Abstract 4035
Background
Breast cancer is one of the most common malignant disease for women. Mammography is the preferred method for breast cancer detection. The purpose is to investigate the feasibility and accuracy of texture features extracted from digital mammograms at predicting benign and malignant breast mass using Radiomics.
Methods
494 digital mammograms data who diagnosed as breast masses (Benign: 251 Malignant: 243) by mammography were enrolled. Enrol criteria: breast masses classified as BI-RADS 3, 4, and 5 and at last confirmed by histopathology. Lesion area was marked with a rectangular frame on the Cranio-Caudal (CC) and MedioLateral Oblique (MLO) images at the 5M workstation. The rectangular regions of interest (ROI) was segmented and 456 radiomics features were extracted from every ROI. Extracted features were dimensioned by Maximum Relevance Minimum Redundancy (MRMR) and Lasso algorithm. Post-dimension features were classified using Support Vector Machine (SVM). 70% of the data as a training set and the other 30% as a testing set. The reliability of the Classifier was evaluated by the 10-fold cross-validation. The classification accuracy was evaluated by the accuracy and sensitivity and AUC.
Results
Both the MRMR and Lasso screened 30 radiomics features respectively. 10-fold cross-validation showed that their accuracy were 88.70% and 86.71%, respectively. In testing sets, Through the MRMR algorithm, the classifier achieves an accuracy of 92.00% and a sensitivity of 91.10% and AUC of 95.10%. Through the lasso dimension reduction algorithm, the classifier achieves an accuracy of 83.26% and a sensitivity of 75.90% and AUC of 89.38%.
Conclusions
Radiomics texture features from digital mammograms may be used for benign and malignant prediction. This method offer better accuracy and sensitivity. It is expected to provide an auxiliary diagnosis for the imaging doctors.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
4614 - Predictors of Response to Checkpoint Inhibitors in Naïve and Ipilimumab-Refractory Melanoma
Presenter: Domenico Mallardo
Session: Poster Display session 3
Resources:
Abstract
2901 - IFN-γ/IL-10 ratio as predictive biomarker for response to anti-PD-1 therapy in metastatic melanoma patients
Presenter: Emilio Giunta
Session: Poster Display session 3
Resources:
Abstract
2306 - Multiplex Chromogenic Immunohistochemistry (IHC) for Spatial Analysis of Checkpoint-Positive Tumor Infiltrating Lymphocytes (TILs)
Presenter: Scott Ely
Session: Poster Display session 3
Resources:
Abstract
1678 - The role of PD-L1 expression as a predictive biomarker in advanced renal cell carcinoma: a meta-analysis of randomized clinical trials.
Presenter: Alberto Carretero-Gonzalez
Session: Poster Display session 3
Resources:
Abstract
5138 - Radiomic Features as a Non-invasive Biomarker to Predict Response to Immunotherapy in Recurrent or Metastatic Urothelial Carcinoma
Presenter: Kye Jin Park
Session: Poster Display session 3
Resources:
Abstract
5800 - Integrative combination of high-plex digital profiling techniques and cluster analysis to reveal complex immune biology in the tumor microenvironment of mesothelioma
Presenter: Carmen Ballesteros-Merino
Session: Poster Display session 3
Resources:
Abstract
5736 - Predictive factors of response to immunotherapy in 198 patients with metastatic non-microcytic lung cancer (mNSCLC): real world data from 2 university hospitals in Spain
Presenter: Juan Felipe Cordoba Ortega
Session: Poster Display session 3
Resources:
Abstract
5645 - Evaluating Lung CT Density Changes Among Patients with Extensive Stage Small Cell Lung Cancer (ES-SCLC) Treated with Thoracic Radiotherapy (TRT) alone or TRT Followed by Combined Ipilimumab (IPI) and Nivolumab (NIVO).
Presenter: Kujtim Latifi
Session: Poster Display session 3
Resources:
Abstract
1540 - Immuno-oncology therapy biomarkers differences between polyoma-virus positive and negative Merkel cell carcinomas
Presenter: Zoran Gatalica
Session: Poster Display session 3
Resources:
Abstract
4538 - Can we improve patient selection for phase 1 clinical trials (Ph1) based on Immuno-Oncology score prognostic index (VIO)?
Presenter: Ignacio Matos Garcia
Session: Poster Display session 3
Resources:
Abstract