skip to main content

Title: Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised Learning
Lung squamous cell carcinoma (LSCC) has a high recurrence and metastasis rate. Factors influencing recurrence and metastasis are currently unknown and there are no distinct histopathological or morphological features indicating the risks of recurrence and metastasis in LSCC. Our study focuses on the recurrence prediction of LSCC based on H&E-stained histopathological whole-slide images (WSI). Due to the small size of LSCC cohorts in terms of patients with available recurrence information, standard end-to-end learning with various convolutional neural networks for this task tends to overfit. Also, the predictions made by these models are hard to interpret. Histopathology WSIs are typically very large and are therefore processed as a set of smaller tiles. In this work, we propose a novel conditional self-supervised learning (SSL) method to learn representations of WSI at the tile level first, and leverage clustering algorithms to identify the tiles with similar histopathological representations. The resulting representations and clusters from self-supervision are used as features of a survival model for recurrence prediction at the patient level. Using two publicly available datasets from TCGA and CPTAC, we show that our LSCC recurrence prediction survival model outperforms both LSCC pathological stage-based approach and machine learning baselines such as multiple instance learning. The proposed method also enables us to explain the recurrence histopathological risk factors via the derived clusters. This can help pathologists derive new hypotheses regarding morphological features associated with LSCC recurrence.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Medical Imaging with Deep Learning
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Automatic histopathological Whole Slide Image (WSI) analysis for cancer classification has been highlighted along with the advancements in microscopic imaging techniques, since manual examination and diagnosis with WSIs are time- and cost-consuming. Recently, deep convolutional neural networks have succeeded in histopathological image analysis. However, despite the success of the development, there are still opportunities for further enhancements. In this paper, we propose a novel cancer texture-based deep neural network (CAT-Net) that learns scalable morphological features from histopathological WSIs. The innovation of CAT-Net is twofold: (1) capturing invariant spatial patterns by dilated convolutional layers and (2) improving predictive performance while reducing model complexity. Moreover, CAT-Net can provide discriminative morphological (texture) patterns formed on cancerous regions of histopathological images comparing to normal regions. We elucidated how our proposed method, CAT-Net, captures morphological patterns of interest in hierarchical levels in the model. The proposed method out-performed the current state-of-the-art benchmark methods on accuracy, precision, recall, and F1 score. 
    more » « less
  2. Histopathological image analysis is critical in cancer diagnosis and treatment. Due to the huge size of histopathological images, most existing works analyze the whole slide pathological image (WSI) as a bag and its patches are considered as instances. However, these approaches are limited to analyzing the patches in a fixed shape, while the malignant lesions can form varied shapes. To address this challenge, we propose the Multi-Instance Multi-Shape Support Vector Machine (MIMSSVM) to analyze the multiple images (instances) jointly where each instance consists of multiple patches in varied shapes. In our approach, we can identify the varied morphologic abnormalities of nuclei shapes from the multiple images. In addition to the multi-instance multi-shape learning capability, we provide an efficient algorithm to optimize the proposed model which scales well to a large number of features. Our experimental results show the proposed MIMSSVM method outperforms the existing SVM and recent deep learning models in histopathological classification. The proposed model also identifies the tissue segments in an image exhibiting an indication of an abnormality which provides utility in the early detection of malignant tumors. 
    more » « less
  3. Abstract

    Breast carcinoma is the most common cancer among women worldwide that consists of a heterogeneous group of subtype diseases. The whole-slide images (WSIs) can capture the cell-level heterogeneity, and are routinely used for cancer diagnosis by pathologists. However, key driver genetic mutations related to targeted therapies are identified by genomic analysis like high-throughput molecular profiling. In this study, we develop a deep-learning model to predict the genetic mutations and biological pathway activities directly from WSIs. Our study offers unique insights into WSI visual interactions between mutation and its related pathway, enabling a head-to-head comparison to reinforce our major findings. Using the histopathology images from the Genomic Data Commons Database, our model can predict the point mutations of six important genes (AUC 0.68–0.85) and copy number alteration of another six genes (AUC 0.69–0.79). Additionally, the trained models can predict the activities of three out of ten canonical pathways (AUC 0.65–0.79). Next, we visualized the weight maps of tumor tiles in WSI to understand the decision-making process of deep-learning models via a self-attention mechanism. We further validated our models on liver and lung cancers that are related to metastatic breast cancer. Our results provide insights into the association between pathological image features, molecular outcomes, and targeted therapies for breast cancer patients.

    more » « less
  4. null (Ed.)
    This work proposes a new unsupervised (or self-supervised) node representation learning method that aims to leverage the coarse-grain information that is available in most graphs. This extends previous attempts that only leverage fine-grain information (similarities within local neighborhoods) or global graph information (similarities across all nodes). Intuitively, the proposed method identifies nodes that belong to the same clusters and maximizes their mutual information. Thus, coarse-grain (cluster-level) similarities that are shared between nodes are preserved in their representations. The core components of the proposed method are (i) a jointly optimized clustering of nodes during learning and (ii) an Infomax objective term that preserves the mutual information among nodes of the same clusters. Our method is able to outperform competing state-of-art methods in various downstream tasks, such as node classification, link prediction, and node clustering. Experiments show that the average gain is between 0.2% and 6.1%, over the best competing approach, over all tasks. Our code is publicly available at: 
    more » « less
  5. null (Ed.)
    Semi-supervised learning (SSL) is an appealing approach to resolve generalization problem for speech emotion recognition (SER) systems. By utilizing large amounts of unlabeled data, SSL is able to gain extra information about the prior distribution of the data. Typically, it can lead to better and robust recognition performance. Existing SSL approaches for SER include variations of encoder-decoder model structures such as autoencoder (AE) and variational autoencoders (VAEs), where it is difficult to interpret the learning mechanism behind the latent space. In this study, we introduce a new SSL framework, which we refer to as the DeepEmoCluster framework, for attribute-based SER tasks. The DeepEmoCluster framework is an end-to-end model with mel-spectrogram inputs, which combines a self-supervised pseudo labeling classification network with a supervised emotional attribute regressor. The approach encourages the model to learn latent representations by maximizing the emotional separation of K-means clusters. Our experimental results based on the MSP-Podcast corpus indicate that the DeepEmoCluster framework achieves competitive prediction performances in fully supervised scheme, outperforming baseline methods in most of the conditions. The approach can be further improved by incorporating extra unlabeled set. Moreover, our experimental results explicitly show that the latent clusters have emotional dependencies, enriching the geometric interpretation of the clusters. 
    more » « less