Abstract 174P
Background
Application of computer and artificial intelligence (AI) has made revolutionary progress in medical fields. Computer-assisted diagnosis (CAD) on pathology is successful in diagnosis, classification, staging and predicting prognosis of cancer.
Methods
In this work, we used the technique of convolutional neural networks (CNN) for training of morphological images of gastric cancer, which is a promising application of artificial intelligence technique for medical image analysis, especially for cancer pathology.
Results
We introduced successful works of AI-aided gastric cancer analysis for over 300 cases. AI-assisted pathology technique could help the pathologist in detecting and locating the abnormal area in images and to diagnose and classify benign or malignant tissues. Therefore, AI exactly improves the diagnostic status of gastric cancer, such as in interpretation of medical images and classification between benign and cancerous tissues. The complete workflow of AI diagnosis for gastric cancer is under construction. AI is more useful in releasing pathologists from repeated work, and improving efficiency.
Conclusions
In conclusions, there are still notable technical obstacles before this approach can be used to improve conventional clinical practice. Higher performance needs corrected marking images by experienced pathologist and require ‘training’ algorithms on tremendous data. We stressed the importance of proper algorithms for improving confidence of analytic results that is close to human experts. Additionally, we indicated the gaps in current research and principal resolutions for advancing the field.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors without further recourse to the authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
4P - Impact of chemotherapy and radiotherapy on tissue expander or implant removal in breast cancer patients
Presenter: Sungmi Jung
Session: Poster display session
Resources:
Abstract
5P - Long-term prognostic effect of hormone receptor subtype on breast cancer
Presenter: Ki-tae Hwang
Session: Poster display session
Resources:
Abstract
6P - Effect of apparent diffusion coefficient in predicting pathologic responses in patients with breast cancer treated with neoadjuvant chemotherapy using nanoparticle albumin-bound paclitaxel
Presenter: Yutaka Mizuno
Session: Poster display session
Resources:
Abstract
7P - Current diagnostic strategy for mammographic microcalcification without specific ultrasound abnormality
Presenter: Naoki Sato
Session: Poster display session
Resources:
Abstract
8P - Comparison of standard uptake value of 18F-FDG-PET-CT with tumour-infiltrating lymphocytes in breast cancer ≥1cm
Presenter: Soeun Park
Session: Poster display session
Resources:
Abstract
10P - Prognosis and effect of adjuvant treatment in small, node(-), HER2(+) breast cancer
Presenter: Seungtaek Lim
Session: Poster display session
Resources:
Abstract
11P - The prognosis of rare histopathologic subtype of breast cancer
Presenter: Soo Youn Bae
Session: Poster display session
Resources:
Abstract
12P - Daily collection of physical activity via smartphone application and smart band for development of distress screening tools in breast cancer survivors: A feasibility study
Presenter: Yungil Shin
Session: Poster display session
Resources:
Abstract
13P - Breast cancer distribution in East Azerbaijan, Iran: Results of population-based cancer registry
Presenter: Shima Pashaei
Session: Poster display session
Resources:
Abstract
14P - Validation of the optimum timing of assessment of tumour infiltrating lymphocytes during preoperative chemotherapy for breast cancer
Presenter: Shinichiro Kashiwagi
Session: Poster display session
Resources:
Abstract