Magnetic resonance (MR) images can play a very important role to evaluate patients' diagnosis. In particular, there is an increasing interest in image processing and advanced texture analysis methods able to extract features from MR images that are not easily to percept by the human eye. Among many, Haralick's features have been strongly exploited referring to texture analysis of medical images. Therefore, in this paper, we have investigated Haralick's features computed from MR T2-weighted acquisitions in order to differentiate benign to malignant salivary gland tumors. The study has involved a total of 6 patients affected by salivary gland cancer: from the followup exams performed by radiologists, 3 patients have been identified as benign tumor affected while 3 patients as malignant one. Haralick's textural features are computed from normalized gray level co-occurrence matrix (GLCM) considering four different spatial relationships. In this preliminary study all the 14 Haralick's textural features are investigated in our attempt to differentiate benign from malignant salivary gland tumors: the obtained results reveal that these textural features may be useful to point out the differences between the tumor's nature, helping the clinicians with the diagnosis routine of the disease.

Losquadro, C., Giunta, G., Pallotta, L., Gabelloni, M., & Neri, E. (2020). MR Image Analysis to Differentiate Salivary Gland Tumors. a Preliminary Study. In Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020 (pp.2215-2220). Institute of Electrical and Electronics Engineers Inc. [10.1109/BIBM49941.2020.9313368].

MR Image Analysis to Differentiate Salivary Gland Tumors. a Preliminary Study

Losquadro C.;Giunta G.;Pallotta L.;
2020

Abstract

Magnetic resonance (MR) images can play a very important role to evaluate patients' diagnosis. In particular, there is an increasing interest in image processing and advanced texture analysis methods able to extract features from MR images that are not easily to percept by the human eye. Among many, Haralick's features have been strongly exploited referring to texture analysis of medical images. Therefore, in this paper, we have investigated Haralick's features computed from MR T2-weighted acquisitions in order to differentiate benign to malignant salivary gland tumors. The study has involved a total of 6 patients affected by salivary gland cancer: from the followup exams performed by radiologists, 3 patients have been identified as benign tumor affected while 3 patients as malignant one. Haralick's textural features are computed from normalized gray level co-occurrence matrix (GLCM) considering four different spatial relationships. In this preliminary study all the 14 Haralick's textural features are investigated in our attempt to differentiate benign from malignant salivary gland tumors: the obtained results reveal that these textural features may be useful to point out the differences between the tumor's nature, helping the clinicians with the diagnosis routine of the disease.
978-1-7281-6215-7
Losquadro, C., Giunta, G., Pallotta, L., Gabelloni, M., & Neri, E. (2020). MR Image Analysis to Differentiate Salivary Gland Tumors. a Preliminary Study. In Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020 (pp.2215-2220). Institute of Electrical and Electronics Engineers Inc. [10.1109/BIBM49941.2020.9313368].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11590/379164
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact