arXiv subjects

Philipp Rostalski

Publications and source records attributed to Philipp Rostalski.

14 recordsLinked to original sources

arXiv2026

Validation of a Computational Respiratory System Model for Mechanical Ventilation

Computational modeling and simulation are powerful tools for the assessment of medical device performance and safety, particularly for in silico clinical trials for automated medical systems. In ventilation, where managing gas exchange, respiratory mechanics, and patient-ventilator interaction is required under evolving pathophysiology, the clinical translation of automated control strategies remains slow and resource-intensive. This paper applies a standards-aligned framework for the credibility assessment of a computational respiratory model, demonstrated using an automated weaning case study. The framework operationalizes ASME V&V 40 and FDA principles within a structured, guidance-based validation workflow. The computational physiological model integrates respiratory mechanics, gas exchange, respiratory control, and a ventilator representation, validated under a clearly defined context of use and explicit questions of interest. Model credibility is assessed through calibration, physiological plausibility, population-based evaluation, and reproduction of emergent behavior. All model requirements derived from the intended context of use are addressed within the proposed credibility assessment plan, and documented gaps are transparently reported. The resulting credibility argument supports the applicability of the model for its context of use. Strengths are demonstrated in population-based comparison and mechanistic plausibility, while residual limitations relate to the extent of in vivo evidence, population representativeness, and external validation. Overall, the model is considered fit for purpose for medium-low risk preclinical in silico clinical trials of automated weaning strategies. Furthermore, the validation procedure outlined in this article provides a blueprint for the validation of this and similar models in other mechanical ventilation algorithms and related use cases.

physics.med-ph↗

arXiv2024

Automated Computation of Therapies Using Failure Mode and Effects Analysis in the Medical Domain

Failure mode and effects analysis (FMEA) is a systematic approach to identify and analyse potential failures and their effects in a system or process. The FMEA approach, however, requires domain experts to manually analyse the FMEA model to derive risk-reducing actions that should be applied. In this paper, we provide a formal framework to allow for automatic planning and acting in FMEA models. More specifically, we cast the FMEA model into a Markov decision process which can then be solved by existing solvers. We show that the FMEA approach can not only be used to support medical experts during the modelling process but also to automatically derive optimal therapies for the treatment of patients.

cs.AI↗

arXiv2023

Anatomy-guided domain adaptation for 3D in-bed human pose estimation

3D human pose estimation is a key component of clinical monitoring systems. The clinical applicability of deep pose estimation models, however, is limited by their poor generalization under domain shifts along with their need for sufficient labeled training data. As a remedy, we present a novel domain adaptation method, adapting a model from a labeled source to a shifted unlabeled target domain. Our method comprises two complementary adaptation strategies based on prior knowledge about human anatomy. First, we guide the learning process in the target domain by constraining predictions to the space of anatomically plausible poses. To this end, we embed the prior knowledge into an anatomical loss function that penalizes asymmetric limb lengths, implausible bone lengths, and implausible joint angles. Second, we propose to filter pseudo labels for self-training according to their anatomical plausibility and incorporate the concept into the Mean Teacher paradigm. We unify both strategies in a point cloud-based framework applicable to unsupervised and source-free domain adaptation. Evaluation is performed for in-bed pose estimation under two adaptation scenarios, using the public SLP dataset and a newly created dataset. Our method consistently outperforms various state-of-the-art domain adaptation methods, surpasses the baseline model by 31%/66%, and reduces the domain gap by 65%/82%. Source code is available at https://github.com/multimodallearning/da-3dhpe-anatomy.

cs.CV↗

arXiv2022

A real-time GP based MPC for quadcopters with unknown disturbances

Gaussian Process (GP) regressions have proven to be a valuable tool to predict disturbances and model mismatches and incorporate this information into a Model Predictive Control (MPC) prediction. Unfortunately, the computational complexity of inference and learning on classical GPs scales cubically, which is intractable for real-time applications. Thus GPs are commonly trained offline, which is not suited for learning disturbances as their dynamics may vary with time. Recently, state-space formulation of GPs has been introduced, allowing inference and learning with linear computational complexity. This paper presents a framework that enables online learning of disturbance dynamics on quadcopters, which can be executed within milliseconds using a state-space formulation of GPs. The obtained disturbance predictions are combined with MPC leading to a significant performance increase in simulations with jMAVSim. The computational burden is evaluated on a Raspberry Pi 4 B to prove the real-time applicability.

