MIAS-IRC
Search
Topics
  Create an account Home  ·  Topics  ·  Your Account  ·  Top 10  ·  Archive  ·  Feedback           XML  
Modules
  • Home
  • AutoTheme
  • AutoTheme
  • AvantGo
  • Content
  • Downloads
  • Feedback
  • Search
  • Statistics
  • Stories Archive
  • Top
  • Topics
  • Your Account

  • Who's Online
    There are currently, 12 guest(s) and 0 member(s) that are online.

    You are Anonymous user. You can register for free by clicking here

    Languages
    Select Interface Language:


    MARS - Models of Appearance, Registration and Segmentation: Technical Notes

    Search on This Topic:   
    [ Go to Home | Select a New Topic ]

    Oxford Presentation on Appearance Model and Non-rigid Registration Evaluation
    Technical Notes As anticipated, there has been little or no activity lately. However, I presented some of the latest development at Oxford last week. The presentation slides are finally online (in a variety of formats). Regarding progress, I handed in a draft of my thesis at the end of August. I am still waiting for feedback.
    Posted by admin on Wednesday, October 04 @ 02:42:00 BST (5297 reads)
    Read More... | 232 comments | Score: 0



    Presentations, Thesis and Halting of Technical Progress
    Technical Notes [This will be personal item rather than a technical one] am attending Medical Image Understanding and Analysis 2006, which begins later today. I will present my work tomorrow. There is also the possibility of a meeting at UCL next week -- one whose aim is to unify registration, modelling, and segmentation. It is part of a long on-going effort which occupies the entire inter-disciplinary research collaboration (IRC). I write up my thesis nowadays, so it is unlikely that I will make any technical progress in the next few months. I will try to post technical items as soon as something interesting emerges.
    Posted by admin on Tuesday, July 04 @ 05:52:50 BST (5646 reads)
    Read More... | 237 comments | Score: 0



    NRR Assessment: 3-D Extension and Other News
    Technical Notes
    An appearance model built from37 brains
    ±2.5 standards deviations shown
    UR assessment framework, which can either evaluate non-rigid registration (NRR) algorithms or evaluate models of shape and intensity (appearance models), has been extended to 3-D. It requires no ground truth. Among other recent development, perhaps the most notable one is that which involves running some these algorithms the in 3-D to obtain encouraging, bug-free output. Due to the immense scale of this problem, true assessment of NRR in 3-D requires clusters, where the program can be easily deployed.

    In other news, we are expecting to have our work included in an issue of IEEE Transactions in Medical Imaging. The initial reviews were very positive and we are running further experiments to alleviate any doubts.
    Posted by admin on Sunday, May 07 @ 07:51:58 BST (5800 reads)
    Read More... | 236 comments | Score: 0



    Registration Benchmark
    Technical Notes E may soon start working in collaboration with the MIAS-Grid, as well as the IRC. MIAS-Grid, where MIAS stands for Medical Images and Signals, is a project which ultimately produces an e-Science workbench for medical image analysis. To demonstrate the utility of the system, a series of use-cases is required and our code might be among these.

    Essentially, the Grid might have our registration assessment algorithms re-created. It will then compartmentale the processes and carry out some analysis in a transparent way that has robust, well-understood interfaces (e.g. XML-RPC). Subsequently, these processes can be embedded as workflows within the workbench, which might involve autonomous and powerful computers. Algorithms can easily be exchanged, thus enabling benchmarks (comparisons) to be rapidly conducted. The idea is reminiscent of the principles and rationale behind the Strategy Patten in OO programming.


    Image registration assessment: the benchmark architecture
    Click image for full-sized version

    We are not too certain about the future of this initiative and, in particular, some of the technicalities. Yet, we would feel privileged to have an opportunity to work on such modern computing architectures. Our particular set of binaries can directly benefit from parallel workflows. In short, here is the framework that can be envisioned already:
    • We are given a set of N images
    • We have M such image sets
    • We need to build a model for each set among these M sets. That can definitely be done in parallel and there is no apparent dependency
    • We now proceed to evaluating M models and again there are no dependencies among the evaluation processes
    To add some context, registration is evaluated through the construction of appearance models. All in all, the process in question need not be serial and it can be handled merely (not entirely) in parallel. We can further refine speeds by treating sub-sets of data (chunks) and then aggregating the results, if needed.

    This would be similar to things we have done in the past, such as deploying banaries in computer clusters, invoking them via SSH, and collecting the output later. At extremity we used 30 units overnight to produce some urgently needed results.

    Posted by admin on Friday, November 04 @ 10:56:29 GMT (12858 reads)
    Read More... | 233 comments | Score: 0



    Registration Without Ground-Truth Solution - Proof of Concept/Empirical Evidence
    Technical Notes T has been rather long since an update was last posted. I am pleased to have stitched together some results from one month of computer labour. The joint and averaged results prove that our endeavour has been a smashing success.

