A deep learning model to predict RNA-Seq expression of tumours from whole slide images

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

Robust mapping of spatiotemporal trajectories and cell-cell interactions in healthy and diseased tissues

Spatial transcriptomics (ST) technologies generate multiple data types from biological samples, namely gene expression, physical distance between data points, and/or tissue morphology. Here we developed three computational-statistical algorithms that integrate all three data types to advance understanding of cellular processes. First, we present a spatial graph-based method, pseudo-time-space (PSTS), to model and uncover relationships between transcriptional states of cells across tissues undergoing dynamic change (e.g. neurodevelopment, brain injury and/or microglia activation, and cancer progression). We further developed a spatially-constrained two-level permutation (SCTP) test to study cell-cell interaction, finding highly interactive tissue regions across thousands of ligand-receptor pairs with markedly reduced false discovery rates. Finally, we present a spatial graph-based imputation method with neural network (stSME), to correct for technical noise/dropout and increase ST data coverage. Together, the algorithms that we developed, implemented in the comprehensive and fast stLearn software, allow for robust interrogation of biological processes within healthy and diseased tissues.

The promise of explainable deep learning for omics data analysis: Adding new discovery tools to AI

Deep learning has already revolutionised the way a wide range of data is processed in many areas of daily life. The ability to learn abstractions and relationships from heterogeneous data has provided impressively accurate prediction and classification tools to handle increasingly big datasets. This has a significant impact on the growing wealth of omics datasets, with the unprecedented opportunity for a better understanding of the complexity of living organisms. While this revolution is transforming the way these data are analyzed, explainable deep learning is emerging as an additional tool with the potential to change the way biological data is interpreted. Explainability addresses critical issues such as transparency, so important when computational tools are introduced especially in clinical environments. Moreover, it empowers artificial intelligence with the capability to provide new insights into the input data, thus adding an element of discovery to these already powerful resources. In this review, we provide an overview of the transformative effects explainable deep learning is having on multiple sectors, ranging from genome engineering and genomics, from radiomics to drug design and clinical trials. We offer a perspective to life scientists, to better understand the potential of these tools, and a motivation to implement them in their research, by suggesting learning resources they can use to move their first steps in this field.

THItoGene: a deep learning method for predicting spatial transcriptomics from histological images

Spatial transcriptomics unveils the complex dynamics of cell regulation and transcriptomes, but it is typically cost-prohibitive. Predicting spatial gene expression from histological images via artificial intelligence offers a more affordable option, yet existing methods fall short in extracting deep-level information from pathological images. In this paper, we present THItoGene, a hybrid neural network that utilizes dynamic convolutional and capsule networks to adaptively sense potential molecular signals in histological images for exploring the relationship between high-resolution pathology image phenotypes and regulation of gene expression. A comprehensive benchmark evaluation using datasets from human breast cancer and cutaneous squamous cell carcinoma has demonstrated the superior performance of THItoGene in spatial gene expression prediction. Moreover, THItoGene has demonstrated its capacity to decipher both the spatial context and enrichment signals within specific tissue regions. THItoGene can be freely accessed at https://github.com/yrjia1015/THItoGene.

N-of-one differential gene expression without control samples using a deep generative model

Differential analysis of bulk RNA-seq data often suffers from lack of good controls. Here, we present a generative model that replaces controls, trained solely on healthy tissues. The unsupervised model learns a low-dimensional representation and can identify the closest normal representation for a given disease sample. This enables control-free, single-sample differential expression analysis. In breast cancer, we demonstrate how our approach selects marker genes and outperforms a state-of-the-art method. Furthermore, significant genes identified by the model are enriched in driver genes across cancers. Our results show that the in silico closest normal provides a more favorable comparison than control samples.

Graph-based multi-modality integration for prediction of cancer subtype and severity

Personalised cancer screening before therapy paves the way toward improving diagnostic accuracy and treatment outcomes. Most approaches are limited to a single data type and do not consider interactions between features, leaving aside the complementary insights that multimodality and systems biology can provide. In this project, we demonstrate the use of graph theory for data integration via individual networks where nodes and edges are individual-specific. We showcase the consequences of early, intermediate, and late graph-based fusion of RNA-Seq data and histopathology whole-slide images for predicting cancer subtypes and severity. The methodology developed is as follows: (1) we create individual networks; (2) we compute the similarity between individuals from these graphs; (3) we train our model on the similarity matrices; (4) we evaluate the performance using the macro F1 score. Pros and cons of elements of the pipeline are evaluated on publicly available real-life datasets. We find that graph-based methods can increase performance over methods that do not study interactions. Additionally, merging multiple data sources often improves classification compared to models based on single data, especially through intermediate fusion. The proposed workflow can easily be adapted to other disease contexts to accelerate and enhance personalized healthcare.

Artificial Intelligence Optical Biopsy for Evaluating the Functional State of Wounds

INTRODUCTION

The clinical characterization of the functional status of active wounds in terms of their driving cellular and molecular biology remains a considerable challenge that currently requires excision via a tissue biopsy. In this pilot study, we use convolutional Siamese neural network (SNN) architecture to predict the functional state of a wound using digital photographs of wounds in a canine model of volumetric muscle loss (VML).

METHODS

Digital images of VML injuries and tissue biopsies were obtained in a standardized fashion from an established canine model of VML. Gene expression profiles for each biopsy site were obtained using RNA sequencing. These profiles were converted to functional profiles by a manual review of validated gene ontology databases in which we determined a hierarchical representation of gene functions based on functional specificity. An SNN was trained to regress functional profile expression values, informed by an image segment showing the surface of a small tissue biopsy.

RESULTS

The SNN was able to predict the functional expression of a range of functions based with error ranging from ∼5% to ∼30%, with functions that are most closely associated with the early state of wound healing to be those best-predicted.

CONCLUSIONS

These initial results suggest promise for further research regarding this novel use of machine learning regression on medical images. The regression of functional profiles, as opposed to specific genes, both addresses the challenge of genetic redundancy and gives a deeper insight into the mechanistic configuration of a region of tissue in wounds.

Leveraging Attention-Based Convolutional Neural Networks for Meningioma Classification in Computational Histopathology

Convolutional neural networks (CNNs) are becoming increasingly valuable tools for advanced computational histopathology, promoting precision medicine through exceptional visual decoding abilities. Meningiomas, the most prevalent primary intracranial tumors, necessitate accurate grading and classification for informed clinical decision-making. Recently, DNA methylation-based molecular classification of meningiomas has proven to be more effective in predicting tumor recurrence than traditional histopathological methods. However, DNA methylation profiling is expensive, labor-intensive, and not widely accessible. Consequently, a digital histology-based prediction of DNA methylation classes would be advantageous, complementing molecular classification. In this study, we developed and rigorously assessed an attention-based multiple-instance deep neural network for predicting meningioma methylation classes using tumor methylome data from 142 (+51) patients and corresponding hematoxylin-eosin-stained histological sections. Pairwise analysis of sample cohorts from three meningioma methylation classes demonstrated high accuracy in two combinations. The performance of our approach was validated using an independent set of 51 meningioma patient samples. Importantly, attention map visualization revealed that the algorithm primarily focuses on tumor regions deemed significant by neuropathologists, offering insights into the decision-making process of the CNN. Our findings highlight the capacity of CNNs to effectively harness phenotypic information from histological sections through computerized images for precision medicine. Notably, this study is the first demonstration of predicting clinically relevant DNA methylome information using computer vision applied to standard histopathology. The introduced AI framework holds great potential in supporting, augmenting, and expediting meningioma classification in the future.

