System, method and computer-accessible medium for the reduction of the dosage of gd-based contrast agent in magnetic resonance imaging

Abstract

An exemplary system, method, and computer-accessible medium for generating a gadolinium (“Gd”) enhanced map(s) of a portion(s) of a patient(s), can include, for example, receiving magnetic resonance imaging (MRI) information of the portion(s), and generating the Gd enhanced map(s) based on the MRI information using a machine learning procedure(s). The Gd enhanced map(s) can be a full dosage Gd enhanced map. The full dosage Gd enhanced map(s) can be a full dosage Gd enhanced cerebral blood volume map(s). The machine learning procedure can be a convolutional neural network. The MRI information can include (i) a low-dosage Gd MRI scan(s), or (ii) a Gd-free MRI scan(s). A Gd contrast can be generated in the Gd enhanced map(s) using a T2-weighted MRI image of the portion(s).

What is claimed is: 
     
         1 . A non-transitory computer-accessible medium having stored thereon computer-executable instructions for generating at least one gadolinium (Gd) enhanced map of at least one portion of at least one patient, wherein, when a computing arrangement executes the instructions, the computing arrangement is configured to perform procedures comprising:
 receiving magnetic resonance imaging (MM) information of the at least one portion; and   generating the at least one Gd enhanced map based on the MRI information using at least one machine learning procedure.   
     
     
         2 . The computer-accessible medium of  claim 1 , wherein the at least one Gd enhanced map is a full dosage Gd enhanced map. 
     
     
         3 . The computer-accessible medium of  claim 2 , wherein the at least one full dosage Gd enhanced map is at least one full dosage Gd enhanced cerebral blood volume map. 
     
     
         4 . The computer-accessible medium of  claim 1 , wherein the at least one machine learning procedure is a convolutional neural network. 
     
     
         5 . The computer-accessible medium of  claim 1 , wherein the MRI information includes (i) at least one low-dosage Gd MM scan, or (ii) at least one Gd-free MM scan. 
     
     
         6 . The computer-accessible medium of  claim 1 , wherein the computer arrangement is further configured to generate a Gd contrast in the at least one Gd enhanced map using a T2-weighted MRI image of the at least one portion. 
     
     
         7 . The computer-accessible medium of  claim 1 , wherein the at least one machine learning procedure includes at least one attention unit and at least one residual unit. 
     
     
         8 . The computer-accessible medium of  claim 7 , wherein the at least one machine learning procedure includes at least five layers. 
     
     
         9 . The computer-accessible medium of  claim 8 , wherein the at least one machine learning procedure includes at least one contraction path configured to encode at least one high resolution image into at least one low resolution representation. 
     
     
         10 . The computer-accessible medium of  claim 9 , wherein the at least one machine learning procedure includes at least one expansion path configured to decode the at least one low resolution representation into at least one further high-resolution image. 
     
     
         11 . The computer-accessible medium of  claim 1 , wherein the at least one machine learning procedure includes at least five encoding layers and at least five decoding layers. 
     
     
         12 . The computer-accessible medium of  claim 11 , wherein each of the at least five encoding layers and each of the at least five decoding layers includes a residual connection. 
     
     
         13 . The computer-accessible medium of  claim 11 , wherein each of the at least five encoding layers and each of the at least five decoding layers include two series of 3×3 two-dimensional convolutions. 
     
     
         14 . The computer-accessible medium of  claim 13 , wherein (i) each of the at least five encoding layers is followed by a 2×2 max-pooling layer, and (ii) each of the at least five decoding layers is followed by at least one 2×2 upsampling layers. 
     
     
         15 . The computer-accessible medium of  claim 1 , wherein the at least one machine learning procedure includes max-pooling and upsampling. 
     
     
         16 . The computer-accessible medium of  claim 15 , wherein the computer arrangement is further configured to perform the max-pooling and the upsampling using a factor of 2. 
     
     
         17 . The computer-accessible medium of  claim 16 , wherein the at least one machine learning procedure includes at least one batch normalization layer and at least one rectified linear unit layer. 
     
     
         18 . The computer-accessible medium of  claim 1 , wherein the at least one portion is at least one section of a brain of the at least one patient. 
     
     
         19 . A method for generating at least one gadolinium (Gd) enhanced map of at least one portion of at least one patient, comprising:
 receiving magnetic resonance imaging (MM) information of the at least one portion; and   using a computer hardware arrangement, generating the at least one Gd enhanced map based on the MM information using at least one machine learning procedure.   
     
     
         20 . A system for generating at least one gadolinium (Gd) enhanced map of at least one portion of at least one patient, comprising:
 a computer hardware arrangement configured to:
 receive magnetic resonance imaging (MM) information of the at least one portion; and 
 generate the at least one Gd enhanced map based on the MRI information using at least one machine learning procedure.