Search

The spread of early-stage (T1 and T2) adenocarcinomas to locoregional lymph nodes is a key event in disease progression of colorectal cancer (CRC). The cellular mechanisms behind this event are not completely understood and existing predictive biomarkers are imperfect. Here, we used an end-to-end deep learning algorithm to identify risk factors for lymph node metastasis (LNM) status in digitized histopathology slides of the primary CRC and its surrounding tissue. In two large population-based cohorts, we show that this system can predict the presence of more than one LNM in pT2 CRC patients with an area under the receiver operating curve (AUROC) of 0.733 (0.67-0.758) and patients with any LNM with an AUROC of 0.711 (0.597-0.797). Similarly, in pT1 CRC patients, the presence of more than one LNM or any LNM was predictable with an AUROC of 0.733 (0.644-0.778) and 0.567 (0.542-0.597), respectively. Based on these findings, we used the deep learning system to guide human pathology experts towards highly predictive regions for LNM in the whole slide images. This hybrid human observer and deep learning approach identified inflamed adipose tissue as the highest predictive feature for LNM presence. Our study is a first proof of concept that artificial intelligence (AI) systems may be able to discover potentially new biological mechanisms in cancer progression. Our deep learning algorithm is publicly available and can be used for biomarker discovery in any disease setting. © 2021 The Pathological Society of Great Britain and Ireland. Published by John WileySons, Ltd.

The publisher regrets that figures were misplaced after the proofing stage. Figure 4 and 5 are duplicates of other figures. The figure legends are not affected. Figure 4 and Figure 5 were corrected in the online version of the article. The publisher would like to apologise for any inconvenience caused.

Artificial intelligence (AI) can extract visual information from histopathological slides and yield biological insight and clinical biomarkers. Whole slide images are cut into thousands of tiles and classification problems are often weakly-supervised: the ground truth is only known for the slide, not for every single tile. In classical weakly-supervised analysis pipelines, all tiles inherit the slide label while in multiple-instance learning (MIL), only bags of tiles inherit the label. However, it is still unclear how these widely used but markedly different approaches perform relative to each other. We implemented and systematically compared six methods in six clinically relevant end-to-end prediction tasks using data from N=2980 patients for training with rigorous external validation. We tested three classical weakly-supervised approaches with convolutional neural networks and vision transformers (ViT) and three MIL-based approaches with and without an additional attention module. Our results empirically demonstrate that histological tumor subtyping of renal cell carcinoma is an easy task in which all approaches achieve an area under the receiver operating curve (AUROC) of above 0.9. In contrast, we report significant performance differences for clinically relevant tasks of mutation prediction in colorectal, gastric, and bladder cancer. In these mutation prediction tasks, classical weakly-supervised workflows outperformed MIL-based weakly-supervised methods for mutation prediction, which is surprising given their simplicity. This shows that new end-to-end image analysis pipelines in computational pathology should be compared to classical weakly-supervised methods. Also, these findings motivate the development of new methods which combine the elegant assumptions of MIL with the empirically observed higher performance of classical weakly-supervised approaches. We make all source codes publicly available at https://github.com/KatherLab/HIA, allowing easy application of all methods to any similar task.

A disturbed synchronization of the ventricular contraction can cause a highly developed systolic heart failure in affected patients with reduction of the left ventricular ejection fraction, which can often be explained by a diseased left bundle branch block (LBBB). If medication remains unresponsive, the concerned patients will be treated with a cardiac resynchronization therapy (CRT) system. The aim of this study was to integrate His-bundle pacing into the Offenburg heart rhythm model in order to visualize the electrical pacing field generated by His-Bundle-Pacing. Modelling and electrical field simulation activities were performed with the software CST (Computer Simulation Technology) from Dessault Systèms. CRT with biventricular pacing is to be achieved by an apical right ventricular electrode and an additional left ventricular electrode, which is floated into the coronary vein sinus. The non-responder rate of the CRT therapy is about one third of the CRT patients. His- Bundle-Pacing represents a physiological alternative to conventional cardiac pacing and cardiac resynchronization. An electrode implanted in the His-bundle emits a stronger electrical pacing field than the electrical pacing field of conventional cardiac pacemakers. The pacing of the Hisbundle was performed by the Medtronic Select Secure 3830 electrode with pacing voltage amplitudes of 3 V, 2 V and 1,5 V in combination with a pacing pulse duration of 1 ms. Compared to conventional pacemaker pacing, His-bundle pacing is capable of bridging LBBB conduction disorders in the left ventricle. The His-bundle pacing electrical field is able to spread via the physiological pathway in the right and left ventricles for CRT with a narrow QRS-complex in the surface ECG.