HistoMIL: A Python package for training multiple instance learning models on histopathology slides

Hematoxylin and eosin (H&E) stained slides are widely used in disease diagnosis. Remarkable advances in deep learning have made it possible to detect complex molecular patterns in these histopathology slides, suggesting automated approaches could help inform pathologists' decisions. Multiple instance learning (MIL) algorithms have shown promise in this context, outperforming transfer learning (TL) methods for various tasks, but their implementation and usage remains complex. We introduce HistoMIL, a Python package designed to streamline the implementation, training and inference process of MIL-based algorithms for computational pathologists and biomedical researchers. It integrates a self-supervised learning module for feature encoding, and a full pipeline encompassing TL and three MIL algorithms: ABMIL, DSMIL, and TransMIL. The PyTorch Lightning framework enables effortless customization and algorithm implementation. We illustrate HistoMIL's capabilities by building predictive models for 2,487 cancer hallmark genes on breast cancer histology slides, achieving AUROC performances of up to 85%.

Neuropathologist-level integrated classification of adult-type diffuse gliomas using deep learning from whole-slide pathological images

Current diagnosis of glioma types requires combining both histological features and molecular characteristics, which is an expensive and time-consuming procedure. Determining the tumor types directly from whole-slide images (WSIs) is of great value for glioma diagnosis. This study presents an integrated diagnosis model for automatic classification of diffuse gliomas from annotation-free standard WSIs. Our model is developed on a training cohort (n = 1362) and a validation cohort (n = 340), and tested on an internal testing cohort (n = 289) and two external cohorts (n = 305 and 328, respectively). The model can learn imaging features containing both pathological morphology and underlying biological clues to achieve the integrated diagnosis. Our model achieves high performance with area under receiver operator curve all above 0.90 in classifying major tumor types, in identifying tumor grades within type, and especially in distinguishing tumor genotypes with shared histological features. This integrated diagnosis model has the potential to be used in clinical scenarios for automated and unbiased classification of adult-type diffuse gliomas.

Feasibility of Inferring Spatial Transcriptomics from Single-Cell Histological Patterns for Studying Colon Cancer Tumor Heterogeneity

Background

Spatial transcriptomics involves studying the spatial organization of gene expression within tissues, offering insights into the molecular diversity of tumors. While spatial gene expression is commonly amalgamated from 1-10 cells across 50-micron spots, recent methods have demonstrated the capability to disaggregate this information at subspot resolution by leveraging both expression and histological patterns. However, elucidating such information from histology alone presents a significant challenge but if solved can better permit spatial molecular analysis at cellular resolution for instances where Visium data is not available, reducing study costs. This study explores integrating single-cell histological and transcriptomic data to infer spatial mRNA expression patterns in whole slide images collected from a cohort of stage pT3 colorectal cancer patients. A cell graph neural network algorithm was developed to align histological information extracted from detected cells with single cell RNA patterns through optimal transport methods, facilitating the analysis of cellular groupings and gene relationships. This approach leveraged spot-level expression as an intermediary to co-map histological and transcriptomic information at the single-cell level.

Results

Our study demonstrated that single-cell transcriptional heterogeneity within a spot could be predicted from histological markers extracted from cells detected within a spot. Furthermore, our model exhibited proficiency in delineating overarching gene expression patterns across whole-slide images. This approach compared favorably to traditional patch-based computer vision methods as well as other methods which did not incorporate single cell expression during the model fitting procedures. Topological nuances of single-cell expression within a Visium spot were preserved using the developed methodology.

Conclusion

This innovative approach augments the resolution of spatial molecular assays utilizing histology as a sole input through synergistic co-mapping of histological and transcriptomic datasets at the single-cell level, anchored by spatial transcriptomics. While initial results are promising, they warrant rigorous validation. This includes collaborating with pathologists for precise spatial identification of distinct cell types and utilizing sophisticated assays, such as Xenium, to attain deeper subcellular insights.

The Overlooked Role of Specimen Preparation in Bolstering Deep Learning-Enhanced Spatial Transcriptomics Workflows

The application of deep learning methods to spatial transcriptomics has shown promise in unraveling the complex relationships between gene expression patterns and tissue architecture as they pertain to various pathological conditions. Deep learning methods that can infer gene expression patterns directly from tissue histomorphology can expand the capability to discern spatial molecular markers within tissue slides. However, current methods utilizing these techniques are plagued by substantial variability in tissue preparation and characteristics, which can hinder the broader adoption of these tools. Furthermore, training deep learning models using spatial transcriptomics on small study cohorts remains a costly endeavor. Necessitating novel tissue preparation processes enhance assay reliability, resolution, and scalability. This study investigated the impact of an enhanced specimen processing workflow for facilitating a deep learning-based spatial transcriptomics assessment. The enhanced workflow leveraged the flexibility of the Visium CytAssist assay to permit automated H&E staining (e.g., Leica Bond) of tissue slides, whole-slide imaging at 40x-resolution, and multiplexing of tissue sections from multiple patients within individual capture areas for spatial transcriptomics profiling. Using a cohort of thirteen pT3 stage colorectal cancer (CRC) patients, we compared the efficacy of deep learning models trained on slide prepared using an enhanced workflow as compared to the traditional workflow which leverages manual tissue staining and standard imaging of tissue slides. Leveraging Inceptionv3 neural networks, we aimed to predict gene expression patterns across matched serial tissue sections, each stemming from a distinct workflow but aligned based on persistent histological structures. Findings indicate that the enhanced workflow considerably outperformed the traditional spatial transcriptomics workflow. Gene expression profiles predicted from enhanced tissue slides also yielded expression patterns more topologically consistent with the ground truth. This led to enhanced statistical precision in pinpointing biomarkers associated with distinct spatial structures. These insights can potentially elevate diagnostic and prognostic biomarker detection by broadening the range of spatial molecular markers linked to metastasis and recurrence. Future endeavors will further explore these findings to enrich our comprehension of various diseases and uncover molecular pathways with greater nuance. Combining deep learning with spatial transcriptomics provides a compelling avenue to enrich our understanding of tumor biology and improve clinical outcomes. For results of the highest fidelity, however, effective specimen processing is crucial, and fostering collaboration between histotechnicians, pathologists, and genomics specialists is essential to herald this new era in spatial transcriptomics-driven cancer research.

HAVOC: Small-scale histomic mapping of cancer biodiversity across large tissue distances using deep neural networks

Intratumoral heterogeneity can wreak havoc on current precision medicine strategies because of challenges in sufficient sampling of geographically separated areas of biodiversity distributed across centimeter-scale tumor distances. To address this gap, we developed a deep learning pipeline that leverages histomorphologic fingerprints of tissue to create "Histomic Atlases of Variation Of Cancers" (HAVOC). Using a number of objective molecular readouts, we demonstrate that HAVOC can define regional cancer boundaries with distinct biology. Using larger tumor specimens, we show that HAVOC can map biodiversity even across multiple tissue sections. By guiding profiling of 19 partitions across six high-grade gliomas, HAVOC revealed that distinct differentiation states can often coexist and be regionally distributed within these tumors. Last, to highlight generalizability, we benchmark HAVOC on additional tumor types. Together, we establish HAVOC as a versatile tool to generate small-scale maps of tissue heterogeneity and guide regional deployment of molecular resources to relevant biodiverse niches.

