Nianping Jiang1, Li Zhong2, Chunlai Zhang1, Xiangguo Luo1, Peng Zhong3, Xiaoguang Li1. 1. Department of Radiology, Daping Hospital, Army Medical University, Chongqing, China. 2. Department of Radiation Oncology, Daping Hospital, Army Medical University, Chongqing, China. 3. Department of Pathology, Daping Hospital, Army Medical University, Chongqing, China.
Abstract
BACKGROUND: There is substantial overlap in MRI findings between phyllodes tumors (PTs) and fibroadenomas (FAs). Our study was performed to investigate the value of conventional MRI texture analysis in the differential diagnosis of PTs and FAs. METHODS: Preoperative MRI data - including axial T1WI, T2WIFS (T2WI with fat suppression), dynamic contrast-enhanced (DCE)-T1WI2min and DCE-T1WI7min (T1WI post-strengthened for 2 and 7 min, respectively, on DCE-MRI) - of 45 patients with PTs and 67 patients with FAs were retrospectively analyzed. MaZda 4.7 software was used to manually draw the maximum ROIs at the same lesion level of the above MRI images. The optimized feature selection methods included Fisher's coefficient, probability of classification error and average correction coefficient (POE + ACC), and mutual information (MI) as well as a combination of the above 3 methods (F + POE + ACC + MI [FPM]), respectively. The misclassification rates of PTs and FAs were compared between texture analysis and subjective diagnosis by radiologists. RESULTS: The DCE-T1WI7min images had the lowest misclassification rate of 10.71% (12/112). The misclassification rate for the radiologists' analysis (31.25%, 35/112) was higher than that of all the texture analysis, and there was a statistically significant difference between the radiologists' misclassification rates and those from the FPM method in terms of the T2WIFS and DCE-T1WI2min images (all p < 0.05), and for the DCE-T1WI7min images by using the Fisher and FPM methods (all p < 0.05). CONCLUSION: Texture analysis of conventional MRI can be used as an assistant tool in providing a certain objective basis for differentiating PTs from FAs.
BACKGROUND: There is substantial overlap in MRI findings between phyllodes tumors (PTs) and fibroadenomas (FAs). Our study was performed to investigate the value of conventional MRI texture analysis in the differential diagnosis of PTs and FAs. METHODS: Preoperative MRI data - including axial T1WI, T2WIFS (T2WI with fat suppression), dynamic contrast-enhanced (DCE)-T1WI2min and DCE-T1WI7min (T1WI post-strengthened for 2 and 7 min, respectively, on DCE-MRI) - of 45 patients with PTs and 67 patients with FAs were retrospectively analyzed. MaZda 4.7 software was used to manually draw the maximum ROIs at the same lesion level of the above MRI images. The optimized feature selection methods included Fisher's coefficient, probability of classification error and average correction coefficient (POE + ACC), and mutual information (MI) as well as a combination of the above 3 methods (F + POE + ACC + MI [FPM]), respectively. The misclassification rates of PTs and FAs were compared between texture analysis and subjective diagnosis by radiologists. RESULTS: The DCE-T1WI7min images had the lowest misclassification rate of 10.71% (12/112). The misclassification rate for the radiologists' analysis (31.25%, 35/112) was higher than that of all the texture analysis, and there was a statistically significant difference between the radiologists' misclassification rates and those from the FPM method in terms of the T2WIFS and DCE-T1WI2min images (all p < 0.05), and for the DCE-T1WI7min images by using the Fisher and FPM methods (all p < 0.05). CONCLUSION: Texture analysis of conventional MRI can be used as an assistant tool in providing a certain objective basis for differentiating PTs from FAs.
Authors: Piotr M Szczypiński; Michał Strzelecki; Andrzej Materka; Artur Klepaczko Journal: Comput Methods Programs Biomed Date: 2008-10-14 Impact factor: 5.428
Authors: Benjamin Y Tan; Geza Acs; Sophia K Apple; Sunil Badve; Ira J Bleiweiss; Edi Brogi; José P Calvo; David J Dabbs; Ian O Ellis; Vincenzo Eusebi; Gelareh Farshid; Stephen B Fox; Shu Ichihara; Sunil R Lakhani; Emad A Rakha; Jorge S Reis-Filho; Andrea L Richardson; Aysegul Sahin; Fernando C Schmitt; Stuart J Schnitt; Kalliopi P Siziopikou; Fernando A Soares; Gary M Tse; Anne Vincent-Salomon; Puay Hoon Tan Journal: Histopathology Date: 2016-01 Impact factor: 5.087
Authors: Fresia Pareja; Felipe C Geyer; Rahul Kumar; Pier Selenica; Salvatore Piscuoglio; Charlotte K Y Ng; Kathleen A Burke; Marcia Edelweiss; Melissa P Murray; Edi Brogi; Britta Weigelt; Jorge S Reis-Filho Journal: NPJ Breast Cancer Date: 2017-10-12