Search

In this work, we propose a deep learning system for weakly supervised object detection in digital pathology whole slide images. We designed the system to be organ- and object-agnostic, and to be adapted on-the-fly to detect novel objects based on a few examples provided by the user. We tested our method on detection of healthy glands in colon biopsies and ductal carcinoma in situ (DCIS) of the breast, showing that (1) the same system is capable of adapting to detect requested objects with high accuracy, namely 87% accuracy assessed on 582 detections in colon tissue, and 93% accuracy assessed on 163 DCIS detections in breast tissue; (2) in some settings, the system is capable of retrieving similar cases with little to none false positives (i.e., precision equal to 1.00); (3) the performance of the system can benefit from previously detected objects with high confidence that can be reused in new searches in an iterative fashion.

The tumour microenvironment has been shown to be a valuable source of prognostic information for different cancer types. This holds in particular for triple negative breast cancer (TNBC), a breast cancer subtype for which currently no prognostic biomarkers are established. Although different methods to assess tumour infiltrating lymphocytes (TILs) have been published, it remains unclear which method (marker, region) yields the most optimal prognostic information. In addition, to date, no objective TILs assessment methods are available. For this proof of concept study, a subset of our previously described TNBC cohort (n = 94) was stained for CD3, CD8 and FOXP3 using multiplex immunohistochemistry and subsequently imaged by a multispectral imaging system. Advanced whole-slide image analysis algorithms, including convolutional neural networks (CNN) were used to register unmixed multispectral images and corresponding H&E sections, to segment the different tissue compartments (tumour, stroma) and to detect all individual positive lymphocytes. Densities of positive lymphocytes were analysed in different regions within the tumour and its neighbouring environment and correlated to relapse free survival (RFS) and overall survival (OS). We found that for all TILs markers the presence of a high density of positive cells correlated with an improved survival. None of the TILs markers was superior to the others. The results of TILs assessment in the various regions did not show marked differences between each other. The negative correlation between TILs and survival in our cohort are in line with previous studies. Our results provide directions for optimizing TILs assessment methodology., Highlights • Deep learning algorithms enable objective assessment of biomarkers. • Automated assessment of tumour infiltrating lymphocytes is feasible. • Tumour infiltrating lymphocytes are prognostic in triple negative breast cancer.

Automated detection of cancer metastases in lymph nodes has the potential to improve the assessment of prognosis for patients. To enable fair comparison between the algorithms for this purpose, we set up the CAMELYON17 challenge in conjunction with the IEEE International Symposium on Biomedical Imaging 2017 Conference in Melbourne. Over 300 participants registered on the challenge website, of which 23 teams submitted a total of 37 algorithms before the initial deadline. Participants were provided with 899 whole-slide images (WSIs) for developing their algorithms. The developed algorithms were evaluated based on the test set encompassing 100 patients and 500 WSIs. The evaluation metric used was a quadratic weighted Cohen's kappa. We discuss the algorithmic details of the 10 best pre-conference and two post-conference submissions. All these participants used convolutional neural networks in combination with pre- and postprocessing steps. Algorithms differed mostly in neural network architecture, training strategy, and pre- and postprocessing methodology. Overall, the kappa metric ranged from 0.89 to -0.13 across all submissions. The best results were obtained with pre-trained architectures such as ResNet. Confusion matrix analysis revealed that all participants struggled with reliably identifying isolated tumor cells, the smallest type of metastasis, with detection rates below 40%. Qualitative inspection of the results of the top participants showed categories of false positives, such as nerves or contamination, which could be targeted for further optimization. Last, we show that simple combinations of the top algorithms result in higher kappa metric values than any algorithm individually, with 0.93 for the best combination.

