Detection of Lung Cancer Lymph Node Metastases from Whole-Slide Histopathologic Images Using a Two-Step Deep Learning Approach

Abstract

The application of deep learning for the detection of lymph node metastases on histologic slides has attracted worldwide attention due to its potentially important role in patient treatment and prognosis. Despite this attention, false-positive predictions remain problematic, particularly in the case of reactive lymphoid follicles. In this study, a novel two-step deep learning algorithm was developed to address the issue of false-positive prediction while maintaining accurate cancer detection. Three-hundred and fortynine whole-slide lung cancer lymph node images, including 233 slides for algorithm training, 10 slides for validation, and 106 slides for evaluation, were collected. In the first step, a deep learning algorithm was used to eliminate frequently misclassified noncancerous regions (lymphoid follicles). In the second step, a deep learning classifier was developed to detect cancer cells. Using this two-step approach, errors were reduced by 36.4% on average and up to 89% in slides with reactive lymphoid follicles. Furthermore, 100% sensitivity was reached in cases of macrometastases, micrometastases, and isolated tumor cells. To reduce the small number of remaining false positives, a receiver-operating characteristic curve was created using foci size thresholds of 0.6 mm and 0.7 mm, achieving sensitivity and specificity of 79.6% and 96.5%, and 75.5% and 98.2%, respectively. A two-step approach can be used to detect lung cancer metastases in lymph node tissue effectively and with few false positives.

Development and Validation of a Nomogram for Preoperative Prediction of Lymph Node Metastasis in Lung Adenocarcinoma Based on Radiomics Signature and Deep Learning Signature

“…The model developed by deep learning has been successfully applied to the detection of skin cancer, diabetic retinopathy, breast cancer and so on (17)(18)(19)(20). There are also studies related to deep learning in the diagnosis of lymph nodes of lung cancer (21,22). However, few studies used both radiomics and deep learning to predict LN metastasis.…”

Radiomics: from qualitative to quantitative imaging

“…89 Pham et al used a two-step deep learning approach for evaluating lymph node metastases with accurate cancer detection. 90 Instead of using data from a single time point, deep recurrent convolutional network architectures can be used to analyse data from multiple time points to monitor treatment response. 91 Brain Brain tumours are usually graded based on clinical or pathological analysis to define their malignancy.…”

Quality control stress test for deep learning-based diagnostic model in digital pathology

“…Principle component analysis and t-distributed stochastic neighbor embedding (t-SNE) modules from scikit-learn package for Python were used for analysis of similarity of image patch content. For this purpose, convolutional base of the model was disconnected from classification head and connected to three consecutive global average pooling layers to reduce the dimensions of output vector; output of the last convolutional layer with dimensions (8,8,1536) was therefore transformed to a vector (1,1,1536). Principal component analysis was performed using 700 components as first step with further t-SNE using 2 components and 3000 iterations.…”

“…The latter use unsupervised feature generation by convolving images using multiple different filters and aggregate the corresponding representations in different ways to achieve a prediction. Many studies to date addressed the feasibility of DL for diagnostic applications with high accuracy [4][5][6][7][8][9][10][11][12][13][14][15][16] resulting in several commercial diagnostic products that are being developed for prostate cancer, breast cancer, skin diseases, and in other medical domains. However, this is still a work in progress.…”