To comprehensively understand tissue and organism physiology and pathophysiology, it is essential to create complete three-dimensional (3D) cellular maps. These maps require structural data, such as the 3D configuration and positioning of tissues and cells, and molecular data on the constitution of each cell, spanning from the DNA sequence to protein expression. While single-cell transcriptomics is illuminating the cellular and molecular diversity across species and tissues, the 3D spatial context of these molecular data is often overlooked. Here, I discuss emerging 3D tissue histology techniques that add the missing third spatial dimension to biomedical research. Through innovations in tissue-clearing chemistry, labeling and volumetric imaging that enhance 3D reconstructions and their synergy with molecular techniques, these technologies will provide detailed blueprints of entire organs or organisms at the cellular level. Machine learning, especially deep learning, will be essential for extracting meaningful insights from the vast data. Further development of integrated structural, molecular and computational methods will unlock the full potential of next-generation 3D histology.

The preparation and processing of rodent brains for evaluation by immunohistochemistry is time-consuming. A large number of mouse brains are routinely used in experiments in neuroscience laboratories to evaluate several models of human diseases. Thus, methods are needed to reduce the time associated with processing brains for histology. A scalable method was developed to embed, section, and stain multiple mouse brains using supplies found in any common histology laboratory. Section collection schemes can be scaled to provide identical bregma locations between adjacent sections for immunohistochemistry, facilitating comprehensive, high-quality immunohistochemistry. As a result, sectioning and staining times are considerably reduced as sections from multiple blocks are stained simultaneously. This method improves on previous procedures and allows multiple embedding and subsequent immunostaining of brains easily with a dramatically reduced time requirement. Furthermore, we expand this method for use in numerous mouse tissues, rat brain tissue, and post-mortem human brain and arterial tissues. In summary, this procedure allows the processing of many rodent or human tissues from perfusion through microscopy in 10 days or less.

Scanning electron microscopy (SEM) is used to observe the surface structure of an object by irradiating an electron beam onto the sample and detecting the reflected and emitted electrons. Because of its large depth of focus, SEM can provide the three-dimensional structure of small surfaces that cannot be observed using an optical microscope. Furthermore, the cross-sectional structure of the tissue can be observed by freeze-cracking. Observing the ultrastructure of organisms that contain large amounts of water in their bodies while maintaining high resolution is challenging; however, this has recently become possible. Here, we explain the fixation and freeze-cracking method for mouse brain samples.

Objective. Effective fusion of histology slides and molecular profiles from genomic data has shown great potential in the diagnosis and prognosis of gliomas. However, it remains challenging to explicitly utilize the consistent-complementary information among different modalities and create comprehensive representations of patients. Additionally, existing researches mainly focus on complete multi-modality data and usually fail to construct robust models for incomplete samples.Approach. In this paper, we propose adual-space disentangled-multimodal network (DDM-net)for glioma diagnosis and prognosis. DDM-net disentangles the latent features generated by two separate variational autoencoders (VAEs) into common and specific components through a dual-space disentangled approach, facilitating the construction of comprehensive representations of patients. More importantly, DDM-net imputes the unavailable modality in the latent feature space, making it robust to incomplete samples.Main results. We evaluated our approach on the TCGA-GBMLGG dataset for glioma grading and survival analysis tasks. Experimental results demonstrate that the proposed method achieves superior performance compared to state-of-the-art methods, with a competitive AUC of 0.952 and a C-index of 0.768.Significance. The proposed model may help the clinical understanding of gliomas and can serve as an effective fusion model with multimodal data. Additionally, it is capable of handling incomplete samples, making it less constrained by clinical limitations.