Manual counting of mitotic tumor cells in tissue sections constitutes one of the strongest prognostic markers for breast cancer. This procedure, however, is time-consuming and error-prone. We developed a method to automatically detect mitotic figures in breast cancer tissue sections based on convolutional neural networks (CNNs). Application of CNNs to hematoxylin and eosin (H&E) stained histological tissue sections is hampered by: (1) noisy and expensive reference standards established by pathologists, (2) lack of generalization due to staining variation across laboratories, and (3) high computational requirements needed to process gigapixel whole-slide images (WSIs). In this paper, we present a method to train and evaluate CNNs to specifically solve these issues in the context of mitosis detection in breast cancer WSIs. First, by combining image analysis of mitotic activity in phosphohistone-H3 (PHH3) restained slides and registration, we built a reference standard for mitosis detection in entire H&E WSIs requiring minimal manual annotation effort. Second, we designed a data augmentation strategy that creates diverse and realistic H&E stain variations by modifying the hematoxylin and eosin color channels directly. Using it during training combined with network ensembling resulted in a stain invariant mitosis detector. Third, we applied knowledge distillation to reduce the computational requirements of the mitosis detection ensemble with a negligible loss of performance. The system was trained in a single-center cohort and evaluated in an independent multicenter cohort from The Cancer Genome Atlas on the three tasks of the Tumor Proliferation Assessment Challenge (TUPAC). We obtained a performance within the top-3 best methods for most of the tasks of the challenge., Accepted to appear in IEEE Transactions on Medical Imaging

The immune system is of critical importance in the development of cancer. The evasion of destruction by the immune system is one of the emerging hallmarks of cancer. We have built a dataset of 171,166 manually annotated CD3 + and CD8 + cells, which we used to train deep learning algorithms for automatic detection of lymphocytes in histopathology images to better quantify immune response. Moreover, we investigate the effectiveness of four deep learning based methods when different subcompartments of the whole-slide image are considered: normal tissue areas, areas with immune cell clusters, and areas containing artifacts. We have compared the proposed methods in breast, colon and prostate cancer tissue slides collected from nine different medical centers. Finally, we report the results of an observer study on lymphocyte quantification, which involved four pathologists from different medical centers, and compare their performance with the automatic detection. The results give insights on the applicability of the proposed methods for clinical use. U-Net obtained the highest performance with an F1-score of 0.78 and the highest agreement with manual evaluation ( κ = 0.72 ), whereas the average pathologists agreement with reference standard was κ = 0.64 . The test set and the automatic evaluation procedure are publicly available at lyon19.grand-challenge.org .

As part of routine histological grading, for every invasive breast cancer the mitotic count is assessed by counting mitoses in the (visually selected) region with the highest proliferative activity. Because this procedure is prone to subjectivity, the present study compares visual mitotic counting with deep learning based automated mitotic counting and fully automated hotspot selection. Two cohorts were used in this study. Cohort A comprised 90 prospectively included tumors which were selected based on the mitotic frequency scores given during routine glass slide diagnostics. This pathologist additionally assessed the mitotic count in these tumors in whole slide images (WSI) within a preselected hotspot. A second observer performed the same procedures on this cohort. The preselected hotspot was generated by a convolutional neural network (CNN) trained to detect all mitotic figures in digitized hematoxylin and eosin (HE) sections. The second cohort comprised a multicenter, retrospective TNBC cohort (n = 298), of which the mitotic count was assessed by three independent observers on glass slides. The same CNN was applied on this cohort and the absolute number of mitotic figures in the hotspot was compared to the averaged mitotic count of the observers. Baseline interobserver agreement for glass slide assessment in cohort A was good (kappa 0.689; 95% CI 0.580-0.799). Using the CNN generated hotspot in WSI, the agreement score increased to 0.814 (95% CI 0.719-0.909). Automated counting by the CNN in comparison with observers counting in the predefined hotspot region yielded an average kappa of 0.724. We conclude that manual mitotic counting is not affected by assessment modality (glass slides, WSI) and that counting mitotic figures in WSI is feasible. Using a predefined hotspot area considerably improves reproducibility. Also, fully automated assessment of mitotic score appears to be feasible without introducing additional bias or variability.

