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
5544 - Evaluation of a radiomic signature of CD8 cells in patients treated with immunotherapy-radiotherapy in three clinical trials.
Presenter: Roger Sun
Session: Poster Display session 3
Resources:
Abstract
1117 - Biomarkers predictive of overall survival in advanced cancer patients treated with a peptide-based cancer vaccine.
Presenter: Shigetaka Suekane
Session: Poster Display session 3
Resources:
Abstract
1922 - Expression of PD-L1 in plasma exosomes of NSCLC patients and its associations with PD-L1 expression of corresponding tumor tissues
Presenter: Shaorong Yu
Session: Poster Display session 3
Resources:
Abstract
5495 - Patient’s perspective on digital biomarkers in advanced urologic malignancies
Presenter: Severin Rodler
Session: Poster Display session 3
Resources:
Abstract
3166 - A comprehensive Pan-cancer study of FGFR Aberrations in Chinese cancer patients
Presenter: Yang Gao
Session: Poster Display session 3
Resources:
Abstract
3277 - A Systemic Inflammation Response Index (SIRI) correlates with survival and could be a Predictive Factor for mFOLFIRINOX in Metastatic Pancreatic Cancer (PC)
Presenter: Vilma Pacheco-Barcia
Session: Poster Display session 3
Resources:
Abstract
2680 - Circulating biomarkers and risk of immune-related adverse events (irAEs) in patients (pts) with advanced Non-small cell lung cancer (aNSCLC) and metastatic melanoma (mMel)
Presenter: Alberto Pavan
Session: Poster Display session 3
Resources:
Abstract
4066 - Breast cancer in young women of Kazakh population depending on germline mutations: results of next-generation sequencing
Presenter: Dilyara Kaidarova
Session: Poster Display session 3
Resources:
Abstract
5514 - Discovery of an ImmunoTranscriptomics signature in blood for early colorectal cancer detection
Presenter: Paolo Angelino
Session: Poster Display session 3
Resources:
Abstract
1595 - Serum Netrin-1 as a Biomarker for Colorectal Cancer Detection
Presenter: Jinzhou Zhu
Session: Poster Display session 3
Resources:
Abstract