This paper presents a comprehensive stability analysis of the black hole solution within Modified General Relativity (MGR), a theory proposing a unified geometric description of dark matter (DM) and dark energy (DE). A rigorous gauge-invariant formalism is employed to analyze gravitational perturbations of the extended Schwarzschild metric. The central finding is a critical pathology within the polar perturbation sector, where metric fluctuations couple to the theory's fundamental line element field. This coupling is governed by a factor that, while well-behaved at the horizon, diverges powerfully in the far-field limit as a direct consequence of the theory's non-asymptotically flat nature. This indicates a strong infrared instability that overwhelms perturbations at large distances. In stark contrast, the axial perturbation sector is found to be completely stable. This dichotomy proves that the instability is not inherent to the background metric but is specifically generated by the novel coupling mechanism encoding MGR's unified dark sectors. The results reveal a fundamental strong-coupling problem within the MGR framework, challenging its physical viability as an alternative to Einstein's General Relativity (EGR).
Ahmed Alagha, Christopher Leclerc, Yousef Kotp
et al.
Whole-slide image (WSI) preprocessing, comprising tissue detection followed by patch extraction, is foundational to AI-driven computational pathology but remains a major bottleneck for scaling to large and heterogeneous cohorts. We present AtlasPatch, a scalable framework that couples foundation-model tissue detection with high-throughput patch extraction at minimal computational overhead. Our tissue detector achieves high precision (0.986) and remains robust across varying tissue conditions (e.g., brightness, fragmentation, boundary definition, tissue heterogeneity) and common artifacts (e.g., pen/ink markings, scanner streaks). This robustness is enabled by our annotated, heterogeneous multi-cohort training set of ~30,000 WSI thumbnails combined with efficient adaptation of the Segment-Anything (SAM) model. AtlasPatch also reduces end-to-end WSI preprocessing time by up to 16$\times$ versus widely used deep-learning pipelines, without degrading downstream task performance. The AtlasPatch tool is open-source, efficiently parallelized for practical deployment, and supports options to save extracted patches or stream them into common feature-extraction models for on-the-fly embedding, making it adaptable to both pathology departments (tissue detection and quality control) and AI researchers (dataset creation and model training). AtlasPatch software package is available at https://github.com/AtlasAnalyticsLab/AtlasPatch.
The development of clinical-grade artificial intelligence in pathology is limited by the scarcity of diverse, high-quality annotated datasets. Generative models offer a potential solution but suffer from semantic instability and morphological hallucinations that compromise diagnostic reliability. To address this challenge, we introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS), the first generative foundation model for pathology-specific text-to-image synthesis. By leveraging a dual-stage training strategy on approximately 2.8 million image-caption pairs, CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy. This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations. Furthermore, CRAFTS-augmented datasets enhance the performance across various clinical tasks, including classification, cross-modal retrieval, self-supervised learning, and visual question answering. In addition, coupling CRAFTS with ControlNet enables precise control over tissue architecture from inputs such as nuclear segmentation masks and fluorescence images. By overcoming the critical barriers of data scarcity and privacy concerns, CRAFTS provides a limitless source of diverse, annotated histology data, effectively unlocking the creation of robust diagnostic tools for rare and complex cancer phenotypes.
The interpretation of chest X-rays (CXRs) poses significant challenges, particularly in achieving accurate multi-label pathology classification and spatial localization. These tasks demand different levels of annotation granularity but are frequently constrained by the scarcity of region-level (dense) annotations. We introduce CLARiTy (Class Localizing and Attention Refining Image Transformer), a vision transformer-based model for joint multi-label classification and weakly-supervised localization of thoracic pathologies. CLARiTy employs multiple class-specific tokens to generate discriminative attention maps, and a SegmentCAM module for foreground segmentation and background suppression using explicit anatomical priors. Trained on image-level labels from the NIH ChestX-ray14 dataset, it leverages distillation from a ConvNeXtV2 teacher for efficiency. Evaluated on the official NIH split, the CLARiTy-S-16-512 (a configuration of CLARiTy), achieves competitive classification performance across 14 pathologies, and state-of-the-art weakly-supervised localization performance on 8 pathologies, outperforming prior methods by 50.7%. In particular, pronounced gains occur for small pathologies like nodules and masses. The lower-resolution variant of CLARiTy, CLARiTy-S-16-224, offers high efficiency while decisively surpassing baselines, thereby having the potential for use in low-resource settings. An ablation study confirms contributions of SegmentCAM, DINO pretraining, orthogonal class token loss, and attention pooling. CLARiTy advances beyond CNN-ViT hybrids by harnessing ViT self-attention for global context and class-specific localization, refined through convolutional background suppression for precise, noise-reduced heatmaps.