Aims Ethanol is a widespread substance that inherits desired effects, but also negative consequences with regard to DUI or battery. Where required, the ethanol concentration is usually determined in peripheral venous blood samples, while the brain is the target organ of the ethanol effects. The aim of this study with three participants was the determination of the ethanol concentration in functionally relevant regions of the brain and the comparison with serum ethanol concentrations. Design After the uptake of ethanol in a calculated amount, leading to a serum ethanol concentration of 0.99 g/L, the ethanol concentrations in the brain were directly analyzed by means of magnetic resonance spectroscopy on a 3 Tesla human MRI system and normalized to the water content. The measurement voxels were located in the occipital cortex, the cerebellum, the frontal cortex, and the putamen and successively examined. Intermittently blood samples were taken, and serum was analyzed for ethanol using HS-GC-FID. Findings and conclusions Ethanol concentrations in brain regions normalized to the water content were lower than the measured serum ethanol results and rather homogenous within the three participants and the various regions of the brain. The maximum ethanol concentration in the brain (normalized to water content) was 0.68 g/L. It was measured in the frontal cortex, in which the highest results were gained. The maximum serum concentration was 1.19 g/L. The course of the brain ethanol curve seems to be flatter than the one of the serum ethanol concentrations.

Histopathology : journal of the British Division of the International Academy of Pathology 80(7), 1121-1127 (2022). doi:10.1111/his.14659, Published by Wiley-Blackwell, Oxford [u.a.]

The journal of pathology 256(1), 50-60 (2022). doi:10.1002/path.5800, Published by Wiley, Bognor Regis [u.a.]

The interpretation of digitized histopathology images has been transformed thanks to artificial intelligence (AI). End-to-end AI algorithms can infer high-level features directly from raw image data, extending the capabilities of human experts. In particular, AI can predict tumor subtypes, genetic mutations and gene expression directly from hematoxylin and eosin (H&E) stained pathology slides. However, existing end-to-end AI workflows are poorly standardized and not easily adaptable to new tasks. Here, we introduce DeepMed, a Python library for predicting any high-level attribute directly from histopathological whole slide images alone, or from images coupled with additional meta-data (https://github.com/KatherLab/deepmed). Unlike earlier computational pipelines, DeepMed is highly developer-friendly: its structure is modular and separates preprocessing, training, deployment, statistics, and visualization in such a way that any one of these processes can be altered without affecting the others. Also, DeepMed scales easily from local use on laptop computers to multi-GPU clusters in cloud computing services and therefore can be used for teaching, prototyping and for large-scale applications. Finally, DeepMed is user-friendly and allows researchers to easily test multiple hypotheses in a single dataset (via cross-validation) or in multiple datasets (via external validation). Here, we demonstrate and document DeepMed’s abilities to predict molecular alterations, histopathological subtypes and molecular features from routine histopathology images, using a large benchmark dataset which we release publicly. In summary, DeepMed is a fully integrated and broadly applicable end-to-end AI pipeline for the biomedical research community.

Artificial intelligence (AI) can extract subtle visual information from digitized histopathology slides and yield scientific insight on genotype-phenotype interactions as well as clinically actionable recommendations. Classical weakly supervised pipelines use an end-to-end approach with residual neural networks (ResNets), modern convolutional neural networks such as EfficientNet, or non-convolutional architectures such as vision transformers (ViT). In addition, multiple-instance learning (MIL) and clustering-constrained attention MIL (CLAM) are being used for pathology image analysis. However, it is unclear how these different approaches perform relative to each other. Here, we implement and systematically compare all five methods in six clinically relevant end-to-end prediction tasks using data from N=4848 patients with rigorous external validation. We show that histological tumor subtyping of renal cell carcinoma is an easy task which approaches successfully solved with an area under the receiver operating curve (AUROC) of above 0.9 without any significant differences between approaches. In contrast, we report significant performance differences for mutation prediction in colorectal, gastric and bladder cancer. Weakly supervised ResNet-and ViT-based workflows significantly outperformed other methods, in particular MIL and CLAM for mutation prediction. As a reason for this higher performance we identify the ability of ResNet and ViT to assign high prediction scores to highly informative image regions with plausible histopathological image features. We make all source codes publicly available athttps://github.com/KatherLab/HIA, allowing easy application of all methods on any end-to-end problem in computational pathology.

