Objective Evaluation of Three-dimensional Image Registration Algorithms – Tools for Optimization and Evaluation

2004 ◽  
Vol 43 (04) ◽  
pp. 367-370 ◽  
Author(s):  
U. Morgenstern ◽  
R. Steinmeier ◽  
F. Uhlemann
Keyword(s):  
Image Registration ◽  
Imaging Modality ◽  
Quality Measures ◽  
Objective Evaluation ◽  
Systematic Evaluation ◽  
Computer Assisted ◽  
Numerical Comparison ◽  
Volume Data ◽  
Registration Accuracy ◽  
Realistic Data

Summary Objective: The registration of medical volume data sets plays an important role when different images or modalities are used during computer-assisted surgical procedures. Nevertheless, it is often questionable how robust and accurate the underlying algorithms really are. Therefore, the goal is to foster the establishment of methods for an objective evaluation. Method: To reliably calculate the accuracy of registration algorithms, a reference transformation must be known. Due to the unknown perfect registration for real clinical data, the simulation of realistic data and successive affine transformations are employed. The simulation is based on models of the respective imaging modality where the dominant physical effects are taken into account. This gives the user full control over all simulation and transformation parameters. Finally, suitable quality measures are applied which allow a systematic evaluation of image registration accuracy by comparing the known theoretical result and the transformation calculated by the algorithm under investigation. Results: During the development of a new registration algorithm, the presented method proved to be a very valuable tool for optimization and evaluation of registration accuracy, since it allows objective numerical comparison of the calculated results. Conclusions: The presented method can be used during the development of algorithms for optimization and for quantitative comparison of different registration schemes. The respective software tool can automatically generate and transform simulated but realistic data. Employing suitable numerical quality measures, an objective evaluation of registration results can be easily obtained. Still, the validity of the relatively simple models has to be verified to draw reliable conclusions with respect to real data.

scholarly journals Detection of vessel bifurcations in CT scans for automatic objective assessment of deformable image registration accuracy

2021 ◽  
Author(s):  
Guillaume Cazoulat ◽  
Brian M Anderson ◽  
Molly M McCulloch ◽  
Bastien Rigaud ◽  
Eugene J Koay ◽  
...  
Keyword(s):  
Image Registration ◽  
Objective Assessment ◽  
Deformable Image Registration ◽  
Ct Scans ◽  
Registration Accuracy ◽  
Vessel Bifurcations

A Literature Survey of Ultrasound and Computed Tomography-Based Cardiac Image Registration

2015 ◽  
Vol 74 (6) ◽  
Author(s):  
Chieng Thion Ming ◽  
Zaid Omar ◽  
Nasrul Humaimi Mahmood ◽  
Suhaini Kadiman
Keyword(s):  
Computed Tomography ◽  
Image Registration ◽  
Imaging Modality ◽  
User Involvement ◽  
Medical Practitioner ◽  
Literature Survey ◽  
Cardiac Image ◽  
Comprehensive Knowledge ◽  
Visualization Systems ◽  
Imaging Sensors

A literature survey of Ultrasound and Computed Tomography (CT) -based cardiac image registration is presented in this article. We aim to provide the reader with a preliminary discussion into the area of cardiac image registration, as well as to briefly describe the major contributions in the field and present collective and comprehensive knowledge as guidelines for beginners in this field to initiate their research. We also highlight the major challenges where CT and Ultrasound are the modalities concerned in fusion and registration tasks. Further, we found that a majority of research in medical image registration are suitably categorized based on these factors: anatomy, imaging modality and image registration methods. Our focus in the article is on Ultrasound-CT image registration of the heart, where numerous algorithms under this scope have been elaborated. Overall, multimodal cardiac image registration offers great benefit for image visualization systems during surgery. It facilitates accurate alignment of the patient’s heart imagery acquired via different imaging sensors, without extensive user involvement and interception. Through registration, the combined anatomical and functional information from multiple modalities may be derived by the medical practitioner to aid in physiological understanding, disease monitoring, clinical treatment and diagnostic purposes.