The prognostic value of mitotic count for invasive breast cancer is firmly established. As yet, however, limited studies have been aimed at assessing mitotic counts as a prognostic factor for triple negative breast cancers (TNBC). Here, we assessed the prognostic value of absolute mitotic counts for TNBC, using both deep learning and manual procedures.A retrospective TNBC cohort (n = 298) was used. The absolute manual mitotic count was assessed by averaging counts from three independent observers. Deep learning was performed using a convolutional neural network on digitized HE slides. Multivariable Cox regression models for relapse-free survival and overall survival served as baseline models. These were expanded with dichotomized mitotic counts, attempting every possible cut-off value, and evaluated by means of the c-statistic.We found that per 2 mmBased on our results we conclude that the level of proliferation, as reflected by mitotic count, does not serve as a prognostic factor for TNBC. Therefore, TNBC patient management based on mitotic count should be discouraged.

The number of mitotic figures per tumor area observed in hematoxylin and eosin (H and E) histological tissue sections under light microscopy is an important biomarker for breast cancer prognosis. Whole-slide imaging and computational pathology have enabled the development of automatic mitosis detection algorithms based on convolutional neural networks (CNNs). These models can suffer from high generalization error, i.e. trained networks often underperform on datasets originating from pathology laboratories different than the one that provided the training data, mainly due to the presence of inter-laboratory stain variations. We propose a novel data augmentation strategy that exploits the properties of the H and E color space to simulate a broad range of realistic H and E stain variations. To our best knowledge, this is the first time that data augmentation is performed directly in the H and E color space, instead of RGB. The proposed technique uses color deconvolution to transform RGB images into the H and E color space, modifies the H and E color channels stochastically, and projects them back to RGB space. We trained a CNN-based mitosis detector on homogeneous data from a single institution, and tested its performance on an external, multicenter cohort that contained a wide range of unseen H and E stain variations. We compared CNNs trained with and without the proposed augmentation strategy and observed a significant improvement in performance and robustness to unseen stain variations when the new color augmentation technique was included. In essence, we have shown that CNNs can be made robust to inter-lab stain variation by incorporating extensive stain augmentation techniques.

IMPORTANCE: Application of deep learning algorithms to whole-slide pathology imagescan potentially improve diagnostic accuracy and efficiency. OBJECTIVE: Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting. DESIGN, SETTING, AND PARTICIPANTS: Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). EXPOSURES: Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. MAIN OUTCOMES AND MEASURES: The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. RESULTS: The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P

Modern pathology diagnostics is being driven toward large scale digitization of microscopic tissue sections. A prerequisite for its safe implementation is the guarantee that all tissue present on a glass slide can also be found back in the digital image. Whole-slide scanners perform a tissue segmentation in a low resolution overview image to prevent inefficient high-resolution scanning of empty background areas. However, currently applied algorithms can fail in detecting all tissue regions. In this study, we developed convolutional neural networks to distinguish tissue from background. We collected 100 whole-slide images of 10 tissue samples—staining categories from five medical centers for development and testing. Additionally, eight more images of eight unfamiliar categories were collected for testing only. We compared our fully-convolutional neural networks to three traditional methods on a range of resolution levels using Dice score and sensitivity. We also tested whether a single neural network can perform equivalently to multiple networks, each specialized in a single resolution. Overall, our solutions outperformed the traditional methods on all the tested resolutions. The resolution-agnostic network achieved average Dice scores between 0.97 and 0.98 across the tested resolution levels, only 0.0069 less than the resolution-specific networks. Finally, its excellent generalization performance was demonstrated by achieving averages of 0.98 Dice score and 0.97 sensitivity on the eight unfamiliar images. A future study should test this network prospectively.

