Weakly Supervised Deep Learning for Whole Slide Lung Cancer Image Analysis

By Xi Wang, Hao Chen, Caixia Gan, Huangjing Lin, Qi-Yan Dou, Efstratios Tsougenis, Qitao Huang, Muyan Cai, P. Heng. IEEE Transactions on Cybernetics, 2020

373 citations recorded by the source corpus.

Histopathology image analysis serves as the gold standard for cancer diagnosis. Efficient and precise diagnosis is quite critical for the subsequent therapeutic treatment of patients. So far, computer-aided diagnosis has not been widely applied in pathological field yet as currently well-addressed tasks are only the tip of the iceberg. Whole slide image (WSI) classification is a quite challenging problem. First, the scarcity of annotations heavily impedes the pace of developing effective approaches. Pixelwise delineated annotations on WSIs are time consuming and tedious, which poses difficulties in building a large-scale training dataset. In addition, a variety of heterogeneous patterns of tumor existing in high magnification field are actually the major obstacle. Furthermore, a gigapixel scale WSI cannot be directly analyzed due to the immeasurable computational cost. How to design the weakly supervised learning methods to maximize the use of available WSI-level labels that can be readily obtained in clinical practice is quite appealing. To overcome these challenges, we present a weakly supervised approach in this article for fast and effective classification on the whole slide lung cancer images. Our method first takes advantage of a patch-based fully convolutional network (FCN) to retrieve discriminative blocks and provides representative deep features with high efficiency. Then, different context-aware block selection and feature aggregation strategies are explored to generate globally holistic WSI descriptor which is ultimately fed into a random forest (RF) classifier for the image-level prediction. To the best of our knowledge, this is the first study to exploit the potential of image-level labels along with some coarse annotations for weakly supervised learning. A large-scale lung cancer WSI dataset is constructed in this article for evaluation, which validates the effectiveness and feasibility of the proposed method. Extensive experiments demonstrate the superior performance of our method that surpasses the state-of-the-art approaches by a significant margin with an accuracy of 97.3%. In addition, our method also achieves the best performance on the public lung cancer WSIs dataset from The Cancer Genome Atlas (TCGA). We highlight that a small number of coarse annotations can contribute to further accuracy improvement. We believe that weakly supervised learning methods have great potential to assist pathologists in histology image diagnosis in the near future.

Subfields: Artificial Intelligence, Cancer Research, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/159f4c05bc29e86bcbf8c1bcd9eae1f33ce2f3da

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification (2022, background): “This problem in turn encourages researchers to develop deep learning based models trained with limited annotations, termed as “Weakly Supervised” or “Semi-Supervised” [22,26,35,41].”
Deep learning in histopathology: the path to the clinic (2021, methodology): “Clinical annotation of WSIs tends to be easier to achieve than manual annotation, and has resulted in large datasets in several studies (for example, for prostate cancer 75 , lung cancer 26 and colorectal cancer 77 ).”
Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks (2020, background): “Recently, researchers have developed many weakly supervised algorithms to medical images including weakly-supervised X-rays screening [25, 26] and WSI classification [27–31].”
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classication (2021, methodology): “In addition, the feature clustering methods [14, 27, 28] calculated the cluster centroids of all the feature embeddings and then the representative feature embeddings was employed to make the final prediction.”
Deep neural network models for computational histopathology: A survey (2019, methodology): “roach China Big Data and AI challenge (1,900 images) Ilse et al. (2018) (X) Multi-Cancers H&E Cancer image classiﬁcation MIL pooling based on gatedattention mechanism CRCHisto (100 images) Shujun Wang et al. (2019) Stomach H&E Gastric cancer detection Two-stage CNN framework forlocalizationa”