scholarly journals A Mask-guided Attention Deep Learning Model for COVID-19 Diagnosis based on an Integrated CT Scan Images Database

2022 ◽  
Author(s):  
Maede Maftouni ◽  
Bo Shen ◽  
Andrew Chung Chee Law ◽  
Niloofar Ayoobi Yazdi ◽  
Zhenyu Kong
Keyword(s):  
Deep Learning ◽  
Ct Scan ◽  
Imaging Modality ◽  
Learning Model ◽  
Classification Performance ◽  
Computer Assisted ◽  
Learning Approach ◽  
Learning Models ◽  
Task Learning ◽  
Data Efficiency

<p>The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images.</p><p>The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task baseline and state-of-the-art models, as measured by various popular metrics. In our experiment with different percentages of data from our curated dataset, the classification performance gain from this multi-task learning approach is more significant for the smaller training sizes. Furthermore, experimental results demonstrate that our method enhances the focus on the lesions, as witnessed by both</p><p>attention and attribution maps, resulting in a more interpretable model.</p>

scholarly journals Objective evaluation of hyperactivated motility in rat spermatozoa using computer-assisted sperm analysis*

2000 ◽  
Vol 15 (6) ◽  
pp. 1322-1328 ◽  
Author(s):  
Aida M. Cancel ◽  
Danelle Lobdell ◽  
Pauline Mendola ◽  
Sally D. Perreault
Keyword(s):  
Objective Evaluation ◽  
Computer Assisted ◽  
Sperm Analysis ◽  
Computer Assisted Sperm Analysis

scholarly journals US/MRI fusion with new optical tracking and marker approach for interventional procedures inside the MRI suite

2016 ◽  
Vol 2 (1) ◽  
pp. 459-462
Author(s):  
Yeshaswini Nagaraj ◽  
Bjoern Menze ◽  
Michael Friebe
Keyword(s):  
Image Registration ◽  
Imaging Modality ◽  
Tracking System ◽  
Optical Tracking ◽  
Line Of Sight ◽  
Optical Tracking System ◽  
The Us ◽  
Phantom Studies ◽  
Inside Out ◽  
Dedicated Mri

AbstractInterventional MRI in closed bore high-field systems is a challenge due to limited space and the need of dedicated MRI compatible equipment and tools. A possible solution could be to perform an ultrasound procedure for guidance of the therapy tools outside the bore, but still on the MRI patient bed. That could track and subsequently combine the superior images of MRI with the real-time features of ultrasound. Conventional optical tracking systems suffer from line of sight issues and electromagnetic tracking does not perform well in the presence of magnetic fields. Hence, to overcome these issues a new optical tracking system called inside-out tracking is used. In this approach, the camera is directly attached to the US probe and the markers are placed onto the patient to achieve the location information of the US slice. The evaluation of our novel system of framed fusion markers can easily be adapted to various imaging modalities without losing image registration. To confirm this evaluation, phantom studies with MRI and US imaging were carried out using a point-registration algorithm along with a similarity measure for fusion. In the inside-out system approach, image registration was found to yield an accuracy of upto 4 mm, depending on the imaging modality and the employed marker arrangement and with that provides an accuracy that cannot be easily achieved by combining pre-operative MRI with live ultrasound.

Multi‐atlas–based auto‐segmentation for prostatic urethra using novel prediction of deformable image registration accuracy

2020 ◽  
Vol 47 (7) ◽  
pp. 3023-3031
Author(s):  
Hisamichi Takagi ◽  
Noriyuki Kadoya ◽  
Tomohiro Kajikawa ◽  
Shohei Tanaka ◽  
Yoshiki Takayama ◽  
...  
Keyword(s):  
Image Registration ◽  
Deformable Image Registration ◽  
Prostatic Urethra ◽  
Registration Accuracy
Sign in / Sign up

Export Citation Format

Share Document