Abstract: A computer-implemented method for explaining an image classifier, the method comprising: receiving an initial image, the initial image having been wrongly classified by the image classifier; receiving an initial gradient of a function executed by the image classifier generated while classifying the initial image, the function being indicative of a probability for the initial image to belong to an initial class; converting the initial image into a latent vector, the latent vector being a representation of the initial image in a latent space; generating a plurality of perturbation vectors using the initial gradient of the function executed by the image classifier; combining the latent vector with each one of the plurality of perturbation vectors, thereby obtaining a plurality of modified vectors; for each one of the plurality of modified vectors, reconstructing a respective image, thereby obtaining a plurality of reconstructed images; transmitting the reconstructed images to the image classifier; for each one o

Abstract: A computer-implemented method for explaining an image classifier, the method comprising: receiving an initial image, the initial image having been wrongly classified by the image classifier; receiving an initial gradient of a function executed by the image classifier generated while classifying the initial image, the function being indicative of a probability for the initial image to belong to an initial class; converting the initial image into a latent vector, the latent vector being a representation of the initial image in a latent space; generating a plurality of perturbation vectors using the initial gradient of the function executed by the image classifier; combining the latent vector with each one of the plurality of perturbation vectors, thereby obtaining a plurality of modified vectors; for each one of the plurality of modified vectors, reconstructing a respective image, thereby obtaining a plurality of reconstructed images; transmitting the reconstructed images to the image classifier; for each one o

Abstract: A monolithic active pixel dosimeter, provided with at least a sensing cell, having at least a junction sensing element. The junction sensing element includes a sensing region, having a first type of conductivity, and a charge collecting region, contiguous to the sensing region and having a second type of conductivity. The sensing cell further includes an ohmic region at least partially overlapping and extending laterally outside the charge collecting region, and an annular insulating region, abutting the ohmic region, so as to form an insulating junction surrounding both the ohmic region and the charge collection region.

Abstract: A radiation measuring device to determine the intensity and/or the dose of the ionizing radiation during a radiological examination of a patient is provided, with the radiation measuring device (1) being arranged in the radiation path between the radiation source and the patient. The radiation measuring device (1) is provided with at least one scintillator (7).

Abstract: A monolithic active pixel dosimeter, provided with at least a sensing cell, having at least a junction sensing element. The junction sensing element includes a sensing region, having a first type of conductivity, and a charge collecting region, contiguous to the sensing region and having a second type of conductivity. The sensing cell further includes an ohmic region at least partially overlapping and extending laterally outside the charge collecting region, and an annular insulating region, abutting the ohmic region, so as to form an insulating junction surrounding both the ohmic region and the charge collection region.