Diffusion models for out-of-distribution detection in digital pathology

The ability to detect anomalies, i.e. anything not seen during training or out-of-distribution (OOD), in medical imaging applications is essential for successfully deploying machine learning systems. Filtering out OOD data using unsupervised learning is especially promising because it does not require costly annotations. A new class of models called AnoDDPMs, based on denoising diffusion probabilistic models (DDPMs), has recently achieved significant progress in unsupervised OOD detection. This work provides a benchmark for unsupervised OOD detection methods in digital pathology. By leveraging fast sampling techniques, we apply AnoDDPM on a large enough scale for whole-slide image analysis on the complete test set of the Camelyon16 challenge. Based on ROC analysis, we show that AnoDDPMs can detect OOD data with an AUC of up to 94.13 and 86.93 on two patch-level OOD detection tasks, outperforming the other unsupervised methods. We observe that AnoDDPMs alter the semantic properties of inputs, replacing anomalous data with more benign-looking tissue. Furthermore, we highlight the flexibility of AnoDDPM towards different information bottlenecks by evaluating reconstruction errors for inputs with different signal-to-noise ratios. While there is still a significant performance gap with fully supervised learning, AnoDDPMs show considerable promise in the field of OOD detection in digital pathology.

Detection and subtyping of basal cell carcinoma in whole-slide histopathology using weakly-supervised learning

The frequency of basal cell carcinoma (BCC) cases is putting an increasing strain on dermatopathologists. BCC is the most common type of skin cancer, and its incidence is increasing rapidly worldwide. AI can play a significant role in reducing the time and effort required for BCC diagnostics and thus improve the overall efficiency of the process. To train such an AI system in a fully-supervised fashion however, would require a large amount of pixel-level annotation by already strained dermatopathologists. Therefore, in this study, our primary objective was to develop a weakly-supervised for the identification of basal cell carcinoma (BCC) and the stratification of BCC into low-risk and high-risk categories within histopathology whole-slide images (WSI). We compared Clustering-constrained Attention Multiple instance learning (CLAM) with StreamingCLAM and hypothesized that the latter would be the superior approach. A total of 5147 images were used to train and validate the models, which were subsequently tested on an internal set of 949 images and an external set of 183 images. The labels for training were automatically extracted from free-text pathology reports using a rule-based approach. All data has been made available through the COBRA dataset. The results showed that both the CLAM and StreamingCLAM models achieved high performance for the detection of BCC, with an area under the ROC curve (AUC) of 0.994 and 0.997, respectively, on the internal test set and 0.983 and 0.993 on the external dataset. Furthermore, the models performed well on risk stratification, with AUC values of 0.912 and 0.931, respectively, on the internal set, and 0.851 and 0.883 on the external set. In every single metric the StreamingCLAM model outperformed the CLAM model or is on par. The performance of both models was comparable to that of two pathologists who scored 240 BCC positive slides. Additionally, in the public test set, StreamingCLAM demonstrated a comparable AUC of 0.958, markedly superior to CLAM's 0.803. This difference was statistically significant and emphasized the strength and better adaptability of the StreamingCLAM approach.

Automatic data augmentation to improve generalization of deep learning in H&E stained histopathology

In histopathology practice, scanners, tissue processing, staining, and image acquisition protocols vary from center to center, resulting in subtle variations in images. Vanilla convolutional neural networks are sensitive to such domain shifts. Data augmentation is a popular way to improve domain generalization. Currently, state-of-the-art domain generalization in computational pathology is achieved using a manually curated set of augmentation transforms. However, manual tuning of augmentation parameters is time-consuming and can lead to sub-optimal generalization performance. Meta-learning frameworks can provide efficient ways to find optimal training hyper-parameters, including data augmentation. In this study, we hypothesize that an automated search of augmentation hyper-parameters can provide superior generalization performance and reduce experimental optimization time. We select four state-of-the-art automatic augmentation methods from general computer vision and investigate their capacity to improve domain generalization in histopathology. We analyze their performance on data from 25 centers across two different tasks: tumor metastasis detection in lymph nodes and breast cancer tissue type classification. On tumor metastasis detection, most automatic augmentation methods achieve comparable performance to state-of-the-art manual augmentation. On breast cancer tissue type classification, the leading automatic augmentation method significantly outperforms state-of-the-art manual data augmentation.

Three-dimensional identification of microvascular pathology and neurovascular inflammation in severe white matter hyperintensity: a case report

White matter hyperintensities (WMH) are the most prevalent markers of cerebral small vessel disease (SVD), which is the major vascular risk factor for dementia. Microvascular pathology and neuroinflammation are suggested to drive the transition from normal-appearing white matter (NAWM) to WMH, particularly in individuals with hypertension. However, current imaging techniques cannot capture ongoing NAWM changes. The transition from NAWM into WMH is a continuous process, yet white matter lesions are often examined dichotomously, which may explain their underlying heterogeneity. Therefore, we examined microvascular and neurovascular inflammation pathology in NAWM and severe WMH three-dimensionally, along with gradual magnetic resonance imaging (MRI) fluid-attenuated inversion recovery (FLAIR) signal (sub-)segmentation. In WMH, the vascular network exhibited reduced length and complexity compared to NAWM. Neuroinflammation was more severe in WMH. Vascular inflammation was more pronounced in NAWM, suggesting its potential significance in converting NAWM into WMH. Moreover, the (sub-)segmentation of FLAIR signal displayed varying degrees of vascular pathology, particularly within WMH regions. These findings highlight the intricate interplay between microvascular pathology and neuroinflammation in the transition from NAWM to WMH. Further examination of neurovascular inflammation across MRI-visible alterations could aid deepening our understanding on WMH conversion, and therewith how to improve the prognosis of SVD.