Advances in Histological and Molecular Classification of Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is a primary liver cancer characterized by hepatocellular differentiation. HCC is molecularly heterogeneous with a wide spectrum of histopathology. The prognosis of patients with HCC is generally poor, especially in those with advanced stages. HCC remains a diagnostic challenge for pathologists because of its morphological and phenotypic diversity. However, recent advances have enhanced our understanding of the molecular genetics and histological subtypes of HCC. Accurate diagnosis of HCC is important for patient management and prognosis. This review provides an update on HCC pathology, focusing on molecular genetics, histological subtypes, and diagnostic approaches.

Deep learning integrates histopathology and proteogenomics at a pan-cancer level

We introduce a pioneering approach that integrates pathology imaging with transcriptomics and proteomics to identify predictive histology features associated with critical clinical outcomes in cancer. We utilize 2,755 H&E-stained histopathological slides from 657 patients across 6 cancer types from CPTAC. Our models effectively recapitulate distinctions readily made by human pathologists: tumor vs. normal (AUROC = 0.995) and tissue-of-origin (AUROC = 0.979). We further investigate predictive power on tasks not normally performed from H&E alone, including TP53 prediction and pathologic stage. Importantly, we describe predictive morphologies not previously utilized in a clinical setting. The incorporation of transcriptomics and proteomics identifies pathway-level signatures and cellular processes driving predictive histology features. Model generalizability and interpretability is confirmed using TCGA. We propose a classification system for these tasks, and suggest potential clinical applications for this integrated human and machine learning approach. A publicly available web-based platform implements these models.

Prediction of cancer treatment response from histopathology images through imputed transcriptomics

Advances in artificial intelligence have paved the way for leveraging hematoxylin and eosin (H&E)-stained tumor slides for precision oncology. We present ENLIGHT-DeepPT, an approach for predicting response to multiple targeted and immunotherapies from H&E-slides. In difference from existing approaches that aim to predict treatment response directly from the slides, ENLIGHT-DeepPT is an indirect two-step approach consisting of (1) DeepPT, a new deep-learning framework that predicts genome-wide tumor mRNA expression from slides, and (2) ENLIGHT, which predicts response based on the DeepPT inferred expression values. DeepPT successfully predicts transcriptomics in all 16 TCGA cohorts tested and generalizes well to two independent datasets. Our key contribution is showing that ENLIGHT-DeepPT successfully predicts true responders in five independent patients' cohorts involving four different treatments spanning six cancer types with an overall odds ratio of 2.44, increasing the baseline response rate by 43.47% among predicted responders, without the need for any treatment data for training. Furthermore, its prediction accuracy on these datasets is comparable to a supervised approach predicting the response directly from the images, which needs to be trained and tested on the same cohort. ENLIGHT-DeepPT future application could provide clinicians with rapid treatment recommendations to an array of different therapies and importantly, may contribute to advancing precision oncology in developing countries.

Applications of discriminative and deep learning feature extraction methods for whole slide image analysis: A survey

Digital pathology technologies, including whole slide imaging (WSI), have significantly improved modern clinical practices by facilitating storing, viewing, processing, and sharing digital scans of tissue glass slides. Researchers have proposed various artificial intelligence (AI) solutions for digital pathology applications, such as automated image analysis, to extract diagnostic information from WSI for improving pathology productivity, accuracy, and reproducibility. Feature extraction methods play a crucial role in transforming raw image data into meaningful representations for analysis, facilitating the characterization of tissue structures, cellular properties, and pathological patterns. These features have diverse applications in several digital pathology applications, such as cancer prognosis and diagnosis. Deep learning-based feature extraction methods have emerged as a promising approach to accurately represent WSI contents and have demonstrated superior performance in histology-related tasks. In this survey, we provide a comprehensive overview of feature extraction methods, including both manual and deep learning-based techniques, for the analysis of WSIs. We review relevant literature, analyze the discriminative and geometric features of WSIs (i.e., features suited to support the diagnostic process and extracted by "engineered" methods as opposed to AI), and explore predictive modeling techniques using AI and deep learning. This survey examines the advances, challenges, and opportunities in this rapidly evolving field, emphasizing the potential for accurate diagnosis, prognosis, and decision-making in digital pathology.

Deep learning exploration of single-cell and spatially resolved cancer transcriptomics to unravel tumour heterogeneity

Tumour heterogeneity is one of the critical confounding aspects in decoding tumour growth. Malignant cells display variations in their gene transcription profiles and mutation spectra even when originating from a single progenitor cell. Single-cell and spatial transcriptomics sequencing have recently emerged as key technologies for unravelling tumour heterogeneity. Single-cell sequencing promotes individual cell-type identification through transcriptome-wide gene expression measurements of each cell. Spatial transcriptomics facilitates identification of cell-cell interactions and the structural organization of heterogeneous cells within a tumour tissue through associating spatial RNA abundance of cells at distinct spots in the tissue section. However, extracting features and analyzing single-cell and spatial transcriptomics data poses challenges. Single-cell transcriptome data is extremely noisy and its sparse nature and dropouts can lead to misinterpretation of gene expression and the misclassification of cell types. Deep learning predictive power can overcome data challenges, provide high-resolution analysis and enhance precision oncology applications that involve early cancer prognosis, diagnosis, patient survival estimation and anti-cancer therapy planning. In this paper, we provide a background to and review of the recent progress of deep learning frameworks to investigate tumour heterogeneity using both single-cell and spatial transcriptomics data types.

Transcriptional intra-tumour heterogeneity predicted by deep learning in routine breast histopathology slides provides independent prognostic information

BACKGROUND

Intra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been demonstrated in large studies. It has previously been shown that deep learning can enable spatially resolved prediction of molecular phenotypes from digital histopathology whole slide images (WSIs). Here we propose a novel method (Deep-ITH) to predict and measure ITH, and we evaluate its prognostic performance in breast cancer.

METHODS

Deep convolutional neural networks were used to spatially predict gene-expression (PAM50 set) from WSIs. For each predicted transcript, 12 measures of heterogeneity were extracted in the training data set (N = 931). A prognostic score to dichotomise patients into Deep-ITH low- and high-risk groups was established using an elastic-net regularised Cox proportional hazards model (recurrence-free survival). Prognostic performance was evaluated in two independent data sets: SöS-BC-1 (N = 1358) and SCAN-B-Lund (N = 1262).

RESULTS

We observed an increase in risk of recurrence in the high-risk group with hazard ratio (HR) 2.11 (95%CI:1.22-3.60; p = 0.007) using nested cross-validation. Subgroup analyses confirmed the prognostic performance in oestrogen receptor (ER)-positive, human epidermal growth factor receptor 2 (HER2)-negative, grade 3, and large tumour subgroups. The prognostic value was confirmed in the independent SöS-BC-1 cohort (HR=1.84; 95%CI:1.03-3.3; p = 3.99 ×10-2). In the other external cohort, significant HR was observed in the subgroup of histological grade 2 patients, as well as in the subgroup of patients with small tumours (<20 mm).

