The development of accessible screening tools for early cancer detection in dogs represents a significant challenge in veterinary medicine. Routine laboratory data offer a promising, low-cost source for such tools, but their utility is hampered by the non-specificity of individual biomarkers and the severe class imbalance inherent in screening populations. This study assesses the feasibility of cancer risk classification using the Golden Retriever Lifetime Study (GRLS) cohort under real-world constraints, including the grouping of diverse cancer types and the inclusion of post-diagnosis samples. A comprehensive benchmark evaluation was conducted, systematically comparing 126 analytical pipelines that comprised various machine learning models, feature selection methods, and data balancing techniques. Data were partitioned at the patient level to prevent leakage. The optimal model, a Logistic Regression classifier with class weighting and recursive feature elimination, demonstrated moderate ranking ability (AUROC = 0.815; 95% CI: 0.793-0.836) but poor clinical classification performance (F1-score = 0.25, Positive Predictive Value = 0.15). While a high Negative Predictive Value (0.98) was achieved, insufficient recall (0.79) precludes its use as a reliable rule-out test. Interpretability analysis with SHapley Additive exPlanations (SHAP) revealed that predictions were driven by non-specific features like age and markers of inflammation and anemia. It is concluded that while a statistically detectable cancer signal exists in routine lab data, it is too weak and confounded for clinically reliable discrimination from normal aging or other inflammatory conditions. This work establishes a critical performance ceiling for this data modality in isolation and underscores that meaningful progress in computational veterinary oncology will require integration of multi-modal data sources.

We then annotated ten thousand WBC images with these attributes, resulting in 113k labels (11 attributes x 10.3k images). Annotating at this level of detail and scale is unprecedented, offering unique value to AI in pathology. Moreover, we conduct experiments to predict these attributes from cell images, and also demonstrate specific applications that can benefit from our detailed annotations.

Label-free imaging has gained broad interest because of its potential to omit elaborate staining procedures which is especially relevant for in vivo use. Label-free multiphoton microscopy (MPM), for instance, exploits two-photon excitation of natural autofluorescence (AF) from native, metabolic proteins, making it ideal for in vivo endomicroscopy. Deep learning (DL) models have been widely used in other optical imaging technologies to predict specific target annotations and thereby digitally augment the specificity of these label-free images. However, this computational specificity has only rarely been implemented for MPM. In this work, we used a data set of label-free MPM images from a series of different immune cell types (5,075 individual cells for binary classification in mixed samples and 3,424 cells for a multi-class classification task) and trained a convolutional neural network (CNN) to classify cell types based on this label-free AF as input. A low-complexity squeezeNet architecture was able to achieve reliable immune cell classification results (0.89 ROC-AUC, 0.95 PR-AUC, for binary classification in mixed samples; 0.689 F1 score, 0.697 precision, 0.748 recall, and 0.683 MCC for six-class classification in isolated samples). Perturbation tests confirmed that the model is not confused by extracellular environment and that both input AF channels (NADH and FAD) are about equally important to the classification. In the future, such predictive DL models could directly detect specific immune cells in unstained images and thus, computationally improve the specificity of label-free MPM which would have great potential for in vivo endomicroscopy.

Precise segmentation and classification of cell instances are vital for analyzing the tissue microenvironment in histology images, supporting medical diagnosis, prognosis, treatment planning, and studies of brain cytoarchitecture. However, the creation of high-quality annotated datasets for training remains a major challenge. This study introduces a novel single-stage approach (HistoSmith) for generating image-label pairs to augment histology datasets. Unlike state-of-the-art methods that utilize diffusion models with separate components for label and image generation, our approach employs a latent diffusion model to learn the joint distribution of cellular layouts, classification masks, and histology images. This model enables tailored data generation by conditioning on user-defined parameters such as cell types, quantities, and tissue types. Trained on the Conic H&E histopathology dataset and the Nissl-stained CytoDArk0 dataset, the model generates realistic and diverse labeled samples. Experimental results demonstrate improvements in cell instance segmentation and classification, particularly for underrepresented cell types like neutrophils in the Conic dataset. These findings underscore the potential of our approach to address data scarcity challenges.

