Haralick’s features have been extensively used in texture analysis of medical images. In this contribution, we have applied Haralick’s to T2-weighted colorectal MRI for a possible cancer evaluation. In particular, the T2-MRI images of 8 patients with colorectal pathology were identified as early stage malignant and later stage malignant using the whole amount of follow-up exams by radiologists. 192 Haralick’s textural features were computed from normalized gray level co-occurrence matrix with respect to four different directions. Mean and standard deviation were also calculated for the extracted features to assess the statistical significance of results. Among all the extracted features, only 5 from 14 Haralick’s textural features (viz. energy, contrast, correlation, entropy and inverse difference moment (IDM)) were found as significant for colorectal cancer evaluation. In future research, these five Haralick’s textural features may be useful to detect and evaluate colorectal cancer as well as constitute a basis for predicting the prognostic trend of the disease.
Soomro, M.H., Giunta, G., Andrea, L., Damiano, C., Maria, C., DE MARCHIS, C., et al. (2017). HARALICK’S TEXTURE ANALYSIS APPLIED TO COLORECTAL T2-WEIGHTED MRI: A PRELIMINARY STUDY OF SIGNIFICANCE FOR CANCER EVOLUTION. In Proceedings of the IASTED International Conference Biomedical Engineering (BioMed 2017). ACTA Press [10.2316/P.2017.852-019].
HARALICK’S TEXTURE ANALYSIS APPLIED TO COLORECTAL T2-WEIGHTED MRI: A PRELIMINARY STUDY OF SIGNIFICANCE FOR CANCER EVOLUTION
SOOMRO, MUMTAZ HUSSAIN;GIUNTA, GAETANO;DE MARCHIS, CRISTIANO;CONFORTO, SILVIA;SCHMID, Maurizio
2017-01-01
Abstract
Haralick’s features have been extensively used in texture analysis of medical images. In this contribution, we have applied Haralick’s to T2-weighted colorectal MRI for a possible cancer evaluation. In particular, the T2-MRI images of 8 patients with colorectal pathology were identified as early stage malignant and later stage malignant using the whole amount of follow-up exams by radiologists. 192 Haralick’s textural features were computed from normalized gray level co-occurrence matrix with respect to four different directions. Mean and standard deviation were also calculated for the extracted features to assess the statistical significance of results. Among all the extracted features, only 5 from 14 Haralick’s textural features (viz. energy, contrast, correlation, entropy and inverse difference moment (IDM)) were found as significant for colorectal cancer evaluation. In future research, these five Haralick’s textural features may be useful to detect and evaluate colorectal cancer as well as constitute a basis for predicting the prognostic trend of the disease.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
