Next Article in Journal
Long Term Efficacy and Assessment of Tumor Response of Transarterial Chemoembolization in Neuroendocrine Liver Metastases: A 15-Year Monocentric Experience
Next Article in Special Issue
Scope of Artificial Intelligence in Gastrointestinal Oncology
Previous Article in Journal
TP53 Mutation Is a Prognostic Factor in Lower Grade Glioma and May Influence Chemotherapy Efficacy
Previous Article in Special Issue
Skin Lesion Classification Based on Surface Fractal Dimensions and Statistical Color Cluster Features Using an Ensemble of Machine Learning Techniques
Article

Breast Invasive Ductal Carcinoma Classification on Whole Slide Images with Weakly-Supervised and Transfer Learning

Medmain Research, Medmain Inc., Fukuoka 810-0042, Japan
*
Author to whom correspondence should be addressed.
Academic Editors: Anke Meyer-Baese, Max Zimmermann and Andreas Stadlbauer
Cancers 2021, 13(21), 5368; https://doi.org/10.3390/cancers13215368
Received: 30 September 2021 / Revised: 22 October 2021 / Accepted: 23 October 2021 / Published: 26 October 2021
(This article belongs to the Special Issue Artificial Intelligence in Oncology)
In this study, we have trained deep learning models using transfer learning and weakly-supervised learning for the classification of breast invasive ductal carcinoma (IDC) in whole slide images (WSIs). We evaluated the models on four test sets: one biopsy (n = 522) and three surgical (n = 1129) achieving AUCs in the range 0.95 to 0.99. We have also compared the trained models to existing pre-trained models on different organs for adenocarcinoma classification and they have achieved lower AUC performances in the range 0.66 to 0.89 despite adenocarcinoma exhibiting some structural similarity to IDC. Therefore, performing fine-tuning on the breast IDC training set was beneficial for improving performance. The results demonstrate the potential use of such models to aid pathologists in clinical practice.
Invasive ductal carcinoma (IDC) is the most common form of breast cancer. For the non-operative diagnosis of breast carcinoma, core needle biopsy has been widely used in recent years for the evaluation of histopathological features, as it can provide a definitive diagnosis between IDC and benign lesion (e.g., fibroadenoma), and it is cost effective. Due to its widespread use, it could potentially benefit from the use of AI-based tools to aid pathologists in their pathological diagnosis workflows. In this paper, we trained invasive ductal carcinoma (IDC) whole slide image (WSI) classification models using transfer learning and weakly-supervised learning. We evaluated the models on a core needle biopsy (n = 522) test set as well as three surgical test sets (n = 1129) obtaining ROC AUCs in the range of 0.95–0.98. The promising results demonstrate the potential of applying such models as diagnostic aid tools for pathologists in clinical practice. View Full-Text
Keywords: breast; invasive ductal carcinoma; deep learning; weakly-supervised learning; transfer learning; whole slide image breast; invasive ductal carcinoma; deep learning; weakly-supervised learning; transfer learning; whole slide image
Show Figures

Figure 1

MDPI and ACS Style

Kanavati, F.; Tsuneki, M. Breast Invasive Ductal Carcinoma Classification on Whole Slide Images with Weakly-Supervised and Transfer Learning. Cancers 2021, 13, 5368. https://doi.org/10.3390/cancers13215368

AMA Style

Kanavati F, Tsuneki M. Breast Invasive Ductal Carcinoma Classification on Whole Slide Images with Weakly-Supervised and Transfer Learning. Cancers. 2021; 13(21):5368. https://doi.org/10.3390/cancers13215368

Chicago/Turabian Style

Kanavati, Fahdi, and Masayuki Tsuneki. 2021. "Breast Invasive Ductal Carcinoma Classification on Whole Slide Images with Weakly-Supervised and Transfer Learning" Cancers 13, no. 21: 5368. https://doi.org/10.3390/cancers13215368

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop