Hsiung C. Automatic classification for pathological prostate images based on fractal analysis (original) (raw)
Related papers
Prostate cancer characterization on MR images using fractal features
Medical Physics, 2011
Purpose: Computerized detection of prostate cancer on T2-weighted MR images. Methods: The authors combined fractal and multifractal features to perform textural analysis of the images. The fractal dimension was computed using the Variance method; the multifractal spectrum was estimated by an adaptation of a multifractional Brownian motion model. Voxels were labeled as tumor/nontumor via nonlinear supervised classification. Two classification algorithms were tested: Support vector machine ͑SVM͒ and AdaBoost. Results: Experiments were performed on images from 17 patients. Ground truth was available from histological images. Detection and classification results ͑sensitivity, specificity͒ were ͑83%, 91%͒ and ͑85%, 93%͒ for SVM and AdaBoost, respectively. Conclusions: Classification using the authors' model combining fractal and multifractal features was more accurate than classification using classical texture features ͑such as Haralick, wavelet, and Gabor filters͒. Moreover, the method was more robust against signal intensity variations. Although the method was only applied to T2 images, it could be extended to multispectral MR.
Indian journal of computer science and engineering, 2022
Prostate cancer diagnosis and staging is of paramount importance to effective treatment planning and better prognosis. Computer aided diagnosis and staging can contribute to improving and speeding up these stages, especially with the advances of deep learning. The International Society of Urological Pathology (ISUP) grading of stained Whole Slide histopathological Images (WSIs) can be considered the gold standard for grading. However, WSIs suffer from large size and wide background areas which hinder the learning process. Hence, a segmentation-based fractal analysis approach is applied to address this issue and elect relevant patches to be input to the learning algorithm. EfficientNet Convolution Neural Network (CNN) achieves a promising accuracy of 80.7% and Quadratic Weighted Kappa (QWK) of 95.4%. The proposed approach remedies the size problem of WSIs and improves the grading accuracy using light weight learning models.
2010
Fractal and texture analysis are computer techniques which can discriminate between the shapes of benign and malignant tumors. The goal of present paper is to describe a method and an algorithm for automatic detection of malignancy of skin lesions which is based on both local fractal features (local fractal dimension) and texture features which derives from the medium co-occurrence matrices (contrast, energy, entropy, homogeneity). The global application was tested on a set of medical images obtained with a dermoscope and a digital camera, all from cases with known diagnostic. The experimental results confirm the efficiency of the proposed method.
BMC Clinical Pathology, 2013
Background: Prostate cancer is a serious public health problem that affects quality of life and has a significant mortality rate. The aim of the present study was to quantify the fractal dimension and Shannon's entropy in the histological diagnosis of prostate cancer. Methods: Thirty-four patients with prostate cancer aged 50 to 75 years having been submitted to radical prostatectomy participated in the study. Histological slides of normal (N), hyperplastic (H) and tumor (T) areas of the prostate were digitally photographed with three different magnifications (40x, 100x and 400x) and analyzed. The fractal dimension (FD), Shannon's entropy (SE) and number of cell nuclei (NCN) in these areas were compared.
Fractal based classification of Colon cancer tissue images
2007
An attempt has been made to classify the histopathological images of Colon cancer tissues from the normal tissues based only on fractal features. The tissue images are modelled as fractal sets in E 3 euclidian space. A new fractal feature estimation algorithm has been used. We call it True Box Counting Method. It is seen that lacunarity features are important parameters and are more important in classification or segmentation than other fractal features like fractal dimension and mass dimension.
Fractal Model for Skin Cancer Diagnosis Using Probabilistic Classifiers
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES
The early detection of skin cancer can lead to high prognosis rate. Thus it is very important to identify abnormalities in skin as early as possible. However, the detection of abnormalities at their early stages is a challenging task since the shape and colour of the abnormalities vary with different persons. In this study, fractal model for skin cancer diagnosis is developed. Differential Box Counting (DBC) method is implemented to get the fractal dimension from the dermoscopic images from two databases; International Skin Imaging Collaboration (ISIC) and PH 2 database. The fractal features are classified using a parametric and non-parametric classification approach. The system provides promising results for skin cancer diagnosis with 96.5% accuracy on PH 2 images and 91.5% accuracy on ISIC database images using the non-parametric classifier whereas parametric classifier gives 95% (PH 2) and 90% (ISIC) images.
Fractal analysis in the detection of colonic cancer images
IEEE Transactions on Information Technology in Biomedicine, 2002
The aim of this study was to investigate the value of fractal dimension in separating normal and cancerous images, and to examine the relationship between fractal dimension and traditional texture analysis features. Forty-four normal images and 58 cancer images from sections of the colon were analyzed. A "leave-one-out" analysis approach was used to classify the samples into each group. With fractal analysis there was a highly significant difference between groups ( 0 0001). Correlation and entropy features showed greater differences between the groups ( 0 0001). Nevertheless, the addition of fractal analysis to the feature analysis improved the sensitivity from 90% to 95% and specificity from 86% to 93%.
Simple fractal method of assessment of histological images for application in medical diagnostics
Nonlinear Biomedical Physics, 2010
We propose new method of assessment of histological images for medical diagnostics. 2-D image is preprocessed to form 1-D landscapes or 1-D signature of the image contour and then their complexity is analyzed using Higuchi's fractal dimension method. The method may have broad medical application, from choosing implant materials to differentiation between benign masses and malignant breast tumors.
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2011
In this paper we present a system for detecting regions of carcinoma of the prostate (CaP) in H&E stained radical prostatectomy specimens using the color fractal dimension. Color textural information is known to be a valuable characteristic to distinguish CaP from benign tissue. In addition to color information, we know that cancer tends to form contiguous regions. Our system leverages the color staining information of histology as well as spatial dependencies. The color and textural information is first captured using color fractal dimension. To incorporate spatial dependencies, we combine the probability map constructed via color fractal dimension with a novel Markov prior called the Probabilistic Pairwise Markov Model (PPMM). To demonstrate the capability of this CaP detection system, we applied the algorithm to 27 radical prostatectomy specimens from 10 patients. A per pixel evaluation was conducted with ground truth provided by an expert pathologist using only the color fractal...