US 11,989,932 B1
Systems and methods for color-coded visualization to aid in diagnosis and prognosis of Alzheimer's disease
Malek Adjouadi, Miami, FL (US); Mohammad Eslami, Miami, FL (US); and Solale Tabarestani, Miami, FL (US)
Assigned to THE FLORIDA INTERNATIONAL UNIVERSITY BOARD OF TRUSTEES, Miami, FL (US)
Filed by Malek Adjouadi, Miami, FL (US); Mohammad Eslami, Miami, FL (US); and Solale Tabarestani, Miami, FL (US)
Filed on Nov. 17, 2023, as Appl. No. 18/512,559.
Int. Cl. G06T 7/00 (2017.01); A61B 5/00 (2006.01); G06T 11/00 (2006.01); G06V 10/77 (2022.01); G06V 10/80 (2022.01); G16H 50/20 (2018.01)
CPC G06V 10/811 (2022.01) [A61B 5/4088 (2013.01); G06T 7/0016 (2013.01); G06T 11/001 (2013.01); G06V 10/7715 (2022.01); G16H 50/20 (2018.01); G06T 2207/10024 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/10104 (2013.01); G06T 2207/30016 (2013.01); G06T 2207/30204 (2013.01); G06V 2201/03 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A system for color-coded visualization to aid in diagnosis and prognosis of Alzheimer's disease (AD), the system comprising:
a processor; and
a machine-readable medium in operable communication with the processor and having instructions stored thereon that, when executed by the processor, perform the following steps:
a) receiving multimodal input data about a subject, the multimodal input data comprising neuroimaging data of the subject;
b) utilizing a machine learning (ML) model on the multimodal input data to perform intra-modality feature extraction and inter-modality feature extraction, followed by multimodal fusion to give fused data; and
c) utilizing the ML model to perform tensorization on the fused data to generate a visual output image, the visual output image being color-coded based on a prognosis of AD for the subject,
the ML model comprising:
a first part comprising a first plurality of layers configured to perform the intra-modality feature extraction, the inter-modality feature extraction, and the multimodal fusion; and
a second part comprising a second plurality of layers configured to perform the tensorization on the fused data to generate the visual output image.