this method is sensitive to imperfect reconstructions, leading to false positives that impede the segmentation. To address this limitation, we construct multiple reconstructions with probabilistic diffusion models. We then analyze the resulting distribution of these reconstructions using the Mahalanobis distance to identify anomalies as outliers. By leveraging information about normal variations and covariance of individual pixels within this distribution, we effectively refine anomaly scoring, leading to improved segmentation. Our experimental results demonstrate substantial performance improvements across various data sets. Specifically, compared to relying solely on single reconstructions, our approach achieves relative improvements of 15.9%, 35.4%, 48.0%, and 4.7% in terms of AUPRC for the BRATS21, ATLAS, MSLUB and WMH data sets, respectively.

eess.IV↗

arXiv2024

A Calibration Approach for Elasticity Estimation with Medical Tools

Soft tissue elasticity is directly related to different stages of diseases and can be used for tissue identification during minimally invasive procedures. By palpating a tissue with a robot in a minimally invasive fashion force-displacement curves can be acquired. However, force-displacement curves strongly depend on the tool geometry which is often complex in the case of medical tools. Hence, a tool calibration procedure is desired to directly map force-displacement curves to the corresponding tissue elasticity.We present an experimental setup for calibrating medical tools with a robot. First, we propose to estimate the elasticity of gelatin phantoms by spherical indentation with a state-of-the-art contact model. We estimate force-displacement curves for different gelatin elasticities and temperatures. Our experiments demonstrate that gelatin elasticity is highly dependent on temperature, which can lead to an elasticity offset if not considered. Second, we propose to use a more complex material model, e.g., a neural network, that can be trained with the determined elasticities. Considering the temperature of the gelatin sample we can represent different elasticities per phantom and thereby increase our training data.We report elasticity values ranging from 10 to 40 kPa for a 10% gelatin phantom, depending on temperature.

q-bio.TO↗

arXiv2024

Self-supervised learning for classifying paranasal anomalies in the maxillary sinus

Purpose: Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies, supervised learning methods require large labelled dataset exhibiting diverse anomaly morphology. Self-supervised learning (SSL) can be used to learn representations from unlabelled data. However, there are no SSL methods designed for the downstream task of classifying paranasal anomalies in the maxillary sinus (MS). Methods: Our approach uses a 3D Convolutional Autoencoder (CAE) trained in an unsupervised anomaly detection (UAD) framework. Initially, we train the 3D CAE to reduce reconstruction errors when reconstructing normal maxillary sinus (MS) image. Then, this CAE is applied to an unlabelled dataset to generate coarse anomaly locations by creating residual MS images. Following this, a 3D Convolutional Neural Network (CNN) reconstructs these residual images, which forms our SSL task. Lastly, we fine-tune the encoder part of the 3D CNN on a labelled dataset of normal and anomalous MS images. Results: The proposed SSL technique exhibits superior performance compared to existing generic self-supervised methods, especially in scenarios with limited annotated data. When trained on just 10% of the annotated dataset, our method achieves an Area Under the Precision-Recall Curve (AUPRC) of 0.79 for the downstream classification task. This performance surpasses other methods, with BYOL attaining an AUPRC of 0.75, SimSiam at 0.74, SimCLR at 0.73 and Masked Autoencoding using SparK at 0.75. Conclusion: A self-supervised learning approach that inherently focuses on localizing paranasal anomalies proves to be advantageous, particularly when the subsequent task involves differentiating normal from anomalous maxillary sinuses. Access our code at https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly

eess.IV↗

arXiv2024

Sliced Online Model Checking for Optimizing the Beam Scheduling Problem in Robotic Radiation Therapy

In robotic radiation therapy, high-energy photon beams from different directions are directed at a target within the patient. Target motion can be tracked by robotic ultrasound and then compensated by synchronous beam motion. However, moving the beams may result in beams passing through the ultrasound transducer or the robot carrying it. While this can be avoided by pausing the beam delivery, the treatment time would increase. Typically, the beams are delivered in an order which minimizes the robot motion and thereby the overall treatment time. However, this order can be changed, i.e., instead of pausing beams, other feasible beam could be delivered. We address this problem of dynamically ordering the beams by applying a model checking paradigm to select feasible beams. Since breathing patterns are complex and change rapidly, any offline model would be too imprecise. Thus, model checking must be conducted online, predicting the patient's current breathing pattern for a short amount of time and checking which beams can be delivered safely. Monitoring the treatment delivery online provides the option to reschedule beams dynamically in order to avoid pausing and hence to reduce treatment time. While human breathing patterns are complex and may change rapidly, we need a model which can be verified quickly and use approximation by a superposition of sine curves. Further, we simplify the 3D breathing motion into separate 1D models. We compensate the simplification by adding noise inside the model itself. In turn, we synchronize between the multiple models representing the different spatial directions, the treatment simulation, and corresponding verification queries. Our preliminary results show a 16.02 % to 37.21 % mean improvement on the idle time compared to a static beam schedule, depending on an additional safety margin. Note that an additional safety margin around the ultrasound robot can decrease idle times but also compromises plan quality by limiting the range of available beam directions. In contrast, the approach using online model checking maintains the plan quality. Further, we compare to a naive machine learning approach that does not achieve its goals while being harder to reason about.

cs.CE↗