eess.SY↗

arXiv2022

Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions

Machine learning is expected to fuel significant improvements in medical care. To ensure that fundamental principles such as beneficence, respect for human autonomy, prevention of harm, justice, privacy, and transparency are respected, medical machine learning systems must be developed responsibly. Many high-level declarations of ethical principles have been put forth for this purpose, but there is a severe lack of technical guidelines explicating the practical consequences for medical machine learning. Similarly, there is currently considerable uncertainty regarding the exact regulatory requirements placed upon medical machine learning systems. This survey provides an overview of the technical and procedural challenges involved in creating medical machine learning systems responsibly and in conformity with existing regulations, as well as possible solutions to address these challenges. First, a brief review of existing regulations affecting medical machine learning is provided, showing that properties such as safety, robustness, reliability, privacy, security, transparency, explainability, and nondiscrimination are all demanded already by existing law and regulations - albeit, in many cases, to an uncertain degree. Next, the key technical obstacles to achieving these desirable properties are discussed, as well as important techniques to overcome these obstacles in the medical context. We notice that distribution shift, spurious correlations, model underspecification, uncertainty quantification, and data scarcity represent severe challenges in the medical context. Promising solution approaches include the use of large and representative datasets and federated learning as a means to that end, the careful exploitation of domain knowledge, the use of inherently transparent models, comprehensive out-of-distribution model testing and verification, as well as algorithmic impact assessments.

cs.LG↗

arXiv2021

Spatial Sensitivity of ECG Electrode Placement

The electrocardiogram (ECG) is a well-known technique used to diagnose cardiac diseases. To acquire the spatial signal characteristics from the thorax, multiple electrodes are commonly used. Displacements of electrodes affect the signal morphologies and can lead to incorrect diagnoses. For quantitative analysis of these effects we propose the usage of a numerical computer simulation. In order to create a realistic representation of the human thorax including the heart and lung a three-dimensional model with a simplified geometry is used. The electrical excitation of the heart is modelled on a cellular level via the bidomain approach. To numerically solve the differential equations, describing the signal propagation within the body, we use the finite element method in COMSOL Multiphysics. The spatial gradients of the simulated body potentials are calculated to determine placement sensitivity maps. The simulated results show that the sensitivity is different for each considered point in time of each ECG wave. In general, the impact of displacement is increased as an electrode is more closely located to the signal source. However, in some specific regions associated with differential ECG leads the placement sensitivity distribution deviates from this simple circular pattern. The results provide useful information to enhance the understanding of placed specific effects on classical ECG features. By additional consideration of patient-specific characteristics in the future, the used model has the ability to investigate additional body-related aspects such as geometrical body shape or composition of various tissue types.

physics.med-ph↗

arXiv2021

A Robust Multi-Channel EMG System for Lower Back and Abdominal Muscles Training

EMG is an established method to acquire the action potentials of contracted muscles. Although commercial EMG systems are available and it is one of the most researched biosignals, it has never become widely used in rehabilitation or fitness training monitoring. The reasons are technical challenges of wearable EMG systems regarding electrode placement, motion artefacts and the complex connectivity of multi-channel EMG measurements. We address this problem for the lower back and abdominal musculature, through a novel dry electrodes belt, multi-channel high density EMG circuitry and problem-specific signal processing. The subject can easily strap the dry electrodes belt around himself which provides 16 EMG channels. Interferences from the ECG and motion artefacts are reduced by a stationary wavelet decomposition. Afterwards, an inter-channel filter is applied to increase the robustness of the signals. Subject measurements during different kinds of typical abdominal and lower back training exercises were performed wearing the novel dry electrodes belt. The results show the possibility of robust EMG measurements from the lower back and abdominal muscles by utilizing the gathered redundancy, appropriately. The additional information obtained via the multi-channel EMG circuitry and spatial oversampling can be used to address current problems of EMG applications. It combines the advantages of robustness and the capability of using comfortable dry electrodes. Therefore, the proposed measurement method for acquiring spatial information about the muscle contractions from the lower trunk can be used for rehabilitation or fitness training monitoring.

physics.med-ph↗

arXiv2019

Scalable Gaussian Process Regression for Kernels with a Non-Stationary Phase

The application of Gaussian processes (GPs) to large data sets is limited due to heavy memory and computational requirements. A variety of methods has been proposed to enable scalability, one of which is to exploit structure in the kernel matrix. Previous methods, however, cannot easily deal with non-stationary processes. This paper presents an efficient GP framework, that extends structured kernel interpolation methods to GPs with a non-stationary phase. We particularly treat mixtures of non-stationary processes, which are commonly used in the context of separation problems e.g. in biomedical signal processing. Our approach employs multiple sets of non-equidistant inducing points to account for the non-stationarity and retrieve Toeplitz and Kronecker structure in the kernel matrix allowing for efficient inference. Kernel learning is done by optimizing the marginal likelihood, which can be approximated efficiently using stochastic trace estimation methods. Our approach is demonstrated on numerical examples and large biomedical datasets.

