Virtual staining for histology by deep learning.

In pathology and biomedical research, histology is the cornerstone method for tissue analysis. Currently, the histological workflow consumes plenty of chemicals, water, and time for staining procedures. Deep learning is now enabling digital replacement of parts of the histological staining procedure. In virtual staining, histological stains are created by training neural networks to produce stained images from an unstained tissue image, or through transferring information from one stain to another. These technical innovations provide more sustainable, rapid, and cost-effective alternatives to traditional histological pipelines, but their development is in an early phase and requires rigorous validation. In this review we cover the basic concepts of virtual staining for histology and provide future insights into the utilization of artificial intelligence (AI)-enabled virtual histology.

A PEG-assisted membrane coating to prepare biomimetic mesoporous silicon for PET/CT imaging of triple-negative breast cancer.

Triple-negative breast cancer (TNBC) diagnosis remains challenging without expressing critical receptors. Cancer cell membrane (CCm) coating has been extensively studied for targeted cancer diagnostics due to attractive features such as good biocompatibility and homotypic tumor-targeting. However, the present study found that widely used CCm coating approaches, such as extrusion, were not applicable for functionalizing irregularly shaped nanoparticles (NPs), such as porous silicon (PSi). To tackle this challenge, we proposed a novel approach that employs polyethylene glycol (PEG)-assisted membrane coating, wherein PEG and CCm are respectively functionalized on PSi NPs through chemical conjugation and physical absorption. Meanwhile, the PSi NPs were grafted with the bisphosphonate (BP) molecules for radiolabeling. Thanks to the good chelating ability of BP and homotypic tumor targeting of cancer CCm coating, a novel PSi-based contrast agent (CCm-PEG-89Zr-BP-PSi) was developed for targeted positron emission tomography (PET)/computed tomography (CT) imaging of TNBC. The novel imaging agent showed good radiochemical purity (∼99 %) and stability (∼95 % in PBS and ∼99 % in cell medium after 48 h). Furthermore, the CCm-PEG-89Zr-BP-PSi NPs had efficient homotypic targeting ability in vitro and in vivo for TNBC. These findings demonstrate a versatile biomimetic coating method to prepare novel NPs for tumor-targeted diagnosis.

Platinum-based drugs induce phenotypic alterations in nucleoli and Cajal bodies in prostate cancer cells.

PURPOSE: Platinum-based drugs are cytotoxic drugs commonly used in cancer treatment. They cause DNA damage, effects of which on chromatin and cellular responses are relatively well described. Yet, the nuclear stress responses related to RNA processing are incompletely known and may be relevant for the heterogeneity with which cancer cells respond to these drugs. Here, we determine the type and extent of nuclear stress responses of prostate cancer cells to clinically relevant platinum drugs. METHODS: We study nucleolar and Cajal body (CB) responses to cisplatin, carboplatin, and oxaliplatin with immunofluorescence-based methods in prostate cancer cells. We utilize organelle-specific markers NPM, Fibrillarin, Coilin, and SMN1, and study CB-regulatory proteins FUS and TDP-43 using siRNA-mediated downregulation. RESULTS: Different types of prostate cancer cells have different sensitivities to platinum drugs. With equally cytotoxic doses, cisplatin, and oxaliplatin induce prominent nucleolar and CB stress responses while the nuclear stress phenotypes to carboplatin are milder. We find that Coilin is a stress-specific marker for platinum drug response heterogeneity. We also find that CB-associated, stress-responsive RNA binding proteins FUS and TDP-43 control Coilin and CB biology in prostate cancer cells and, further, that TDP-43 is associated with stress-responsive CBs in prostate cancer cells. CONCLUSION: Our findings provide insight into the heterologous responses of prostate cancer cells to different platinum drug treatments and indicate Coilin and TDP-43 as stress mediators in the varied outcomes. These results help understand cancer drug responses at a cellular level and have implications in tackling heterogeneity in cancer treatment outcomes.

Biomimetic Inorganic Nanovectors as Tumor-Targeting Theranostic Platform against Triple-Negative Breast Cancer.