CONCLUSION

We developed a novel method for an automated, scalable, and cost-efficient measure of ITH from WSIs that provides independent prognostic value for breast cancer.

SIGNIFICANCE

Transcriptional ITH predicted by deep learning models enables prediction of patient survival from routine histopathology WSIs in breast cancer.

Brain tumor detection and screening using artificial intelligence techniques: Current trends and future perspectives

A brain tumor is an abnormal mass of tissue located inside the skull. In addition to putting pressure on the healthy parts of the brain, it can lead to significant health problems. Depending on the region of the brain tumor, it can cause a wide range of health issues. As malignant brain tumors grow rapidly, the mortality rate of individuals with this cancer can increase substantially with each passing week. Hence it is vital to detect these tumors early so that preventive measures can be taken at the initial stages. Computer-aided diagnostic (CAD) systems, in coordination with artificial intelligence (AI) techniques, have a vital role in the early detection of this disorder. In this review, we studied 124 research articles published from 2000 to 2022. Here, the challenges faced by CAD systems based on different modalities are highlighted along with the current requirements of this domain and future prospects in this area of research.

Synthetic whole-slide image tile generation with gene expression profile-infused deep generative models

In this work, we propose an approach to generate whole-slide image (WSI) tiles by using deep generative models infused with matched gene expression profiles. First, we train a variational autoencoder (VAE) that learns a latent, lower-dimensional representation of multi-tissue gene expression profiles. Then, we use this representation to infuse generative adversarial networks (GANs) that generate lung and brain cortex tissue tiles, resulting in a new model that we call RNA-GAN. Tiles generated by RNA-GAN were preferred by expert pathologists compared with tiles generated using traditional GANs, and in addition, RNA-GAN needs fewer training epochs to generate high-quality tiles. Finally, RNA-GAN was able to generalize to gene expression profiles outside of the training set, showing imputation capabilities. A web-based quiz is available for users to play a game distinguishing real and synthetic tiles: https://rna-gan.stanford.edu/, and the code for RNA-GAN is available here: https://github.com/gevaertlab/RNA-GAN.

A Weakly Supervised Deep Learning Framework for Whole Slide Classification to Facilitate Digital Pathology in Animal Study

The pathology of animal studies is crucial for toxicity evaluations and regulatory assessments, but the manual examination of slides by pathologists remains time-consuming and requires extensive training. One inherent challenge in this process is the interobserver variability, which can compromise the consistency and accuracy of a study. Artificial intelligence (AI) has demonstrated its ability to automate similar examinations in clinical applications with enhanced efficiency, consistency, and accuracy. However, training AI models typically relies on costly pixel-level annotation of injured regions and is often not available for animal pathology. To address this, we developed the PathologAI system, a "weakly" supervised approach for WSI classification in rat images without explicit lesion annotation at the pixel level. Using rat liver imaging data from the Open TG-GATEs system, PathologAI was applied to predict necrosis of n = 816 WSIs (377 controls). TG-GATEs studied 170 compounds at three dose levels (low, middle, and high) for four time points (3, 7, 14, and 28 days). PathologAI first preprocessed WSIs at the tile level to generate a high-level representation with a Generative Adversarial Network architecture. The prediction of liver necrosis relied on an ensemble model of 5 CNN classifiers trained on 335 WSIs. The ensemble model achieved notable classification accuracy on the holdout test set: 87% among 87 control slides free of findings, 83% among 120 controls with spontaneous necrosis, 67% among 147 treated animals with spontaneous minimal or slight necrosis, and 59% among 127 treated animals with minimal or slight necrosis caused by the treatment. Importantly, PathologAI was able to discriminate WSIs with spontaneous necrosis from those with treatment related necrosis and discriminated mild lesion level findings (slight vs minimal) and between treatment dose levels. PathologAI could provide an inexpensive and rapid screening tool to assist the digital pathology analysis in preclinical applications and general toxicological studies.

Breast cancer histopathology image-based gene expression prediction using spatial transcriptomics data and deep learning

Tumour heterogeneity in breast cancer poses challenges in predicting outcome and response to therapy. Spatial transcriptomics technologies may address these challenges, as they provide a wealth of information about gene expression at the cell level, but they are expensive, hindering their use in large-scale clinical oncology studies. Predicting gene expression from hematoxylin and eosin stained histology images provides a more affordable alternative for such studies. Here we present BrST-Net, a deep learning framework for predicting gene expression from histopathology images using spatial transcriptomics data. Using this framework, we trained and evaluated four distinct state-of-the-art deep learning architectures, which include ResNet101, Inception-v3, EfficientNet (with six different variants), and vision transformer (with two different variants), all without utilizing pretrained weights for the prediction of 250 genes. To enhance the generalisation performance of the main network, we introduce an auxiliary network into the framework. Our methodology outperforms previous studies, with 237 genes identified with positive correlation, including 24 genes with a median correlation coefficient greater than 0.50. This is a notable improvement over previous studies, which could predict only 102 genes with positive correlation, with the highest correlation values ranging from 0.29 to 0.34.

Deep Learning Methodologies Applied to Digital Pathology in Prostate Cancer: A Systematic Review

Deep learning (DL), often called artificial intelligence (AI), has been increasingly used in Pathology thanks to the use of scanners to digitize slides which allow us to visualize them on monitors and process them with AI algorithms. Many articles have focused on DL applied to prostate cancer (PCa). This systematic review explains the DL applications and their performances for PCa in digital pathology. Article research was performed using PubMed and Embase to collect relevant articles. A Risk of Bias (RoB) was assessed with an adaptation of the QUADAS-2 tool. Out of the 77 included studies, eight focused on pre-processing tasks such as quality assessment or staining normalization. Most articles (n = 53) focused on diagnosis tasks like cancer detection or Gleason grading. Fifteen articles focused on prediction tasks, such as recurrence prediction or genomic correlations. Best performances were reached for cancer detection with an Area Under the Curve (AUC) up to 0.99 with algorithms already available for routine diagnosis. A few biases outlined by the RoB analysis are often found in these articles, such as the lack of external validation. This review was registered on PROSPERO under CRD42023418661.

Heterogeneity of the tumor immune microenvironment and clinical interventions

The tumor immune microenvironment (TIME) is broadly composed of various immune cells, and its heterogeneity is characterized by both immune cells and stromal cells. During the course of tumor formation and progression and anti-tumor treatment, the composition of the TIME becomes heterogeneous. Such immunological heterogeneity is not only present between populations but also exists on temporal and spatial scales. Owing to the existence of TIME, clinical outcomes can differ when a similar treatment strategy is provided to patients. Therefore, a comprehensive assessment of TIME heterogeneity is essential for developing precise and effective therapies. Facilitated by advanced technologies, it is possible to understand the complexity and diversity of the TIME and its influence on therapy responses. In this review, we discuss the potential reasons for TIME heterogeneity and the current approaches used to explore it. We also summarize clinical intervention strategies based on associated mechanisms or targets to control immunological heterogeneity.