Understanding metric-related pitfalls in image analysis validation

Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multistage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides a reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Although focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation.

Metrics reloaded: recommendations for image analysis validation

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.

Full resolution reconstruction of whole-mount sections from digitized individual tissue fragments

Whole-mount sectioning is a technique in histopathology where a full slice of tissue, such as a transversal cross-section of a prostate specimen, is prepared on a large microscope slide without further sectioning into smaller fragments. Although this technique can offer improved correlation with pre-operative imaging and is paramount for multimodal research, it is not commonly employed due to its technical difficulty, associated cost and cumbersome integration in (digital) pathology workflows. In this work, we present a computational tool named PythoStitcher which reconstructs artificial whole-mount sections from digitized tissue fragments, thereby bringing the benefits of whole-mount sections to pathology labs currently unable to employ this technique. Our proposed algorithm consists of a multi-step approach where it (i) automatically determines how fragments need to be reassembled, (ii) iteratively optimizes the stitch using a genetic algorithm and (iii) efficiently reconstructs the final artificial whole-mount section on full resolution (0.25 µm/pixel). PythoStitcher was validated on a total of 198 cases spanning five datasets with a varying number of tissue fragments originating from different organs from multiple centers. PythoStitcher successfully reconstructed the whole-mount section in 86-100% of cases for a given dataset with a residual registration mismatch of 0.65-2.76 mm on automatically selected landmarks. It is expected that our algorithm can aid pathology labs unable to employ whole-mount sectioning through faster clinical case evaluation and improved radiology-pathology correlation workflows.

The Latent Doctor Model for Modeling Inter-Observer Variability

Many inherently ambiguous tasks in medical imaging suffer from inter-observer variability, resulting in a reference standard defined by a distribution of labels with high variance. Training only on a consensus or majority vote label, as is common in medical imaging, discards valuable information on uncertainty amongst a panel of experts. In this work, we propose to train on the full label distribution to predict the uncertainty within a panel of experts and the most likely ground-truth label. To do so, we propose a new stochastic classification framework based on the conditional variational auto-encoder, which we refer to as the Latent Doctor Model (LDM). In an extensive comparative analysis, we compare the LDM with a model trained on the majority vote label and other methods capable of learning a distribution of labels. We show that the LDM is able to reproduce the reference-standard distribution significantly better than the majority vote baseline. Compared to the other baseline methods, we demonstrate that the LDM performs best at modeling the label distribution and its corresponding uncertainty in two prostate tumor grading tasks. Furthermore, we show competitive performance of the LDM with the more computationally demanding deep ensembles on a tumor budding classification task.

Tumoral Ki67 and PSMA Expression in Fresh Pre-PSMA-RLT Biopsies and Its Relation With PSMA-PET Imaging and Outcomes of PSMA-RLT in Patients With mCRPC

INTRODUCTION

Prostate specific membrane antigen (PSMA) directed radioligand therapy (RLT) is a novel therapy for metastatic castration-resistant prostate cancer (mCRPC) patients. However, it is still poorly understood why approximately 40% of the patients does not respond to PSMA-RLT. The aims of this study were to evaluate the pretreatment PSMA expression on immunohistochemistry (IHC) and PSMA uptake on PET/CT imaging in mCRPC patients who underwent PSMA-RLT. We correlated these parameters and a cell proliferation marker (Ki67) to the therapeutic efficacy of PSMA-RLT.

PATIENTS AND METHODS

In this retrospective study, mCRPC patients who underwent PSMA-RLT were analyzed. Patients biopsies were scored for immunohistochemical Ki67 expression, PSMA staining intensity and percentage of cells with PSMA expression. Moreover, the PSMA tracer uptake of the tumor lesion(s) and healthy organs on PET/CT imaging was assessed. The primary outcome was to evaluate the association between histological PSMA protein expression of tumor in pre-PSMA-RLT biopsies and the PSMA uptake on PSMA PET/CT imaging of the biopsied lesion. Secondary outcomes were to assess the relationship between PSMA expression and Ki67 on IHC and the progression free survival (PFS) and overall survival (OS) following PSMA-RLT.

RESULTS

In total, 22 mCRPC patients were included in this study. Nineteen (86%) patients showed a high and homogenous PSMA expression of >80% on IHC. Three (14%) patients had low PSMA expression on IHC. Although there was limited PSMA uptake on PET/CT imaging, these 3 patients had lower PSMA uptake on PET/CT imaging compared to the patients with high PSMA expression on IHC. Yet, no correlation was found between PSMA uptake on PET/CT imaging and PSMA expression on IHC (SUVmax: R2 = 0.046 and SUVavg: R2 = 0.036). The 3 patients had a shorter PFS compared to the patients with high PSMA expression on IHC (HR: 4.76, 95% CI: 1.14-19.99; P = .033). Patients with low Ki67 expression had a longer PFS and OS compared to patients with a high Ki67 expression (HR: 0.40, 95% CI: 0.15-1.06; P = .013) CONCLUSION: The PSMA uptake on PSMA-PET/CT generally followed the PSMA expression on IHC. However, heterogeneity may be missed on PSMA-PET/CT. Immunohistochemical PSMA and Ki67 expression in fresh tumor biopsies, may contribute to predict treatment efficacy of PSMA-RLT in mCRPC patients. This needs to be further explored in prospective cohorts.

