Challenge name<\/b><\/p>\n
The signal forecast: generalizability of diffusion signal representations<\/span><\/p>\n Purpose and relevance of the challenge<\/b><\/p>\n With this challenge we aim <\/span>to understand the current ability<\/b> of the field at <\/span>describing the signal measured in diffusion MRI<\/b>. The challenge consists of a number of signals sampled from datasets acquired in human and mice with different diffusion sequences. <\/span>Participants will be provided<\/b> with a <\/span>subsampled set<\/b> of the acquired data <\/span>and are asked to predict<\/b> the remaining – unseen – data. The acquired data includes different types of acquisition strategies, such as <\/span>multi-shell and DSI-like<\/b> pulsed gradient spin-echo (<\/span>PGSE<\/b>) [<\/span>1]<\/span>, as well as double diffusion encoding (<\/span>DDE<\/b>) [<\/span>2]<\/span> and double oscillating diffusion encoding (<\/span>DODE<\/b>) [<\/span>3]<\/span>, suitable for a large number of fit approaches. The outcome of this challenge will allow to objectively evaluate the <\/span>generalizability and appropriateness<\/b>\u00a0of current techniques.<\/span><\/p>\n <\/p>\n Datasets<\/b><\/p>\n The challenge includes <\/span>in-vivo brain<\/b> data sampled with <\/span>PGSE<\/b> in a <\/span>human<\/b> volunteer, and with <\/span>DDE \/ DODE <\/b>in<\/span> mice, ex-vivo<\/b>. You can choose which acquisition you would like to predict, and can choose any or all acquisitions strategies.<\/span><\/p>\n The two provided datasets are composed as follows:<\/span><\/p>\n Link to Data :\u00a0See Registration and Data\u00a0Access page<\/strong><\/p>\n Participation (Data given to the participants)<\/b><\/p>\n Participants will be provided with <\/span>part of the measured signals<\/b> for<\/span> 5 different tissue configurations<\/b>. Additionally, they will receive complete details of the acquisition protocol (imaging parameters, diffusion gradients properties) corresponding to the measured data, including both provided and unseen signals. Regarding multi-shell PGSE, we will provide, for each signal, 495 of the 2580 diffusion-weighted measurements, as well as 20 b = 0s\/mm<\/span>2<\/span>. Regarding DSI-like PGSE, we provide 480 of the 1240 measured points and 20 b = 0s\/mm<\/span>2<\/span>. The signals will be distributed in text format in separate files for each acquisition strategy, and do not correspond to the same voxels. For the DDE\/DODE data we will provide data from 1 DDE and 3 DODE waveforms with 4 b-values and 72 directions each (1152 \/ 2520 measurements). Each text file will contain the signal in floating format, with each column representing a different signal, and each row a measurement. The acquisitions details of each measurement can be found in a companion text file \u201c*_AcqParams.txt\u201d. <\/span>Sample scripts<\/b> to load the data and the acquisitions details <\/span>will be provided<\/b> for popular working environments (MATLAB, Python, C\/C++).<\/span><\/p>\n Submission<\/b><\/p>\n Participants are asked to submit signal predictions of the unseen data for one of the provided datasets. We ask to submit a zip file containing a textual description of the performed analysis (info.txt) together with the signal predictions (submission.txt). <\/span><\/p>\n Please include the following details in the info.txt:<\/span><\/p>\n Also, we encourage submissions of models even when suited for only part of the data, as the scope of the challenge goes well beyond the pure prediction. In such case, please mention in the info.txt\u00a0which points are disregarded by your submission.<\/span><\/p>\n The name of the zip file does not matter, however the names of the text files are critical. The predictions must be in the same format of the provided signals, with one column per signal (in the corresponding order), and one row for each measurement specified in the acquisition details of the unprovided data. Predictions of multiple acquisitions strategies (i.e. PGSE DSI-like vs PGSE multi-shell) must be submitted individually (i.e. submit each prediction independently). Although not required, we warmly welcome predictions for multiple datasets (PGSE and DDE\/DODE).<\/span><\/p>\n Example submissions files will be made available with the data.<\/p>\n Evaluation<\/b><\/p>\n Each submission will be evaluated by computing the weighted averaged mean squared error (MSE) between the provided predictions and the corresponding undisclosed data. In case of N points corresponding to a single diffusion weighting (e.g. shell), these will weighted as 1 single point. Three winners will be selected independently for PGSE (shells and grids will be scored together), DDE and DODE. <\/span><\/p>\n How to get the data<\/strong><\/p>\n Please see “Registration and Data Access” Page.<\/p>\n References<\/b><\/p>\n <\/p>\n","protected":false},"excerpt":{"rendered":" Challenge name The signal forecast: generalizability of diffusion signal representations Purpose and relevance of the challenge With this challenge we aim to understand the current ability of the field at describing the signal measured in diffusion MRI. The challenge consists … Continue reading \n
\n
\n