Contains fulltext : 181885.pdf (Publisher’s version ) (Open Access) Currently, histopathological tissue examination by a pathologist represents the gold standard for breast lesion diagnostics. Automated classification of histopathological whole-slide images (WSIs) is challenging owing to the wide range of appearances of benign lesions and the visual similarity of ductal carcinoma in-situ (DCIS) to invasive lesions at the cellular level. Consequently, analysis of tissue at high resolutions with a large contextual area is necessary. We present context-aware stacked convolutional neural networks (CNN) for classification of breast WSIs into normal/benign, DCIS, and invasive ductal carcinoma (IDC). We first train a CNN using high pixel resolution to capture cellular level information. The feature responses generated by this model are then fed as input to a second CNN, stacked on top of the first. Training of this stacked architecture with large input patches enables learning of fine-grained (cellular) details and global tissue structures. Our system is trained and evaluated on a dataset containing 221 WSIs of hematoxylin and eosin stained breast tissue specimens. The system achieves an AUC of 0.962 for the binary classification of nonmalignant and malignant slides and obtains a three-class accuracy of 81.3% for classification of WSIs into normal/benign, DCIS, and IDC, demonstrating its potential for routine diagnostics.

Contains fulltext : 171993.pdf (Publisher’s version ) (Open Access) This paper presents and evaluates a fully automatic method for detection of ductal carcinoma in situ (DCIS) in digitized hematoxylin and eosin (H&E) stained histopathological slides of breast tissue. The proposed method applies multi-scale superpixel classification to detect epithelial regions in whole-slide images (WSIs). Subsequently, spatial clustering is utilized to delineate regions representing meaningful structures within the tissue such as ducts and lobules. A region-based classifier employing a large set of features including statistical and structural texture features and architectural features is then trained to discriminate between DCIS and benign/normal structures. The system is evaluated on two datasets containing a total of 205 WSIs of breast tissue. Evaluation was conducted both on the slide and the lesion level using FROC analysis. The results show that to detect at least one true positive in every DCIS containing slide, the system finds 2.6 false positives per WSI. The results of the per-lesion evaluation show that it is possible to detect 80% and 83% of the DCIS lesions in an abnormal slide, at an average of 2.0 and 3.0 false positives per WSI, respectively. Collectively, the result of the experiments demonstrate the efficacy and accuracy of the proposed method as well as its potential for application in routine pathological diagnostics. To the best of our knowledge, this is the first DCIS detection algorithm working fully automatically on WSIs.

The detection of cell nuclei plays a key role in various histopathological image analysis problems. Considering the high variability of its applications, we propose a novel generic and trainable detection approach. Adaption to specific nuclei detection tasks is done by providing training samples. A trainable deconvolution and classification algorithm is used to generate a probability map indicating the presence of a nucleus. The map is processed by an extended watershed segmentation step to identify the nuclei positions. We have tested our method on data sets with different stains and target nuclear types. We obtained F1-measures between 0.83 and 0.93.

We propose HookNet, a semantic segmentation model for histopathology whole-slide images, which combines context and details via multiple branches of encoder-decoder convolutional neural networks. Concentric patches at multiple resolutions with different fields of view, feed different branches of HookNet, and intermediate representations are combined via a hooking mechanism. We describe a framework to design and train HookNet for achieving high-resolution semantic segmentation and introduce constraints to guarantee pixel-wise alignment in feature maps during hooking. We show the advantages of using HookNet in two histopathology image segmentation tasks where tissue type prediction accuracy strongly depends on contextual information, namely (1) multi-class tissue segmentation in breast cancer and, (2) segmentation of tertiary lymphoid structures and germinal centers in lung cancer. We show the superiority of HookNet when compared with single-resolution U-Net models working at different resolutions as well as with a recently published multi-resolution model for histopathology image segmentation. We have made HookNet publicly available by releasing the source coder as well as in the form of web-based applications) :3 based on the grand-challenge.org platform. (C) 2020 The Authors. Published by Elsevier B.V. Funding Agencies|European UnionEuropean Commission [825292]; Radboud Institute of Health Sciences (RIHS), Nijmegen, The NetherlandsNetherlands Government; Alpe dHuZes/Dutch Cancer Society Fund [KUN 2014-7032]