Gigapixel end-to-end training using streaming and attention

Current hardware limitations make it impossible to train convolutional neural networks on gigapixel image inputs directly. Recent developments in weakly supervised learning, such as attention-gated multiple instance learning, have shown promising results, but often use multi-stage or patch-wise training strategies risking suboptimal feature extraction, which can negatively impact performance. In this paper, we propose to train a ResNet-34 encoder with an attention-gated classification head in an end-to-end fashion, which we call StreamingCLAM, using a streaming implementation of convolutional layers. This allows us to train end-to-end on 4-gigapixel microscopic images using only slide-level labels. We achieve a mean area under the receiver operating characteristic curve of 0.9757 for metastatic breast cancer detection (CAMELYON16), close to fully supervised approaches using pixel-level annotations. Our model can also detect MYC-gene translocation in histologic slides of diffuse large B-cell lymphoma, achieving a mean area under the ROC curve of 0.8259. Furthermore, we show that our model offers a degree of interpretability through the attention mechanism.

Continual learning strategies for cancer-independent detection of lymph node metastases

Recently, large, high-quality public datasets have led to the development of convolutional neural networks that can detect lymph node metastases of breast cancer at the level of expert pathologists. Many cancers, regardless of the site of origin, can metastasize to lymph nodes. However, collecting and annotating high-volume, high-quality datasets for every cancer type is challenging. In this paper we investigate how to leverage existing high-quality datasets most efficiently in multi-task settings for closely related tasks. Specifically, we will explore different training and domain adaptation strategies, including prevention of catastrophic forgetting, for breast, colon and head-and-neck cancer metastasis detection in lymph nodes. Our results show state-of-the-art performance on colon and head-and-neck cancer metastasis detection tasks. We show the effectiveness of adaptation of networks from one cancer type to another to obtain multi-task metastasis detection networks. Furthermore, we show that leveraging existing high-quality datasets can significantly boost performance on new target tasks and that catastrophic forgetting can be effectively mitigated.Last, we compare different mitigation strategies.

Artificial Intelligence in Bone Marrow Histological Diagnostics: Potential Applications and Challenges

The expanding digitalization of routine diagnostic histological slides holds a potential to apply artificial intelligence (AI) to pathology, including bone marrow (BM) histology. In this perspective, we describe potential tasks in diagnostics that can be supported, investigations that can be guided, and questions that can be answered by the future application of AI on whole-slide images of BM biopsies. These range from characterization of cell lineages and quantification of cells and stromal structures to disease prediction. First glimpses show an exciting potential to detect subtle phenotypic changes with AI that are due to specific genotypes. The discussion is illustrated by examples of current AI research using BM biopsy slides. In addition, we briefly discuss current challenges for implementation of AI-supported diagnostics.

Predictive uncertainty estimation for out-of-distribution detection in digital pathology

Machine learning model deployment in clinical practice demands real-time risk assessment to identify situations in which the model is uncertain. Once deployed, models should be accurate for classes seen during training while providing informative estimates of uncertainty to flag abnormalities and unseen classes for further analysis. Although recent developments in uncertainty estimation have resulted in an increasing number of methods, a rigorous empirical evaluation of their performance on large-scale digital pathology datasets is lacking. This work provides a benchmark for evaluating prevalent methods on multiple datasets by comparing the uncertainty estimates on both in-distribution and realistic near and far out-of-distribution (OOD) data on a whole-slide level. To this end, we aggregate uncertainty values from patch-based classifiers to whole-slide level uncertainty scores. We show that results found in classical computer vision benchmarks do not always translate to the medical imaging setting. Specifically, we demonstrate that deep ensembles perform best at detecting far-OOD data but can be outperformed on a more challenging near-OOD detection task by multi-head ensembles trained for optimal ensemble diversity. Furthermore, we demonstrate the harmful impact OOD data can have on the performance of deployed machine learning models. Overall, we show that uncertainty estimates can be used to discriminate in-distribution from OOD data with high AUC scores. Still, model deployment might require careful tuning based on prior knowledge of prospective OOD data.

Generalization of Deep Learning in Digital Pathology: Experience in Breast Cancer Metastasis Detection

Simple Summary

Pathology is a cornerstone in cancer diagnostics, and digital pathology and artificial intelligence-driven image analysis could potentially save time and enhance diagnostic accuracy. For clinical implementation of artificial intelligence, a major question is whether the computer models maintain high performance when applied to new settings. We tested the generalizability of a highly accurate deep learning model for breast cancer metastasis detection in sentinel lymph nodes from, firstly, unseen sentinel node data and, secondly, data with a small change in surgical indication, in this case lymph nodes from axillary dissections. Model performance dropped in both settings, particularly on axillary dissection nodes. Retraining of the model was needed to mitigate the performance drop. The study highlights the generalization challenge of clinical implementation of AI models, and the possibility that retraining might be necessary.

Abstract

Poor generalizability is a major barrier to clinical implementation of artificial intelligence in digital pathology. The aim of this study was to test the generalizability of a pretrained deep learning model to a new diagnostic setting and to a small change in surgical indication. A deep learning model for breast cancer metastases detection in sentinel lymph nodes, trained on CAMELYON multicenter data, was used as a base model, and achieved an AUC of 0.969 (95% CI 0.926–0.998) and FROC of 0.838 (95% CI 0.757–0.913) on CAMELYON16 test data. On local sentinel node data, the base model performance dropped to AUC 0.929 (95% CI 0.800–0.998) and FROC 0.744 (95% CI 0.566–0.912). On data with a change in surgical indication (axillary dissections) the base model performance indicated an even larger drop with a FROC of 0.503 (95%CI 0.201–0.911). The model was retrained with addition of local data, resulting in about a 4% increase for both AUC and FROC for sentinel nodes, and an increase of 11% in AUC and 49% in FROC for axillary nodes. Pathologist qualitative evaluation of the retrained model´s output showed no missed positive slides. False positives, false negatives and one previously undetected micro-metastasis were observed. The study highlights the generalization challenge even when using a multicenter trained model, and that a small change in indication can considerably impact the model´s performance.

