Ping an Technology (Shenzhen) Co., Ltd.

The United States of America, as Represented by the Secretary, Department of Health and Human Services

Alibaba (China) Co., Ltd.

Chang Gung Memorial Hospital, Linkou

Le Lu

Adam Patrick Harrison

Dakai Jin

Jinzheng Cai

Shun P Miao

Ke P Yan

Kang Zheng

Yirui Wang

Dazhou Guo

Yuankai Huo

Jiawen Yao

Youbao Tang

Ronald M Summers

Ling Zhang

Ashwin Raju

Xiansheng Hua

Yingda Xia

Weijian Li

Yuhang Lu

Zhuotun Zhu

Fakai Wang

Xiaosong Wang

Chang-Fu Kuo

Ziyue Xu

Bo Zhou

Kai Cao

Haomin Chen

Tianyi Zhao

Ke Yan

Yifan Peng

Zhiyong Lu

Fengze Liu

Daniel Joseph Mollura

Xiaoyun Zhou

A method, an apparatus, and a non-transitory computer readable medium for training an image processing model are provided. The method includes: acquiring a sample image comprising a target object to determine an object segmentation image of the target object in the sample image; constructing an object coordinate map corresponding to the object segmentation image according to the object segmentation image; and training an image processing model comprising a self-attention mechanism layer according to the sample image, the object segmentation image, and the object coordinate map.

Method, apparatus, and non-transitory computer readable medium for training image processing model

An image processing method is provided. The method includes obtaining a to-be-processed image comprising a target object, and inputting the to-be-processed image to a convolutional layer of an image processing model, to obtain an initial feature map of the to-be-processed image, wherein the image processing model comprises an encoder and a decoder; inputting the initial feature map to a self-attention mechanism layer of the encoder, and obtaining a target feature map corresponding to the initial feature map according to position information of each feature in the initial feature map and a position relationship between the each feature and other features; and inputting the target feature map to the decoder for processing, to obtain an object segmentation map and an object label of the target object in the to-be-processed image.

Image processing method, apparatus and non-transitory computer readable medium for performing image processing

A method of opportunistic screening of osteoporosis includes obtaining a plain film chest X-ray (CXR); extracting regions of interest (ROIs) from the plain film CXR; and providing individual bone mineral density (BMD) scores corresponding to the extracted ROIs and a joint BMD corresponding to the plain film CXR based on a multi-ROI model by performing: inputting the extracted ROIs into a backbone network to generate individual feature vectors, each individual feature vector corresponding to one of the extracted ROIs; concatenating the individual feature vectors into a joint feature vector; individually decoding the individual feature vectors by a shared fully connected (FC) layer to generate the individual BMDs, each individual BMD corresponding to one of the individual feature vectors; and decoding the joint feature vector by a separate FC layer to generate the joint BMD.

Method, system, and storage medium for opportunistic screening of osteoporosis using plain film chest X-ray (CXR)

A method for pancreatic mass diagnosis and patient management includes: receiving CT images of a pancreas of a patient, the pancreas of the patient including a mass; performing a segmentation process on the CT images of the pancreas and the mass to obtain a segmentation mask of the pancreas and the mass of the patient; performing a mask-to-mesh process on the segmentation mask of the pancreas and the mass of the patient to obtain a mesh model of the pancreas and the mass of the patient; performing a classification process on the mesh model of the pancreas and the mass of the patient to identify a type and a grade of a segmented pancreatic mass; and outputting updated CT images of the pancreas of the patient, the updated CT images including the segmented pancreatic mass highlighted thereon and the type and the grade of the segmented pancreatic mass annotated thereon.

Method, device, and storage medium for pancreatic mass segmentation, diagnosis, and quantitative patient management

The present disclosure provides a computer-implemented method, a device, and a storage medium. The method includes inputting an image into an attention-enhanced high-resolution network (AHRNet) to extract feature maps for generating a first feature map; generating a first probability map which is concatenated with the first feature map to form a concatenated first feature map, and updating the AHRNet using the first segmentation loss; generating a second feature map, and scaling the second feature map to form a third feature map; generating a second probability map which is concatenated with the third feature map to form a concatenated third feature map, and updating the AHRNet using the second segmentation loss; generating a fourth feature map, and scaling the fourth feature map to form a fifth feature map; updating the AHRNet using the third segmentation loss and the regional level set loss; and outputting the third probability map.

Method, device, and storage medium for weakly-supervised universal lesion segmentation with regional level set loss

Knowledge distillation method for fracture detection includes obtaining medical images including region-level labeled images, image-level diagnostic positive images, and image-level diagnostic negative images, in chest X-rays; performing a supervised pre-training process on the region-level labeled images and the image-level diagnostic negative images to train a neural network to generate pre-trained weights; and performing a semi-supervised training process on the image-level diagnostic positive images using the pre-trained weights. A teacher model is employed to produce pseudo ground-truths (GTs) on the image-level diagnostic positive images for supervising training of a student model, and the pseudo GTs are processed by an adaptive asymmetric label sharpening (AALS) operator to produce sharpened pseudo GTs to provide positive detection responses on the image-level diagnostic positive images.

Knowledge distillation with adaptive asymmetric label sharpening for semi-supervised fracture detection in chest x-rays

A preoperative survival prediction method and a computing device applying the method include constructing a data seta according to a plurality of enhanced medical images and a resection margin of each enhanced medical image and obtaining a plurality of training data sets from the constructed data set. For each training data set, multi-task prediction models are trained. A target multi-task prediction model is selected from the plurality, and a resection margin prediction value and a survival risk prediction value are obtained by predicting an enhanced medical image to be measured through the target multi-task prediction model. The multi-task prediction model more effectively captures the changes over time of the tumor in multiple stages, so as to enable a joint prediction of a resection margin prediction value and a survival risk prediction value.