Mesoporous silicon nanoparticles (PSi NPs) are promising platforms of nanomedicine because of their good compatibility, high payload capacities of anticancer drugs, and easy chemical modification. Here, PSi surfaces were functionalized with bisphosphonates (BP) for radiolabeling, loaded with doxorubicin (DOX) for chemotherapy, and the NPs were coated with cancer cell membrane (CCm) for homotypic cancer targeting. To enhance the CCm coating, the NP surfaces were covered with polyethylene glycol prior to the CCm coating. The effects of the BP amount and pH conditions on the radiolabeling efficacy were studied. The maximum BP was (2.27 wt%) on the PSi surfaces, and higher radiochemical yields were obtained for 99mTc (97% ± 2%) and 68Ga (94.6% ± 0.2%) under optimized pH conditions (pH = 5). The biomimetic NPs exhibited a good radiochemical and colloidal stability in phosphate-buffered saline and cell medium. In vitro studies demonstrated that the biomimetic NPs exhibited an enhanced cellular uptake and increased delivery of DOX to cancer cells, resulting in better chemotherapy than free DOX or pure NPs. Altogether, these findings indicate the potential of the developed platform for cancer treatment and diagnosis.

Deformation equivariant cross-modality image synthesis with paired non-aligned training data.

Cross-modality image synthesis is an active research topic with multiple medical clinically relevant applications. Recently, methods allowing training with paired but misaligned data have started to emerge. However, no robust and well-performing methods applicable to a wide range of real world data sets exist. In this work, we propose a generic solution to the problem of cross-modality image synthesis with paired but non-aligned data by introducing new deformation equivariance encouraging loss functions. The method consists of joint training of an image synthesis network together with separate registration networks and allows adversarial training conditioned on the input even with misaligned data. The work lowers the bar for new clinical applications by allowing effortless training of cross-modality image synthesis networks for more difficult data sets.

A Multi-Stain Breast Cancer Histological Whole-Slide-Image Data Set from Routine Diagnostics.

The analysis of FFPE tissue sections stained with haematoxylin and eosin (H&E) or immunohistochemistry (IHC) is essential for the pathologic assessment of surgically resected breast cancer specimens. IHC staining has been broadly adopted into diagnostic guidelines and routine workflows to assess the status of several established biomarkers, including ER, PGR, HER2 and KI67. Biomarker assessment can also be facilitated by computational pathology image analysis methods, which have made numerous substantial advances recently, often based on publicly available whole slide image (WSI) data sets. However, the field is still considerably limited by the sparsity of public data sets. In particular, there are no large, high quality publicly available data sets with WSIs of matching IHC and H&E-stained tissue sections from the same tumour. Here, we publish the currently largest publicly available data set of WSIs of tissue sections from surgical resection specimens from female primary breast cancer patients with matched WSIs of corresponding H&E and IHC-stained tissue, consisting of 4,212 WSIs from 1,153 patients.

Complementary analysis of proteome-wide proteomics reveals changes in RNA binding protein-profiles during prostate cancer progression.

BACKGROUND: Accumulating evidence indicates importance of RNA regulation in cancer. This includes events such as splicing, translation, and regulation of noncoding RNAs, functions which are governed by RNA binding proteins (RBPs). AIMS: To find which RBPs could be relevant for prostate cancer, we performed systematic screening of RBP expression in clinical prostate cancer. METHODS AND RESULTS: We interrogated four proteome-wide proteomics datasets including tumor samples of primary, castration resistant, and metastatic prostate cancer. We found that, while the majority of RBPs are expressed but not significantly altered during prostate cancer development and progression, expression of several RBPs increases in advanced disease. Interestingly, most of the differentially expressed RBPs are not targets of differential posttranscriptional phosphorylation during disease progression. The RBPs undergoing expression changes have functions in, especially, poly(A)-RNA binding, nucleocytoplasmic transport, and cellular stress responses, suggesting that these may play a role in formation of castration resistance. Pathway analyzes indicate that increased ribosome production and chromatin-related functions of RBPs are also linked to castration resistant and metastatic prostate cancers. We selected a group of differentially expressed RBPs and studied their role in cultured prostate cancer cells. With siRNA screens, several of these were indicated in survival (DDX6, EIF4A3, PABPN1), growth (e.g., EIF5A, HNRNPH2, LRRC47, and NVL), and migration (e.g., NOL3 and SLTM) of prostate cancer cells. Our analyzes further show that RRP9, a U3 small nucleolar protein essential for ribosome formation, undergoes changes at protein level during metastasis in prostate cancer. CONCLUSION: In this work, we recognized significant molecular alterations in RBP profiles during development and evolution of prostate cancer. Our study further indicates several functionally significant RBPs warranting further investigation for their functions and possible targetability in prostate cancer.

