Explore the vast range of titles available.

Background There is growing interest in utilizing artificial intelligence, and particularly deep learning, for computer vision in histopathology. While accumulating studies highlight expert-level performance of convolutional neural networks (CNNs) on focused classification tasks, most studies rely on probability distribution scores with empirically defined cutoff values based on post-hoc analysis. More generalizable tools that allow humans to visualize histology-based deep learning inferences and decision making are scarce. Results Here, we leverage t-distributed Stochastic Neighbor Embedding (t-SNE) to reduce dimensionality and depict how CNNs organize histomorphologic information. Unique to our workflow, we develop a quantitative and transparent approach to visualizing classification decisions prior to softmax compression. By discretizing the relationships between classes on the t-SNE plot, we show we can super-impose randomly sampled regions of test images and use their distribution to render statistically-driven classifications. Therefore, in addition to providing intuitive outputs for human review, this visual approach can carry out automated and objective multi-class classifications similar to more traditional and less-transparent categorical probability distribution scores. Importantly, this novel classification approach is driven by a priori statistically defined cutoffs. It therefore serves as a generalizable classification and anomaly detection tool less reliant on post-hoc tuning. Conclusion Routine incorporation of this convenient approach for quantitative visualization and error reduction in histopathology aims to accelerate early adoption of CNNs into generalized real-world applications where unanticipated and previously untrained classes are often encountered.

Glioblastoma is an aggressive form of brain cancer with well-established patterns of intra-tumoral heterogeneity implicated in treatment resistance and progression. While regional and single cell transcriptomic variations of glioblastoma have been recently resolved, downstream phenotype-level proteomic programs have yet to be assigned across glioblastoma’s hallmark histomorphologic niches. Here, we leverage mass spectrometry to spatially align abundance levels of 4,794 proteins to distinct histologic patterns across 20 patients and propose diverse molecular programs operational within these regional tumor compartments. Using machine learning, we overlay concordant transcriptional information, and define two distinct proteogenomic programs, MYC- and KRAS-axis hereon, that cooperate with hypoxia to produce a tri-dimensional model of intra-tumoral heterogeneity. Moreover, we highlight differential drug sensitivities and relative chemoresistance in glioblastoma cell lines with enhanced KRAS programs. Importantly, these pharmacological differences are less pronounced in transcriptional glioblastoma subgroups suggesting that this model may provide insights for targeting heterogeneity and overcoming therapy resistance. Gioblastoma tumours consist of different niches defined by histology. Here, the authors use proteomics and machine learning to assign protein expression programs to these niches, and reveal that KRAS and hypoxia are associated with drug resistance.

Deep learning has proven capable of automating key aspects of histopathologic analysis. However, its context-specific nature and continued reliance on large expert-annotated training datasets hinders the development of a critical mass of applications to garner widespread adoption in clinical/research workflows. Here, we present an online collaborative platform that streamlines tissue image annotation to promote the development and sharing of custom computer vision models for PHenotyping And Regional Analysis Of Histology (PHARAOH; https://www.pathologyreports.ai/ ). Specifically, PHARAOH uses a weakly supervised, human-in-the-loop learning framework whereby patch-level image features are leveraged to organize large swaths of tissue into morphologically-uniform clusters for batched annotation by human experts. By providing cluster-level labels on only a handful of cases, we show how custom PHARAOH models can be developed efficiently and used to guide the quantification of cellular features that correlate with molecular, pathologic and patient outcome data. Moreover, by using our PHARAOH pipeline, we showcase how correlation of cohort-level cytoarchitectural features with accompanying biological and outcome data can help systematically devise interpretable morphometric models of disease. Both the custom model design and feature extraction pipelines are amenable to crowdsourcing, positioning PHARAOH to become a fully scalable, systems-level solution for the expansion, generalization and cataloging of computational pathology applications. Faust, Chen, and colleagues present PHARAOH, a collaborative computational pathology platform that allows histologists to quickly develop custom labelled image datasets to train and catalogue a variety of machine learning models for histopathological analysis.

Advancements in computer vision and artificial intelligence (AI) carry the potential to make significant contributions to health care, particularly in diagnostic specialties such as radiology and pathology. The impact of these technologies on physician stakeholders is the subject of significant speculation. There is however a dearth of information regarding the opinions, enthusiasm, and concerns of the pathology community at large. Here, we report results from a survey of 487 pathologist-respondents practicing in 54 countries, conducted to examine perspectives on AI implementation in clinical practice. Despite limitations, including difficulty with quantifying response bias and verifying identity of respondents to this anonymous and voluntary survey, several interesting findings were uncovered. Overall, respondents carried generally positive attitudes towards AI, with nearly 75% reporting interest or excitement in AI as a diagnostic tool to facilitate improvements in workflow efficiency and quality assurance in pathology. Importantly, even within the more optimistic cohort, a significant number of respondents endorsed concerns about AI, including the potential for job displacement and replacement. Overall, around 80% of respondents predicted the introduction of AI technology in the pathology laboratory within the coming decade. Attempts to identify statistically significant demographic characteristics (e.g., age, sex, type/place of practice) predictive of attitudes towards AI using Kolmogorov–Smirnov (KS) testing revealed several associations. Important themes which were commented on by respondents included the need for increasing efforts towards physician training and resolving medical-legal implications prior to the generalized implementation of AI in pathology.