The Medical Segmentation Decathlon

International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)-a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.

Prostate158 - An expert-annotated 3T MRI dataset and algorithm for prostate cancer detection

BACKGROUND

The development of deep learning (DL) models for prostate segmentation on magnetic resonance imaging (MRI) depends on expert-annotated data and reliable baselines, which are often not publicly available. This limits both reproducibility and comparability.

METHODS

Prostate158 consists of 158 expert annotated biparametric 3T prostate MRIs comprising T2w sequences and diffusion-weighted sequences with apparent diffusion coefficient maps. Two U-ResNets trained for segmentation of anatomy (central gland, peripheral zone) and suspicious lesions for prostate cancer (PCa) with a PI-RADS score of ≥4 served as baseline algorithms. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), the Hausdorff distance (HD), and the average surface distance (ASD). The Wilcoxon test with Bonferroni correction was used to evaluate differences in performance. The generalizability of the baseline model was assessed using the open datasets Medical Segmentation Decathlon and PROSTATEx.

RESULTS

Compared to Reader 1, the models achieved a DSC/HD/ASD of 0.88/18.3/2.2 for the central gland, 0.75/22.8/1.9 for the peripheral zone, and 0.45/36.7/17.4 for PCa. Compared with Reader 2, the DSC/HD/ASD were 0.88/17.5/2.6 for the central gland, 0.73/33.2/1.9 for the peripheral zone, and 0.4/39.5/19.1 for PCa. Interrater agreement measured in DSC/HD/ASD was 0.87/11.1/1.0 for the central gland, 0.75/15.8/0.74 for the peripheral zone, and 0.6/18.8/5.5 for PCa. Segmentation performances on the Medical Segmentation Decathlon and PROSTATEx were 0.82/22.5/3.4; 0.86/18.6/2.5 for the central gland, and 0.64/29.2/4.7; 0.71/26.3/2.2 for the peripheral zone.

CONCLUSIONS

We provide an openly accessible, expert-annotated 3T dataset of prostate MRI and a reproducible benchmark to foster the development of prostate segmentation algorithms.

A Decade of GigaScience: The Challenges of Gigapixel Pathology Images

In the last decade, the field of computational pathology has advanced at a rapid pace because of the availability of deep neural networks, which achieved their first successes in computer vision tasks in 2012. An important driver for the progress of the field were public competitions, so called 'Grand Challenges', in which increasingly large data sets were offered to the public to solve clinically relevant tasks. Going from the first Pathology challenges, which had data obtained from 23 patients, to current challenges sharing data of thousands of patients, performance of developed deep learning solutions has reached (and sometimes surpassed) the level of experienced pathologists for specific tasks. We expect future challenges to broaden the horizon, for instance by combining data from radiology, pathology and tumor genetics, and to extract prognostic and predictive information independent of currently used grading schemes.

Predicting biochemical recurrence of prostate cancer with artificial intelligence

Background

The first sign of metastatic prostate cancer after radical prostatectomy is rising PSA levels in the blood, termed biochemical recurrence. The prediction of recurrence relies mainly on the morphological assessment of prostate cancer using the Gleason grading system. However, in this system, within-grade morphological patterns and subtle histopathological features are currently omitted, leaving a significant amount of prognostic potential unexplored.

Methods

To discover additional prognostic information using artificial intelligence, we trained a deep learning system to predict biochemical recurrence from tissue in H&E-stained microarray cores directly. We developed a morphological biomarker using convolutional neural networks leveraging a nested case-control study of 685 patients and validated on an independent cohort of 204 patients. We use concept-based explainability methods to interpret the learned tissue patterns.

Results

The biomarker provides a strong correlation with biochemical recurrence in two sets (n = 182 and n = 204) from separate institutions. Concept-based explanations provided tissue patterns interpretable by pathologists.

Conclusions

These results show that the model finds predictive power in the tissue beyond the morphological ISUP grading.

To determine the prognosis of patients with prostate cancer, several clinical factors are taken into account. One of these is the cancer grade, assigned by a pathologist based on the cancer’s appearance under a microscope. The grade ranges from 1 to 5, where 5 is the most aggressive tumour type. This study explored whether deep learning—a technique in which computer software learns patterns from multiple examples—can learn to predict the risk of patients’ cancers recurring from microscopic images of the tumours. We show, on two clinical datasets from different institutions, that such a system can help to better predict prognosis, beyond the information provided by grade alone. In the future, this type of method could help clinicians to predict the prognosis of individual prostate cancer patients.

Pinckaers et al. develop a deep learning system to predict biochemical recurrence in prostate cancer patients treated with radical prostatectomy. The authors’ morphological biomarker provides predictive power beyond traditional Gleason grading, based on analysis of two clinical datasets from different institutions.

