公开(公告)号：WO1995014979A1

公开(公告)日：1995-06-01

申请号：PCT/US1994013282

申请日：1994-11-29

Applicant: ARCH DEVELOPMENT CORPORATION

Inventor： ARCH DEVELOPMENT CORPORATION ,  GIGER, Maryellen, L. ,  DOI, Kunio ,  LU, Ping ,  HUO, Zhimin

IPC: G06K09/00

CPC classification number: G06K9/00127 ,  G06T7/0012

Abstract: A method and system for automated detection and classification of masses in mammograms. This method and system include the performance of iterative, multi-level gray level thresholding (202), followed by lesion extraction (203) and feature extraction techniques (205) for classifying true masses from false-postive masses and malignant masses from benign masses. The method and system provide improvements in the detection of masses including multi-gray-level thresholding (202) of the processed images to increase sensitivity and accurate region growing and feature analysis to increase specificity. Novel improvements in the classification of masses include a cumulative edge gradient orientation histogram analysis relative to the radial angle of the pixels in question; i.e. either around the margin of the mass or within or around the mass in question. The classification of the mass leads to a likelihood malignancy.

Abstract translation: 乳房X线照片中质量自动检测和分类的方法和系统。 该方法和系统包括迭代，多级灰度阈值（202），随后的病变提取（203）和特征提取技术（205）的性能，用于从假性质量和良性肿块的恶性质量分类真实质量。 该方法和系统提供了质量检测的改进，包括处理图像的多灰度阈值（202），以增加灵敏度和准确的区域生长和特征分析以增加特异性。 质量分类的新改进包括相对于所讨论的像素的径向角的累积边缘梯度取向直方图分析; 即在质量的边缘周围或在所讨论的质量块内或周围。 质量的分类导致恶性肿瘤的可能性。

公开(公告)号：WO1996025879A1

公开(公告)日：1996-08-29

申请号：PCT/US1996002065

申请日：1996-02-23

Applicant: ARCH DEVELOPMENT CORPORATION

Inventor： ARCH DEVELOPMENT CORPORATION ,  GIGER, Maryellen, L. ,  ZHANG, Ming ,  LU, Ping

IPC: A61B06/00

CPC classification number: G06T7/0012 ,  G06T7/11 ,  G06T2207/10116 ,  G06T2207/20061 ,  G06T2207/20132 ,  G06T2207/30068 ,  G06T2207/30096

Abstract: A method and system for automated detection of lesions such as masses and/or parenchymal distortions in medical images such as mammograms. Dense regions and subcutaneous fat regions (102) within a mammogram (100) are segmented (101). A background correction may be performed within the dense regions. Hough spectrum within ROIs (104) placed in the breast region of a mammogram (100) are calculated and thresholded (106) using the intensity value eta in order to increase sensitivity and reduce the number of false-positive detections. Lesions are detected based on the thresholded Hough spectra. The thresholded Hough spectra are also used to differentiate between benign and malignant masses.

Abstract translation: 用于自动检测诸如乳房X线照相术的医学图像中的质量和/或实质变形的病变的方法和系统。 乳房X线照片（100）内的密集区域和皮下脂肪区域（102）被分割（101）。 可以在密集区域内进行背景校正。 计算放置在乳房X线照片（100）的乳房区域内的ROI（104）内的霍夫谱，并使用强度值eta阈值化（106），以增加灵敏度并减少假阳性检测的数量。 基于阈值霍夫光谱检测病变。 阈值霍夫光谱也用于区分良性和恶性肿块。

公开(公告)号：EP0757544A1

公开(公告)日：1997-02-12

申请号：EP96908470.0

申请日：1996-02-23

Applicant: ARCH DEVELOPMENT CORPORATION

Inventor： GIGER, Maryellen, L. ,  ZHANG, Ming ,  LU, Ping

IPC: A61B6 ,  G06F19 ,  G06T1 ,  G06T5 ,  G06T7

CPC classification number: G06T7/0012 ,  G06T7/11 ,  G06T2207/10116 ,  G06T2207/20061 ,  G06T2207/20132 ,  G06T2207/30068 ,  G06T2207/30096

Abstract: A method and system for automated detection of lesions such as masses and/or parenchymal distortions in medical images such as mammograms. Dense regions and subcutaneous fat regions (102) within a mammogram (100) are segmented (101). A background correction may be performed within the dense regions. Hough spectrum within ROIs (104) placed in the breast region of a mammogram (100) are calculated and thresholded (106) using the intensity value θ in order to increase sensitivity and reduce the number of false-positive detections. Lesions are detected based on the thresholded Hough spectra. The thresholded Hough spectra are also used to differentiate between benign and malignant masses.