Human immune system contains white blood cells (WBC) that are good indicator of many diseases like bacterial infections, AIDS, cancer, spleen, etc. White blood cells have been sub classified into four types: monocytes, lymphocytes, eosinophils and neutrophils on the basis of their nucleus, shape and cytoplasm. Traditionally in laboratories, pathologists and hematologists analyze these blood cells through microscope and then classify them manually. This manual process takes more time and increases the chance of human error. Hence, there is a need to automate this process. In this paper, first we have used different CNN pre-train models such as ResNet-50, InceptionV3, VGG16 and MobileNetV2 to automatically classify the white blood cells. These pre-train models are applied on Kaggle dataset of microscopic images. Although we achieved reasonable accuracy ranging between 92 to 95%, still there is need to enhance the performance. Hence, inspired by these architectures, a framework has been proposed to automatically categorize the four kinds of white blood cells with increased accuracy. The aim is to develop a convolution neural network (CNN) based classification system with decent generalization ability. The proposed CNN model has been tested on white blood cells images from Kaggle and LISC datasets. Accuracy achieved is 99.57% and 98.67% for both datasets respectively. Our proposed convolutional neural network-based model provides competitive performance as compared to previous results reported in literature.

Human blood primarily comprises plasma, red blood cells, white blood cells, and platelets. It plays a vital role in transporting nutrients to different organs, where it stores essential health-related data about the human body. Blood cells are utilized to defend the body against diverse infections, including fungi, viruses, and bacteria. Hence, blood analysis can help physicians assess an individual's physiological condition. Blood cells have been sub-classified into eight groups: Neutrophils, eosinophils, basophils, lymphocytes, monocytes, immature granulocytes (promyelocytes, myelocytes, and metamyelocytes), erythroblasts, and platelets or thrombocytes on the basis of their nucleus, shape, and cytoplasm. Traditionally, pathologists and hematologists in laboratories have examined these blood cells using a microscope before manually classifying them. The manual approach is slower and more prone to human error. Therefore, it is essential to automate this process. In our paper, transfer learning with CNN pre-trained models. VGG16, VGG19, ResNet-50, ResNet-101, ResNet-152, InceptionV3, MobileNetV2, and DenseNet-20 applied to the PBC dataset's normal DIB. The overall accuracy achieved with these models lies between 91.375 and 94.72%. Hence, inspired by these pre-trained architectures, a model has been proposed to automatically classify the ten types of blood cells with increased accuracy. A novel CNN-based framework has been presented to improve accuracy. The proposed CNN model has been tested on the PBC dataset normal DIB. The outcomes of the experiments demonstrate that our CNN-based framework designed for blood cell classification attains an accuracy of 99.91% on the PBC dataset. Our proposed convolutional neural network model performs competitively when compared to earlier results reported in the literature.

Generative models capable of capturing nuanced clinical features in medical images hold great promise for facilitating clinical data sharing, enhancing rare disease datasets, and efficiently synthesizing annotated medical images at scale. Despite their potential, assessing the quality of synthetic medical images remains a challenge. While modern generative models can synthesize visually-realistic medical images, the clinical validity of these images may be called into question. Domain-agnostic scores, such as FID score, precision, and recall, cannot incorporate clinical knowledge and are, therefore, not suitable for assessing clinical sensibility. Additionally, there are numerous unpredictable ways in which generative models may fail to synthesize clinically plausible images, making it challenging to anticipate potential failures and manually design scores for their detection. To address these challenges, this paper introduces a pathologist-in-the-loop framework for generating clinically-plausible synthetic medical images. Starting with a diffusion model pretrained using real images, our framework comprises three steps: (1) evaluating the generated images by expert pathologists to assess whether they satisfy clinical desiderata, (2) training a reward model that predicts the pathologist feedback on new samples, and (3) incorporating expert knowledge into the diffusion model by using the reward model to inform a finetuning objective. We show that human feedback significantly improves the quality of synthetic images in terms of fidelity, diversity, utility in downstream applications, and plausibility as evaluated by experts.

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge's improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.

