Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Biocybernetics and Biomedical Engineering

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Automatic mitosis detection in breast histopathology images using Convolutional Neural Network based deep transfer learning

Sabeena Beevi K., Nair Madhu S., Bindu G. R.

Biocybernetics and Biomedical Engineering

2019

Vol. 39, no. 1

214--223

The exact measure of mitotic count is one of the crucial parameters in breast cancer grading and prognosis. Detection of mitosis in standard H & E stained histopathology images is challenging due to diffused intensities along object boundaries and shape variation in different stages of mitosis. This paper explores the feasibility of transfer learning for mitosis detection. A pre-trained Convolutional Neural Network is transformed by coupling random forest classifier with the initial fully connected layers to extract discriminant features from nuclei patches and to precisely prognosticate the class label of cell nuclei. The modified Convolutional Neural Network accurately classify the detected cell nuclei with limited training data. The designed framework accomplishes higher classification accuracy by carefully fine tuning the pre-trained model and pre-processing the extracted features. Moreover, proposed method is evaluated on MITOS dataset provided for the MITOS-ATYPIA contest 2014 and clinical data set from Regional Cancer Centre, Thiruvananthapuram, India. Significance of Convolutional Neural Network based method is justified by comparing with recently reported works including a Multi Classifier System based on Deep Belief Network. Experiments show that the pre-trained Convolutional Neural Network model outperforms conventionally used detection systems and provides at least 15% improvement in F-score on other state-of-the-art techniques.

Automatic segmentation of cell nuclei using Krill Herd optimization based multi-thresholding and Localized Active Contour Model

Beevi K. S., Nair M. S., Bindu G. R.

Biocybernetics and Biomedical Engineering

2016

Vol. 36, no. 4

584--596

Analysis of tissue components in histopathology image stays on as the gold standard in detecting different types of cancers. Active Contour Models (ACM) serve as a widely useful tool in object segmentation in pathology images. Since the ACMs are susceptible to initial contour placement, efficiency of object detection is very much influenced by the selection of primary curve placement technique. In this paper, in order to handle diffused intensities present along object boundaries in histopathology images, segmentation of nuclei from breast histopathology images are carried out by Localized Active Contour Model (LACM) utilizing bio-inspired optimization techniques in the detection stage. Krill Herd Algorithm (KHA) based optimal curve placement provides better initial boundaries compared with other detection techniques. The segmentation performance is investigated based on Housdorff (HD) and Maximum Absolute Distance (MAD) measures. The algorithm also shows comparable performance with other state-of-the-art techniques in terms of quantitative measures such as Precision, Accuracy and Touching Nuclei Resolution when applied to complex images of stained breast biopsy slides.