Computer‐aided diagnosis: Automatic detection of malignant masses in digitized mammograms

Abstract

A computerized method to automatically detect malignant masses on digital mammograms based on bilateral subtraction to identify asymmetries between left and right breast images was developed. After the digitization, in order to align left and right mammograms the breast border and nipple were automatically detected. Images were corrected to avoid differences in brightness due to the recording procedure. Left and right mammograms were subtracted and a threshold was applied to obtain a binary image with the information of suspicious areas. The suspicious regions or asymmetries were delimited by a region growing algorithm. Size and eccentricity tests were used to eliminate false-positive responses and texture features were extracted from suspicious regions to reject normal tissue regions. The scheme, tested in 70 pairs of digital mammograms, achieved a true-positive rate of 71% with an average number of 0.67 false positives per image. Computerized detection was evaluated by using free-response operating characteristic analysis (FROC). An area under the AFROC (A1) of 0.667 was obtained. Our results show that the scheme may be helpful to the radiologists by serving as a second reader in mammographic screening. The low number of false positives indicates that our scheme would not confuse the radiologist by suggesting normal regions as suspicious.

A computer-based automated algorithm for assessing acinar cell loss after experimental pancreatitis

“…To our knowledge, the current study is also the first to demonstrate use of a computer-learning algorithm to solve a pancreas-related problem. The method is novel in its approach compared to existing commercial software because in the machine-learning system, the computer creates its own identifiers in the form of a prediction rule rather than simply using a few code-defined characteristics [26,27,28]. This unique advantage allows the system to develop multiple color and pixel identifiers from digital images of HE stained pancreatic sections of uninjured and injured tissue.…”

An Efficient Approach to De-noising Mammogram Images

“…These forms the Gaussian filter physically unrealizable and are usually of no consequence to the applications from where the filter bandwidth is much greater to the signal. In real-time systems, a delay incurs because incoming samples are needed to fill the filter window before the filter is to be applied to the signal [14]. Advantages of the Gaussian filter over the other known filters is that ,no amount of delay that helps to make a Gaussian filter causal, because the Gaussian functions are never zero.…”

“…Similarly techniques used for contrast enhancement on mammographic images broadly categories into six category such as unsharp masking, adaptive neighbourhood contrast enhancement histogram equalization, spatial filtering , wavelet enhancement and fuzzy model [14]. Among above mentioned techniques, adaptive contrast enhancement [15,16] and wavelets [17,18] proved to be more suitable for mammography.…”

Incorporating Breast Asymmetry Studies into CADx Systems

“…Thus, in order to efficiently measure asymmetry, a better and automatic registration must be performed [28]. To do so, alignment has been improved by using the nipple as a reference point [29] and by co-registering both breasts using a robust point matching approach [22]. Nevertheless, none of those works include a fully automated bilateral registration.…”