Variations in color and texture of histopathology images are caused by differences in staining conditions and imaging devices between hospitals. These biases decrease the robustness of machine learning models exposed to out-of-domain data. To address this issue, we introduce a comprehensive histopathology image dataset named PathoLogy Images of Scanners and Mobile phones (PLISM). The dataset consisted of 46 human tissue types stained using 13 hematoxylin and eosin conditions and captured using 13 imaging devices. Precisely aligned image patches from different domains allowed for an accurate evaluation of color and texture properties in each domain. Variation in PLISM was assessed and found to be significantly diverse across various domains, particularly between whole-slide images and smartphones. Furthermore, we assessed the improvement in domain shift using a convolutional neural network pre-trained on PLISM. PLISM is a valuable resource that facilitates the precise evaluation of domain shifts in digital pathology and makes significant contributions towards the development of robust machine learning models that can effectively address challenges of domain shift in histological image analysis.

Histological images are frequently impaired by local artifacts from scanner malfunctions or iatrogenic processes - caused by preparation - impacting the performance of Deep Learning models. Models often struggle with the slightest out-of-distribution shifts, resulting in compromised performance. Detecting artifacts and failure modes of the models is crucial to ensure open-world applicability to whole slide images for tasks like segmentation or diagnosis. We introduce a novel technique for out-of-distribution detection within whole slide images, compatible with any segmentation or classification model. Our approach tiles multi-layer features into sliding window patches and leverages optimal transport to align them with recognized in-distribution samples. We average the optimal transport costs over tiles and layers to detect out-of-distribution samples. Notably, our method excels in identifying failure modes that would harm downstream performance, surpassing contemporary out-of-distribution detection techniques. We evaluate our method for both natural and synthetic artifacts, considering distribution shifts of various sizes and types. The results confirm that our technique outperforms alternative methods for artifact detection. We assess our method components and the ability to negate the impact of artifacts on the downstream tasks. Finally, we demonstrate that our method can mitigate the risk of performance drops in downstream tasks, enhancing reliability by up to 77%. In testing 7 annotated whole slide images with natural artifacts, our method boosted the Dice score by 68%, highlighting its real open-world utility.

Clinically, histopathology images always offer a golden standard for disease diagnosis. With the development of artificial intelligence, digital histopathology significantly improves the efficiency of diagnosis. Nevertheless, noisy labels are inevitable in histopathology images, which lead to poor algorithm efficiency. Curriculum learning is one of the typical methods to solve such problems. However, existing curriculum learning methods either fail to measure the training priority between difficult samples and noisy ones or need an extra clean dataset to establish a valid curriculum scheme. Therefore, a new curriculum learning paradigm is designed based on a proposed ranking function, which is named The Ranking Margins (TRM). The ranking function measures the \'distances\' between samples and decision boundaries, which helps distinguish difficult samples and noisy ones. The proposed method includes three stages: the warm-up stage, the main training stage and the fine-tuning stage. In the warm-up stage, the margin of each sample is obtained through the ranking function. In the main training stage, samples are progressively fed into the networks for training, starting from those with larger margins to those with smaller ones. Label correction is also performed in this stage. In the fine-tuning stage, the networks are retrained on the samples with corrected labels. In addition, we provide theoretical analysis to guarantee the feasibility of TRM. The experiments on two representative histopathologies image datasets show that the proposed method achieves substantial improvements over the latest Label Noise Learning (LNL) methods.

