Wyniki wyszukiwania - BazTech

1

Multi-View Attention-based Late Fusion (MVALF) CADx system for breast cancer using deep learning

Iftikhar Hina, Shahid Ahmad Raza, Raza Basit, Khan Hasan

Machine Graphics and Vision

|

2020

|

Vol. 29, No. 1/4

55--78

EN

Breast cancer is a leading cause of death among women. Early detection can significantly reduce the mortality rate among women and improve their prognosis. Mammography is the first line procedure for early diagnosis. In the early era, conventional Computer-Aided Diagnosis (CADx) systems for breast lesion diagnosis were based on just single view information. The last decade evidence the use of two views mammogram: Medio-Lateral Oblique (MLO) and Cranio-Caudal (CC) view for the CADx systems. Most recent studies show the effectiveness of four views of mammogram to train CADx system with feature fusion strategy for classification task. In this paper, we proposed an end-to-end Multi-View Attention-based Late Fusion (MVALF) CADx system that fused the obtained predictions of four view models, which is trained for each view separately. These separate models have different predictive ability for each class. The appropriate fusion of multi-view models can achieve better diagnosis performance. So, it is necessary to assign the proper weights to the multi-view classification models. To resolve this issue, attention-based weighting mechanism is adopted to assign the proper weights to trained models for fusion strategy. The proposed methodology is used for the classification of mammogram into normal, mass, calcification, malignant masses and benign masses. The publicly available datasets CBIS-DDSM and mini-MIAS are used for the experimentation. The results show that our proposed system achieved 0.996 AUC for normal vs. abnormal, 0.922 for mass vs. calcification and 0.896 for malignant vs. benign masses. Superior results are seen for the classification of malignant vs benign masses with our proposed approach, which is higher than the results using single view, two views and four views early fusion-based systems. The overall results of each level show the potential of multi-view late fusion with transfer learning in the diagnosis of breast cancer.

2

Mammografia cyfrowa – wymogi przepisów krajowych, UE oraz NFZ dla programu badań przesiewowych

Laska Robert, Lutak Andrzej

Inżynier i Fizyk Medyczny

|

2019

|

Vol. 8, nr 1

58--59

PL

W Polsce od wielu lat funkcjonuje program profilaktyki raka piersi. W ramach tego programu kobietom w wieku 50-69 lat wykonuje się badanie mammograficzne. Istotnym elementem zapewniającym wymaganą skuteczność tego programu jest wysoka jakość otrzymywanych obrazów mammograficznych. Zapewnić to mogą jedynie nowoczesne i odpowiednio funkcjonujące urządzenie radiologiczne (prawidłowo wykalibrowany mammograf i monitory) wraz z kompetentnym i wykwalifikowanym personelem.

3

Abnormal Breast Detection in Mammogram Images by Feed-forward Neural Network Trained by Jaya Algorithm

Wang S., Rao R. V., Chen P., Zhang Y., Liu A., Wei L.

Fundamenta Informaticae

|

2017

|

Vol. 151, nr 1/4

191--211

EN

(Aim) Abnormal breast can be diagnosed using the digital mammography. Traditional manual interpretation method cannot yield high accuracy. (Method) In this study, we proposed a novel computer-aided diagnosis system for detecting abnormal breasts in mammogram images. First, we segmented the region-of-interest. Next, the weighted-type fractional Fourier transform (WFRFT) was employed to obtain the unified time-frequency spectrum. Third, principal component analysis (PCA) was introduced and used to reduce the spectrum to only 18 principal components. Fourth, feed-forward neural network (FNN) was utilized to generate the classifier. Finally, a novel algorithm-specific parameter free approach, Jaya, was employed to train the classifier. (Results) Our proposed WFRFT + PCA + Jaya-FNN achieved sensitivity of 92.26% ± 3.44%, specificity of 92.28% ± 3.58%, and accuracy of 92.27% ± 3.49%. (Conclusions) The proposed CAD system is effective in detecting abnormal breasts and performs better than 5 state-of-the-art systems. Besides, Jaya is more effective in training FNN than BP, MBP, GA, SA, and PSO.

4

Automatic breast - line and pectoral muscle segmentation

Czaplicka K., Włodarczyk J.

Schedae Informaticae

|

2011

|

Vol. 20

195-209

EN

Pre-processing of mammograms is a crucial step in computer-aided analysis systems. The aim of segmentation is to extract a breast region by estimation of a breast skin-line and a pectoral muscle as well as removing radiographic artifacts and the background of the mammogram. Knowledge of the breast contour also allows further analysis of breast abnormalities such as bilateral asymmetry. In this paper we propose a fully automatic algorithm for segmentation of a breast region, based on two types of global image thresholding: the multi-level Otsu and minimizing the measure of fuzziness as well as the gradient estimation and linear regression. The results of our experiments showed that our method can be used to nd a breast line and a pectoral muscle accurately.

5

A connected component labelling algorithm for greyscale mammography image processing as a pre-processing tool

Yapa R. D., Harada K.

Machine Graphics and Vision

|

2007

|

Vol. 16, No. 3/4

305-327

EN

A new algorithm for connected component-labelling is presented in this paper. The proposed algorithm requires only one scan through an image for labelling connected components. Once this algorithm encounters a starting pixel of a component, it traces in full all the contour pixels and all internal pixels of that particular component. The algorithm recognizes components of the image one at a time while scanning in the raster order. This property will be useful in areas such as image matching, image registration, content-based information retrieval and image segmentation. It is also capable of extracting the contour pixels of an image and storing them in a clock-wise directional order, which will provide useful information in many applications. The algorithm assigns consecutive label numbers to different components, and therefore requires a minimum number of labels. We have used the algorithm in mammography image processing as a pre-processing tool, and have demonstrated the possibility of using it for breast tissue segmentation and for detecting regions of interest in breast tissue. Another important advantage of the algorithm is that it can be used as a content-based image retrieval tool for retrieving images based on the visual contents of a given image. This would be very useful in retrieving related images from large scale medical databases.