Streaming Convolutional Neural Networks for End-to-End Learning With Multi-Megapixel Images

Due to memory constraints on current hardware, most convolution neural networks (CNN) are trained on sub-megapixel images. For example, most popular datasets in computer vision contain images much less than a megapixel in size (0.09MP for ImageNet and 0.001MP for CIFAR-10). In some domains such as medical imaging, multi-megapixel images are needed to identify the presence of disease accurately. We propose a novel method to directly train convolutional neural networks using any input image size end-to-end. This method exploits the locality of most operations in modern convolutional neural networks by performing the forward and backward pass on smaller tiles of the image. In this work, we show a proof of concept using images of up to 66-megapixels (8192×8192), saving approximately 50GB of memory per image. Using two public challenge datasets, we demonstrate that CNNs can learn to extract relevant information from these large images and benefit from increasing resolution. We improved the area under the receiver-operating characteristic curve from 0.580 (4MP) to 0.706 (66MP) for metastasis detection in breast cancer (CAMELYON17). We also obtained a Spearman correlation metric approaching state-of-the-art performance on the TUPAC16 dataset, from 0.485 (1MP) to 0.570 (16MP). Code to reproduce a subset of the experiments is available at https://github.com/DIAGNijmegen/StreamingCNN.

Automated quantification of levels of breast terminal duct lobular (TDLU) involution using deep learning

Convolutional neural networks (CNNs) offer the potential to generate comprehensive quantitative analysis of histologic features. Diagnostic reporting of benign breast disease (BBD) biopsies is usually limited to subjective assessment of the most severe lesion in a sample, while ignoring the vast majority of tissue features, including involution of background terminal duct lobular units (TDLUs), the structures from which breast cancers arise. Studies indicate that increased levels of age-related TDLU involution in BBD biopsies predict lower breast cancer risk, and therefore its assessment may have potential value in risk assessment and management. However, assessment of TDLU involution is time-consuming and difficult to standardize and quantitate. Accordingly, we developed a CNN to enable automated quantitative measurement of TDLU involution and tested its performance in 174 specimens selected from the pathology archives at Mayo Clinic, Rochester, MN. The CNN was trained and tested on a subset of 33 biopsies, delineating important tissue types. Nine quantitative features were extracted from delineated TDLU regions. Our CNN reached an overall dice-score of 0.871 (±0.049) for tissue classes versus reference standard annotation. Consensus of four reviewers scoring 705 images for TDLU involution demonstrated substantial agreement with the CNN method (unweighted κappa = 0.747 ± 0.01). Quantitative involution measures showed anticipated associations with BBD histology, breast cancer risk, breast density, menopausal status, and breast cancer risk prediction scores (p < 0.05). Our work demonstrates the potential to improve risk prediction for women with BBD biopsies by applying CNN approaches to generate automated quantitative evaluation of TDLU involution.

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge-the largest histopathology competition to date, joined by 1,290 developers-to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840-0.884) and 0.868 (95% CI, 0.835-0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.

Using deep learning for quantification of cellularity and cell lineages in bone marrow biopsies and comparison to normal age-related variation

Cellularity estimation forms an important aspect of the visual examination of bone marrow biopsies. In clinical practice, cellularity is estimated by eye under a microscope, which is rapid, but subjective and subject to inter- and intraobserver variability. In addition, there is little consensus in the literature on the normal variation of cellularity with age. Digital image analysis may be used for more objective quantification of cellularity. As such, we developed a deep neural network for the segmentation of six major cell and tissue types in digitized bone marrow trephine biopsies. Using this segmentation, we calculated the overall bone marrow cellularity in a series of biopsies from 130 patients across a wide age range. Using intraclass correlation coefficients (ICC), we measured the agreement between the quantification by the neural network and visual estimation by two pathologists and compared it to baseline human performance. We also examined the age-related changes of cellularity and cell lineages in bone marrow and compared our results to those found in the literature. The network was capable of accurate segmentation (average accuracy and dice score of 0.95 and 0.76, respectively). There was good neural network-pathologist agreement on cellularity measurements (ICC=0.78, 95% CI 0.58-0.85). We found a statistically significant downward trend for cellularity, myelopoiesis and megakaryocytes with age in our cohort. The mean cellularity began at approximately 50% in the third decade of life and then decreased ±2% per decade to 40% in the seventh and eighth decade, but the normal range was very wide (30-70%).

Detection of Prostate Cancer in Whole-Slide Images Through End-to-End Training With Image-Level Labels

Prostate cancer is the most prevalent cancer among men in Western countries, with 1.1 million new diagnoses every year. The gold standard for the diagnosis of prostate cancer is a pathologists' evaluation of prostate tissue. To potentially assist pathologists deep / learning / based cancer detection systems have been developed. Many of the state-of-the-art models are patch / based convolutional neural networks, as the use of entire scanned slides is hampered by memory limitations on accelerator cards. Patch-based systems typically require detailed, pixel-level annotations for effective training. However, such annotations are seldom readily available, in contrast to the clinical reports of pathologists, which contain slide-level labels. As such, developing algorithms which do not require manual pixel-wise annotations, but can learn using only the clinical report would be a significant advancement for the field. In this paper, we propose to use a streaming implementation of convolutional layers, to train a modern CNN (ResNet / 34) with 21 million parameters end-to-end on 4712 prostate biopsies. The method enables the use of entire biopsy images at high-resolution directly by reducing the GPU memory requirements by 2.4 TB. We show that modern CNNs, trained using our streaming approach, can extract meaningful features from high-resolution images without additional heuristics, reaching similar performance as state-of-the-art patch-based and multiple-instance learning methods. By circumventing the need for manual annotations, this approach can function as a blueprint for other tasks in histopathological diagnosis. The source code to reproduce the streaming models is available at https://github.com/DIAGNijmegen/ pathology-streaming-pipeline.

