Deep Learning (DL) techniques have been used in medical imaging to improve quality and generate new images from reduced medical imaging acquisitions. They have implied a true revolution in the medical field, with myriads of new applications rising every year. We cannot deny the excellent outcomes these applications produce, with high-quality images and compelling results. However, when applied to medical images, most of the validation of these techniques has been done visually and/or qualitatively, not necessarily adequately assessed in clinical studies. There is a key question that may affect many of the DL applications in medical studies: 

“Are we losing relevant quantitative clinical information when generating high-quality images with artificial intelligence techniques?”

The question is related to the validity of traditional quality measures such as the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) or Normalized Root Mean Squared Error (NRMSE), commonly used in medical image analysis. Strictly speaking, it is not enough that the images look alike as they must also preserve all the relevant clinical information.

In this challenge, we will try to answer the question about the validity of reconstructed images in a real clinical study. To that end, we will focus on a real diffusion magnetic resonance imaging (dMRI) study on migraine. Data were acquired for a clinical study carried out in a local hospital (Hospital Clinico Universitario, Valladolid, Spain) by a group of neurologists. 
We have selected migraine considering that it is a pathology in which differences between groups are subtle and very dependent on the number of gradient directions. 

The angular resolution (i.e. the parameter that is proportional to the reciprocal number of diffusion gradient directions) is one of the crucial design parameters used in a diffusion MRI experiment. Depending on the method employed to represent the diffusion MRI signal, a different number of gradient directions are required to fit the basis starting from six gradients in diffusion tensor imaging (DTI) to several dozens or hundreds in High Angular Resolution Diffusion Imaging (HARDI) techniques. In clinical studies, we are generally interested in optimizing the number of gradient directions to limit the acquisition duration and guarantee the patient's comfort during the examination. However, reducing the number of gradient directions may lead to a loss of subtle changes in angular characteristics of diffusion MRI data, which translates then to quantitative measures retrieved from a fitted model.

Recent studies have suggested that decreasing the number of gradients leads to clinical information loss, and it becomes impossible to detect differences in various types of medical conditions. A reported key factor influencing the values of diffusion/DTI descriptors is the number of diffusion gradient orientations, which (may) impact the results of their statistical comparison between clinical groups.

For the challenge, we will share two datasets:

1.- Training dataset: A fully-sampled diffusion-weighted MRI dataset acquired with 61 gradient directions at b=1000 s/mm2 coming from 60 healthy controls. The sampling scheme allows the 61 gradient directions to be easily subsampled to 21 gradients.

2.- Migraine dataset: A set of 50 Chronic migraine (CM) and 50 episodic migraine (EM) patients, all acquired in a subsampled scenario with 21 gradient directions and b=1000 s/mm2.

Organizers have the migraine dataset acquired with 61 gradient directions. A clinical study (statistical test) has been carried out to find the differences between EM and CM, with the following result:

- There are many significant differences when using 61 gradient directions.
- Most of the differences disappear when using 21 gradient directions. 

Differences found with 61 gradient directions will be considered the Golden Standard. A new statistical test will be carried out with each set of volumes submitted by the participants. Results will be compared with the golden standard.