In the field of radiology, mammographic screened images (i.e., X-ray image sensing) are very challenging and difficult to interpret. The expert radiologist visually hunts the mammograms for any specific abnormality. However, human factor causes a low degree of precision that often results in biopsy and anxiety for the patient involved. This paper proposes a novel computer-aided detection (CAD) system to reduce the human factor involvement and to help the radiologist in automatic diagnosis of malignant/nonmalignant breast tissues by utilizing polar complex exponential transform (PCET) moments as texture descriptors. The input region of interest is extracted manually and subjected to further number of preprocessing stages. Both magnitude and phase of PCET moments are used for feature extraction of suspicious region. Moreover, a new classifier adaptive differential evolution wavelet neural network is introduced to improve the classification accuracy of the proposed CAD system. The proposed system is tested on the mammographic images from Mammographic Image Analysis Society database. The designed system attains a fair accuracy of 97.965% with 98.196% sensitivity and 97.194% specificity. The best area under the receiver operational characteristics curve for the proposed classifier is found to be 0.984 with confidence interval from 0.968 to 0.999 and ±0.0108 standard error
Breast Cancer Detection Using PCPCET and ADEWNN: A Geometric Invariant Approach to Medical X-Ray Image Sensors
LAY EKUAKILLE, Aime
2016-01-01
Abstract
In the field of radiology, mammographic screened images (i.e., X-ray image sensing) are very challenging and difficult to interpret. The expert radiologist visually hunts the mammograms for any specific abnormality. However, human factor causes a low degree of precision that often results in biopsy and anxiety for the patient involved. This paper proposes a novel computer-aided detection (CAD) system to reduce the human factor involvement and to help the radiologist in automatic diagnosis of malignant/nonmalignant breast tissues by utilizing polar complex exponential transform (PCET) moments as texture descriptors. The input region of interest is extracted manually and subjected to further number of preprocessing stages. Both magnitude and phase of PCET moments are used for feature extraction of suspicious region. Moreover, a new classifier adaptive differential evolution wavelet neural network is introduced to improve the classification accuracy of the proposed CAD system. The proposed system is tested on the mammographic images from Mammographic Image Analysis Society database. The designed system attains a fair accuracy of 97.965% with 98.196% sensitivity and 97.194% specificity. The best area under the receiver operational characteristics curve for the proposed classifier is found to be 0.984 with confidence interval from 0.968 to 0.999 and ±0.0108 standard errorI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