Preoperative survival prediction method based on enhanced medical images and computing device using thereof

The present disclosure describes a computer-implemented method for image landmark detection. The method includes receiving an input image for the image landmark detection, generating a feature map for the input image via a convolutional neural network, initializing an initial graph based on the generated feature map, the initial graph representing initial landmarks of the input image, performing a global graph convolution of the initial graph to generate a global graph, where landmarks in the global graph move closer to target locations associated with the input image, and iteratively performing a local graph convolution of the global graph to generate a series of local graphs, where landmarks in the series of local graphs iteratively move further towards the target locations associated with the input image.

Structured landmark detection via topology-adapting deep graph learning

A method for performing a computer-aided diagnosis (CAD) includes: acquiring a medical image set; generating a three-dimensional (3D) tumor distance map corresponding to the medical image set, each voxel of the tumor distance map representing a distance from the voxel to a nearest boundary of a primary tumor present in the medical image set; and performing neural-network processing of the medical image set to generate a predicted probability map to predict presence and locations of oncology significant lymph nodes (OSLNs) in the medical image set, wherein voxels in the medical image set are stratified and processed according to the tumor distance map.

Device and method for detecting clinically important objects in medical images with distance-based decision stratification

A vertebra localization and identification method includes: receiving one or more images of vertebrae of a spine; applying a machine learning model on the one or more images to generate three-dimensional (3-D) vertebra activation maps of detected vertebra centers; performing a spine rectification process on the 3-D vertebra activation maps to convert each 3-D vertebra activation map into a corresponding one-dimensional (1-D) vertebra activation signal; performing an anatomically-constrained optimization process on each 1-D vertebra activation signal to localize and identify each vertebra center in the one or more images; and outputting the one or more images, wherein on each of the one or more outputted images, a location and an identification of each vertebra center are specified.

Method and device for vertebra localization and identification

A method of harvesting lesion annotations includes conditioning a lesion proposal generator (LPG) based on a first two-dimensional (2D) image set to obtain a conditioned LPG, including adding lesion annotations to the first 2D image set to obtain a revised first 2D image set, forming a three-dimensional (3D) composite image according to the revised first 2D image set, reducing false-positive lesion annotations from the revised first 2D image set according to the 3D composite image to obtain a second-revised first 2D image set, and feeding the second-revised first 2D image set to the LPG to obtain the conditioned LPG, and applying the conditioned LPG to a second 2D image set different than the first 2D image set to harvest lesion annotations.

Method and system for harvesting lesion annotations

An image segmentation method includes generating a CTN (contour transformer network) model for image segmentation, where generating the CTN model includes providing an annotated image, the annotated image including an annotated contour, providing a plurality of unannotated images, pairing the annotated image to each of the plurality of unannotated images to obtain a plurality of image pairs, feeding the plurality of image pairs to an image encoder to obtain a plurality of first-processed image pairs, and feeding the plurality of first-processed image pairs to a contour tuner to obtain a plurality of second-processed image pairs.

Method and system for image segmentation using a contour transformer network model

The present disclosure provides a method, a device, and a computer program product using a self-supervised anatomical embedding (SAM) method. The method includes randomly selecting a plurality of images; for each image of the plurality of images, performing random data augmentation to obtain a patch pair, generating global and local embedding tensors for each patch of the patch pair, and selecting positive pixel pairs from the patch pair and obtaining positive embedding pairs; for each positive pixel pair, computing global and local similarity maps, finding global hard negative embeddings, selecting global random negative embeddings, pooling the global hard negative embeddings and the global random negative embeddings to obtain final global negative embeddings, and finding local hard negative embeddings using the global and local similarity maps, and randomly sampling final local negative embeddings from the local hard negative embeddings; and minimizing a final info noise contrastive estimation (InfoNCE) loss.

Method, device, and computer program product for self-supervised learning of pixel-wise anatomical embeddings in medical images

A new chest X-ray database, referred to as 'ChestX-ray8', is disclosed herein, which comprises over 100,000 frontal view X-ray images of over 32,000 unique patients with the text-mined eight disease image labels (where each image can have multi-labels), from the associated radiological reports using natural language processing. We demonstrate that these commonly occurring thoracic diseases can be detected and spatially-located via a unified weakly supervised multi-label image classification and disease localization framework, which is validated using our disclosed dataset.

Method and system of building hospital-scale chest X-ray database for entity extraction and weakly-supervised classification and localization of common thorax diseases

The present disclosure describes a computer-implemented method for processing clinical three-dimensional image. The method includes training a fully supervised segmentation model using a labelled image dataset containing images for a disease at a predefined set of contrast phases or modalities, allow the segmentation model to segment images at the predefined set of contrast phases or modalities; finetuning the fully supervised segmentation model through co-heterogenous training and adversarial domain adaptation (ADA) using an unlabelled image dataset containing clinical multi-phase or multi-modality image data, to allow the segmentation model to segment images at contrast phases or modalities other than the predefined set of contrast phases or modalities; and further finetuning the fully supervised segmentation model using domain-specific pseudo labelling to identify pathological regions missed by the segmentation model.

Growing community of inventors

Bethesda, MD, United States of America

Le Lu