SVM for prostate cancer using electrical impedance measurements

Abstract

Biopsies are currently the 'gold standard' method for identifying cancer of the prostate. While biopsies yield very accurate information regarding the area they sample, they are performed at discrete points and provide no information on the adjacent tissue. To enhance procedural accuracy, biopsies of a large number of sites are routinely carried out. Although more accurate, this method is both more complex and nevertheless remains discrete. In this paper, we evaluate the advantages of using bio-impedance information as the input for a support vector machines (SVMs) classifier to overcome these limitations. In this method, the biopsy probes are used as electrodes to obtain electrical impedance data during each biopsy sample. Using a computer model of the prostate, a SVM was trained and tested. Different tumor shapes and conductivity values, and the classifier's ability to generalize to these different properties, were examined. We demonstrate that by using this classifier the number of biopsies can be reduced and valuable information concerning the adjacent tissue which was not biopsied can be generated.

Development and validation of surface energies estimator (SEE) using computational intelligence technique

“…It has diverse practical applications in several field of study and has been recently deployed in estimating the properties of materials that are difficult to obtain experimentally [6,7]. In medical field, AI techniques help in identifying different kinds of cancers so as to take proper steps toward their cure [8,9]. Compressive strength of concrete that are difficult to determine using experimental approach are now being predicted using AI techniques [10].…”

Stroke Damage Detection Using Classification Trees on Electrical Bioimpedance Cerebral Spectroscopy Measurements

“…Earlier studies have demonstrated the use of classification methods such as support vector machine (SVM) or multimodality classifier for detection of deteriorations in tissue or tissue characterization [42,43]. In this study, features extracted from EBIS measurements are fed into a relatively simple classification tree with the goal of separating healthy brain hemispheres from brain hemispheres with stroke damage.…”

Pilot study: electrical impedance based tissue classification using support vector machine classifier

“…One of the classification methods introduced in 1995 and gaining interest for tissue classification is SVMs [22]. Recently, SVM has been gaining popularity in tissue classification [23][24][25][26]. The SVM-based classifications have utilised training data from prior work done by Jossinet [6] or www.ietdl.org through simulations.…”