Deep learning transforms colorectal cancer biomarker prediction from histopathology images.

Artificial intelligence (AI) is rapidly gaining interest in medicine, including pathological assessments for personalized medicine. In this issue of Cancer Cell, Wagner et al. demonstrate superior accuracy of transformer-based deep learning in predicting biomarker status in CRC. The work has implications for increased efficiency and accuracy in clinical diagnostics guiding treatment decisions in precision oncology.

Identification of long noncoding RNAs with aberrant expression in prostate cancer metastases.

Prostate cancer (PCa) is the second-most common cause of male cancer-related death in western industrialized countries, and the emergence of metastases is a key challenge in the treatment of PCa. Accumulating studies have shown that long noncoding RNAs (lncRNAs) play an important role in the regulation of diverse cellular and molecular processes during the development and progression of cancer. Here, we utilized a unique cohort of castration-resistant prostate cancer metastases (mCRPC) and corresponding localized tumors and RNA sequencing (RNA-seq). First, we showed that patient-to-patient variability accounted for most of the variance in lncRNA expression between the samples, suggesting that genomic alterations in the samples are the main drivers of lncRNA expression in PCa metastasis. Subsequently, we identified 27 lncRNAs with differential expression (DE-lncRNAs) between metastases and corresponding primary tumors, suggesting that they are mCRPC-specific lncRNAs. Analyses of potential regulation by transcription factors (TFs) revealed that approximately half of the DE-lncRNAs have at least one binding site for the androgen receptor in their regulatory regions. In addition, TF enrichment analysis revealed the enrichment of binding sites for PCa-associated TFs, such as FOXA1 and HOXB13, in the regulatory regions of the DE-lncRNAs. In a cohort of prostatectomy-treated prostate tumors, four of the DE-lncRNAs showed association with progression-free time and two of them (lnc-SCFD2-2 and lnc-R3HCC1L-8) were independent prognostic markers. Our study highlights several mCRPC-specific lncRNAs that might be important in the progression of the disease to the metastatic stage and may also serve as potential biomarkers for aggressive PCa.

The effect of neural network architecture on virtual H&E staining: Systematic assessment of histological feasibility.

Conventional histopathology has relied on chemical staining for over a century. The staining process makes tissue sections visible to the human eye through a tedious and labor-intensive procedure that alters the tissue irreversibly, preventing repeated use of the sample. Deep learning-based virtual staining can potentially alleviate these shortcomings. Here, we used standard brightfield microscopy on unstained tissue sections and studied the impact of increased network capacity on the resulting virtually stained H&E images. Using the generative adversarial neural network model pix2pix as a baseline, we observed that replacing simple convolutions with dense convolution units increased the structural similarity score, peak signal-to-noise ratio, and nuclei reproduction accuracy. We also demonstrated highly accurate reproduction of histology, especially with increased network capacity, and demonstrated applicability to several tissues. We show that network architecture optimization can improve the image translation accuracy of virtual H&E staining, highlighting the potential of virtual staining in streamlining histopathological analysis.

Unstained Tissue Imaging and Virtual Hematoxylin and Eosin Staining of Histologic Whole Slide Images.

Tissue structures, phenotypes, and pathology are routinely investigated based on histology. This includes chemically staining the transparent tissue sections to make them visible to the human eye. Although chemical staining is fast and routine, it permanently alters the tissue and often consumes hazardous reagents. On the other hand, on using adjacent tissue sections for combined measurements, the cell-wise resolution is lost owing to sections representing different parts of the tissue. Hence, techniques providing visual information of the basic tissue structure enabling additional measurements from the exact same tissue section are required. Here we tested unstained tissue imaging for the development of computational hematoxylin and eosin (HE) staining. We used unsupervised deep learning (CycleGAN) and whole slide images of prostate tissue sections to compare the performance of imaging tissue in paraffin, as deparaffinized in air, and as deparaffinized in mounting medium with section thicknesses varying between 3 and 20 µm. We showed that although thicker sections increase the information content of tissue structures in the images, thinner sections generally perform better in providing information that can be reproduced in virtual staining. According to our results, tissue imaged in paraffin and as deparaffinized provides a good overall representation of the tissue for virtually HE-stained images. Further, using a pix2pix model, we showed that the reproduction of overall tissue histology can be clearly improved with image-to-image translation using supervised learning and pixel-wise ground truth. We also showed that virtual HE staining can be used for various tissues and used with both 20× and 40× imaging magnifications. Although the performance and methods of virtual staining need further development, our study provides evidence of the feasibility of whole slide unstained microscopy as a fast, cheap, and feasible approach to producing virtual staining of tissue histology while sparing the exact same tissue section ready for subsequent utilization with follow-up methods at single-cell resolution.