公开(公告)号：EP0731952B1

公开(公告)日：2003-05-02

申请号：EP95903554.4

申请日：1994-11-29

Applicant: ARCH DEVELOPMENT CORPORATION

Inventor： GIGER, Maryellen, L. ,  DOI, Kunio ,  LU, Ping ,  HUO, Zhimin

IPC: G06T5/00 ,  G06K9/00 ,  G06K9/46 ,  G06K9/44 ,  G06K9/62 ,  G06K9/38 ,  G06T7/00

CPC classification number: G06K9/00127 ,  G06T7/0012

Abstract: A method and system for automated detection and classification of masses in mammograms. This method and system include the performance of iterative, multi-level gray level thresholding (202), followed by lesion extraction (203) and feature extraction techniques (205) for classifying true masses from false-postive masses and malignant masses from benign masses. The method and system provide improvements in the detection of masses including multi-gray-level thresholding (202) of the processed images to increase sensitivity and accurate region growing and feature analysis to increase specificity. Novel improvements in the classification of masses include a cumulative edge gradient orientation histogram analysis relative to the radial angle of the pixels in question; i.e. either around the margin of the mass or within or around the mass in question. The classification of the mass leads to a likelihood malignancy.

公开(公告)号：EP0757544B1

公开(公告)日：2010-12-15

申请号：EP96908470.6

申请日：1996-02-23

Applicant: Arch Development Corporation

Inventor： GIGER, Maryellen, L. ,  ZHANG, Ming ,  LU, Ping

IPC: A61B6/00 ,  G06T5/00

CPC classification number: G06T7/0012 ,  G06T7/11 ,  G06T2207/10116 ,  G06T2207/20061 ,  G06T2207/20132 ,  G06T2207/30068 ,  G06T2207/30096

Abstract: A method and system for automated detection of lesions such as masses and/or parenchymal distortions in medical images such as mammograms. Dense regions and subcutaneous fat regions (102) within a mammogram (100) are segmented (101). A background correction may be performed within the dense regions. Hough spectrum within ROIs (104) placed in the breast region of a mammogram (100) are calculated and thresholded (106) using the intensity value θ in order to increase sensitivity and reduce the number of false-positive detections. Lesions are detected based on the thresholded Hough spectra. The thresholded Hough spectra are also used to differentiate between benign and malignant masses.

Abstract translation: 用于自动检测诸如乳房X线照相术的医学图像中的质量和/或组织（实质）变形的病变的方法和系统。 乳房X线照片内的密集区域和皮下脂肪区域被分割。 可以在密集区域内执行背景校正。 使用强度值eta计算放置在乳房X线照片的乳房区域内的ROI内的霍夫谱，并使其阈值化，以增加灵敏度并减少假阳性检测的数量。 基于阈值霍夫光谱检测病变。 阈值霍夫光谱也用于区分良性和恶性肿块。

公开(公告)号：EP0731952A1

公开(公告)日：1996-09-18

申请号：EP95903554.0

申请日：1994-11-29

Applicant: ARCH DEVELOPMENT CORPORATION

Inventor： GIGER, Maryellen, L. ,  DOI, Kunio ,  LU, Ping ,  HUO, Zhimin

IPC: A61B6 ,  G06K9 ,  G06T1 ,  G06T7

CPC classification number: G06K9/00127 ,  G06T7/0012

Abstract: A method and system for automated detection and classification of masses in mammograms. This method and system include the performance of iterative, multi-level gray level thresholding (202), followed by lesion extraction (203) and feature extraction techniques (205) for classifying true masses from false-postive masses and malignant masses from benign masses. The method and system provide improvements in the detection of masses including multi-gray-level thresholding (202) of the processed images to increase sensitivity and accurate region growing and feature analysis to increase specificity. Novel improvements in the classification of masses include a cumulative edge gradient orientation histogram analysis relative to the radial angle of the pixels in question; i.e. either around the margin of the mass or within or around the mass in question. The classification of the mass leads to a likelihood malignancy.