Neutrophils play a major role in the early immune response and are recruited in large numbers into inflamed and infected tissues. By secreting chemoattractants that bind G protein–coupled receptors (GPCRs) on neighboring cells, neutrophils coordinate their behavior as a swarm. Less clear is how this auto-amplifying swarming activity is ultimately turned off. Kienle et al. show that desensitization of these GPCRs by the same chemoattractants by GPCR-kinase 2 (GRK2) is one way in which these swarms are shut down (see the Perspective by Rocha-Gregg and Huttenlocher). Unexpectedly, mice with GRK2-deficient neutrophils showed impaired rather than enhanced bacterial clearance. The heightened scanning ability of GRK2-deficient neutrophils may come at the cost of suboptimal phagocytosis and containment of bacteria. Science , abe7729, this issue p. [eabe7729][1]; see also abj3065, p. [1262][2] ### INTRODUCTION The collective behavior of cells and insects often relies on self-organizing processes. By releasing attractant signals, a few individuals can initiate the accumulation and aggregation of a whole population. Neutrophils, key players in the innate immune response, infiltrate inflamed and infected tissues in large numbers. These cells make use of such positive feedback amplification to find and kill bacteria in tissues. By secreting attractants that act through cell surface–expressed G protein–coupled receptors (GPCRs) on neighboring cells, neutrophils use this form of intercellular communication and coordinate their hunt for pathogens as a swarm. How this swarming response is terminated to avoid uncontrolled neutrophil accumulations and prevent excessive inflammation is currently unknown. ### RATIONALE The stop signals for neutrophil swarming in mammalian tissues have not yet been defined. They may be derived from cells of the surrounding inflammatory environment or from neutrophils themselves. We reasoned that the attractants released by neutrophils may become highly concentrated at sites where these cells cluster in larger numbers. It is well established that high chemoattractant concentrations can attenuate cellular responses by a process termed GPCR desensitization. We hypothesized a self-limiting mechanism for swarming: The local accumulation of the same neutrophil-expressed attractants that amplify swarming during early stages would cause desensitization of their respective GPCRs at later stages of neutrophil clustering. This led us to investigate the role of GPCR desensitization in neutrophil tissue navigation and host defense. ### RESULTS We generated mouse strains whose neutrophils were deficient in GPCR kinases (GRKs), critical enzymes for mediating the GPCR desensitization process. Of the four GRK isoforms tested, in vitro experiments identified GRK2 as the kinase necessary to desensitize GPCRs activated by swarm-released attractants (LTB4 and CXCL2). When neutrophils sense high concentrations of swarm attractants in vitro, GRK2 desensitizes the corresponding receptors to induce migration arrest. Two-photon intravital imaging of injured skin and infected lymph nodes of mice showed that GRK2 and GPCR desensitization play critical roles during neutrophil swarming in physiological tissue. At sites where swarming neutrophils accumulate and self-generate local fields of high swarm attractant concentration, GPCR desensitization was crucial to stop neutrophil migration arrest. Desensitization-resistant neutrophils moved faster and explored larger areas of lymph node tissue infected with the bacterium Pseudomonas aeruginosa . Such behavior suggested more effective bacterial sampling throughout the infected organ. Surprisingly, mice with GRK2-deficient neutrophils showed impaired rather than improved bacterial clearance. This finding could not be explained by altered antibacterial effector functions. In vitro assays for the detailed analysis of swarming behavior and bacterial growth revealed that GPCR desensitization to swarm attractants is required to induce neutrophil arrest for optimal bacterial phagocytosis and containment in swarm clusters. ### CONCLUSION We describe a cell-intrinsic stop mechanism for the self-organization of neutrophil collectives in infected tissues, which is based on sensing the local accumulation of the same cell-secreted attractants that amplify swarming during early stages. GPCR desensitization acts as a negative feedback control mechanism to stop neutrophil migration in swarm aggregates. This navigation mechanism allows neutrophils to self-limit their dynamics within forming swarms and ensures optimal elimination of bacteria. Desensitization to a self-produced activation signal as a principle of self-organization is important for immune host defense against bacteria, and likely informs other categories of collective behavior in cells and insects. ![Figure][3] Self-organization of neutrophil swarms. Top: Swarming neutrophils self-amplify their highly chemotactic recruitment toward sites of tissue injury or bacterial invasion by releasing attractants that act on neighboring neutrophils. Neutrophils are displayed as spheres with migration tracks (right). Bottom: The local accumulation of the same cell-secreted attractants stops neutrophils when they accumulate and form clusters, a process important for the containment of bacteria in infected tissues. Neutrophils communicate with each other to form swarms in infected organs. Coordination of this population response is critical for the elimination of bacteria and fungi. Using transgenic mice, we found that neutrophils have evolved an intrinsic mechanism to self-limit swarming and avoid uncontrolled aggregation during inflammation. G protein–coupled receptor (GPCR) desensitization acts as a negative feedback control to stop migration of neutrophils when they sense high concentrations of self-secreted attractants that initially amplify swarming. Interference with this process allows neutrophils to scan larger tissue areas for microbes. Unexpectedly, this does not benefit bacterial clearance as containment of proliferating bacteria by neutrophil clusters becomes impeded. Our data reveal how autosignaling stops self-organized swarming behavior and how the finely tuned balance of neutrophil chemotaxis and arrest counteracts bacterial escape. [1]: /lookup/doi/10.1126/science.abe7729 [2]: /lookup/doi/10.1126/science.abj3065 [3]: pending:yes