Nuclear Organization in Response to Stress: A Special Focus on Nucleoli.

In this chapter, we discuss the nuclear organization and how it responds to different types of stress. A key component in these responses is molecular traffic between the different sub-nucleolar compartments, such as nucleoplasm, chromatin, nucleoli, and various speckle and body compartments. This allows specific repair and response activities in locations where they normally are not active and serve to halt sensitive functions until the stress insult passes and inflicted damage has been repaired. We focus on mammalian cells and their nuclear organization, especially describing the central role of the nucleolus in nuclear stress responses. We describe events after multiple stress types, including DNA damage, various drugs, and toxic compounds, and discuss the involvement of macromolecular traffic between dynamic, phase-separated nuclear organelles and foci. We delineate the key proteins and non-coding RNA in the formation of stress-responsive, non-membranous nuclear organelles, many of which are relevant to the formation of and utilization in cancer treatment.

Nuclear size rectification: A potential new therapeutic approach to reduce metastasis in cancer.

Research on metastasis has recently regained considerable interest with the hope that single cell technologies might reveal the most critical changes that support tumor spread. However, it is possible that part of the answer has been visible through the microscope for close to 200 years. Changes in nuclear size characteristically occur in many cancer types when the cells metastasize. This was initially discarded as contributing to the metastatic spread because, depending on tumor types, both increases and decreases in nuclear size could correlate with increased metastasis. However, recent work on nuclear mechanics and the connectivity between chromatin, the nucleoskeleton, and the cytoskeleton indicate that changes in this connectivity can have profound impacts on cell mobility and invasiveness. Critically, a recent study found that reversing tumor type-dependent nuclear size changes correlated with reduced cell migration and invasion. Accordingly, it seems appropriate to now revisit possible contributory roles of nuclear size changes to metastasis.

Nonmalignant AR-positive prostate epithelial cells and cancer cells respond differently to androgen.

Prostate cancer research suffers from the lack of suitable models to study the role of normal cells in prostate carcinogenesis. To address this challenge, we developed a cell line model mimicking luminal prostate epithelial cells by modifying the immortalized prostate epithelial cell line RWPE-1 to constitutively express the androgen receptor (AR). RWPE-1-AR cells express known AR target genes, and exhibit coexpression of luminal and basal markers characteristic of transient amplifying cells, and an RNA signature resembling prostate luminal progenitor cells. Under unstimulated conditions, constitutive AR expression does not have a biologically significant effect on the proliferation of RWPE-1 cells, but when stimulated by androgens, growth is retarded. The transcriptional response of RWPE-1-AR cells to androgen stimulation involves suppression of the growth-related KRAS pathway and is thus markedly different from that of the prostate cancer cell line LNCaP and its derivative AR-overexpressing LNCaP-ARhi cells, in which growth- and cancer-related pathways are upregulated. Hence, the nonmalignant AR-positive RWPE-1-AR cell line model could be used to study the transformation of the prostate epithelium.

miR-32 promotes MYC-driven prostate cancer.

