公开(公告)号：US20230197253A1

公开(公告)日：2023-06-22

申请号：US18173733

申请日：2023-02-23

Applicant: FUJIFILM Corporation

Inventor： Keigo NAKAMURA ,  Akimichi ICHINOSE

IPC: G16H30/40 ,  G06T7/00 ,  G06V10/25

CPC classification number: G16H30/40 ,  G06T7/0012 ,  G06V10/25 ,  G06T2207/10072 ,  G06T2207/20104

Abstract: A medical image processing apparatus includes at least one processor, in which the processor is configured to: acquire a result of detecting at least one region of interest included in a medical image, which is detected by analyzing the medical image; specify a region of attention that a user has paid attention to in the medical image; specify a non-attention region of interest, which is a region of interest having a structure different from a structure related to the region of attention, among the regions of interest; and display a result of specifying the non-attention region of interest on a display.

公开(公告)号：US20230070906A1

公开(公告)日：2023-03-09

申请号：US17897195

申请日：2022-08-28

Applicant: FUJIFILM Corporation

Inventor： Akimichi ICHINOSE

IPC: G06N20/00 ,  G06F40/30 ,  G06F40/20

Abstract: The processor divides a sentence into predetermined units, determines at least one of an attribute, a factuality, or a relationship of each unit, decides a weight for each unit according to a result of the determination, and derives a feature amount of each unit by using a derivation model constructed by machine learning and derive a feature amount of the sentence by performing weighting calculation on the feature amount of each unit based on the weight.

公开(公告)号：US20210319210A1

公开(公告)日：2021-10-14

申请号：US17356498

申请日：2021-06-23

Applicant: FUJIFILM Corporation

Inventor： Akimichi ICHINOSE ,  Yoshiro KITAMURA

IPC: G06K9/00 ,  G06T7/11 ,  G06T7/143 ,  G06T7/168 ,  G06T7/246 ,  G06K9/62 ,  G06T7/149

Abstract: A region specification apparatus, a region specification method, and a region specification program efficiently specify any object included in an input image. A convolutional neural network of an object specification unit generates a convolutional feature map from an input image (S0). A first discriminator selects an anchor based on a similarity in shape and size to a ground truth box including an object candidate from among a plurality of anchors having various shapes and various sizes. The first discriminator specifies an object candidate region in the input image based on the selected anchor.