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
174P - Unlocking the potential of blood-based biomarkers in pancreatic cancer for early detection and therapeutic screening
Presenter: Belinda Lee
Session: Poster Display
Resources:
Abstract
175P - Genomic evolution of peritoneal metastasis in gastric adenocarcinoma
Presenter: Lan Tu
Session: Poster Display
Resources:
Abstract
176P - Identification of novel diagnostic markers for pancreatic neuroendocrine tumors by proteomics with patient blood
Presenter: HEE SEON Kim
Session: Poster Display
Resources:
Abstract
177P - Burden of stomach cancer attributable to smoking in South Asia from 1990-2019, its projection of deaths to 2040: A benchmarking and comparative analysis
Presenter: Pranay Vaghela
Session: Poster Display
Resources:
Abstract
178P - Survival benefit of splenic hilar lymph nodes (no.10) dissection in B4 type gastric carcinoma: An IPTW propensity score analysis of large multi-institutional data
Presenter: Oh Jeong
Session: Poster Display
Resources:
Abstract
179P - The impact of pre-operative nutritional/rehabilitative assessments and support on postoperative outcomes in very elderly gastric cancer patients
Presenter: Yuki Ushimaru
Session: Poster Display
Resources:
Abstract
180P - Appraisal of surgical outcomes and oncological efficiency of intraoperative adverse events in robotic radical gastrectomy for gastric cancer
Presenter: shangguan Zhixin
Session: Poster Display
Resources:
Abstract
181P - TQB2450 (PD-L1 blockade) in combination with anlotinib as a perioperative treatment for patients with hepatocellular carcinoma at high risk of recurrence: Primary results from a prospective, single-arm, phase Ib study
Presenter: Zhen Huang
Session: Poster Display
Resources:
Abstract
182P - Cytoreductive surgery and chemotherapy in metastatic gastric adenocarcinoma: A population-based study
Presenter: Dana Al Zamer
Session: Poster Display
Resources:
Abstract
183P - Final analysis of phase II clinical study evaluating the safety and effectiveness of neoadjuvant S-1 + oxaliplatin combination therapy for older patients with locally advanced gastric cancer
Presenter: Eiji Oki
Session: Poster Display
Resources:
Abstract