Deep learning in histopathology: the path to the clinic

Machine learning techniques have great potential to improve medical diagnostics, offering ways to improve accuracy, reproducibility and speed, and to ease workloads for clinicians. In the field of histopathology, deep learning algorithms have been developed that perform similarly to trained pathologists for tasks such as tumor detection and grading. However, despite these promising results, very few algorithms have reached clinical implementation, challenging the balance between hope and hype for these new techniques. This Review provides an overview of the current state of the field, as well as describing the challenges that still need to be addressed before artificial intelligence in histopathology can achieve clinical value.

Optimized tumour infiltrating lymphocyte assessment for triple negative breast cancer prognostics

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.

Mini Review: The Last Mile-Opportunities and Challenges for Machine Learning in Digital Toxicologic Pathology

The 2019 manuscript by the Special Interest Group on Digital Pathology and Image Analysis of the Society of Toxicologic pathology suggested that a synergism between artificial intelligence (AI) and machine learning (ML) technologies and digital toxicologic pathology would improve the daily workflow and future impact of toxicologic pathologists globally. Now 2 years later, the authors of this review consider whether, in their opinion, there is any evidence that supports that thesis. Specifically, we consider the opportunities and challenges for applying ML (the study of computer algorithms that are able to learn from example data and extrapolate the learned information to unseen data) algorithms in toxicologic pathology and how regulatory bodies are navigating this rapidly evolving field. Although we see similarities with the "Last Mile" metaphor, the weight of evidence suggests that toxicologic pathologists should approach ML with an equal dose of skepticism and enthusiasm. There are increasing opportunities for impact in our field that leave the authors cautiously excited and optimistic. Toxicologic pathologists have the opportunity to critically evaluate ML applications with a "call-to-arms" mentality. Why should we be late adopters? There is ample evidence to encourage engagement, growth, and leadership in this field.

Deep Learning Methods for Lung Cancer Segmentation in Whole-Slide Histopathology Images-The ACDC@LungHP Challenge 2019

Accurate segmentation of lung cancer in pathology slides is a critical step in improving patient care. We proposed the ACDC@LungHP (Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology) challenge for evaluating different computer-aided diagnosis (CADs) methods on the automatic diagnosis of lung cancer. The ACDC@LungHP 2019 focused on segmentation (pixel-wise detection) of cancer tissue in whole slide imaging (WSI), using an annotated dataset of 150 training images and 50 test images from 200 patients. This paper reviews this challenge and summarizes the top 10 submitted methods for lung cancer segmentation. All methods were evaluated using metrics using the precision, accuracy, sensitivity, specificity, and DICE coefficient (DC). The DC ranged from 0.7354 ±0.1149 to 0.8372 ±0.0858. The DC of the best method was close to the inter-observer agreement (0.8398 ±0.0890). All methods were based on deep learning and categorized into two groups: multi-model method and single model method. In general, multi-model methods were significantly better (p 0.01) than single model methods, with mean DC of 0.7966 and 0.7544, respectively. Deep learning based methods could potentially help pathologists find suspicious regions for further analysis of lung cancer in WSI.

Neural Image Compression for Gigapixel Histopathology Image Analysis

We propose Neural Image Compression (NIC), a two-step method to build convolutional neural networks for gigapixel image analysis solely using weak image-level labels. First, gigapixel images are compressed using a neural network trained in an unsupervised fashion, retaining high-level information while suppressing pixel-level noise. Second, a convolutional neural network (CNN) is trained on these compressed image representations to predict image-level labels, avoiding the need for fine-grained manual annotations. We compared several encoding strategies, namely reconstruction error minimization, contrastive training and adversarial feature learning, and evaluated NIC on a synthetic task and two public histopathology datasets. We found that NIC can exploit visual cues associated with image-level labels successfully, integrating both global and local visual information. Furthermore, we visualized the regions of the input gigapixel images where the CNN attended to, and confirmed that they overlapped with annotations from human experts.

Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists

The Gleason score is the most important prognostic marker for prostate cancer patients, but it suffers from significant observer variability. Artificial intelligence (AI) systems based on deep learning can achieve pathologist-level performance at Gleason grading. However, the performance of such systems can degrade in the presence of artifacts, foreign tissue, or other anomalies. Pathologists integrating their expertise with feedback from an AI system could result in a synergy that outperforms both the individual pathologist and the system. Despite the hype around AI assistance, existing literature on this topic within the pathology domain is limited. We investigated the value of AI assistance for grading prostate biopsies. A panel of 14 observers graded 160 biopsies with and without AI assistance. Using AI, the agreement of the panel with an expert reference standard increased significantly (quadratically weighted Cohen's kappa, 0.799 vs. 0.872; p = 0.019). On an external validation set of 87 cases, the panel showed a significant increase in agreement with a panel of international experts in prostate pathology (quadratically weighted Cohen's kappa, 0.733 vs. 0.786; p = 0.003). In both experiments, on a group-level, AI-assisted pathologists outperformed the unassisted pathologists and the standalone AI system. Our results show the potential of AI systems for Gleason grading, but more importantly, show the benefits of pathologist-AI synergy.

