Frank Niemeyer

Frank Niemeyer
OSORA Medical Fracture Analytics

Dr. biol. hum. Dipl.-Inf.

About

60
Publications
6,560
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
514
Citations
Introduction
Current main research interest: Deep learning for biomedical image analysis (classification, landmark localization, segmentation on X-ray, CT and MRI data)
Additional affiliations
April 2021 - present
OSORA Medical Fracture Analytics
Position
  • Co-Founder & CTO
Description
  • OSORA is working on transfering the Ulm bone healing model into a software product for a wide range of possible applications (med tech, education & research, decision support for clinicians, ...)
September 2013 - March 2021
Ulm University
Position
  • PostDoc Position
Description
  • Deep learning approaches for biomedical image analysis (detection, localization, classification, generation); machine learning methods for automatic parameter estimation for complex biomedical numerical models
December 2012 - September 2016
Ulm University
Position
  • PostDoc Position
Description
  • Development & optimization of a novel spinal fusion device via simulation; industry projects; advancing the fracture healing model; simulating implant resorption; HPC cluster administration
Education
September 2000 - August 2007
Ulm University
Field of study
  • Computer Science

Publications

Publications (60)
Article
Objectives: Although magnetic resonance imaging-based formalized grading schemes for intervertebral disc degeneration offer improved reproducibility compared with purely subjective ratings, their intrarater and interrater reliability are not nearly good enough to be able to detect small to medium effects in clinical longitudinal studies. The aim o...
Conference Paper
The present work deals with a specific step of a fracture healing simulation (see e.g. [1], [2]). In this step, the given concentration distribution of a biological tissue, such as bone, is smoothed (i.e. smeared over the three-dimensional healing domain). The current implementa-tion of this smoothing operation in the form of a matrix-vector multip...
Article
We trained a deep neural network for the three-dimensional estimation of the direction of the three anatomical axes (cranio-caudal, anteroposterior and laterolateral) of individual vertebrae from a single sagittal radiographic image acquired from an approximately lateral direction with large deviations from a perfect alignment up to 60 degrees. To...
Article
Full-text available
Purpose We present an automated method for extracting anatomical parameters from biplanar radiographs of the spine, which is able to deal with a wide scenario of conditions, including sagittal and coronal deformities, degenerative phenomena as well as images acquired with different fields of view. Methods The location of 78 landmarks (end plate ce...
Article
Full-text available
In silico trials recently emerged as a disruptive technology, which may reduce the costs related to the development and marketing approval of novel medical technologies, as well as shortening their time-to-market. In these trials, virtual patients are recruited from a large database and their response to the therapy, such as the implantation of a m...
Article
Modic changes (MC) and endplate abnormalities (EA) have been shown to impact preoperative symptoms and outcomes following spinal surgery. However, little is known about how these phenotypes impact cervical alignment. This study aimed to evaluate the impact that these phenotypes have on preoperative, postoperative, and changes in cervical alignment...
Preprint
Full-text available
Purpose. Imaging studies about the relevance of muscles in spinal disorders, and sarcopenia in general, require the segmentation of the muscles in the images which is very labour-intensive if performed manually and poses a practical limit to the number of investigated subjects. This study aimed at developing a deep learning-based tool able to fully...
Conference Paper
Currently, fracture-healing simulations are primarily applied to diaphyseal fractures. In order to simulate metaphyseal fracture healing, we extended the previously developed and tested computational model for diaphyseal fractures [1] to metaphyseal fractures [2]. Up to now, the investigations were analyzed in 2D rotational symmetric geometries. Re...
Article
Full-text available
Purpose To clarify the relative influence of age, sex, disc height loss and T1 slope on upper (Occiput-C2) and lower cervical lordosis (C2–C7). Methods Standing lateral cervical radiographs of 865 adult subjects were evaluated. The presence and severity of disc height loss from C2/C3 to C6/C7 (a total of 4325 discs) were assessed using a validated...
Article
Full-text available
Many recent studies have focused on the functional and clinical importance of cervical lordosis. However, there is little accurate knowledge of the anatomical parameters that constitute cervical lordosis (i.e., the sagittal wedging angles of intervertebral discs and vertebral bodies) and their associations with age and sex. Standing lateral cervica...
Article
Full-text available
PurposeWe investigated the flexion–extension range of motion and centre of rotation of lumbar motion segments in a large population of 602 patients (3612 levels), and the associations between lumbar motion and other parameters such as sex, age and intervertebral disc degeneration.Methods Lumbar radiographs in flexion–extension of 602 patients suffe...
Article
This study describes a novel, combined Modic changes (MC) and structural endplate abnormality phenotype of the cervical spine, which we have termed the Modic‐Endplate‐Complex (MEC), and its association with preoperative symptoms and outcomes in anterior cervical discectomy and fusion (ACDF) patients. This was a retrospective study of prospectively...
Article
Full-text available
Simulating diaphyseal fracture healing via numerical models has been investigated for a long time. It is apparent from in vivo studies that metaphyseal fracture healing should follow similar biomechanical rules although the speed and healing pattern might differ. To investigate this hypothesis, a pre-existing, well-established diaphyseal fracture h...
Article
Full-text available
Purpose The aims of this study were (1) to determine the prevalence of radiographic cervical disc degeneration in a large population of patients aged from 18 to 97 years; (2) to investigate individually the prevalence and distribution of height loss, osteophyte formation, endplate sclerosis and spondylolisthesis; and (3) to describe the patterns of...
Article
Full-text available
Study Design Retrospective cohort study. Objectives This study aimed to address the prevalence, distribution, and clinical significance of cervical high-intensity zones (HIZs) on magnetic resonance imaging (MRI) with respect to pain and other patient-reported outcomes in the setting of patients that will undergo an anterior cervical discectomy and...
Article
Degenerative spine imaging findings have been extensively studied in the lumbar spine and are associated with pain and adverse clinical outcomes after surgery. However, few studies have investigated the significance of these imaging “phenotypes” in the cervical spine. Patients with degenerative cervical spine pathology undergoing ACDF from 2008‐201...
Article
Study design: Retrospective cohort OBJECTIVE.: To determine how type, location, and size of endplate lesions on magnetic resonance imaging (MRI) may be associated with symptomatology and clinical outcomes after ACDF. Summary of background data: Structural endplate abnormalities are important phenomena that remain understudied in the cervical spi...
Conference Paper
Currently, fracture-healing simulations are primarily applied to diaphyseal fractures. In order to simulate metaphyseal fracture healing, we extend the previously developed and tested computational model by Simon et al. [1]. As this model is a continuum (i.e. organ-level) model of fracture healing, the complex trabecular structure is not required b...
Article
The motion of the costovertebral joint (CVJ) is governed by the material properties and its morphology. The goal of this numerical study was to identify the material and morphology parameters with the greatest influence on the motion of the CVJ. A fully parametric finite element model of the anatomy and material properties of the CVJ was developed....
Article
The kinematics of a spinal motion segment is determined by the material properties of the soft-tissue and the morphology. The material properties can vary within subjects and between vertebral levels, leading to a wide possible range of motion of a spinal segment independently on its morphology. The goal of this numerical study was to identify the...
Article
Full-text available
Background Knee braces are prescribed by physicians to protect the knee from various loading conditions during sports or after surgery, even though the effect of bracing for various loading scenarios remains unclear. Purpose To extensively investigate whether bracing protects the knee against impacts from the lateral, medial, anterior, or posterio...
Article
Full-text available
Purpose: Adolescent idiopathic scoliosis (AIS) is a three-dimensional deformity of the spine which exhibits morphological changes during growth. The goal of this study was to identify morphological patterns that could be explained by different loading patterns for AIS. Methods: Computed tomography data of 21 patients with diagnosed AIS and 48 pa...
Article
We present a novel numerical model of the fracture-healing process using interface-capturing techniques, a well-known approach from fields like fluid dynamics, to describe tissue growth. One advantage of this method is its direct connection to experimentally observable parameters, including tissue-growth velocities. In our model, osteogenesis, chon...
Article
Full-text available
PurposeThe mechanical link between the pleural physiology and the development of scoliosis is still unresolved. The intrapleural pressure (IPP) which is distributed across the inner chest wall has yet been widely neglected in etiology debates. With this study, we attempted to investigate the mechanical influence of the IPP distribution on the shape...
Article
Full-text available
Distraction osteogenesis is an effective method for generating large amounts of bone in situ for treating pathologies such as large bone defects or skeletal malformations, for instance leg-length discrepancies. While an optimized distraction procedure might have the potential to reduce the rate of complications significantly, our knowledge of the u...
Data
Differentiation rules. Fuzzy logic membership functions and linguistic rules controlling tissue differentiation. (PDF)
Data
Mathematical notation. (PDF)
Conference Paper
MRI provides the most informative imaging data for assessing the degree of degeneration of intervertebral discs. Pfirrmann’s evaluation scheme uses T2-weighted sagittal sections to categorize a disc’s level of degeneration depending on signal intensity, homogeneity and disc height. Comparing the gradings of different raters in a meaningful way is h...
