The level of PD-L1 expression in immunohistochemistry (IHC) assays is a key biomarker for the identification of Non-Small-Cell-Lung-Cancer (NSCLC) patients that may respond to anti PD-1/PD-L1 ...treatments. The quantification of PD-L1 expression currently includes the visual estimation by a pathologist of the percentage (tumor proportional scoring or TPS) of tumor cells showing PD-L1 staining. Known challenges like differences in positivity estimation around clinically relevant cut-offs and sub-optimal quality of samples makes visual scoring tedious and subjective, yielding a scoring variability between pathologists. In this work, we propose a novel deep learning solution that enables the first automated and objective scoring of PD-L1 expression in late stage NSCLC needle biopsies. To account for the low amount of tissue available in biopsy images and to restrict the amount of manual annotations necessary for training, we explore the use of semi-supervised approaches against standard fully supervised methods. We consolidate the manual annotations used for training as well the visual TPS scores used for quantitative evaluation with multiple pathologists. Concordance measures computed on a set of slides unseen during training provide evidence that our automatic scoring method matches visual scoring on the considered dataset while ensuring repeatability and objectivity.
The identification of new tumor biomarkers for patient stratification before therapy, for monitoring of disease progression, and for characterization of tumor biology plays a crucial role in cancer ...research. The status of these biomarkers is mostly scored manually by a pathologist and such scores typically, do not consider the spatial heterogeneity of the protein's expression in the tissue. Using advanced image analysis methods, marker expression can be determined quantitatively with high accuracy and reproducibility on a per-cell level. To aggregate such per-cell marker expressions on a patient level, the expression values for single cells are usually averaged for the whole tissue. However, averaging neglects the spatial heterogeneity of the marker expression in the tissue. We present two novel approaches for quantitative scoring of spatial marker expression heterogeneity. The first approach is based on a co-occurrence analysis of the marker expression in neighboring cells. The second approach accounts for the local variability of the protein's expression by tiling the tissue with a regular grid and assigning local spatial heterogeneity phenotypes per tile. We apply our novel scores to quantify the spatial expression of four different membrane markers, i.e., HER2, CMET, CD44, and EGFR in immunohistochemically (IHC) stained tissue sections of colorectal cancer patients. We evaluate the prognostic relevance of our spatial scores in this cohort and show that the spatial heterogeneity scores clearly outperform the marker expression average as a prognostic factor (CMET: p-value=0.01 vs. p-value=0.3).
Many targeted cancer therapies rely on biomarkers assessed by scoring of immunohistochemically (IHC)-stained tissue, which is subjective, semiquantitative, and does not account for expression ...heterogeneity. We describe an image analysis-based method for quantitative continuous scoring (QCS) of digital whole-slide images acquired from baseline human epidermal growth factor receptor 2 (HER2) IHC-stained breast cancer tissue. Candidate signatures for patient stratification using QCS of HER2 expression on subcellular compartments were identified, addressing the spatial distribution of tumor cells and tumor-infiltrating lymphocytes. Using data from trastuzumab deruxtecan-treated patients with HER2-positive and HER2-negative breast cancer from a phase 1 study (NCT02564900; DS8201-A-J101; N = 151), QCS-based patient stratification showed longer progression-free survival (14.8 vs 8.6 months) with higher prevalence of patient selection (76.4 vs 56.9%) and a better cross-validated log-rank p value (0.026 vs 0.26) than manual scoring based on the American Society of Clinical Oncology / College of American Pathologists guidelines. QCS-based features enriched the HER2-negative subgroup by correctly predicting 20 of 26 responders.
•CNNs for Action Recognition can be learned from visual data available on the web.•One of the main problems in webly-supervised learning is cleaning the noisy data.•We present a method that avoids ...bias from the filtering technique.•Trimmed and untrimmed classification and localization is possible without retraining.
Webly-supervised learning has recently emerged as an alternative paradigm to traditional supervised learning based on large-scale datasets with manual annotations. The key idea is that models such as CNNs can be learned from the noisy visual data available on the web. In this work we aim to exploit web data for video understanding tasks such as action recognition and detection. One of the main problems in webly-supervised learning is cleaning the noisy labeled data from the web. The state-of-the-art paradigm relies on training a first classifier on noisy data that is then used to clean the remaining dataset. Our key insight is that this procedure biases the second classifier towards samples that the first one understands. Here we train two independent CNNs, a RGB network on web images and video frames and a second network using temporal information from optical flow. We show that training the networks independently is vastly superior to selecting the frames for the flow classifier by using our RGB network. Moreover, we show benefits in enriching the training set with different data sources from heterogeneous public web databases. We demonstrate that our framework outperforms all other webly-supervised methods on two public benchmarks, UCF-101 and Thumos’14.
Unsupervised and unpaired domain translation using generative adversarial neural networks, and more precisely CycleGAN, is state of the art for the stain translation of histopathology images. It ...often, however, suffers from the presence of cycle-consistent but non structure-preserving errors. We propose an alternative approach to the set of methods which, relying on segmentation consistency, enable the preservation of pathology structures. Focusing on immunohistochemistry (IHC) and multiplexed immunofluorescence (mIF), we introduce a simple yet effective guidance scheme as a loss function that leverages the consistency of stain translation with stain isolation. Qualitative and quantitative experiments show the ability of the proposed approach to improve translation between the two domains.