UNASSIGNED: The interference-holographic method of phase scanning of fields of scattered laser radiation is proposed. The effectiveness of this method for the selection of variously dispersed components is demonstrated. This method made it possible to obtain polarization maps of biological tissues at a high level of depolarized background. The scale-selective analysis of such maps was used to determine necrotic changes in the optically anisotropic architectonics of biological tissues.
UNASSIGNED: Development and experimental approbation of layered phase polarimetry of repeatedly scattered fields in diffuse layers of biological tissues. Application of scale-selective processing of the found coordinate distributions of polarization states in various phase sections of object fields. Determination of criteria (markers) for histological differential diagnosis of the causes of necrotic changes in optical anisotropy of biological tissues.
UNASSIGNED: We used a synthesis of three instrumental and analytical methods. Polarization-interference registration of laser radiation scattered by a sample of biological tissue. Digital holographic reconstruction and layered phase scanning of distributions of complex amplitudes of the object field. Analytical determination of polarization maps of various phase cross-sections of repeatedly scattered radiation. Application of wavelet analysis of the distributions of polarization states in the phase plane of a single scattered component of an object field. Determination of criteria (markers) for differential diagnosis of necrotic changes in biological tissues with different morphological structure. Two cases are considered. The first case is the myocardium of those who died as a result of coronary heart disease and acute coronary insufficiency. The second case is lung tissue samples of deceased with bronchial asthma and fibrosis.
UNASSIGNED: A method of polarization-interference mapping of diffuse object fields of biological tissues has been developed and experimentally implemented. With the help of digital holographic reconstruction of the distributions of complex amplitudes, polarization maps in various phase sections of a diffuse object field are found. The wavelet analysis of azimuth and ellipticity distributions of polarization in the phase plane of a single scattered component of laser radiation is used. Scenarios for changing the amplitude of the wavelet coefficients for different scales of the scanning salt-like MHAT function are determined. Statistical moments of the first to fourth orders are determined for the distributions of the amplitudes of the wavelet coefficients of the azimuth maps and the ellipticity of polarization. As a result, diagnostic markers of necrotic changes in the myocardium and lung tissue were determined. The statistical criteria found are the basis for determining the accuracy of their differential diagnosis of various necrotic states of biological tissues.
UNASSIGNED: Necrotic changes caused by \"coronary artery disease-acute coronary insufficiency\" and \"asthma-pulmonary fibrosis\" were demonstrated by the method of wavelet differentiation with polarization interference with excellent accuracy.

Detecting breast tissue alterations is essential for cancer diagnosis. However, inherent bidimensionality limits histological procedures\' effectiveness in identifying these changes. Our study applies a 3D virtual histology method based on X-ray phase-contrast microtomography (PhC μ CT), performed at a synchrotron facility, to investigate breast tissue samples including different types of lesions, namely intraductal papilloma, micropapillary intracystic carcinoma, and invasive lobular carcinoma. One-to-one comparisons of X-ray and histological images explore the clinical potential of 3D X-ray virtual histology. Results show that PhC μ CT technique provides high spatial resolution and soft tissue sensitivity, while being non-destructive, not requiring a dedicated sample processing and being compatible with conventional histology. PhC μ CT can enhance the visualization of morphological characteristics such as stromal tissue, fibrovascular core, terminal duct lobular unit, stromal/epithelium interface, basement membrane, and adipocytes. Despite not reaching the (sub) cellular level, the three-dimensionality of PhC μ CT images allows to depict in-depth alterations of the breast tissues, potentially revealing pathologically relevant details missed by a single histological section. Compared to serial sectioning, PhC μ CT allows the virtual investigation of the sample volume along any orientation, possibly guiding the pathologist in the choice of the most suitable cutting plane. Overall, PhC μ CT virtual histology holds great promise as a tool adding to conventional histology for improving efficiency, accessibility, and diagnostic accuracy of pathological evaluation.

Counting of mitotic figures is a fundamental step in grading and prognostication of several cancers. However, manual mitosis counting is tedious and time-consuming. In addition, variation in the appearance of mitotic figures causes a high degree of discordance among pathologists. With advances in deep learning models, several automatic mitosis detection algorithms have been proposed but they are sensitive to domain shift often seen in histology images. We propose a robust and efficient two-stage mitosis detection framework, which comprises mitosis candidate segmentation (Detecting Fast) and candidate refinement (Detecting Slow) stages. The proposed candidate segmentation model, termed EUNet, is fast and accurate due to its architectural design. EUNet can precisely segment candidates at a lower resolution to considerably speed up candidate detection. Candidates are then refined using a deeper classifier network, EfficientNet-B7, in the second stage. We make sure both stages are robust against domain shift by incorporating domain generalization methods. We demonstrate state-of-the-art performance and generalizability of the proposed model on the three largest publicly available mitosis datasets, winning the two mitosis domain generalization challenge contests (MIDOG21 and MIDOG22). Finally, we showcase the utility of the proposed algorithm by processing the TCGA breast cancer cohort (1,124 whole-slide images) to generate and release a repository of more than 620K potential mitotic figures (not exhaustively validated).