Deep learning can detect microsatellite instability (MSI) from routine histology images in colorectal cancer (CRC). However, ethical and legal barriers impede sharing of images and genetic data, hampering development of new algorithms for detection of MSI and other biomarkers. We hypothesized that histology images synthesized by conditional generative adversarial networks (CGANs) retain information about genetic alterations. To test this, we developed a 'histology CGAN' which was trained on 256 patients (training cohort 1) and 1457 patients (training cohort 2). The CGAN synthesized 10 000 synthetic MSI and non-MSI images which contained a range of tissue types and were deemed realistic by trained observers in a blinded study. Subsequently, we trained a deep learning detector of MSI on real or synthetic images and evaluated the performance of MSI detection in a held-out set of 142 patients. When trained on real images from training cohort 1, this system achieved an area under the receiver operating curve (AUROC) of 0.742 [0.681, 0.854]. Training on the larger cohort 2 only marginally improved the AUROC to 0.757 [0.707, 0.869]. Training on purely synthetic data resulted in an AUROC of 0.743 [0.658, 0.801]. Training on both real and synthetic data further increased AUROC to 0.777 [0.715, 0.821]. We conclude that synthetic histology images retain information reflecting underlying genetic alterations in colorectal cancer. Using synthetic instead of real images to train deep learning systems yields non-inferior classifiers. This approach can be used to create large shareable data sets or to augment small data sets with rare molecular features. (c) 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.

Background and Aims: Microsatellite instability (MSI) and mismatch-repair deficiency (dMMR) in colorectal tumors are used to select treatment for patients. Deep learning can detect MSI and dMMR in tumor samples on routine histology slides faster and cheaper than molecular assays. But clinical application of this technology requires high performance and multisite validation, which have not yet been performed. Methods: We collected hematoxylin and eosin-stained slides, and findings from molecular analyses for MSI and dMMR, from 8836 colorectal tumors (of all stages) included in the MSIDETECT consortium study, from Germany, the Netherlands, the United Kingdom, and the United States. Specimens with dMMR were identified by immunohistochemistry analyses of tissue microarrays for loss of MLH1, MSH2, MSH6, and/or PMS2. Specimens with MSI were identified by genetic analyses. We trained a deep-learning detector to identify samples with MSI from these slides; performance was assessed by cross-validation (n=6406 specimens) and validated in an external cohort (n=771 specimens). Prespecified endpoints were area under the receiver operating characteristic (AUROC) curve and area under the precision-recall curve (AUPRC). Results: The deep-learning detector identified specimens with dMMR or MSI with a mean AUROC curve of 0.92 (lower bound 0.91, upper bound 0.93) and an AUPRC of 0.63 (range, 0.59–0.65), or 67% specificity and 95% sensitivity, in the cross-validation development cohort. In the validation cohort, the classifier identified samples with dMMR with an AUROC curve of 0.95 (range, 0.92–0.96) without image-preprocessing and an AUROC curve of 0.96 (range, 0.93–0.98) after color normalization. Conclusions: We developed a deep-learning system that detects colorectal cancer specimens with dMMR or MSI using hematoxylin and eosin-stained slides; it detected tissues with dMMR with an AUROC of 0.96 in a large, international validation cohort. This system might be used for high-throughput, low-cost evaluation of colorectal tissue specimens.

Die visuellen Welten des Stummfilms sind vielfach durch ornamentale Oberflächen geprägt: Interieurs wie Vorhänge, Teppiche, Tapeten, Möbel, Lampen und ebenso Kostüme. Neben der Funktion als Schmuck im diegetischen Raum erfasst das Ornamentale auch die Beziehung zwischen Figur und Umgebung sowie die Komposition des Filmbildes als Ganzes. Galt das Ornament lange als ‹konservative› Form, so hat sich die ihm innewohnende Abstraktionskraft als ein Prinzip der Moderne erwiesen. Entsprechend zeichnet die Studie an ausgewählten Fallbeispielen film- und stilhistorisch nach, welche Rolle ornamentgeprägte Filmbilder für die Ausformung einer innovativen Filmsprache spielten und welche Ideen des zeitgenössischen Ornament-Diskurses sich in Kunst- und Filmtheorie damit verbinden. Das Buch zeigt, wie Prinzipien des Ornamentierens – vom Kino um 1910 bis hin zur Hochphase der Avantgarde in den 1920er Jahren – in die Inszenierung des Verhältnisses von Fläche und Raum eingreifen und eine neuartige Qualität des filmisch Visuellen schaffen.

Molecular alterations in cancer can cause phenotypic changes in tumor cells and their microenvironment. Routine histopathology tissue slides, which are ubiquitously available, can reflect such morphological changes. Here, we show that deep learning can consistently infer a wide range of genetic mutations, molecular tumor subtypes, gene expression signatures and standard pathology biomarkers directly from routine histology. We developed, optimized, validated and publicly released a one-stop-shop workflow and applied it to tissue slides of more than 5,000 patients across multiple solid tumors. Our findings show that a single deep learning algorithm can be trained to predict a wide range of molecular alterations from routine, paraffin-embedded histology slides stained with hematoxylin and eosin. These predictions generalize to other populations and are spatially resolved. Our method can be implemented on mobile hardware, potentially enabling point-of-care diagnostics for personalized cancer treatment. More generally, this approach could elucidate and quantify genotype-phenotype links in cancer. Two papers by Kather and colleagues and Gerstung and colleagues develop workflows to predict a wide range of molecular alterations from pan-cancer digital pathology slides.