We report the ability of two deep learning-based decision systems to stratify non-small cell lung cancer (NSCLC) patients treated with checkpoint inhibitor therapy into two distinct survival groups. ...Both systems analyze functional and morphological properties of epithelial regions in digital histopathology whole slide images stained with the SP263 PD-L1 antibody. The first system learns to replicate the pathologist assessment of the Tumor Cell (TC) score with a cut-point for positivity at 25% for patient stratification. The second system is free from assumptions related to TC scoring and directly learns patient stratification from the overall survival time and event information. Both systems are built on a novel unpaired domain adaptation deep learning solution for epithelial region segmentation. This approach significantly reduces the need for large pixel-precise manually annotated datasets while superseding serial sectioning or re-staining of slides to obtain ground truth by cytokeratin staining. The capacity of the first system to replicate the TC scoring by pathologists is evaluated on 703 unseen cases, with an addition of 97 cases from an independent cohort. Our results show Lin's concordance values of 0.93 and 0.96 against pathologist scoring, respectively. The ability of the first and second system to stratify anti-PD-L1 treated patients is evaluated on 151 clinical samples. Both systems show similar stratification powers (first system: HR = 0.539, p = 0.004 and second system: HR = 0.525, p = 0.003) compared to TC scoring by pathologists (HR = 0.574, p = 0.01).
Generative Adversarial Networks (GANs) are state of the art for image synthesis. Here, we present dapi2ck, a novel GAN-based approach to synthesize cytokeratin (CK) staining from immunofluorescent ...(IF) DAPI staining of nuclei in non-small cell lung cancer (NSCLC) images. We use the synthetic CK to segment epithelial regions, which, compared to expert annotations, yield equally good results as segmentation on stained CK. Considering the limited number of markers in a multiplexed IF (mIF) panel, our approach allows to replace CK by another marker addressing the complexity of the tumor micro-environment (TME) to facilitate patient selection for immunotherapies. In contrast to stained CK, dapi2ck does not suffer from issues like unspecific CK staining or loss of tumoral CK expression.
The detection of nuclei is one of the most fundamental components of computational pathology. Current state-of-the-art methods are based on deep learning, with the prerequisite that extensive labeled ...datasets are available. The increasing number of patient cohorts to be analyzed, the diversity of tissue stains and indications, as well as the cost of dataset labeling motivates the development of novel methods to reduce labeling effort across domains. We introduce in this work a weakly supervised 'inter-domain' approach that (i) performs stain normalization and unpaired image-to-image translation to transform labeled images on a source domain to synthetic labeled images on an unlabeled target domain and (ii) uses the resulting synthetic labeled images to train a detection network on the target domain. Extensive experiments show the superiority of the proposed approach against the state-of-the-art 'intra-domain' detection based on fully-supervised learning.
The analysis of the tumor environment on digital histopathology slides is becoming key for the understanding of the immune response against cancer, supporting the development of novel ...immuno-therapies. We introduce here a novel deep learning solution to the related problem of tumor epithelium segmentation. While most existing deep learning segmentation approaches are trained on time-consuming and costly manual annotation on single stain domain (PD-L1), we leverage here semi-automatically labeled images from a second stain domain (Cytokeratin-CK). We introduce an end-to-end trainable network that jointly segment tumor epithelium on PD-L1 while leveraging unpaired image-to-image translation between CK and PD-L1, therefore completely bypassing the need for serial sections or re-staining of slides. Extending the method to differentiate between PD-L1 positive and negative tumor epithelium regions enables the automated estimation of the PD-L1 Tumor Cell (TC) score. Quantitative experimental results demonstrate the accuracy of our approach against state-of-the-art segmentation methods.
The level of PD-L1 expression in immunohistochemistry (IHC) assays is a key biomarker for the identification of Non-Small-Cell-Lung-Cancer (NSCLC) patients that may respond to anti PD-1/PD-L1 ...treatments. The quantification of PD-L1 expression currently includes the visual estimation of a Tumor Cell (TC) score by a pathologist and consists of evaluating the ratio of PD-L1 positive and PD-L1 negative tumor cells. Known challenges like differences in positivity estimation around clinically relevant cut-offs and sub-optimal quality of samples makes visual scoring tedious and subjective, yielding a scoring variability between pathologists. In this work, we propose a novel deep learning solution that enables the first automated and objective scoring of PD-L1 expression in late stage NSCLC needle biopsies. To account for the low amount of tissue available in biopsy images and to restrict the amount of manual annotations necessary for training, we explore the use of semi-supervised approaches against standard fully supervised methods. We consolidate the manual annotations used for training as well the visual TC scores used for quantitative evaluation with multiple pathologists. Concordance measures computed on a set of slides unseen during training provide evidence that our automatic scoring method matches visual scoring on the considered dataset while ensuring repeatability and objectivity.