Back to results
US 12,711,626 B2Granted
Methods and systems for image processing
AssigneeShanghai United Imaging Healthcare Co., Ltd.
InventorsHaihua Zhou, Na Zhang, Le Yang, Hao Chen, Wanli Teng, Yueyan Bian, Chunhua Jiang, Jing Yan
Life of this patent
Estimating the term…
Abstract
Methods and systems for image processing are provided. A target image may be acquired, wherein the target image may include a plurality of elements, an element of which may correspond to a pixel or a voxel. The target image may be decomposed into at least one layer, wherein the at least one layer may include a low frequency sub-image and a high frequency sub-image. The at least one layer may be transformed. The transformed layer may be reconstructed into a composite image.
Claims18
An image processing method implemented on at least one machine each of which has at least one processor and storage, the method comprising:
- acquiring a target image, the target image including a plurality of elements, an element corresponding to a pixel or a voxel;
- decomposing the target image into a low frequency sub-image and a high frequency sub-image;
- transforming the low frequency sub-image using a gray level transformation to obtain a transformed low frequency sub-image;
- and
- reconstructing, based on the transformed low frequency sub-image and the high frequency sub-image, a composite image, wherein
- the target image is a breast image, and the acquiring the target image comprises:
- acquiring an initial image acquired from an imaging device;
- extracting an ROI from the initial image, the ROI being a breast:
- extracting an ROI edge based on gray level variation characteristics of the ROI edge in the initial image, the ROI edge being a breast edge, comprising:
- denoising the initial image to generate a denoised image;
- enhancing gray levels of elements of the ROI edge in the denoised image to generate an enhanced image;
- and
- extracting the ROI edge from the enhanced image;
- and
- determining the target image based on the ROI and the ROI edge.
12 more elements
A system comprising:
- at least one processor, and
- instructions that, when executed by the at least one processor, cause the at least one processor to effectuate a method comprising:
- acquiring a target image, the target image including a plurality of elements, an element corresponding to a pixel or a voxel;
- decomposing the target image into a low frequency sub-image and a high frequency sub-image;
- transforming the low frequency sub-image using a gray level transformation to obtain a transformed low frequency sub-image;
- and
- reconstructing, based on the transformed low frequency sub-image and the high frequency sub-image, a composite image, wherein
- the target image is a breast image, and the acquiring the target image comprises:
- acquiring an initial image acquired from an imaging device;
- extracting an ROI from the initial image, the ROI being a breast;
- extracting an ROI edge based on gray level variation characteristics of the ROI edge in the initial image, the ROI edge being a breast edge comprising:
- denoising the initial image to generate a denoised image;
- enhancing gray levels of elements of the ROI edge in the denoised image to generate an enhanced image;
- and
- extracting the ROI edge from the enhanced image;
- and
- determining the target image based on the ROI and the ROI edge.
14 more elements
A non-transitory computer readable medium comprising executable instructions that, when executed by at least one processor, cause the at least one processor to effectuate a method comprising:
- acquiring a target image, the target image including a plurality of elements, an element corresponding to a pixel or a voxel;
- decomposing the target image into a low frequency sub-image and a high frequency sub-image;
- transforming the low frequency sub-image using a gray level transformation to obtain a transformed low frequency sub-image;
- and
- reconstructing, based on the transformed low frequency sub-image and the high frequency sub-image, a composite image, wherein
- the transforming the low frequency sub-image comprises:
- determining a characteristic curve based on the low frequency sub-image, the characteristic curve illustrating a relationship between a distance and a gray level corresponding to the distance;
- determining, based on the characteristic curve, a transformation curve, the transformation curve illustrating a relationship between the gray level nnn before transformation and a gray level after transformation, comprising:
- dividing the characteristic curve into N characteristic curve segments;
- determining, based on the N characteristic curve segments, N transformation curve segments, wherein one of the N characteristic curve segments corresponds to one of the N transformation curve segments:
- generating, based on the N transformation curve segments, the transformation curve;
- determining a gray level range of the characteristic curve, wherein the gray level range is a range within which at least one gray level is to be transformed, and the gray level range corresponds to a portion of the characteristic curve;
- and
- designating a maximum value or a minimum value of the gray level range as a gray level of a predetermined point in the characteristic curve;
- generating the transformed low frequency sub-image by updating, based on the transformation curve, gray levels of elements in a predetermined region of the low frequency sub-image.
12 more elements
Dependencies are inferred from the claim text.