Yanan Guo

A new method of micro-calcifications detection in digitized mammograms based on improved simplified PCNN

GoalThe micro-calcifications is early symptom of breast cancer, however it is inefficient for radiologists to read mammograms manually. In this study, an automatic detection method for micro-calcification clusters (MCs) in digitized mammograms is proposed. MethodFirstly, the Otsu thresholding method and a minimum enclosing rectangle are used to obtain the breast area. Secondly, we use mathematical morphology and a non-linear transform to enhance contrast, and then bi-orthogonal wavelet is used to extract wavelet high-frequency coefficients. Finally, the MCs are obtained by a modified Simplified Pulse Coupled Neural Network (SPCNN) model. ResultThe system is tested both on the Mammographic Image Analysis Society (MIAS) Database and the database from Japanese Society of Medical Imaging Technology, moreover the clinical database of Peoples Hospital of Gansu Province is also obtained to verify this proposed method. The detection result shows that this new method is effective both on experiment and clinic. ContributionFirstly, the relationship between the iteration step and the segmentation result is studied to improve the detection rate; secondly, an improved Pulse Coupled Neural Network (PCNN) model without training is proposed to detect MCs, and it is proved to be more practical and effective than the current state-of-the-art models.

Improved Saliency Detection for Abnormalities in Mammograms

Goal: Mammography is the most effective technique for breast cancer screening, and the detection of abnormalities plays a vital role in Computer Aided Detection (CAD) system. This paper proposes a detection method for abnormal mammograms based on improved saliency detection. Methods: The proposed method comprises three main steps: firstly, enhance abnormal mammograms using dual morphological top-hat operations with a non-flat structuring element, secondly, utilize a simple and efficient saliency detector to obtain the saliency value and then employ the modified Simplified Pulse-Coupled Neural Network (SPCNN) to manipulate these saliency value for obtaining suspicious abnormal area, thirdly, the post processing is done to reduce false positives. Conclusion: The proposed method is implemented on open and common database of MIAS, the results show that this novel method outperforms the current state-of-art algorithms. In addition, this method is verified on the mammograms from Gansu Provincial Cancer Hospital, the detection results reveal that our method can accurately detect the abnormal in clinical application. Contributions: we introduce the improved saliency detection to detect abnormalities in mammograms, and the proposed method not only can detect mass, but also can detect micro-calcifications clusters. Significance: This proposed method is simple and effective, furthermore it can achieve high detection rate, we deem it could be considered to be used in CAD system to assist radiologist for breast cancer diagnosis in the future.

Mass Segmentation in Mammograms Based on the Combination of the Spiking Cortical Model (SCM) and the Improved CV Model

In this paper, a novel method based on CV model for the mass segmentation is proposed. Firstly, selecting the largest connected region, seeded region growing, and singular value decomposition (SVD) are used to pre-processing. After that apply the Spiking Cortical Model (SCM) on the pre-processed image to locate the lesion. Finally, the mass boundary is accurately segmented by the improved CV model. The validity of the proposed method is evaluated through two well-known digitized datasets (DDSM and MIAS). The performance of the method is evaluated with detection rate and area overlap. The results indicate the proposed scheme could obtain better performance when compared with several existing schemes.

Saliency Motivated Improved Simplified PCNN Model for object Segmentation

Abstract Based on the fact that PCNN and saliency detection method all can achieve the better simulation of HVS to locate the objects that have the most interests in an image, a novel approach for object segmentation, termed as saliency motivated improved simplified pulse coupled neural network (SM-ISPCNN) algorithm, is proposed in this paper. Instead of adopting pure gray-scale to activate the ISPCNN neurons, it is better to introduce the saliency feature value to motivate this model. The introduced saliency stimulus applies a sliding window to precisely exploit the distributions of the objects and surroundings, weakens the influence of background while retaining the region of interest; the highlight of this ASLFC saliency feature lies on: (1) the saliency estimation is based on semi-local areas instead of pixel level; (2) the estimations of the conditional distributions is manipulated via integral histogram approach; (3) the adaptive prior probability setting method is employed to achieve more promising saliency map. For improvement of convergence speed of SM-ISPCNN model for object segmentation, at each iteration, we regard top 5 regions as feedback input for next iteration, which can raise the robustness of SM-ISPCNN model against noise and other interferences. We demonstrate the proposed model based on the mammograms from open and common database of MIAS, gray images from Weizmann segmentation evaluation database and color images from public database with ground truth annotations. Compared with five competitive methods, our model has the obvious superiority for segmentation capacity and algorithm robustness, furthermore, it does not requires any training and can be used in various occasions of object segmentation. In addition, this method is verified on the mammograms from Gansu Provincial Cancer Hospital, the detection results reveal that this model has great potential in clinical application.