Background: Deep learning can predict clinically relevant features such as genetic alterations directly from H&E stained histology images.In practice, many clinically relevant questions are limited by availability of clinical data and by the lack of standardized preprocessing pipelines. In our research projects, we strive to keep a consistent data format across projects to facilitate downstream analysis. Workflow: We analyze cohorts of cancer patients and try to predict clinically relevant labels directly from whole slide images (WSI). To achieve this, we manually or automatically detect tumor tissue in the WSI, tessellate the tumor into smaller image tiles and store these tiles in a cohort directory (Figure 1). We prepare a Slide Master Table, specifying which WSI belongs to which patient and a Patient Master Table, specifying the labels (target categories) for each patient. Our publicly available scripts automate the remaining workflow: Tiles are loaded, are matched to WSIs, which are matched to patients, which are matched to labels. Deep neural networks are trained to predict the labels and are evaluated on external cohorts. Target audience: This is a best practice manual focused on practical aspects such as file names, ground truth data tables and ROI annotation. This document is intended for onboarding new team members and for our academic collaborators. We hope that beyond our teams, this consensus document might be useful for other groups in the deep learning histopathology community. Our data standards are is inspired by The Cancer Genome Atlas (TCGA) standards (http://portal.gdc.cancer.gov). Please give your feedback on http://kather.ai.

Precision treatment of cancer relies on genetic alterations which are diagnosed by molecular biology assays.1 These tests can be a bottleneck in oncology workflows because of high turnaround time, tissue usage and costs.2 Here, we show that deep learning can predict point mutations, molecular tumor subtypes and immune-related gene expression signatures3,4 directly from routine histological images of tumor tissue. We developed and systematically optimized a one-stop-shop workflow and applied it to more than 4000 patients with breast5, colon and rectal6, head and neck7, lung8,9, pancreatic10, prostate11 cancer, melanoma12 and gastric13 cancer. Together, our findings show that a single deep learning algorithm can predict clinically actionable alterations from routine histology data. Our method can be implemented on mobile hardware14, potentially enabling point-of-care diagnostics for personalized cancer treatment in individual patients.

Ethanol is a widespread substance that inherits desired effects, but also negative consequences with regard to DUI or battery. Where required, the ethanol concentration is usually determined in peripheral venous blood samples, while the brain is the target organ of the ethanol effects. The aim of this study with three participants was the determination of the ethanol concentration in functionally relevant regions of the brain and the comparison with serum ethanol concentrations. After the uptake of ethanol in a calculated amount, leading to a serum ethanol concentration of 0.99 g/L, the ethanol concentrations in the brain were directly analyzed by means of magnetic resonance spectroscopy on a 3 Tesla human MRI system and normalized to the water content. The measurement voxels were located in the occipital cortex, the cerebellum, the frontal cortex, and the putamen and successively examined. Intermittently blood samples were taken, and serum was analyzed for ethanol using HS-GC-FID. Ethanol concentrations in brain regions normalized to the water content were lower than the measured serum ethanol results and rather homogenous within the three participants and the various regions of the brain. The maximum ethanol concentration in the brain (normalized to water content) was 0.68 g/L. It was measured in the frontal cortex, in which the highest results were gained. The maximum serum concentration was 1.19 g/L. The course of the brain ethanol curve seems to be flatter than the one of the serum ethanol concentrations.

Die visuellen Welten des Stummfilms sind vielfach durch ornamentale Oberflächen geprägt: Interieurs wie Vorhänge, Teppiche, Tapeten, Möbel, Lampen und ebenso Kostüme. Neben der Funktion als Schmuck im diegetischen Raum erfasst das Ornamentale auch die Beziehung zwischen Figur und Umgebung sowie die Komposition des Filmbildes als Ganzes. Galt das Ornament lange als ‹konservative› Form, so hat sich die ihm innewohnende Abstraktionskraft als ein Prinzip der Moderne erwiesen. Entsprechend zeichnet die Studie an ausgewählten Fallbeispielen film- und stilhistorisch nach, welche Rolle ornamentgeprägte Filmbilder für die Ausformung einer innovativen Filmsprache spielten und welche Ideen des zeitgenössischen Ornament-Diskurses sich in Kunst- und Filmtheorie damit verbinden.