Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

Abstract

Fast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

WITHDRAWN: Few-shot Learning on the Diagnosis of Lymphatic Metastasis of Lung Carcinoma

“…The clinical-grade pathology using was trained by weakly supervised deep learning with over thousands of slides dataset including prostate core biopsy, breast cancer metastatic lymph node, and skin lesion separately; and the area under the curve (AUC) can be 0.965 on the test of breast axillary lymph node metastasis [8]. The accuracy of the weakly supervised deep learning may be affected by the labels [9] and the size of the dataset which could be improved by upgrading the algorithm iteration [11][12][13]. Atsushi Teramoto improves 4% AUC by using a two-step supervised strategy for the classification of lung cytological images with 60 cases dataset [14].…”

A prognostic and predictive computational pathology image signature for added benefit of adjuvant chemotherapy in early stage non-small-cell lung cancer

“…Secondly, for predicting benefit to ACT, the surgery only and the surgery+ACT groups used in the analysis were not strictly and homogeneously controlled (including ACT protocol), it is likely that the assignment and protocol of ACT might have differed across the institutions considered in this study. Recently, transfer learning based approaches have been applied in tumor detection and classification [ 36 , 37 ]. An avenue for future investigation might involve the use of transfer learning, potentially leveraging other data streams like quantitative immunofluorescence, for the problems of cancer prognosis and response prediction.…”

A review of transfer learning for medical image classification

“…Random initialization often appeared in the literature [29][30][31][32]. These studies re-use the skeleton of CNN models only and train the model from scratch.…”