Article
the app is available at http://ultrasound-ar.com/ Purpose: Virtual and augmented reality are upcoming new technical features used in the entertainment industry. Here the first theoretic preparations towards implementing an augmented reality based ultrasound training are presented.3D objects in a wavefront file format should be visualized like on a...
Thesis
Full-text available
Superficially, bone seems to be a static part of the human body. In reality, bone tissue constantly adapts itself to an ever changing mechanical environment. This work explores mathematical models approximating the complex biological processes that provide bone with its unique regenerative capabilities. We apply numerical simulations implementing t...
Article
Full-text available
Numerical models of secondary fracture healing are based on mechanoregulatory algorithms that use distortional strain alone or in combination with either dilatational strain or fluid velocity as determining stimuli for tissue differentiation and development. Comparison of these algorithms has previously suggested that healing processes under torsio...
Conference Paper
Creating finite element models of the spine is a tedious task. Building a working model of the full spine with its complex geometry from the ground up based on imaging data can easily take years. This elaborate approach yields models of high geometric fidelity that match one particular anatomy and are therefore in a sense “patient-specific.” Whi...
Conference Paper
Let’s face it: The quality of most custom-written software for research purposes leaves a lot to be desired. Approaching deadlines encourage a “quick-and-dirty” style of development, which at first does not seem to be a big deal, as most software for research is intended to be short-lived and to be replaced by entirely new and different implemen...
Article
Typical FE models of the human lumbar spine consider a single, fixed geometry. Such models cannot account for potential effects of the natural variability of the spine's geometry. In this study, we performed a probabilistic uncertainty and sensitivity analysis of a fully parameterized, geometrically simplified model of the L3–L4 segment. We examine...
Article
Full-text available
Typical FE models of the human lumbar spine consider a single, fixed geometry. Such models cannot account for potential effects of the natural variability of the spine's geometry. In this study, we performed a probabilistic uncertainty and sensitivity analysis of a fully parameterized, geometrically simplified model of the L3-L4 segment. We examine...
Article
Bone transport is a well accepted technique for the treatment of large bony defects. This process is mechanically driven, where mechanical forces play a central role in the development of tissues within the distracted gap. One of the most important mechanical factors that conditions the success of bone regeneration during distraction osteogenesis i...
Article
The rat is of increasing importance for experimental studies on fracture healing. The healing outcome of long bone fractures is strongly influenced by mechanical factors, such as the interfragmentary movement. This movement depends on the stability of the fracture fixation and the musculoskeletal loads. However, little is known about these loads in...
Article
The healing outcome of long bone fractures is strongly influenced by the interfragmentary movement of the bone fragments. This depends on the fixation stability, the optimum value of which is still not known. The aim of this study was to simulate a patient-specific human healing process using a numerical algorithm and to retrospectively analyse the...
Article
The healing process for bone fractures is sensitive to mechanical stability and blood supply at the fracture site. Most currently available mechanobiological algorithms of bone healing are based solely on mechanical stimuli, while the explicit analysis of revascularization and its influences on the healing process have not been thoroughly investiga...
Conference Paper
Full-text available
We present a method that allows rendering finite element models in a semi-transparent way by adapting well known methods from the field of computer graphics like ray tracing/casting. The energy of virtual X-rays travelling through the FE mesh gets partially absorbed depending on scalar values defined inside each element, like e.g. density or concen...
Conference Paper
The objective of this paper is to present an optimization algorithm for the optimization of the axial stiness of a fixator used in fracture healing. To this end, numerical simulations of fracture healing with 2D and 3D models are used. The simulation is extended by a tool to observe the bridging of two bone fragments, called bridge detector. Using...

Network

Cited By

Projects

Projects (9)
Project
http://www.biostec.org/DeepMSK.aspx For this Special Session at BIOSTEC 2020 (La Valletta, February 24-26, 2020), we invite papers about Deep Learning in the field of musculoskeletal radiology, including but not limited to automated diagnosis, detection and localization of lesions or anatomical landmarks, segmentation, scoring features such as degenerative phenotypes or fractures, as well as ethical issues.
Archived project
Automatically estimate the stiffness of a bone fracture from given CT data using FEA