Focal cortical dysplasia (FCD) is a neurodevelopmental malformation that often manifests as medically refractory epilepsy. A key histological hallmark of FCD type II is the presence of cytomegalic dysmorphic neurons (CDNs), which are considered to be major contributors to cortical network hyperexcitability. However, the relatively low frequency of CDNs within resected lesions has challenged their unbiased molecular characterization. Here, we leverage deep learning approaches to objectively map key anatomical compartments of FCD IIb and guide regional spatial transcriptomic profiling. Using this approach, we generate an anatomical transcriptional catalog of type IIb FCD, and uncover non‐canonical markers of signaling and neurotransmitter pathways in CDNs that may serve as new therapeutic targets for this debilitating disorder.

AimsImmunohistochemistry (IHC) assessment of tissue is a central component of the modern pathology workflow, but quantification is challenged by subjective estimates by pathologists or manual steps in semi-automated digital tools. This study integrates various computer vision tools to develop a fully automated workflow for quantifying Ki-67, a standard IHC test used to assess cell proliferation on digital whole slide images (WSIs).MethodsWe create an automated nuclear segmentation strategy by deploying a Mask R-CNN classifier to recognise and count 3,3′-diaminobenzidine positive and negative nuclei. To further improve automation, we replaced manual selection of regions of interest (ROIs) by aligning Ki-67 WSIs with corresponding H&E-stained sections, using scale-invariant feature transform (SIFT) and a conventional histomorphological convolutional neural networks to define tumour-rich areas for quantification.ResultsThe Mask R-CNN was tested on 147 images generated from 34 brain tumour Ki-67 WSIs and showed a high concordance with aggregate pathologists’ estimates ( n=3 assessors; y=0.9712x−1.945, r=0.9750). Concordance of each assessor’s Ki-67 estimates was higher when compared with the Mask R-CNN than between individual assessors (ravg=0.9322 vs 0.8703; p=0.0213). Coupling the Mask R-CNN with SIFT-CNN workflow demonstrated ROIs can be automatically chosen and partially sampled to improve automation and dramatically decrease computational time (average: 88.55–19.28 min; p<0.0001).ConclusionsWe show how innovations in computer vision can be serially compounded to automate and improve implementation in clinical workflows. Generalisation of this approach to other ancillary studies has significant implications for computational pathology.

Deep learning is an emerging transformative tool in diagnostic medicine, yet limited access and the interpretability of learned parameters hinders widespread adoption. Here we have generated a diverse repository of 838,644 histopathologic images and used them to optimize and discretize learned representations into 512-dimensional feature vectors. Importantly, we show that individual machine-engineered features correlate with salient human-derived morphologic constructs and ontological relationships. Deciphering the overlap between human and machine reasoning may aid in eliminating biases and improving automation and accountability for artificial intelligence-assisted medicine. Neural networks are a promising digital pathology tool but are often criticized for their limited explainability. Faust and others demonstrate how machine-learned features correlate with human-understandable histological patterns and groupings, permitting increased transparency of deep learning tools in medicine.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Deep learning has proven to be capable of automating key aspects of histopathologic analysis, but its continual reliance on large expert-annotated training datasets hinders widespread adoption. Here, we present an online collaborative portal that streamlines tissue image annotation to promote the development and sharing of custom computer vision models for PHenotyping And Regional Analysis Of Histology (PHARAOH; https://www.pathologyreports.ai/). PHARAOH uses a weakly supervised active learning framework whereby patch-level image features are leveraged to organize large swaths of tissue into morphologically-uniform clusters for batched human annotation. By providing cluster-level labels on only a handful of cases, we show how custom PHARAOH models can be developed and used to guide the quantification of cellular features that correlate with molecular, pathologic and patient outcome data. Both custom model design and feature extraction pipelines are amenable to crowdsourcing making PHARAOH a fully scalable systems-level solution for the systematic expansion and cataloging of computational pathology applications.

Fecal microbiome variation in the average, healthy population has remained under-investigated. Here, we analyzed two independent, extensively phenotyped cohorts: the Belgian Flemish Gut Flora Project (FGFP; discovery cohort; N = 1106) and the Dutch LifeLines-DEEP study (LLDeep; replication; N = 1135). Integration with global data sets (N combiend = 3948) revealed a 14-genera core microbiota, but the 664 identified genera still underexplore total gut diversity. Sixty-nine clinical and questionnaire-based covariates were found associated to microbiota compositional variation with a 92% replication rate. Stool consistency showed the largest effect size, whereas medication explained largest total variance and interacted with other covariate-microbiota associations. Early-life events such as birth mode were not reflected in adult microbiota composition. Finally, we found that proposed disease marker genera associated to host covariates, urging inclusion of the latter in study design.