Deep learning predicts patients outcome and mutations from digitized histology slides in gastrointestinal stromal tumor

Risk assessment of gastrointestinal stromal tumor (GIST) according to the AFIP/Miettinen classification and mutational profiling are major tools for patient management. However, the AFIP/Miettinen classification depends heavily on mitotic counts, which is laborious and sometimes inconsistent between pathologists. It has also been shown to be imperfect in stratifying patients. Molecular testing is costly and time-consuming, therefore, not systematically performed in all countries. New methods to improve risk and molecular predictions are hence crucial to improve the tailoring of adjuvant therapy. We have built deep learning (DL) models on digitized HES-stained whole slide images (WSI) to predict patients' outcome and mutations. Models were trained with a cohort of 1233 GIST and validated on an independent cohort of 286 GIST. DL models yielded comparable results to the Miettinen classification for relapse-free-survival prediction in localized GIST without adjuvant Imatinib (C-index=0.83 in cross-validation and 0.72 for independent testing). DL splitted Miettinen intermediate risk GIST into high/low-risk groups (p value = 0.002 in the training set and p value = 0.29 in the testing set). DL models achieved an area under the receiver operating characteristic curve (AUC) of 0.81, 0.91, and 0.71 for predicting mutations in KIT, PDGFRA and wild type, respectively, in cross-validation and 0.76, 0.90, and 0.55 in independent testing. Notably, PDGFRA exon18 D842V mutation, which is resistant to Imatinib, was predicted with an AUC of 0.87 and 0.90 in cross-validation and independent testing, respectively. Additionally, novel histological criteria predictive of patients' outcome and mutations were identified by reviewing the tiles selected by the models. As a proof of concept, our study showed the possibility of implementing DL with digitized WSI and may represent a reproducible way to improve tailoring therapy and precision medicine for patients with GIST.

Grading of lung adenocarcinomas with simultaneous segmentation by artificial intelligence (GLASS-AI)

Preclinical genetically engineered mouse models (GEMMs) of lung adenocarcinoma are invaluable for investigating molecular drivers of tumor formation, progression, and therapeutic resistance. However, histological analysis of these GEMMs requires significant time and training to ensure accuracy and consistency. To achieve a more objective and standardized analysis, we used machine learning to create GLASS-AI, a histological image analysis tool that the broader cancer research community can utilize to grade, segment, and analyze tumors in preclinical models of lung adenocarcinoma. GLASS-AI demonstrates strong agreement with expert human raters while uncovering a significant degree of unreported intratumor heterogeneity. Integrating immunohistochemical staining with high-resolution grade analysis by GLASS-AI identified dysregulation of Mapk/Erk signaling in high-grade lung adenocarcinomas and locally advanced tumor regions. Our work demonstrates the benefit of employing GLASS-AI in preclinical lung adenocarcinoma models and the power of integrating machine learning and molecular biology techniques for studying the molecular pathways that underlie cancer progression.

Spatial cellular architecture predicts prognosis in glioblastoma

Intra-tumoral heterogeneity and cell-state plasticity are key drivers for the therapeutic resistance of glioblastoma. Here, we investigate the association between spatial cellular organization and glioblastoma prognosis. Leveraging single-cell RNA-seq and spatial transcriptomics data, we develop a deep learning model to predict transcriptional subtypes of glioblastoma cells from histology images. Employing this model, we phenotypically analyze 40 million tissue spots from 410 patients and identify consistent associations between tumor architecture and prognosis across two independent cohorts. Patients with poor prognosis exhibit higher proportions of tumor cells expressing a hypoxia-induced transcriptional program. Furthermore, a clustering pattern of astrocyte-like tumor cells is associated with worse prognosis, while dispersion and connection of the astrocytes with other transcriptional subtypes correlate with decreased risk. To validate these results, we develop a separate deep learning model that utilizes histology images to predict prognosis. Applying this model to spatial transcriptomics data reveal survival-associated regional gene expression programs. Overall, our study presents a scalable approach to unravel the transcriptional heterogeneity of glioblastoma and establishes a critical connection between spatial cellular architecture and clinical outcomes.

A deep learning approach to private data sharing of medical images using conditional generative adversarial networks (GANs)

Clinical data sharing can facilitate data-driven scientific research, allowing a broader range of questions to be addressed and thereby leading to greater understanding and innovation. However, sharing biomedical data can put sensitive personal information at risk. This is usually addressed by data anonymization, which is a slow and expensive process. An alternative to anonymization is construction of a synthetic dataset that behaves similar to the real clinical data but preserves patient privacy. As part of a collaboration between Novartis and the Oxford Big Data Institute, a synthetic dataset was generated based on images from COSENTYX® (secukinumab) ankylosing spondylitis (AS) clinical studies. An auxiliary classifier Generative Adversarial Network (ac-GAN) was trained to generate synthetic magnetic resonance images (MRIs) of vertebral units (VUs), conditioned on the VU location (cervical, thoracic and lumbar). Here, we present a method for generating a synthetic dataset and conduct an in-depth analysis on its properties along three key metrics: image fidelity, sample diversity and dataset privacy.

DeeP4med: deep learning for P4 medicine to predict normal and cancer transcriptome in multiple human tissues

BACKGROUND

P4 medicine (predict, prevent, personalize, and participate) is a new approach to diagnosing and predicting diseases on a patient-by-patient basis. For the prevention and treatment of diseases, prediction plays a fundamental role. One of the intelligent strategies is the design of deep learning models that can predict the state of the disease using gene expression data.

RESULTS

We create an autoencoder deep learning model called DeeP4med, including a Classifier and a Transferor that predicts cancer's gene expression (mRNA) matrix from its matched normal sample and vice versa. The range of the F1 score of the model, depending on tissue type in the Classifier, is from 0.935 to 0.999 and in Transferor from 0.944 to 0.999. The accuracy of DeeP4med for tissue and disease classification was 0.986 and 0.992, respectively, which performed better compared to seven classic machine learning models (Support Vector Classifier, Logistic Regression, Linear Discriminant Analysis, Naive Bayes, Decision Tree, Random Forest, K Nearest Neighbors).

CONCLUSIONS

Based on the idea of DeeP4med, by having the gene expression matrix of a normal tissue, we can predict its tumor gene expression matrix and, in this way, find effective genes in transforming a normal tissue into a tumor tissue. Results of Differentially Expressed Genes (DEGs) and enrichment analysis on the predicted matrices for 13 types of cancer showed a good correlation with the literature and biological databases. This led that by using the gene expression matrix, to train the model with features of each person in a normal and cancer state, this model could predict diagnosis based on gene expression data from healthy tissue and be used to identify possible therapeutic interventions for those patients.

An aggregation of aggregation methods in computational pathology

Image analysis and machine learning algorithms operating on multi-gigapixel whole-slide images (WSIs) often process a large number of tiles (sub-images) and require aggregating predictions from the tiles in order to predict WSI-level labels. In this paper, we present a review of existing literature on various types of aggregation methods with a view to help guide future research in the area of computational pathology (CPath). We propose a general CPath workflow with three pathways that consider multiple levels and types of data and the nature of computation to analyse WSIs for predictive modelling. We categorize aggregation methods according to the context and representation of the data, features of computational modules and CPath use cases. We compare and contrast different methods based on the principle of multiple instance learning, perhaps the most commonly used aggregation method, covering a wide range of CPath literature. To provide a fair comparison, we consider a specific WSI-level prediction task and compare various aggregation methods for that task. Finally, we conclude with a list of objectives and desirable attributes of aggregation methods in general, pros and cons of the various approaches, some recommendations and possible future directions.