Heterogeneous SPCNN and its application in image segmentation

Abstract Based on the fact that actual cerebral cortex has different structure, a new heterogeneous simplified pulse coupled neural network (HSPCNN) model is proposed in this paper for image segmentation. HSPCNN is constructed with several simplified pulse coupled neural network (SPCNN) models, which have different parameters corresponding to different neurons. An image is segmented by HSPCNN into several regions according to their gray levels. Moreover, the parameter of HSPCNN is set automatically in this paper, the experimental segmentation results of the gray natural images from the Berkeley Segmentation Dataset (BSD 300) show the validity and efficiency of the proposed segmentation method. Finally, an evaluation index is proposed to measure the segmentation result.

Regions of micro-calcifications clusters detection based on new features from imbalance data in mammograms

Breast cancer is the most common cancer among women. Micro-calcification cluster on X-ray mammogram is one of the most important abnormalities, and it is effective for early cancer detection. Surrounding Region Dependence Method (SRDM), a statistical texture analysis method is applied for detecting Regions of Interest (ROIs) containing microcalcifications. Inspired by the SRDM, we present a method that extract gray and other features which are effective to predict the positive and negative regions of micro-calcifications clusters in mammogram. By constructing a set of artificial images only containing micro-calcifications, we locate the suspicious pixels of calcifications of a SRDM matrix in original image map. Features are extracted based on these pixels for imbalance date and then the repeated random subsampling method and Random Forest (RF) classifier are used for classification. True Positive (TP) rate and False Positive (FP) can reflect how the result will be. The TP rate is 90% and FP rate is 88.8% when the threshold q is 10. We draw the Receiver Operating Characteristic (ROC) curve and the Area Under the ROC Curve (AUC) value reaches 0.9224. The experiment indicates that our method is effective. A novel regions of micro-calcifications clusters detection method is developed, which is based on new features for imbalance data in mammography, and it can be considered to help improving the accuracy of computer aided diagnosis breast cancer.

A Non-integer Step Index PCNN Model and Its Applications

In this paper, based on the Simplified pulse coupled neural network (SPCNN) model, a non-integer step index PCNN model is proposed to solve “the mathematic coupled firing” phenomenon in classical PCNN. Method: A time parameter is introduced into SPCNN model, which make each iteration step value of SPCNN not an integer number any more, thus to emulate an analogue time system more closely. This model is used to accomplish two different tasks, detect micro-calcifications in mammograms and detect noise in natural image. The experimental results show that the model performers better in micro-calcifications detection. Furthermore, it is effectively to use this model in image noise reducing.

A New Study on Mammographic Image Denoising using Multiresolution Techniques

Mammography is the most simple and effective technology for early detection of breast cancer. However, the lesion areas of breast are difficult to detect which due to mammograms are mixed with noise. This work focuses on discussing various multiresolution denoising techniques which include the classical methods based on wavelet and contourlet; moreover the emerging multiresolution methods are also researched. In this work, a new denoising method based on dual tree contourlet transform (DCT) is proposed, the DCT possess the advantage of approximate shift invariant, directionality and anisotropy. The proposed denoising method is implemented on the mammogram, the experimental results show that the emerging multiresolution method succeeded in maintaining the edges and texture details; and it can obtain better performance than the other methods both on visual effects and in terms of the Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR) and Structure Similarity (SSIM) values.