Artificial intelligence to detect MYC translocation in slides of diffuse large B-cell lymphoma

In patients with suspected lymphoma, the tissue biopsy provides lymphoma confirmation, classification, and prognostic factors, including genetic changes. We developed a deep learning algorithm to detect MYC rearrangement in scanned histological slides of diffuse large B-cell lymphoma. The H&E-stained slides of 287 cases from 11 hospitals were used for training and evaluation. The overall sensitivity to detect MYC rearrangement was 0.93 and the specificity 0.52, showing that prediction of MYC translocation based on morphology alone was possible in 93% of MYC-rearranged cases. This would allow a simple and fast prescreening, saving approximately 34% of genetic tests with the current algorithm.

Impact of rescanning and normalization on convolutional neural network performance in multi-center, whole-slide classification of prostate cancer

Algorithms can improve the objectivity and efficiency of histopathologic slide analysis. In this paper, we investigated the impact of scanning systems (scanners) and cycle-GAN-based normalization on algorithm performance, by comparing different deep learning models to automatically detect prostate cancer in whole-slide images. Specifically, we compare U-Net, DenseNet and EfficientNet. Models were developed on a multi-center cohort with 582 WSIs and subsequently evaluated on two independent test sets including 85 and 50 WSIs, respectively, to show the robustness of the proposed method to differing staining protocols and scanner types. We also investigated the application of normalization as a pre-processing step by two techniques, the whole-slide image color standardizer (WSICS) algorithm, and a cycle-GAN based method. For the two independent datasets we obtained an AUC of 0.92 and 0.83 respectively. After rescanning the AUC improves to 0.91/0.88 and after style normalization to 0.98/0.97. In the future our algorithm could be used to automatically pre-screen prostate biopsies to alleviate the workload of pathologists.

Diagnostic accuracy of contrast-enhanced diffusion-weighted MRI for liver metastases of pancreatic cancer: towards adequate staging and follow-up of pancreatic cancer - DIA-PANC study: study protocol for an international, multicenter, diagnostic trial

BACKGROUND

At the time of surgery, approximately 10-20% of the patients with pancreatic cancer are considered unresectable because of unexpected liver metastasis, peritoneal carcinomatosis or locally advanced disease. This leads to futile surgical treatment with all the associated morbidity, mortality and costs. More than 50% of all liver metastases develop in the first six months postoperatively. These (subcentimeter) liver metastases are most likely already present at the time of diagnosis and have not been identified pre-operatively, due to the poor sensitivity of routine preoperative contrast-enhanced CT (CECT).

METHODS

The DIA-PANC study is a prospective, international, multicenter, diagnostic cohort study investigating diffusion-weighted, contrast-enhanced MRI for the detection of liver metastases in patients with all stages of pancreatic cancer. Indeterminate or malignant liver lesions on MRI will be further investigated histopathologically. For patients with suspected liver lesions without histopathological proof, follow up imaging with paired CT and MRI at 3-, 6- and 12-months will serve as an alternative reference standard.

DISCUSSION

The DIA-PANC trial is expected to report high-level evidence of the diagnostic accuracy of MRI for the detection of liver metastases, resulting in significant value for clinical decision making, guideline development and improved stratification for treatment strategies and future trials. Furthermore, DIA-PANC will contribute to our knowledge of liver metastases regarding incidence, imaging characteristics, their number and extent, and their change in time with or without treatment. It will enhance the worldwide implementation of MRI and consequently improve personalized treatment of patients with suspected pancreatic ductal adenocarcinoma.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT03469726 . Registered on March 19th 2018 - Retrospectively registered.

Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study

BACKGROUND

The Gleason score is the strongest correlating predictor of recurrence for prostate cancer, but has substantial inter-observer variability, limiting its usefulness for individual patients. Specialised urological pathologists have greater concordance; however, such expertise is not widely available. Prostate cancer diagnostics could thus benefit from robust, reproducible Gleason grading. We aimed to investigate the potential of deep learning to perform automated Gleason grading of prostate biopsies.

METHODS

In this retrospective study, we developed a deep-learning system to grade prostate biopsies following the Gleason grading standard. The system was developed using randomly selected biopsies, sampled by the biopsy Gleason score, from patients at the Radboud University Medical Center (pathology report dated between Jan 1, 2012, and Dec 31, 2017). A semi-automatic labelling technique was used to circumvent the need for manual annotations by pathologists, using pathologists' reports as the reference standard during training. The system was developed to delineate individual glands, assign Gleason growth patterns, and determine the biopsy-level grade. For validation of the method, a consensus reference standard was set by three expert urological pathologists on an independent test set of 550 biopsies. Of these 550, 100 were used in an observer experiment, in which the system, 13 pathologists, and two pathologists in training were compared with respect to the reference standard. The system was also compared to an external test dataset of 886 cores, which contained 245 cores from a different centre that were independently graded by two pathologists.

FINDINGS

We collected 5759 biopsies from 1243 patients. The developed system achieved a high agreement with the reference standard (quadratic Cohen's kappa 0·918, 95% CI 0·891-0·941) and scored highly at clinical decision thresholds: benign versus malignant (area under the curve 0·990, 95% CI 0·982-0·996), grade group of 2 or more (0·978, 0·966-0·988), and grade group of 3 or more (0·974, 0·962-0·984). In an observer experiment, the deep-learning system scored higher (kappa 0·854) than the panel (median kappa 0·819), outperforming 10 of 15 pathologist observers. On the external test dataset, the system obtained a high agreement with the reference standard set independently by two pathologists (quadratic Cohen's kappa 0·723 and 0·707) and within inter-observer variability (kappa 0·71).