Overcoming the challenges to implementation of artificial intelligence in pathology

Pathologists worldwide are facing remarkable challenges with increasing workloads and lack of time to provide consistently high-quality patient care. The application of artificial intelligence (AI) to digital whole-slide images has the potential of democratizing the access to expert pathology and affordable biomarkers by supporting pathologists in the provision of timely and accurate diagnosis as well as supporting oncologists by directly extracting prognostic and predictive biomarkers from tissue slides. The long-awaited adoption of AI in pathology, however, has not materialized, and the transformation of pathology is happening at a much slower pace than that observed in other fields (eg, radiology). Here, we provide a critical summary of the developments in digital and computational pathology in the last 10 years, outline key hurdles and ways to overcome them, and provide a perspective for AI-supported precision oncology in the future.

Deciphering the tumour immune microenvironment cell by cell

Immune checkpoint inhibitors (ICIs) have rejuvenated therapeutic approaches in oncology. Although responses tend to be durable, response rates vary in many cancer types. Thus, the identification and validation of predictive biomarkers is a key clinical priority, the answer to which is likely to lie in the tumour microenvironment (TME). A wealth of data demonstrates the huge impact of the TME on ICI response and resistance. However, these data also reveal the complexity of the TME composition including the spatiotemporal interactions between different cell types and their dynamic changes in response to ICIs. Here, we briefly review some of the modalities that sculpt the TME, in particular the metabolic milieu, hypoxia and the role of cancer-associated fibroblasts. We then discuss recent approaches to dissect the TME with a focus on single-cell RNA sequencing, spatial transcriptomics and spatial proteomics. We also discuss some of the clinically relevant findings these multi-modal analyses have yielded.

Domain-specific transfer learning in the automated scoring of tumor-stroma ratio from histopathological images of colorectal cancer

Tumor-stroma ratio (TSR) is a prognostic factor for many types of solid tumors. In this study, we propose a method for automated estimation of TSR from histopathological images of colorectal cancer. The method is based on convolutional neural networks which were trained to classify colorectal cancer tissue in hematoxylin-eosin stained samples into three classes: stroma, tumor and other. The models were trained using a data set that consists of 1343 whole slide images. Three different training setups were applied with a transfer learning approach using domain-specific data i.e. an external colorectal cancer histopathological data set. The three most accurate models were chosen as a classifier, TSR values were predicted and the results were compared to a visual TSR estimation made by a pathologist. The results suggest that classification accuracy does not improve when domain-specific data are used in the pre-training of the convolutional neural network models in the task at hand. Classification accuracy for stroma, tumor and other reached 96.1% on an independent test set. Among the three classes the best model gained the highest accuracy (99.3%) for class tumor. When TSR was predicted with the best model, the correlation between the predicted values and values estimated by an experienced pathologist was 0.57. Further research is needed to study associations between computationally predicted TSR values and other clinicopathological factors of colorectal cancer and the overall survival of the patients.

Privacy risks of whole-slide image sharing in digital pathology

Access to large volumes of so-called whole-slide images-high-resolution scans of complete pathological slides-has become a cornerstone of the development of novel artificial intelligence methods in pathology for diagnostic use, education/training of pathologists, and research. Nevertheless, a methodology based on risk analysis for evaluating the privacy risks associated with sharing such imaging data and applying the principle "as open as possible and as closed as necessary" is still lacking. In this article, we develop a model for privacy risk analysis for whole-slide images which focuses primarily on identity disclosure attacks, as these are the most important from a regulatory perspective. We introduce a taxonomy of whole-slide images with respect to privacy risks and mathematical model for risk assessment and design . Based on this risk assessment model and the taxonomy, we conduct a series of experiments to demonstrate the risks using real-world imaging data. Finally, we develop guidelines for risk assessment and recommendations for low-risk sharing of whole-slide image data.

Assessing Biomaterial-Induced Stem Cell Lineage Fate by Machine Learning-Based Artificial Intelligence

Current functional assessment of biomaterial-induced stem cell lineage fate in vitro mainly relies on biomarker-dependent methods with limited accuracy and efficiency. Here a "Mesenchymal stem cell Differentiation Prediction (MeD-P)" framework for biomaterial-induced cell lineage fate prediction is reported. MeD-P contains a cell-type-specific gene expression profile as a reference by integrating public RNA-seq data related to tri-lineage differentiation (osteogenesis, chondrogenesis, and adipogenesis) of human mesenchymal stem cells (hMSCs) and a predictive model for classifying hMSCs differentiation lineages using the k-nearest neighbors (kNN) strategy. It is shown that MeD-P exhibits an overall accuracy of 90.63% on testing datasets, which is significantly higher than the model constructed based on canonical marker genes (80.21%). Moreover, evaluations of multiple biomaterials show that MeD-P provides accurate prediction of lineage fate on different types of biomaterials as early as the first week of hMSCs culture. In summary, it is demonstrated that MeD-P is an efficient and accurate strategy for stem cell lineage fate prediction and preliminary biomaterial functional evaluation.

hist2RNA: An Efficient Deep Learning Architecture to Predict Gene Expression from Breast Cancer Histopathology Images

Gene expression can be used to subtype breast cancer with improved prediction of risk of recurrence and treatment responsiveness over that obtained using routine immunohistochemistry (IHC). However, in the clinic, molecular profiling is primarily used for ER+ breast cancer, which is costly, tissue destructive, requires specialised platforms, and takes several weeks to obtain a result. Deep learning algorithms can effectively extract morphological patterns in digital histopathology images to predict molecular phenotypes quickly and cost-effectively. We propose a new, computationally efficient approach called hist2RNA inspired by bulk RNA sequencing techniques to predict the expression of 138 genes (incorporated from 6 commercially available molecular profiling tests), including luminal PAM50 subtype, from hematoxylin and eosin (H&E)-stained whole slide images (WSIs). The training phase involves the aggregation of extracted features for each patient from a pretrained model to predict gene expression at the patient level using annotated H&E images from The Cancer Genome Atlas (TCGA, n = 335). We demonstrate successful gene prediction on a held-out test set (n = 160, corr = 0.82 across patients, corr = 0.29 across genes) and perform exploratory analysis on an external tissue microarray (TMA) dataset (n = 498) with known IHC and survival information. Our model is able to predict gene expression and luminal PAM50 subtype (Luminal A versus Luminal B) on the TMA dataset with prognostic significance for overall survival in univariate analysis (c-index = 0.56, hazard ratio = 2.16 (95% CI 1.12-3.06), p < 5 × 10-3), and independent significance in multivariate analysis incorporating standard clinicopathological variables (c-index = 0.65, hazard ratio = 1.87 (95% CI 1.30-2.68), p < 5 × 10-3). The proposed strategy achieves superior performance while requiring less training time, resulting in less energy consumption and computational cost compared to patch-based models. Additionally, hist2RNA predicts gene expression that has potential to determine luminal molecular subtypes which correlates with overall survival, without the need for expensive molecular testing.

Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status

The detection of tumour gene mutations by DNA or RNA sequencing is crucial for the prescription of effective targeted therapies. Recent developments showed promising results for tumoral mutational status prediction using new deep learning based methods on histopathological images. However, it is still unknown whether these methods can be useful aside from sequencing methods for efficient population diagnosis. In this retrospective study, we use a standard prediction pipeline based on a convolutional neural network for the detection of cancer driver genomic alterations in The Cancer Genome Atlas (TCGA) breast (BRCA, n = 719), lung (LUAD, n = 541) and colon (COAD, n = 459) cancer datasets. We propose 3 diagnostic strategies using deep learning methods as first-line diagnostic tools. Focusing on cancer driver genes such as KRAS, EGFR or TP53, we show that these methods help reduce DNA sequencing by up to 49.9% with a high sensitivity (95%). In a context of limited resources, these methods increase sensitivity up to 69.8% at a 30% capacity of DNA sequencing tests, up to 85.1% at a 50% capacity, and up to 91.8% at a 70% capacity. These methods can also be used to prioritize patients with a positive predictive value up to 90.6% in the 10% patient most at risk of being mutated. Limitations of this study include the lack of external validation on non-TCGA data, dependence on prevalence of mutations in datasets, and use of a standard DL method on a limited dataset. Future studies using state-of-the-art methods and larger datasets are needed for better evaluation and clinical implementation.

A scoping review on deep learning for next-generation RNA-Seq. data analysis

In the last decade, transcriptome research adopting next-generation sequencing (NGS) technologies has gathered incredible momentum amongst functional genomics scientists, particularly amongst clinical/biomedical research groups. The progressive enfoldment/adoption of NGS technologies has incited an abundance of next-generation transcriptomic data harbouring an opulence of new knowledge in public databases. Nevertheless, knowledge discovery from these next-generation RNA-Seq. data analysis necessitates extensive bioinformatics know-how besides elaborate data analysis software packages consistent with the type and context of data analysis. Several reliability and reproducibility concerns continue to impede RNA-Seq. data analysis. Characteristic challenges comprise of data quality, hardware and networking provisions, selection and prioritisation of data analysis tools, and yet significantly implementing of robust machine learning algorithms for maximised exploitation of these experimental transcriptomic data. Over the years, numerous machine learning algorithms have been implemented for improved transcriptomic data analysis executing predominantly shallow learning approaches. More recently, deep learning algorithms are becoming more mainstream, and enactment for next-generation RNA-Seq. data analysis could be revolutionary in the coming years in the biomedical domain. In this scoping review, we attempt to determine the existing literature's size and potential nature in deep learning and NGS RNA-Seq. data analysis. An analysis of the contemporary topics of next-generation RNA-Seq. data analysis based on deep learning algorithms is critically reviewed, emphasising open-source resources.

SynapseCLR: Uncovering features of synapses in primary visual cortex through contrastive representation learning

3D electron microscopy (EM) connectomics image volumes are surpassing 1 mm3, providing information-dense, multi-scale visualizations of brain circuitry and necessitating scalable analysis techniques. We present SynapseCLR, a self-supervised contrastive learning method for 3D EM data, and use it to extract features of synapses from mouse visual cortex. SynapseCLR feature representations separate synapses by appearance and functionally important structural annotations. We demonstrate SynapseCLR's utility for valuable downstream tasks, including one-shot identification of defective synapse segmentations, dataset-wide similarity-based querying, and accurate imputation of annotations for unlabeled synapses, using manual annotation of only 0.2% of the dataset's synapses. In particular, excitatory versus inhibitory neuronal types can be assigned with >99.8% accuracy to individual synapses and highly truncated neurites, enabling neurite-enhanced connectomics analysis. Finally, we present a data-driven, unsupervised study of synaptic structural variation on the representation manifold, revealing its intrinsic axes of variation and showing that representations contain inhibitory subtype information.

Integration of clinical features and deep learning on pathology for the prediction of breast cancer recurrence assays and risk of recurrence

Gene expression-based recurrence assays are strongly recommended to guide the use of chemotherapy in hormone receptor-positive, HER2-negative breast cancer, but such testing is expensive, can contribute to delays in care, and may not be available in low-resource settings. Here, we describe the training and independent validation of a deep learning model that predicts recurrence assay result and risk of recurrence using both digital histology and clinical risk factors. We demonstrate that this approach outperforms an established clinical nomogram (area under the receiver operating characteristic curve of 0.83 versus 0.76 in an external validation cohort, p = 0.0005) and can identify a subset of patients with excellent prognoses who may not need further genomic testing.

Biological insights and novel biomarker discovery through deep learning approaches in breast cancer histopathology

Breast cancer remains a highly prevalent disease with considerable inter- and intra-tumoral heterogeneity complicating prognostication and treatment decisions. The utilization and depth of genomic, transcriptomic and proteomic data for cancer has exploded over recent times and the addition of spatial context to this information, by understanding the correlating morphologic and spatial patterns of cells in tissue samples, has created an exciting frontier of research, histo-genomics. At the same time, deep learning (DL), a class of machine learning algorithms employing artificial neural networks, has rapidly progressed in the last decade with a confluence of technical developments - including the advent of modern graphic processing units (GPU), allowing efficient implementation of increasingly complex architectures at scale; advances in the theoretical and practical design of network architectures; and access to larger datasets for training - all leading to sweeping advances in image classification and object detection. In this review, we examine recent developments in the application of DL in breast cancer histology with particular emphasis of those producing biologic insights or novel biomarkers, spanning the extraction of genomic information to the use of stroma to predict cancer recurrence, with the aim of suggesting avenues for further advancing this exciting field.

A robust and lightweight deep attention multiple instance learning algorithm for predicting genetic alterations

Self-attention mechanism-based algorithms are attractive in digital pathology due to their interpretability, but suffer from computation complexity. This paper presents a novel, lightweight Attention-based Multiple Instance Mutation Learning (AMIML) model to allow small-scale attention operations for predicting gene mutations. Compared to the standard self-attention model, AMIML reduces the number of model parameters by approximately 70%. Using data for 24 clinically relevant genes from four cancer cohorts in TCGA studies (UCEC, BRCA, GBM, and KIRC), we compare AMIML with a standard self-attention model, five other deep learning models, and four traditional machine learning models. The results show that AMIML has excellent robustness and outperforms all the baseline algorithms in the vast majority of the tested genes. Conversely, the performance of the reference deep learning and machine learning models vary across different genes, and produce suboptimal prediction for certain genes. Furthermore, with the flexible and interpretable attention-based pooling mechanism, AMIML can further zero in and detect predictive image patches.

Self-supervised attention-based deep learning for pan-cancer mutation prediction from histopathology

The histopathological phenotype of tumors reflects the underlying genetic makeup. Deep learning can predict genetic alterations from pathology slides, but it is unclear how well these predictions generalize to external datasets. We performed a systematic study on Deep-Learning-based prediction of genetic alterations from histology, using two large datasets of multiple tumor types. We show that an analysis pipeline that integrates self-supervised feature extraction and attention-based multiple instance learning achieves a robust predictability and generalizability.

