Wyniki wyszukiwania - BazTech

1

A novel artificial intelligence-based hybrid system to improve breast cancer detection using DCE-MRI

Akgül İsmail, Kaya Volkan, Karavaş Erdal, Aydin Sonay, Baran Ahmet

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2024

|

Vol. 72, nr 3

art. no. e149172

EN

The interpretation of breast magnetic resonance imaging (MRI) in the healthcare field depends on the good knowledge and experience of radiologists. Recent developments in artificial intelligence (AI) have shown advances in the field of radiology. However, the desired levels have not been reached in the field of radiology yet. In this study, a novel model structure is proposed to characterize the diagnostic performance of AI technology for individual breast dynamic contrast material–enhanced (DCE) MRI sequences. In the proposed model structure, Inception-v3, EfficientNet-B3, and DenseNet-201 models were used as hybrids together with the Yolo-v3 algorithm to detect breast and cancer regions. In the proposed model, DCE-MRI sequences (T2, ADC, Diffusion, Non-Contrast Fat Non-Suppressed T1, Non-Contrast Fat Suppressed T1, Contrast Fat Suppressed T1, and Subtraction T1) were evaluated separately and validation was made, thus providing a unique perspective. According to the validation results, the model structure with the best performance was determined as Yolo-v3 + DenseNet-201. With this model structure, 92.41% accuracy, 0.5936 loss, 92.44% sensitivity, and 92.44% specificity rates were obtained. In addition, it was determined that the results obtained without using contrast material in the best model were 91.53% accuracy, 0.9646 loss, 92.19% sensitivity, and 92.19% specificity. Therefore, it is predicted that the need for contrast material use can be reduced with the help of this model structure.

2

Grey Wolf optimization based breast cancer detection using 1D Convolution LSTM classifier

Jebarani Esther P., Umadevi N.

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 1

1--9

EN

Women are particularly vulnerable to breast cancer. Breast cancer diagnosis has benefited greatly from the utilization of ultrasound imaging. Breast UltraSound (BUS) image segmentation remains a difficult challenge due to low image quality. Furthermore, BUS image segmentation, as well as classification, is an important stage in the analysis process. Initially, the image associated with breast cancer is gathered from MIAS database. The gathered image undergoes pre-processing operation using the adaptive median filtering technique. Subsequently, the segmentation is performed in the pre-processed images using the hybrid method consisting of GMM and K-Means. These segmented images undergo the feature extraction steps further where the features are extracted by utilizing the Gray Level Co-occurrence Matrix (GLCM). Grey Wolf Optimization (GWO) selects the optimal features for further classification using a novel 1D Convolution LSTM. Here, the pooling layer of 1D CNN is replaced by the LSTM. The objective function behind the optimal feature selection and classification is the accuracy maximization. Finally, the novel One Dimensional Convolution Long Short Term Memory (1 DCLSTM) classifies the outcome into normal, benign, and malignant, respectively. The proposed method is compared with the other state of art methods related to this research.

PL

Kobiety są szczególnie narażone na raka piersi. Diagnostyka raka piersi bardzo skorzystała na wykorzystaniu obrazowania ultrasonograficznego. Segmentacja obrazu UltraSound (BUS) piersi pozostaje trudnym wyzwaniem ze względu na niską jakość obrazu. Ponadto segmentacja obrazu BUS, a także klasyfikacja, jest ważnym etapem procesu analizy. Początkowo obraz związany z rakiem piersi pozyskiwany jest z bazy MIAS. Zgromadzony obraz jest poddawany wstępnemu przetwarzaniu przy użyciu techniki adaptacyjnego filtrowania medianowego. Następnie na wstępnie przetworzonych obrazach przeprowadzana jest segmentacja metodą hybrydową składającą się z GMM i K-Means. Te podzielone na segmenty obrazy przechodzą kolejne etapy ekstrakcji cech, w których cechy są wyodrębniane przy użyciu macierzy współwystępowania poziomu szarości (GLCM). Optymalizacja Gray Wolf (GWO) wybiera optymalne funkcje do dalszej klasyfikacji przy użyciu nowatorskiego rozwiązania 1D Convolution LSTM. W tym przypadku warstwa łączenia 1D CNN zostaje zastąpiona przez LSTM. Funkcją celu stojącą za optymalnym doborem i klasyfikacją cech jest maksymalizacja dokładności. Wreszcie, powieść jednowymiarowa pamięć krótkoterminowa z konwolucją jednowymiarową (1 DCLSTM) klasyfikuje wynik odpowiednio na normalny, łagodny i złośliwy. Proponowana metoda jest porównywana z innymi nowoczesnymi metodami związanymi z tymi badaniami.

3

DeepBreastNet: A novel and robust approach for automated breast cancer detection from histopathological images

Demir Fatih

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 3

1123--1139

EN

The analysis of histopathological images is the core way for detecting breast cancer, the most insidious type of cancer for women. Artificial intelligence-based applications are used as an effective and supportive tool for automated breast cancer detection. Especially, deep learning models are among the most popular approaches due to their high performances in classification problems of medical images. In this study, a novel and robust approach, based on the convolutional-LSTM (CLSTM) learning model, the pre-processing technique using marker-controlled watershed segmentation algorithm (MWSA), and the optimized SVM classifier, was proposed for detecting breast cancer automatically from histopathological images (HPIs). The CLSTM model trained on the BreakHis dataset, which is popular in the research community, composes of binary and eight-class classification tasks. The classification performance of the CLSTM model was significantly increased by using the processed HPIs with MWSA. For binary and eight-class classification tasks, the best scores were obtained by using the optimized SVM classifier with Bayesian optimization instead of the softmax classifier of the CLSTM model. The proposed approach, which provided very high performance for both classification tasks, was compared to the existing approaches using the BreakHis dataset.

