Abstract 14P
Background
Classification of molecular subtypes of breast cancer is widely used in clinical decision-making, leading to different treatment responses and clinical outcomes. We classified molecular subtypes using a novel deep learning algorithm in whole-slide histopathological images (WSIs) with invasive ductal carcinoma of the breast.
Methods
We obtained 1,094 breast cancer cases with available hematoxylin and eosin-stained WSIs from the TCGA database. We applied a new deep learning algorithm for artificial neural networks (ANNs) that is completely different from the back-propagation method developed in previous studies.
Results
Our model based on the ANN algorithm had an accuracy of 67.8% for all datasets (training and testing), and the area under the receiver operating characteristic curve was 0.819 when classifying molecular subtypes of breast cancer. In approximately 30% of cases, the molecular subtype did not reflect the unique histological subtype, which lowered the accuracy. The set revealed relatively high sensitivity (70.5%) and specificity (84.4%).
Conclusions
Our approach involving this ANN model has favorable diagnostic performance for molecular classification of breast cancer based on WSIs and could provide reliable results for planning treatment strategies.
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
321P - Epidemiology and survival analysis of epithelial ovarian cancer: Results from comprehensive care center in north India
Presenter: Amit Badola
Session: Poster Display
Resources:
Abstract
322P - Evaluation of chemotherapy response score as a prognostic factor in advanced epithelial ovarian cancer: A prospective single centre study
Presenter: Upasana Palo
Session: Poster Display
Resources:
Abstract
323P - Platelet-to-lymphocyte ratio, neutrophil-to-lymphocyte ratio, and lymphocyte-to-monocyte ratio as prognostic biomarkers in ovarian cancer among the Asian population: A meta-analysis
Presenter: Wikania Wira Wiguna I Gede
Session: Poster Display
Resources:
Abstract
324P - All-<italic>trans</italic> retinoic acid sensitizes ovarian cancer to niraparib by inhibiting ALDH1A1 activity
Presenter: Bingjie Mei
Session: Poster Display
Resources:
Abstract
325TiP - A phase III randomized controlled trial in primary stage three and four ovarian cancer after interval cytoreductive surgery (FOCUS/KOV-HIPEC-04)
Presenter: Myong Cheol Lim
Session: Poster Display
Resources:
Abstract
327TiP - A single arm phase II study of single agent pemetrexed in platinum resistant/refractory epithelial ovarian or primary peritoneal cancer
Presenter: Swasthik Parampalli
Session: Poster Display
Resources:
Abstract
337P - Demographic patterns and survival outcomes of patients with T and NK-cell lymphoma at the National Cancer Centre Singapore
Presenter: Mohamed Haniffa Bin Hasan Mohamed
Session: Poster Display
Resources:
Abstract
338P - Multicenter real-world study of advanced-stage non-nasal type NK/T cell lymphoma (NKTCL): Clinical features, treatment and prognosis
Presenter: Yuce Wei
Session: Poster Display
Resources:
Abstract
339P - A comparison of survival of patients with relapsed or refractory diffuse large B cell lymphoma undergoing allogeneic stem cell transplantation or receiving CAR-T therapy
Presenter: Kenta Hayashino
Session: Poster Display
Resources:
Abstract
340P - The role of CT scans and laboratory tests for surveillance in patients with diffuse large B cell lymphoma who achieved complete remission after first-line chemotherapy
Presenter: YU Yagi
Session: Poster Display
Resources:
Abstract