Inference of single cell profiles from histology stains with the Single-Cell omics from Histology Analysis Framework (SCHAF)

Tissue biology involves an intricate balance between cell-intrinsic processes and interactions between cells organized in specific spatial patterns, which can be respectively captured by single-cell profiling methods, such as single-cell RNA-seq (scRNA-seq), and histology imaging data, such as Hematoxylin-and-Eosin (H&E) stains. While single-cell profiles provide rich molecular information, they can be challenging to collect routinely and do not have spatial resolution. Conversely, histological H&E assays have been a cornerstone of tissue pathology for decades, but do not directly report on molecular details, although the observed structure they capture arises from molecules and cells. Here, we leverage adversarial machine learning to develop SCHAF (Single-Cell omics from Histology Analysis Framework), to generate a tissue sample's spatially-resolved single-cell omics dataset from its H&E histology image. We demonstrate SCHAF on two types of human tumors-from lung and metastatic breast cancer-training with matched samples analyzed by both sc/snRNA-seq and by H&E staining. SCHAF generated appropriate single-cell profiles from histology images in test data, related them spatially, and compared well to ground-truth scRNA-Seq, expert pathologist annotations, or direct MERFISH measurements. SCHAF opens the way to next-generation H&E2.0 analyses and an integrated understanding of cell and tissue biology in health and disease.

Learning to predict RNA sequence expressions from whole slide images with applications for search and classification

Deep learning methods are widely applied in digital pathology to address clinical challenges such as prognosis and diagnosis. As one of the most recent applications, deep models have also been used to extract molecular features from whole slide images. Although molecular tests carry rich information, they are often expensive, time-consuming, and require additional tissue to sample. In this paper, we propose tRNAsformer, an attention-based topology that can learn both to predict the bulk RNA-seq from an image and represent the whole slide image of a glass slide simultaneously. The tRNAsformer uses multiple instance learning to solve a weakly supervised problem while the pixel-level annotation is not available for an image. We conducted several experiments and achieved better performance and faster convergence in comparison to the state-of-the-art algorithms. The proposed tRNAsformer can assist as a computational pathology tool to facilitate a new generation of search and classification methods by combining the tissue morphology and the molecular fingerprint of the biopsy samples.

Direct prediction of Homologous Recombination Deficiency from routine histology in ten different tumor types with attention-based Multiple Instance Learning: a development and validation study

Background

Homologous Recombination Deficiency (HRD) is a pan-cancer predictive biomarker that identifies patients who benefit from therapy with PARP inhibitors (PARPi). However, testing for HRD is highly complex. Here, we investigated whether Deep Learning can predict HRD status solely based on routine Hematoxylin & Eosin (H&E) histology images in ten cancer types.

Methods

We developed a fully automated deep learning pipeline with attention-weighted multiple instance learning (attMIL) to predict HRD status from histology images. A combined genomic scar HRD score, which integrated loss of heterozygosity (LOH), telomeric allelic imbalance (TAI) and large-scale state transitions (LST) was calculated from whole genome sequencing data for n=4,565 patients from two independent cohorts. The primary statistical endpoint was the Area Under the Receiver Operating Characteristic curve (AUROC) for the prediction of genomic scar HRD with a clinically used cutoff value.

Results

We found that HRD status is predictable in tumors of the endometrium, pancreas and lung, reaching cross-validated AUROCs of 0.79, 0.58 and 0.66. Predictions generalized well to an external cohort with AUROCs of 0.93, 0.81 and 0.73 respectively. Additionally, an HRD classifier trained on breast cancer yielded an AUROC of 0.78 in internal validation and was able to predict HRD in endometrial, prostate and pancreatic cancer with AUROCs of 0.87, 0.84 and 0.67 indicating a shared HRD-like phenotype is across tumor entities.

Conclusion

In this study, we show that HRD is directly predictable from H&E slides using attMIL within and across ten different tumor types.

sPhaseStation: a whole slide quantitative phase imaging system based on dual-view transport of intensity phase microscopy

Whole slide imaging scans a microscope slide into a high-resolution digital image, and it paves the way from pathology to digital diagnostics. However, most of them rely on bright-field and fluorescence imaging with sample labels. In this work, we designed sPhaseStation, which is a dual-view transport of intensity phase microscopy-based whole slide quantitative phase imaging system for label-free samples. sPhaseStation relies on a compact microscopic system with two imaging recorders that can capture both under and over-focus images. Combined with the field of view (FoV) scan, a series of these defocus images in different FoVs can be captured and stitched into two FoV-extended under and over-focus ones, which are used for phase retrieval via solving the transport of intensity equation. Using a 10× micro-objective, sPhaseStation reaches the spatial resolution of 2.19 µm and obtains the phase with high accuracy. Additionally, it acquires a whole slide image of a 3m m×3m m region in 2 min. The reported sPhaseStation could be a prototype of the whole slide quantitative phase imaging device, which may provide a new perspective for digital pathology.

Predicting gene mutation status via artificial intelligence technologies based on multimodal integration (MMI) to advance precision oncology

Personalized treatment strategies for cancer frequently rely on the detection of genetic alterations which are determined by molecular biology assays. Historically, these processes typically required single-gene sequencing, next-generation sequencing, or visual inspection of histopathology slides by experienced pathologists in a clinical context. In the past decade, advances in artificial intelligence (AI) technologies have demonstrated remarkable potential in assisting physicians with accurate diagnosis of oncology image-recognition tasks. Meanwhile, AI techniques make it possible to integrate multimodal data such as radiology, histology, and genomics, providing critical guidance for the stratification of patients in the context of precision therapy. Given that the mutation detection is unaffordable and time-consuming for a considerable number of patients, predicting gene mutations based on routine clinical radiological scans or whole-slide images of tissue with AI-based methods has become a hot issue in actual clinical practice. In this review, we synthesized the general framework of multimodal integration (MMI) for molecular intelligent diagnostics beyond standard techniques. Then we summarized the emerging applications of AI in the prediction of mutational and molecular profiles of common cancers (lung, brain, breast, and other tumor types) pertaining to radiology and histology imaging. Furthermore, we concluded that there truly exist multiple challenges of AI techniques in the way of its real-world application in the medical field, including data curation, feature fusion, model interpretability, and practice regulations. Despite these challenges, we still prospect the clinical implementation of AI as a highly potential decision-support tool to aid oncologists in future cancer treatment management.

Facts and Hopes on the Use of Artificial Intelligence for Predictive Immunotherapy Biomarkers in Cancer

Immunotherapy by immune checkpoint inhibitors has become a standard treatment strategy for many types of solid tumors. However, the majority of patients with cancer will not respond, and predicting response to this therapy is still a challenge. Artificial intelligence (AI) methods can extract meaningful information from complex data, such as image data. In clinical routine, radiology or histopathology images are ubiquitously available. AI has been used to predict the response to immunotherapy from radiology or histopathology images, either directly or indirectly via surrogate markers. While none of these methods are currently used in clinical routine, academic and commercial developments are pointing toward potential clinical adoption in the near future. Here, we summarize the state of the art in AI-based image biomarkers for immunotherapy response based on radiology and histopathology images. We point out limitations, caveats, and pitfalls, including biases, generalizability, and explainability, which are relevant for researchers and health care providers alike, and outline key clinical use cases of this new class of predictive biomarkers.