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
5520 - Patient’s Usability Test results of a CINV Diary Application For Smartphones
Presenter: Paz Fernandez
Session: Poster Display session 3
Resources:
Abstract
2323 - Colorectal Telephone Assessment Pathway (CTAP) - A viable means of shortening time to a definitive diagnosis of Colorectal Cancer (CRC)
Presenter: Harriet Watson
Session: Poster Display session 3
Resources:
Abstract
6119 - Cancer Nursing and Social Media: Capturing the Zeitgeist
Presenter: Mark Foulkes
Session: Poster Display session 3
Resources:
Abstract
1776 - Examination of mobile applications on breast cancer
Presenter: AYDANUR AYDIN
Session: Poster Display session 3
Resources:
Abstract
4128 - E-health effectiveness to increase patient adherence for immunotherapy; a cost-benefit study.
Presenter: Maria José Dias
Session: Poster Display session 3
Resources:
Abstract
3219 - Experiences of internet-based stepped care among individuals with recently diagnosed cancer and symptoms of anxiety and/or depression
Presenter: Anna Hauffman
Session: Poster Display session 3
Resources:
Abstract
5010 - What do cancer patients know about their immunotherapy treatment?
Presenter: Mónica Arellano
Session: Poster Display session 3
Resources:
Abstract
4503 - Prospective Comparison of Travel Burden, Cost and Time to Obtain Tumor Board Treatment Plan Through In-Person Visits vs. an AI Enabled Health Technology (N=1803)
Presenter: Rajendra Badwe
Session: Poster Display session 3
Resources:
Abstract
4123 - Cancer care through the fire and flames: 3-year experience in the utilisation of electronic consultation and referral system at the Red Zone in Southern Thailand
Presenter: Nanthiya Rattanakhot
Session: Poster Display session 3
Resources:
Abstract
2087 - The effect of e-mobile education on the quality of life in women with breast cancer
Presenter: Derya ÇInar
Session: Poster Display session 3
Resources:
Abstract