miR-32 is an androgen receptor (AR)-regulated microRNA, expression of which is increased in castration-resistant prostate cancer (PC). We have previously shown that overexpression of miR-32 in the prostate of transgenic mice potentiates proliferation in prostate epithelium. Here, we set out to determine whether increased expression of miR-32 influences growth or phenotype in prostate adenocarcinoma in vivo. We studied transgenic mice expressing MYC oncogene (hiMYC mice) to induce tumorigenesis in the mouse prostate and discovered that transgenic overexpression of miR-32 resulted in increased tumor burden as well as a more aggressive tumor phenotype in this model. Elevated expression of miR-32 increased proliferation as assessed by Ki-67 immunohistochemistry, increased nuclear density, and higher mitotic index in the tumors. By gene expression analysis of the tumorous prostate tissue, we confirmed earlier findings that miR-32 expression regulates prostate secretome by modulating expression levels of several PC-related target genes such as Spink1, Spink5, and Msmb. Further, we identified Pdk4 as a tumor-associated miR-32 target in the mouse prostate. Expression analysis of PDK4 in human PC reveals an inverse correlation with miR-32 expression and Gleason score, a decrease in castration-resistant and metastatic tumors compared to untreated primary PC, and an association of low PDK4 expression with a shorter recurrence-free survival of patients. Although decreased PDK4 expression induces the higher metabolic activity of PC cells, induced expression of PDK4 reduces both mitotic respiration and glycolysis rates as well as inhibits cell growth. In conclusion, we show that miR-32 promotes MYC-induced prostate adenocarcinoma and identifies PDK4 as a PC-relevant metabolic target of miR-32-3p.

Spatial analysis of histology in 3D: quantification and visualization of organ and tumor level tissue environment.

Histological changes in tissue are of primary importance in pathological research and diagnosis. Automated histological analysis requires ability to computationally separate pathological alterations from normal tissue. Conventional histopathological assessments are performed from individual tissue sections, leading to the loss of three-dimensional context of the tissue. Yet, the tissue context and spatial determinants are critical in several pathologies, such as in understanding growth patterns of cancer in its local environment. Here, we develop computational methods for visualization and quantitative assessment of histopathological alterations in three dimensions. First, we reconstruct the 3D representation of the whole organ from serial sectioned tissue. Then, we proceed to analyze the histological characteristics and regions of interest in 3D. As our example cases, we use whole slide images representing hematoxylin-eosin stained whole mouse prostates in a Pten+/- mouse prostate tumor model. We show that quantitative assessment of tumor sizes, shapes, and separation between spatial locations within the organ enable characterizing and grouping tumors. Further, we show that 3D visualization of tissue with computationally quantified features provides an intuitive way to observe tissue pathology. Our results underline the heterogeneity in composition and cellular organization within individual tumors. As an example, we show how prostate tumors have nuclear density gradients indicating areas of tumor growth directions and reflecting varying pressure from the surrounding tissue. The methods presented here are applicable to any tissue and different types of pathologies. This work provides a proof-of-principle for gaining a comprehensive view from histology by studying it quantitatively in 3D.

Chemical Interrogation of Nuclear Size Identifies Compounds with Cancer Cell Line-Specific Effects on Migration and Invasion.

Background: Lower survival rates for many cancer types correlate with changes in nuclear size/scaling in a tumor-type/tissue-specific manner. Hypothesizing that such changes might confer an advantage to tumor cells, we aimed at the identification of commercially available compounds to guide further mechanistic studies. We therefore screened for Food and Drug Administration (FDA)/European Medicines Agency (EMA)-approved compounds that reverse the direction of characteristic tumor nuclear size changes in PC3, HCT116, and H1299 cell lines reflecting, respectively, prostate adenocarcinoma, colonic adenocarcinoma, and small-cell squamous lung cancer. Results: We found distinct, largely nonoverlapping sets of compounds that rectify nuclear size changes for each tumor cell line. Several classes of compounds including, e.g., serotonin uptake inhibitors, cyclo-oxygenase inhibitors, ß-adrenergic receptor agonists, and Na+/K+ ATPase inhibitors, displayed coherent nuclear size phenotypes focused on a particular cell line or across cell lines and treatment conditions. Several compounds from classes far afield from current chemotherapy regimens were also identified. Seven nuclear size-rectifying compounds selected for further investigation all inhibited cell migration and/or invasion. Conclusions: Our study provides (a) proof of concept that nuclear size might be a valuable target to reduce cell migration/invasion in cancer treatment and (b) the most thorough collection of tool compounds to date reversing nuclear size changes specific to individual cancer-type cell lines. Although these compounds still need to be tested in primary cancer cells, the cell line-specific nuclear size and migration/invasion responses to particular drug classes suggest that cancer type-specific nuclear size rectifiers may help reduce metastatic spread.

