M
Menelaos Malamas
Publications - 6
Citations - 308
Menelaos Malamas is an academic researcher. The author has contributed to research in topics: Probabilistic neural network & Artificial neural network. The author has an hindex of 6, co-authored 6 publications receiving 285 citations.
Papers
More filters
Journal ArticleDOI
Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features
Pantelis Georgiadis,Dionisis Cavouras,Ioannis Kalatzis,Antonis Daskalakis,George C. Kagadis,Koralia Sifaki,Menelaos Malamas,George Nikiforidis,Ekaterini Solomou +8 more
TL;DR: The proposed classifier is a modified probabilistic neural network (PNN), incorporating a non-linear least squares features transformation (LSFT) into the PNN classifier, improved PNN performance, increased class separability and resulted in dimensionality reduction.
Journal ArticleDOI
Enhancing the discrimination accuracy between metastases, gliomas and meningiomas on brain MRI by volumetric textural features and ensemble pattern recognition methods
Pantelis Georgiadis,Dionisis Cavouras,Ioannis Kalatzis,Dimitris Glotsos,Emmanouil Athanasiadis,Spiros Kostopoulos,Koralia Sifaki,Menelaos Malamas,George Nikiforidis,Ekaterini Solomou +9 more
TL;DR: The proposed pattern recognition system, designed as an ensemble classification scheme employing a support vector machine classifier, enabled boosting up the performance of the system in discriminating metastatic, malignant and benign brain tumors with 77.14%, 89.19% and 93.33% accuracy, respectively.
Journal ArticleDOI
Pattern recognition system for the discrimination of multiple sclerosis from cerebral microangiopathy lesions based on texture analysis of magnetic resonance images
Pantelis Theocharakis,Dimitris Glotsos,Ioannis Kalatzis,Spiros Kostopoulos,Pantelis Georgiadis,Koralia Sifaki,Katerina Tsakouridou,Menelaos Malamas,George Delibasis,Dionisis Cavouras,George Nikiforidis +10 more
TL;DR: MS regions were darker, of higher contrast, less homogeneous and rougher as compared to CM, and statistically significant differences exist in the values of the textural features between CM and MS.
Book ChapterDOI
Non-linear least squares features transformation for improving the performance of probabilistic neural networks in classifying human brain tumors on MRI
Pantelis Georgiadis,Dionisis Cavouras,Ioannis Kalatzis,Antonis Daskalakis,George C. Kagadis,Koralia Sifaki,Menelaos Malamas,George Nikiforidis,Ekaterini Solomou +8 more
TL;DR: A modified probabilistic neural network is proposed, incorporating a second degree least squares features transformation (LSFT) into the PNN classifier, which improved PNN performance, increased class separability, and resulted in dimensionality reduction.
Journal ArticleDOI
Quantitative combination of volumetric MR imaging and MR spectroscopy data for the discrimination of meningiomas from metastatic brain tumors by means of pattern recognition.
Pantelis Georgiadis,Spiros Kostopoulos,Dionisis Cavouras,Dimitris Glotsos,Ioannis Kalatzis,Koralia Sifaki,Menelaos Malamas,Ekaterini Solomou,George Nikiforidis +8 more
TL;DR: The purpose of this study was to investigate the efficiency of the combination of textural MRI features and MRS metabolite ratios by means of a pattern recognition system in the task of discriminating between meningiomas and metastatic brain tumors.