cs.LG↗

arXiv2019

Convolutive Blind Source Separation on Surface EMG Signals for Respiratory Diagnostics and Medical Ventilation Control

The electromyogram (EMG) is an important tool for assessing the activity of a muscle and thus also a valuable measure for the diagnosis and control of respiratory support. In this article we propose convolutive blind source separation (BSS) as an effective tool to pre-process surface electromyogram (sEMG) data of the human respiratory muscles. Specifically, the problem of discriminating between inspiratory, expiratory and cardiac muscle activity is addressed, which currently poses a major obstacle for the clinical use of sEMG for adaptive ventilation control. It is shown that using the investigated broadband algorithm, a clear separation of these components can be achieved. The algorithm is based on a generic framework for BSS that utilizes multiple statistical signal characteristics. Apart from a four-channel FIR structure, there are no further restrictive assumptions on the demixing system.

eess.SP↗

arXiv2019

On Approximate Nonlinear Gaussian Message Passing On Factor Graphs

Factor graphs have recently gained increasing attention as a unified framework for representing and constructing algorithms for signal processing, estimation, and control. One capability that does not seem to be well explored within the factor graph tool kit is the ability to handle deterministic nonlinear transformations, such as those occurring in nonlinear filtering and smoothing problems, using tabulated message passing rules. In this contribution, we provide general forward (filtering) and backward (smoothing) approximate Gaussian message passing rules for deterministic nonlinear transformation nodes in arbitrary factor graphs fulfilling a Markov property, based on numerical quadrature procedures for the forward pass and a Rauch-Tung-Striebel-type approximation of the backward pass. These message passing rules can be employed for deriving many algorithms for solving nonlinear problems using factor graphs, as is illustrated by the proposition of a nonlinear modified Bryson-Frazier (MBF) smoother based on the presented message passing rules.

stat.ML↗

arXiv2015

Deciding polyhedrality of spectrahedra

Spectrahedra are linear sections of the cone of positive semidefinite matrices that, as convex bodies, generalize the class of polyhedra. In this paper we investigate the problem of recognizing when a spectrahedron is polyhedral. We reprove a result of Ramana (1998) regarding the structure of spectrahedra and we devise a normal form of representations of spectrahedra. This normal form is effectively computable and leads to an algorithm for deciding polyhedrality.

math.OC↗

arXiv2011

Moment Matrices, Border Bases and Real Radical Computation

In this paper, we describe new methods to compute the radical (resp. real radical) of an ideal, assuming it complex (resp. real) variety is finite. The aim is to combine approaches for solving a system of polynomial equations with dual methods which involve moment matrices and semi-definite programming. While the border basis algorithms of [17] are efficient and numerically stable for computing complex roots, algorithms based on moment matrices [12] allow the incorporation of additional polynomials, e.g., to re- strict the computation to real roots or to eliminate multiple solutions. The proposed algorithm can be used to compute a border basis of the input ideal and, as opposed to other approaches, it can also compute the quotient structure of the (real) radical ideal directly, i.e., without prior algebraic techniques such as Gröbner bases. It thus combines the strength of existing algorithms and provides a unified treatment for the computation of border bases for the ideal, the radical ideal and the real radical ideal.

math.AG↗

arXiv2010

Dualities in Convex Algebraic Geometry

Convex algebraic geometry concerns the interplay between optimization theory and real algebraic geometry. Its objects of study include convex semialgebraic sets that arise in semidefinite programming and from sums of squares. This article compares three notions of duality that are relevant in these contexts: duality of convex bodies, duality of projective varieties, and the Karush-Kuhn-Tucker conditions derived from Lagrange duality. We show that the optimal value of a polynomial program is an algebraic function whose minimal polynomial is expressed by the hypersurface projectively dual to the constraint set. We give an exposition of recent results on the boundary structure of the convex hull of a compact variety, we contrast this to Lasserre's representation as a spectrahedral shadow, and we explore the geometric underpinnings of semidefinite programming duality.

math.OC↗

arXiv2005

An algebraic geometry approach to nonlinear parametric optimization in control

We present a method for nonlinear parametric optimization based on algebraic geometry. The problem to be studied, which arises in optimal control, is to minimize a polynomial function with parameters subject to semialgebraic constraints. The method uses Groebner bases computation in conjunction with the eigenvalue method for solving systems of polynomial equations. In this way, certain companion matrices are constructed off-line. Then, given the parameter value, an on-line algorithm is used to efficiently obtain the optimizer of the original optimization problem in real time.

math.OC↗