Proteomic Landscape of Prostate Cancer: The View Provided by Quantitative Proteomics, Integrative Analyses, and Protein Interactomes.

Prostate cancer is the second most frequent cancer of men worldwide. While the genetic landscapes and heterogeneity of prostate cancer are relatively well-known already, methodological developments now allow for studying basic and dynamic proteomes on a large scale and in a quantitative fashion. This aids in revealing the functional output of cancer genomes. It has become evident that not all aberrations at the genetic and transcriptional level are translated to the proteome. In addition, the proteomic level contains heterogeneity, which increases as the cancer progresses from primary prostate cancer (PCa) to metastatic and castration-resistant prostate cancer (CRPC). While multiple aspects of prostate adenocarcinoma proteomes have been studied, less is known about proteomes of neuroendocrine prostate cancer (NEPC). In this review, we summarize recent developments in prostate cancer proteomics, concentrating on the proteomic landscapes of clinical prostate cancer, cell line and mouse model proteomes interrogating prostate cancer-relevant signaling and alterations, and key prostate cancer regulator interactomes, such as those of the androgen receptor (AR). Compared to genomic and transcriptomic analyses, the view provided by proteomics brings forward changes in prostate cancer metabolism, post-transcriptional RNA regulation, and post-translational protein regulatory pathways, requiring the full attention of studies in the future.

Virtual reality for 3D histology: multi-scale visualization of organs with interactive feature exploration.

BACKGROUND: Virtual reality (VR) enables data visualization in an immersive and engaging manner, and it can be used for creating ways to explore scientific data. Here, we use VR for visualization of 3D histology data, creating a novel interface for digital pathology to aid cancer research. METHODS: Our contribution includes 3D modeling of a whole organ and embedded objects of interest, fusing the models with associated quantitative features and full resolution serial section patches, and implementing the virtual reality application. Our VR application is multi-scale in nature, covering two object levels representing different ranges of detail, namely organ level and sub-organ level. In addition, the application includes several data layers, including the measured histology image layer and multiple representations of quantitative features computed from the histology. RESULTS: In our interactive VR application, the user can set visualization properties, select different samples and features, and interact with various objects, which is not possible in the traditional 2D-image view used in digital pathology. In this work, we used whole mouse prostates (organ level) with prostate cancer tumors (sub-organ objects of interest) as example cases, and included quantitative histological features relevant for tumor biology in the VR model. CONCLUSIONS: Our application enables a novel way for exploration of high-resolution, multidimensional data for biomedical research purposes, and can also be used in teaching and researcher training. Due to automated processing of the histology data, our application can be easily adopted to visualize other organs and pathologies from various origins.

A systematic comparison of data- and knowledge-driven approaches to disease subtype discovery.

Typical clustering analysis for large-scale genomics data combines two unsupervised learning techniques: dimensionality reduction and clustering (DR-CL) methods. It has been demonstrated that transforming gene expression to pathway-level information can improve the robustness and interpretability of disease grouping results. This approach, referred to as biological knowledge-driven clustering (BK-CL) approach, is often neglected, due to a lack of tools enabling systematic comparisons with more established DR-based methods. Moreover, classic clustering metrics based on group separability tend to favor the DR-CL paradigm, which may increase the risk of identifying less actionable disease subtypes that have ambiguous biological and clinical explanations. Hence, there is a need for developing metrics that assess biological and clinical relevance. To facilitate the systematic analysis of BK-CL methods, we propose a computational protocol for quantitative analysis of clustering results derived from both DR-CL and BK-CL methods. Moreover, we propose a new BK-CL method that combines prior knowledge of disease relevant genes, network diffusion algorithms and gene set enrichment analysis to generate robust pathway-level information. Benchmarking studies were conducted to compare the grouping results from different DR-CL and BK-CL approaches with respect to standard clustering evaluation metrics, concordance with known subtypes, association with clinical outcomes and disease modules in co-expression networks of genes. No single approach dominated every metric, showing the importance multi-objective evaluation in clustering analysis. However, we demonstrated that, on gene expression data sets derived from TCGA samples, the BK-CL approach can find groupings that provide significant prognostic value in both breast and prostate cancers.