公开(公告)号：US20240312183A1

公开(公告)日：2024-09-19

申请号：US18276470

申请日：2022-02-10

Applicant: BeamWorks INC.

Inventor： Jae Il Kim ,  Won Hwa ,  Hye Jung Kim

IPC: G06V10/764 ,  G06V10/25 ,  G06V10/72 ,  G06V10/774

CPC classification number: G06V10/764 ,  G06V10/25 ,  G06V10/72 ,  G06V10/774 ,  G06V2201/032

Abstract: A breast ultrasound diagnosis method using weakly supervised deep-learning artificial intelligence comprises: an ultrasound image preprocessing step of generating input data including only an image region necessary for learning, by deleting personal information about a patient from a breast ultrasound image; a deep-learning step of receiving the input data, obtaining a feature map from the received input data by using a convolutional neural network (CNN) and global average pooling (GAP), and carrying out re-learning; a differential diagnosis step of determining the input data as one of normal, benign, and malignant by using the GAP, and when the input data is determined to be malignant, calculating a probability of malignancy (POM) indicating accuracy of the determination; and a contribution region determination and visualization step of backpropagating a determination result through the CNN, calculating a contribution degree of each pixel that has contributed to the determination result as a gradient and a feature value, and visualizing a contribution region that has contributed to the determination, together with the POM, on the basis of the calculated contribution degree of each pixel, wherein, in the deep-learning step, learning is carried out on the basis of verified performance of the contribution region and the POM.