Aims and objectives
to compare Radiomic's data between two groups of mammograms: breast cancer mammograms and the negative controlateral mammograms,
same projection,
in order to prove a quantitative value to detect the breast cancer.
Methods and materials
We reviewed a retrospective cohort of 1530 women patients with clinical Mammograms between April 2018 and September 2018 in an Italian Hospital.
All the mammograms have been performed by the same device.
We included the patients with breast cancer mass histopathology proved (we excluded microcalcificantion lesions) and images in full compliance with standard quality.
We evaluated two different groups of images: first group made of mammograms with breast cancer and the second group made of controlateral mammograms without brast cancer and neither suspicius lesions.
We...
Results
We obtained a final cohort of 84 images (CC and MLO mammograms) and a total of 43 cases of breast cancer,
with different histopathology results (in one case the same mammogram showed two different breast cancers).
We found differences of Radiomic's data between the two groups were statistically significant (p<0.05) for Compactness 1 (p= 0.044),
Major Axis (p= 0.043) and Zone Percentage (p= 0.042).
Conclusion
Our results show how Radiomic could provide a post processing quantitative value that could point out Mammograms with breast cancer comparing the controlateral negative mammogram.
These results could provide a good tool for the breast Radiologist in the most challenging case of mammograms like in dense breast or in case of no previews exams available during the reporting.
References
Quantitative texture analysis: robustness of radiomics across two digital mammography manufacturers' systems.
Mendel KR,
Li H,
Lan L,
Cahill CM,
Rael V,
Abe H,
Giger ML.
Radiomics based detection and characterization of suspicious lesions on full field digital mammograms.
Sapate SG,
Mahajan A,
Talbar SN,
Sable N,
Desai S,
Thakur M.
Added Value of Radiomics on Mammography for Breast Cancer Diagnosis: A Feasibility Study.
Mao N,
Yin P,
Wang Q,
Liu M,
Dong J,
Zhang X,
Xie H,
Hong N.
Radiomic Phenotypes of Mammographic Parenchymal...