    Below lie two graphs which illustrate our ability to evaluate registration without any ground truth, e.g. data labels which had been manually placed a priori. In other words, we can evaluate registration from just the raw images and the registration's deformation fields. The method relies on models of appearance and the shuffle distance, as previously and quite repeatedly described. The method was also shown to be correlated with results that are in fact based on the ground truth, namely the manually annotated brains from MGH. More information on these results is available in a previous write-up.


    Our measures increase monotonically as mis-registration in brain data increases (click to enlarge)

    As misregistration increases, so do the Specificity and Generalisation ability of an automatically constructed appearance model.

    The implementation we took advantage of had been written in C++, but it was derived from my earlier and equivalent implementation in MATLAB, soon to be published as an Open Source project.

    Meanwhile, I am beginning to write up my thesis, which will cover all my work rather concisely and yet at a greater level of depth.

    I recently noticed that a few dozens of people syndicate this site and/or have subscribed as members. Thank you all very much for showing interest.

    Posted by admin on Thursday, September 15 @ 18:19:20 BST (38288 reads)
    Read More... | 348 comments | Score: 0



    Registration: Tanimoto Overlap and Model-based Evaluation
    Technical Notes here is evidence to suggest that the Tanimoto formulation for overlap can be used in evaluation of registration. The figure below shows that as overlap between brain labels decreases, so does the measure as computed by Tanimoto's method. More importantly, there is a good correlation between the measure of Specificity derived by computing shuffle distance and that of overlap.
    Posted by admin on Wednesday, August 24 @ 15:48:58 BST (16445 reads)
    Read More... | 290 comments | Score: 0



    Specificity, Generalisation and Registration
    Technical Notes e currently work on heavy and extensive experiments where registration gets evaluated using models of appearance. Models of the brains are built from progressively eroded registration and from these models we derive Specificity and Generalisability (Generalisation ability) values. The figures below show that our method successfully discerns good registration from a worse one within a wide range of deformations (perturbations) of the correct solution. Lower values indicate a better registration. 4 types of shuffle distances (including the Euclidean distance) are used in the process. It is worth pointing out that our method requires no ground truth to be provided for evaluation and it was shown to be tightly-correlated to overlap-based measures, which require manual segmentation of data labels.



    See related paper:
    Carole Twining, Tim Cootes, Stephen Marsland, Vladimir Petrovic, Roy Schestowitz, and Chris Taylor. A Unified Information-Theoretic Approach to Groupwise Non-Rigid Registration and Model Building. Presented in Information Processing in Medical Images (IPMI), Lecture Notes in Computer Science, vol. 3565, pp. (PDF, BibTeX)
    Posted by admin on Thursday, August 18 @ 04:43:51 BST (298897 reads)
    Read More... | 301 comments | Score: 0



    Segmentation in Relation to Models and NRR
    Technical Notes The following observations motivate work towards the inclusion of segmentation in the process of automatic (appearance) model-building:

    • Registration aims at getting segments to overlap
    • Maybe segment one image and propagate to all others via model
    • Use segmentation to improve evaluation (similar to label)
    • Conversely, improve segmentation using dynamics of models (built using NRR)
    • Look at many images (sequence) of modelled images, project back from model to get segmentation
    • The approach gives registration, model, and segmentation directly from the raw data
    • Segmentation is arbitrary (not rational but data-driven), just like choice of landmark points
    • Create small compartmentalised models of constituent segments
    • When model is built, see variances in mean and optimise points, then re-run model-building
    • This approach can progressively improve identification of landmarks
    • Hence, better models can be built automatically
    • Expensive approach as models are built over and over again to get refined


    [From the May 31st 2005 Progress Report]

    Posted by admin on Friday, July 01 @ 12:16:59 BST (8549 reads)
    Read More... | 431 comments | Score: 0



    Survey
    There isn't content right now for this block.

    Login
    Nickname

    Password

    Don't have an account yet? You can create one. As a registered user you have some advantages like theme manager, comments configuration and post comments with your name.

    Big Story of Today
    There isn't a Biggest Story for Today, yet.

    Old Articles
    There isn't content right now for this block.

    Information

    Powered by PHP-Nuke

    Valid HTML 4.01!

    Valid CSS!



     


    All logos and trademarks in this site are property of their respective owner. The comments are property of their posters.
    You can syndicate news using RSS
    PHP-Nuke Copyright © 2005 by Francisco Burzi. This is free software, and you may redistribute it under the GPL. PHP-Nuke comes with absolutely no warranty, for details, see the license.