4

Breast cancer detection from histopathology images using modified residual neural networks

Gupta Varun, Vasudev Megha, Doegar Amit, Sambyal Nitigya

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 4

1272--1287

EN

Breast cancer is one of the major causes of death among women worldwide. Efficient diagnosis of breast cancer in the early phases can reduce the associated morbidity and mortality and can provide a higher probability of full recovery. Computer-aided detection systems use computer technologies to detect abnormalities in clinical images which can assist medical professionals in a faster and more accurate diagnosis. In this paper, we propose a modified residual neural network-based method for breast cancer detection using histopathology images. The proposed approach provides good performance over varying magnification factors of 40X, 100X, 200X and 400X. The network obtains an average classification accuracy of 99.75%, precision of 99.18% and recall of 99.37% on BreakHis dataset with 40X magnification factor. The proposed work outperforms the existing methods and delivers state-of-the-art results on the benchmark breast cancer dataset.

5

Contralateral asymmetry for breast cancer detection: A CADx approach

Celaya-Padilla J. M., Guzmán-Valdivia C. H., Galván-Tejada C. E., Galván-Tejada J. I., Gamboa-Rosales H., Garza-Veloz I., Martinez-Fierro M. L., Cid-Báez M. A., Martinez-Torteya A., Martinez-Ruiz F. J., Luna-García H., Moreno-Baez A., Nandal A.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 1

115--125

EN

Early detection is fundamental for the effective treatment of breast cancer and the screening mammography is the most common tool used by the medical community to detect early breast cancer development. Screening mammograms include images of both breasts using two standard views, and the contralateral asymmetry per view is a key feature in detecting breast cancer. However, most automated detection algorithms do not take it into account. In this research, we propose a methodology to incorporate said asymmetry information into a computer-aided diagnosis system that can accurately discern between healthy subjects and subjects at risk of having breast cancer. Furthermore, we generate features that measure not only a view-wise asymmetry, but a subject-wise one. Briefly, the methodology co-registers the left and right mammograms, extracts image characteristics, fuses them into subject-wise features, and classifies subjects. In this study, 152 subjects from two independent databases, one with analog- and one with digital mammograms, were used to validate the methodology. Areas under the receiver operating characteristic curve of 0.738 and 0.767, and diagnostic odds ratios of 23.10 and 9.00 were achieved, respectively. In addition, the proposed method has the potential to rank subjects by their probability of having breast cancer, aiding in the re-scheduling of the radiologists' image queue, an issue of utmost importance in developing countries.

6

Comparison of time-series registration methods in breast dynamic infrared imaging

Riyahi-Alam S., Agostini V., Molinari F., Knaflitz M.

Opto-Electronics Review

|

2015

|

Vol. 23, No. 1

66-75

EN

Automated motion reduction in dynamic infrared imaging is on demand in clinical applications, since movement disarranges time-temperature series of each pixel, thus originating thermal artifacts that might bias the clinical decision. All previously proposed registration methods are feature based algorithms requiring manual intervention. The aim of this work is to optimize the registration strategy specifically for Breast Dynamic Infrared Imaging and to make it user-independent. We implemented and evaluated 3 different 3D time-series registration methods: 1. Linear affine, 2. Non-linear Bspline, 3. Demons applied to 12 datasets of healthy breast thermal images. The results are evaluated through normalized mutual information with average values of 0.70 ±0.03, 0.74 ±0.03 and 0.81 ±0.09 (out of 1) for Affine, Bspline and Demons registration, respectively, as well as breast boundary overlap and Jacobian determinant of the deformation field. The statistical analysis of the results showed that symmetric diffeomorphic Demons’ registration method outperforms also with the best breast alignment and non-negative Jacobian values which guarantee image similarity and anatomical consistency of the transformation, due to homologous forces enforcing the pixel geometric disparities to be shortened on all the frames. We propose Demons’ registration as an effective technique for time-series dynamic infrared registration, to stabilize the local temperature oscillation.

7

Variational Bayesian inversion for microwave breast imaging

Gharsalli L., Ayasso H., Duchêne B., Mohammad-Djafari A.

Computer Assisted Methods in Engineering and Science

|

2014

|

Vol. 21, no. 3-4

199--210

EN

Microwave imaging is considered as a nonlinear inverse scattering problem and tackled in a Bayesian estimation framework. The object under test (a breast affected by a tumor) is assumed to be composed of compact regions made of a restricted number of different homogeneous materials. This a priori knowledge is defined by a Gauss-Markov-Potts distribution. First, we express the joint posterior of all the unknowns; then, we present in detail the variational Bayesian approximation used to compute the estimators and reconstruct both permittivity and conductivity maps. This approximation consists of the best separable probability law that approximates the true posterior distribution in the Kullback-Leibler sense. This leads to an implicit parametric optimization scheme which is solved iteratively. Some preliminary results, obtained by applying the proposed method to synthetic data, are presented and compared with those obtained by means of the classical contrast source inversion method.