INTERPRETATION

Our automated deep-learning system achieved a performance similar to pathologists for Gleason grading and could potentially contribute to prostate cancer diagnosis. The system could potentially assist pathologists by screening biopsies, providing second opinions on grade group, and presenting quantitative measurements of volume percentages.

FUNDING

Dutch Cancer Society.

Resolution-agnostic tissue segmentation in whole-slide histopathology images with convolutional neural networks

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.

Learning to detect lymphocytes in immunohistochemistry with deep learning

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.

Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks

Recent years have seen a growing awareness of the role the immune system plays in successful cancer treatment, especially in novel therapies like immunotherapy. The characterization of the immunological composition of tumors and their micro-environment is thus becoming a necessity. In this paper we introduce a deep learning-based immune cell detection and quantification method, which is based on supervised learning, i.e., the input data for training comprises labeled images. Our approach objectively deals with staining variation and staining artifacts in immunohistochemically stained lung cancer tissue and is as precise as humans. This is evidenced by the low cell count difference to humans of 0.033 cells on average. This method, which is based on convolutional neural networks, has the potential to provide a new quantitative basis for research on immunotherapy.

From Detection of Individual Metastases to Classification of Lymph Node Status at the Patient Level: The CAMELYON17 Challenge

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.

Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard

Given the importance of gland morphology in grading prostate cancer (PCa), automatically differentiating between epithelium and other tissues is an important prerequisite for the development of automated methods for detecting PCa. We propose a new deep learning method to segment epithelial tissue in digitised hematoxylin and eosin (H&E) stained prostatectomy slides using immunohistochemistry (IHC) as reference standard. We used IHC to create a precise and objective ground truth compared to manual outlining on H&E slides, especially in areas with high-grade PCa. 102 tissue sections were stained with H&E and subsequently restained with P63 and CK8/18 IHC markers to highlight epithelial structures. Afterwards each pair was co-registered. First, we trained a U-Net to segment epithelial structures in IHC using a subset of the IHC slides that were preprocessed with color deconvolution. Second, this network was applied to the remaining slides to create the reference standard used to train a second U-Net on H&E. Our system accurately segmented both intact glands and individual tumour epithelial cells. The generalisation capacity of our system is shown using an independent external dataset from a different centre. We envision this segmentation as the first part of a fully automated prostate cancer grading pipeline.

1399 H&E-stained sentinel lymph node sections of breast cancer patients: the CAMELYON dataset

Background

The presence of lymph node metastases is one of the most important factors in breast cancer prognosis. The most common way to assess regional lymph node status is the sentinel lymph node procedure. The sentinel lymph node is the most likely lymph node to contain metastasized cancer cells and is excised, histopathologically processed, and examined by a pathologist. This tedious examination process is time-consuming and can lead to small metastases being missed. However, recent advances in whole-slide imaging and machine learning have opened an avenue for analysis of digitized lymph node sections with computer algorithms. For example, convolutional neural networks, a type of machine-learning algorithm, can be used to automatically detect cancer metastases in lymph nodes with high accuracy. To train machine-learning models, large, well-curated datasets are needed.

Results

We released a dataset of 1,399 annotated whole-slide images (WSIs) of lymph nodes, both with and without metastases, in 3 terabytes of data in the context of the CAMELYON16 and CAMELYON17 Grand Challenges. Slides were collected from five medical centers to cover a broad range of image appearance and staining variations. Each WSI has a slide-level label indicating whether it contains no metastases, macro-metastases, micro-metastases, or isolated tumor cells. Furthermore, for 209 WSIs, detailed hand-drawn contours for all metastases are provided. Last, open-source software tools to visualize and interact with the data have been made available.

Conclusions

A unique dataset of annotated, whole-slide digital histopathology images has been provided with high potential for re-use.

Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks

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 noisy and expensive reference standards established by pathologists, lack of generalization due to staining variation across laboratories, and 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 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 H&E 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. We obtained a performance within the top three best methods for most of the tasks of the challenge.

The association between portal system vein diameters and outcomes in acute pancreatitis

BACKGROUND/OBJECTIVES

Acute pancreatitis (AP) progresses to necrotizing pancreatitis in 15% of cases. An important pathophysiological mechanism in AP is third spacing of fluids, which leads to intravascular volume depletion. This results in a reduced splanchnic circulation and reduced venous return. Non-visualisation of the portal and splenic vein on early computed tomography (CT) scan, which might be the result of smaller vein diameter due to decreased venous flow, is associated with infected necrosis and mortality in AP. This observation led us to hypothesize that smaller diameters of portal system veins (portal, splenic and superior mesenteric) are associated with increased severity of AP.

METHODS

We conducted a post-hoc analysis of data from two randomized controlled trials that included patients with predicted severe and mild AP. The primary endpoint was AP-related mortality. The secondary endpoints were (infected) necrotizing pancreatitis and (persistent) organ failure. We performed additional CT measurements of portal system vein diameters and calculated their prognostic value through univariate and multivariate Poisson regression.

RESULTS

Multivariate regression showed a significant inverse association between splenic vein diameter and mortality (RR 0.75 (0.59-0.97)). Furthermore, there was a significant inverse association between splenic and superior mesenteric vein diameter and (infected) necrosis. Diameters of all veins were inversely associated with organ failure and persistent organ failure.

CONCLUSIONS

We observed an inverse relationship between portal system vein diameter and morbidity and an inverse relationship between splenic vein diameter and mortality in AP. Further research is needed to test whether these results can be implemented in predictive scoring systems.

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer

Importance

Application of deep learning algorithms to whole-slide pathology images can 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 < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC).

Conclusions and Relevance

In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images

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.