Student Projects

Pre-clinical mechanical evaluation of a novel spinal implant

Lower back pain is one of the most prevalent health issues in Switzerland, with severe socio-economic consequences and a leading cause of reduced work performance. Approximately 20% of spinal fusion surgeries performed using off-the-shelf implants result in the surgical outcome being compromised post-operatively, often requiring one or more revision surgeries to address the associated pain. The Laboratory of Orthopedic Technology has recently developed a novel spinal implant using topology optimization, which is currently undergoing a feasibility study for clinical applications. We are seeking a master’s student who is passionate about medical devices and mechanical design and testing to join us for a master thesis. In this role, you will gain insight into the spinal surgery process, receive input from surgeons, and contribute to the mechanical testing of the implant on human cadaveric spine. Objectives: • Perform the CT scan on human cadaveric vertebrae • Evaluate the influence of implant placement/location variability • Mechanical testing on the implant and failure mode analysis • Develop surgical tools if needed • Write related SOPs and testing report Your Profile: • Hands-on and detail-oriented, need to work with human cadaveric bones. • Experience with SolidWorks or Fusion 360, as well as Python or Matlab. • Need to have Hepatitis B Vaccine to be able to work in BSL 2 level labs

Keywords

implant, medical device, mechanical testing, clinical application

Labels

Master Thesis

Contact Details

More information

Open this project...

Published since: 2025-06-10 , Earliest start: 2025-06-23 , Latest end: 2026-01-30

Organization Bone Pathologies and Treatment

Hosts Du Xiaoyu

Topics Medical and Health Sciences

Time-series Pose Prediction of Knee Joint for Next Frames Estimation using deep learning

Accurately estimating knee joint kinematics is crucial for understanding joint motion and diagnosing conditions like osteoarthritis. Traditional methods for pose estimation often rely on manual intervention, which is time-consuming and prone to human error. At the Laboratory of Movement Biomechanics, we have developed a pose refiner based on an iterative optimization approach, commonly employed in 2D-3D image registration (2D-3D pose estimation). However, this method requires an initial pose estimate for the refiner to function effectively. This project proposes the use of deep learning techniques to predict the next-frame pose of the knee joint based on previous sequences of kinematic data. By leveraging transformer-based models and advanced time series analysis, the goal is to provide robust, automatic prediction of future poses, streamlining knee kinematics analysis with increased accuracy and efficiency.

Keywords

TSA (Time Series Analysis); Joint Kinematics; Deep Learning; Pose Estimation; Transformer.

Labels

Semester Project , Master Thesis

Description

Goal

Contact Details

More information

Open this project...

Published since: 2025-05-20 , Earliest start: 2025-06-16

Organization Taylor Group / Dual-Plane Fluoroscope

Hosts Wang Jinhao

Topics Medical and Health Sciences , Information, Computing and Communication Sciences

Automated kinematic estimation of the knee joint using deep learning

Knee kinematics is critical for diagnosing pathologies such as osteoarthritis and providing guidance for implant design. Estimating knee kinematics requires aligning a model with a target X-ray image. This estimation process, often implemented by human labor, can be very time-consuming. This research aims to use a deep learning network to estimate the pose (kinematics) from X-ray images, partially replacing manual labor. Such a network should predict a pose from a current fluoroscopic image. By the end of this project, a robust pipeline should be completed, achieving baseline performance to provide convincing pose estimation for images from different modalities (single-plane system & dual-plane system; natural bone model & implant model).

Keywords

Deep learning;X-ray; Computational method; Medical image; Image registration; Rendering.

Labels

Semester Project , Internship , Master Thesis , ETH Zurich (ETHZ)

Description

Goal

Contact Details

More information

Open this project...

Published since: 2025-05-20 , Earliest start: 2025-06-17

Applications limited to ETH Zurich

Organization Taylor Group / Dual-Plane Fluoroscope

Hosts Wang Jinhao

Topics Medical and Health Sciences , Information, Computing and Communication Sciences , Engineering and Technology

Automated 2D3D image registration of dual-plane fluoroscopic image using deep learning enhancement

Understanding knee kinematics is a key requirement for understanding the processes occurring during injury or pathology as well as their remedies. Compared to optical systems, x-ray fluoroscopy directly measures the joint kinematics without soft-tissue artifacts and is thus the method of choice whenever such high performance is required. To extract the 3D knee kinematics the rendering of each bone (3D geometry acquired independently by e.g. CT) is matched to the x-ray image in a process called 2D-3D pose estimation or 'image registration'. Current manual registration methods are time-consuming, expensive, and prone to operator bias. For example, a 10-second trial measurement acquired at 30 Hz consists of about 300 images and takes an experienced operator about 1500 minutes to match manually. Since most studies often consist of thousands of images, an automated way of performing image registration to assist or replace manual alignment becomes crucial. With the help of modern deep networks, we wish to extend the current bolder of traditional 2D3D image registration to reach higher accuracy and robustness.

Keywords

Deep learning, Fluoroscopy, X-ray, CT, Image registration, Optimization, Rendering.

Labels

Semester Project , Master Thesis , ETH Zurich (ETHZ)

Description

In this project, we are going to investigate traditional 2d3d pose estimation (image registration) method and its possible improvements. Traditional 2d3d pose estimation often relies on a process called ‘iterative model optimization’ (Figure 1) where we utilize the power of rendering with accurate 3d models obtained from segmentation or manufacturer. A similarity metric (e.g. Normalized Cross Correlation) could compare the difference between our target X-ray image and our rendered image. Then, based on the value calculated by that metric, an optimizer (either derivative-based or derivative-free) could gradually adjust the position of our 3d model in rendering until the metric is maximized. Such process requires a starting pose (or initial pose) to begin with, and the final converged position of our anatomy model is our estimated pose for the knee joint. So far, the existing program in LMB enable a volumetric, differentiable renderer in iterative model optimization pipeline where both gradient-based and non-gradient-based optimizers are available in our 2d3d pose estimation algorithm. Yet, this algorithm is not fully automated as the initial pose still requires strategy to determine. Moreover, there are plenty of rooms left for this program to improve its final estimation accuracy and robustness. Since rendering bone models has speed limit depending on GPU type, we intend to accelerate this process by advanced optimization strategy. The original X-ray image from fluoroscopic device also suffers from pixel noise such vignetting, artefacts, skin markers, and distortion. A box of image processing tools should be examined and used to enhance the pose estimation accuracy. Most importantly, since the differentiable renderer is novel and has a high compatibility with Pytorch3d frame, we are going to empower the traditional 2D3D image registration algorithm with extra attentions (such as segmentation, kinematics prediction, and deep learning pose estimation). The result will make break through and contribution to traditional medical image analysis.

Goal

Contact Details

More information

Open this project...

Published since: 2025-05-20 , Earliest start: 2024-06-17

Organization Taylor Group / Dual-Plane Fluoroscope

Hosts Wang Jinhao

Topics Medical and Health Sciences , Information, Computing and Communication Sciences , Engineering and Technology

Design and development of a novel printing approach

3D printing has revolutionized the way objects are designed and fabricated across a wide range of industries—from aerospace and automotive to healthcare and consumer products. It enables rapid prototyping, complex geometries, customized solutions, and recently bioprinting of living tissues that are difficult or impossible to achieve with traditional manufacturing methods. Every 3D printing method has certain drawbacks, often related to resolution, material compatibility, speed, or scalability. The ongoing search for new approaches aims to overcome these challenges and expand the potential of the technology. We have developed and demonstrated a proof of concept for a novel printing approach, and are now seeking to advance it into a fully functional prototype.

Labels

Semester Project , Master Thesis

Description

Goal

Contact Details

More information

Open this project...

Published since: 2025-05-15 , Earliest start: 2025-06-01 , Latest end: 2025-12-31

Organization Zenobi-Wong Group / Tissue Engineering and Biofabrication

Hosts Janiak Jakub

Topics Engineering and Technology

Tissue Engineering Approaches to Study Tendon Injury, Disease, and Therapy

Join a dynamic research team at the intersection of biomechanics, tissue engineering, and cell biology. This project offers hands-on training in state-of-the-art methods to investigate how tendon tissue responds to injury, disease processes, and mechanical stimulation during exercise-based therapy.

