WITHDRAWN: Few-shot Learning on the Diagnosis of Lymphatic Metastasis of Lung Carcinoma

Abstract

Background：Lymph node metastasis of lung cancer plays an important part in lung cancer diagnosis since its close relationship with patients’ prognosis and subsequent treatment, however, diagnosis of lymph node metastases often was tedious and takes too much time for pathologists. Automatized classification with few-shot learning algorithms is required for clinical situations that only unbalanced and small datasets can be collected. We developed a few-shot learning algorithms for automatized classification of lymphatic metastasis of lung carcinoma from Whole Slide Images (WSIs) through a deep convolutional neural network (DCNN).Material and methods: Lymph node slides of patients with lung cancer collected from July to December 2018 were reviewed and used for model development retrospectively. A total of 1701 lymph node slides from 453 lung cancer patients with different histological types were enrolled. Each slide could provide a different number of patches, in which 6, 8, 10, 20, and 30 positive patches and 12, 16, 20, 40, and 60 negative patches for training and validation, respectively. A total of 1577 WSIs were used. The receiver operating characteristic (ROC) analysis of the model was performed for estimating the performance and compared to the traditional deep learning approach Resnet34.Results: Deep learning methods, when trained with very few shots (6 positive/12 negative, 8 positive/16 negative, and 10 positive/20 negative patches), the traditional deep learning approach Resnet34 was outperformed by our Aitrox model. When the dataset was raised to 20 positive/40 negative patches, similar performance was achieved with AUC 0.5895 (95% CI, 0.5833-0.5910) for Resnet34 and 0.6124 (95% CI, 0.6077-0.6147) for our Aitrox model. Resnet34 over-performed our Aitrox model (AUC=0.6450 [95%CI, 0.6397-0.6470]) with an AUC of 0.7481 (95%CI, 0.7120-0.7485) when the training and validation dataset was raised to 30 positive/60 negative patches.Conclusions: This proposed few-shot method may address AI approaches to the diagnosis of lymphatic metastasis of lung carcinoma and other kinds of carcinoma in the future.

FHIST: A Benchmark for Few-shot Classification of Histological Images

“…A few recent works tackled few-shot learning in specific medical-imaging areas [46,12,51,47,85,72]. In [46], for instance, two few-shot learning methods, namely Reptile [49] and Prototypical Networks [66], were applied to skin-disease identification.…”

“…In [47], a deep Siamese neural network was trained to transfer knowledge from a dataset containing colon tissue to another dataset containing colon, lung and breast tissue. Finally, [72] proposed a few-shot learning algorithm based on Prototypical Networks, for classifiying lymphatic metastasis of lung carcinoma from Whole Slide Images (WSIs).…”

“…Despite the high clinical relevance of few-shot classification of histology images, the literature on the subject is, to our knowledge, very limited [47,72] and confined to specific cancer sites, in-house data sets and binary classification, which do not reflect the high diversity and fine granularity of cancer related tissue classification tasks encountered in realistic settings. For instance, [47] used a private data set and is limited to binary classification (cancerous/non-cancerous).…”