Keywords

Tendon biology, tissue engineering, mechanobiology, cell culture, microscopy, regenerative medicine, exercise therapy, inflammation, ECM remodeling

Labels

Master Thesis

Description

Goal

Contact Details

More information

Open this project...

Published since: 2025-04-15 , Earliest start: 2025-05-01 , Latest end: 2026-12-31

Organization Snedeker Group / Laboratory for Orthopaedic Biomechanics

Hosts Snedeker Jess, Prof.

Topics Engineering and Technology

Exploring the Mechanoregulation of Bone Regeneration

In over 100 years, the remarkable ability of bone to adapt to its mechanical environment has been a source of scientific fascination. Bone regeneration has been shown to be highly dependent on the mechanical environment at the fracture site. It has been demonstrated that mechanical stimuli can either accelerate or impede regeneration. Despite the fundamental importance of the mechanical environment in influencing bone regeneration, the molecular mechanisms underlying this phenomenon are complex and poorly understood.

Keywords

Bone, Mechanobiology, Spatial transcriptomics, Gene expression, Finite element modelling, Image processing

Labels

Semester Project , Internship , Bachelor Thesis , Master Thesis

Description

Goal

Contact Details

More information

Open this project...

Published since: 2025-03-23 , Earliest start: 2024-11-01 , Latest end: 2025-08-31

Organization Müller Group / Laboratory for Bone Biomechanics

Hosts Mathavan Neashan

Topics Medical and Health Sciences , Engineering and Technology

Exploring the 3D Mineralization Behavior in Material-Induced Osteoinduction Through a Multiscale Micro-CT Imaging Approach

The project aims at investigating material-induced osteoinduction using the available mouse model of orthotopic or ectopic bone graft substitute (BGS) application. Through the 3D-3D registration of ex vivo and in vivo multiscale micro-CT images, crucial 3D mineralization behavior of the BGS can be investigated.

Keywords

Femur, Bone Graft Substitute, Critical Size Defect, Osteoinduction, in vivo, micro-CT, 3D-3D Image Registration, Image Analysis, Image Processing, Python, Computational

Labels

Semester Project , Bachelor Thesis , Master Thesis

Description

Bone defects that do not heal spontaneously despite surgical stabilization and require further surgical intervention are termed critical sized defects (CSD). They pose dramatic consequences to a person’s well-being and life expectancy due to their impact on the skeletal system’s integrity. Bone graft substitutes (BGS) present a treatment approach by enhancing and facilitating the natural healing capacity of the bone tissue using their osteoconductive and osteoinductive potential and filling up the physical space of lost bone for mechanical support. The key property of a BGS in treatment of a large bone defect is osteoinduction. Physiological processes in bone usually happen on different spatial scales, spanning from the whole organ, to tissue, to cellular and even to the molecular level. Therefore, an ideal imaging setup to **unravel the underlying mechanisms of material-induced osteoinduction** would require a **multiscale approach** to connect orang and tissue level processes with the cellular and subcellular scale. Micro-CT can be considered the gold standard in hierarchical 3D imaging of bone structure and function and allows a non-destructive _ex vivo_ and _in vivo_ image acquisition. **Time-lapsed _in vivo_ micro-CT images** can reveal distinct information on the longitudinal development of implant calcification or resorption. However, its resolution is relatively low and certain details can not be detected. _Ex vivo_ micro-CT on the other hand allows scans of higher resolution and therefore complements the _in vivo_ micro-CT well. The 3D-3D registration of high-resolution _ex vivo_ and low-resolution _in vivo_ micro-CT images generates a multiscale micro-CT imaging approach. Advanced image analysis methods can help identify newly formed bone and generally distinguish bone and the BGS. By combined analysis of multiscale micro-CT measurements of murine femur samples with implanted ectopic or orthotopic BGS, critical 3D mineralization behavior in material-induced osteoinduction can be investigated.

Goal

Contact Details

More information

Open this project...

Published since: 2025-03-11 , Earliest start: 2025-04-01 , Latest end: 2026-01-31

Organization Müller Group / Laboratory for Bone Biomechanics

Hosts Lindenmann Sara

Topics Medical and Health Sciences , Engineering and Technology