Multiple Instance Learning (MIL) is increasingly being used as a support tool within clinical settings for pathological diagnosis decisions, achieving high performance and removing the annotation burden. However, existing approaches for clinical MIL tasks have not adequately addressed the priority issues that exist in relation to pathological symptoms and diagnostic classes, causing MIL models to ignore priority among classes. To overcome this clinical limitation of MIL, we propose a new method that addresses priority issues using two hierarchies: vertical inter-hierarchy and horizontal intra-hierarchy. The proposed method aligns MIL predictions across each hierarchical level and employs an implicit feature re-usability during training to facilitate clinically more serious classes within the same level. Experiments with real-world patient data show that the proposed method effectively reduces misdiagnosis and prioritizes more important symptoms in multiclass scenarios. Further analysis verifies the efficacy of the proposed components and qualitatively confirms the MIL predictions against challenging cases with multiple symptoms.
Pathology image classification plays a crucial role in accurate medical diagnosis and treatment planning. Training high-performance models for this task typically requires large-scale annotated datasets, which are both expensive and time-consuming to acquire. Active Learning (AL) offers a solution by iteratively selecting the most informative samples for annotation, thereby reducing the labeling effort. However, most AL methods are designed under the assumption of a closed-set scenario, where all the unannotated images belong to target classes. In real-world clinical environments, the unlabeled pool often contains a substantial amount of Out-Of-Distribution (OOD) data, leading to low efficiency of annotation in traditional AL methods. Furthermore, most existing AL methods start with random selection in the first query round, leading to a significant waste of labeling costs in open-set scenarios. To address these challenges, we propose OpenPath, a novel open-set active learning approach for pathological image classification leveraging a pre-trained Vision-Language Model (VLM). In the first query, we propose task-specific prompts that combine target and relevant non-target class prompts to effectively select In-Distribution (ID) and informative samples from the unlabeled pool. In subsequent queries, Diverse Informative ID Sampling (DIS) that includes Prototype-based ID candidate Selection (PIS) and Entropy-Guided Stochastic Sampling (EGSS) is proposed to ensure both purity and informativeness in a query, avoiding the selection of OOD samples. Experiments on two public pathology image datasets show that OpenPath significantly enhances the model's performance due to its high purity of selected samples, and outperforms several state-of-the-art open-set AL methods. The code is available at \href{https://github.com/HiLab-git/OpenPath}{https://github.com/HiLab-git/OpenPath}..
The detection of semantic and covariate out-of-distribution (OOD) examples is a critical yet overlooked challenge in digital pathology (DP). Recently, substantial insight and methods on OOD detection were presented by the ML community, but how do they fare in DP applications? To this end, we establish a benchmark study, our highlights being: 1) the adoption of proper evaluation protocols, 2) the comparison of diverse detectors in both a single and multi-model setting, and 3) the exploration into advanced ML settings like transfer learning (ImageNet vs. DP pre-training) and choice of architecture (CNNs vs. transformers). Through our comprehensive experiments, we contribute new insights and guidelines, paving the way for future research and discussion.
Falah Jabar, Lill-Tove Rasmussen Busund, Biagio Ricciuti
et al.
In recent years, the use of deep learning (DL) methods, including convolutional neural networks (CNNs) and vision transformers (ViTs), has significantly advanced computational pathology, enhancing both diagnostic accuracy and efficiency. Hematoxylin and Eosin (H&E) Whole Slide Images (WSI) plays a crucial role by providing detailed tissue samples for the analysis and training of DL models. However, WSIs often contain regions with artifacts such as tissue folds, blurring, as well as non-tissue regions (background), which can negatively impact DL model performance. These artifacts are diagnostically irrelevant and can lead to inaccurate results. This paper proposes a fully automatic supervised DL pipeline for WSI Quality Assessment (WSI-QA) that uses a fused model combining CNNs and ViTs to detect and exclude WSI regions with artifacts, ensuring that only qualified WSI regions are used to build DL-based computational pathology applications. The proposed pipeline employs a pixel-based segmentation model to classify WSI regions as either qualified or non-qualified based on the presence of artifacts. The proposed model was trained on a large and diverse dataset and validated with internal and external data from various human organs, scanners, and H&E staining procedures. Quantitative and qualitative evaluations demonstrate the superiority of the proposed model, which outperforms state-of-the-art methods in WSI artifact detection. The proposed model consistently achieved over 95% accuracy, precision, recall, and F1 score across all artifact types. Furthermore, the WSI-QA pipeline shows strong generalization across different tissue types and scanning conditions.
Yitong Li, Igor Yakushev, Dennis M. Hedderich
et al.
Positron emission tomography (PET) is a well-established functional imaging technique for diagnosing brain disorders. However, PET's high costs and radiation exposure limit its widespread use. In contrast, magnetic resonance imaging (MRI) does not have these limitations. Although it also captures neurodegenerative changes, MRI is a less sensitive diagnostic tool than PET. To close this gap, we aim to generate synthetic PET from MRI. Herewith, we introduce PASTA, a novel pathology-aware image translation framework based on conditional diffusion models. Compared to the state-of-the-art methods, PASTA excels in preserving both structural and pathological details in the target modality, which is achieved through its highly interactive dual-arm architecture and multi-modal condition integration. A cycle exchange consistency and volumetric generation strategy elevate PASTA's capability to produce high-quality 3D PET scans. Our qualitative and quantitative results confirm that the synthesized PET scans from PASTA not only reach the best quantitative scores but also preserve the pathology correctly. For Alzheimer's classification, the performance of synthesized scans improves over MRI by 4%, almost reaching the performance of actual PET. Code is available at https://github.com/ai-med/PASTA.
Neda Zamanitajeddin, Mostafa Jahanifar, Kesi Xu
et al.
Deep learning models have shown immense promise in computational pathology (CPath) tasks, but their performance often suffers when applied to unseen data due to domain shifts. Addressing this requires domain generalization (DG) algorithms. However, a systematic evaluation of DG algorithms in the CPath context is lacking. This study aims to benchmark the effectiveness of 30 DG algorithms on 3 CPath tasks of varying difficulty through 7,560 cross-validation runs. We evaluate these algorithms using a unified and robust platform, incorporating modality-specific techniques and recent advances like pretrained foundation models. Our extensive cross-validation experiments provide insights into the relative performance of various DG strategies. We observe that self-supervised learning and stain augmentation consistently outperform other methods, highlighting the potential of pretrained models and data augmentation. Furthermore, we introduce a new pan-cancer tumor detection dataset (HISTOPANTUM) as a benchmark for future research. This study offers valuable guidance to researchers in selecting appropriate DG approaches for CPath tasks.
Milda Pocevičiūtė, Gabriel Eilertsen, Stina Garvin
et al.
Multiple-instance learning (MIL) is an attractive approach for digital pathology applications as it reduces the costs related to data collection and labelling. However, it is not clear how sensitive MIL is to clinically realistic domain shifts, i.e., differences in data distribution that could negatively affect performance, and if already existing metrics for detecting domain shifts work well with these algorithms. We trained an attention-based MIL algorithm to classify whether a whole-slide image of a lymph node contains breast tumour metastases. The algorithm was evaluated on data from a hospital in a different country and various subsets of this data that correspond to different levels of domain shift. Our contributions include showing that MIL for digital pathology is affected by clinically realistic differences in data, evaluating which features from a MIL model are most suitable for detecting changes in performance, and proposing an unsupervised metric named Fréchet Domain Distance (FDD) for quantification of domain shifts. Shift measure performance was evaluated through the mean Pearson correlation to change in classification performance, where FDD achieved 0.70 on 10-fold cross-validation models. The baselines included Deep ensemble, Difference of Confidence, and Representation shift which resulted in 0.45, -0.29, and 0.56 mean Pearson correlation, respectively. FDD could be a valuable tool for care providers and vendors who need to verify if a MIL system is likely to perform reliably when implemented at a new site, without requiring any additional annotations from pathologists.
Marc Aubreville, Jonathan Ganz, Jonas Ammeling
et al.
The QUILT-1M dataset is the first openly available dataset containing images harvested from various online sources. While it provides a huge data variety, the image quality and composition is highly heterogeneous, impacting its utility for text-conditional image synthesis. We propose an automatic pipeline that provides predictions of the most common impurities within the images, e.g., visibility of narrators, desktop environment and pathology software, or text within the image. Additionally, we propose to use semantic alignment filtering of the image-text pairs. Our findings demonstrate that by rigorously filtering the dataset, there is a substantial enhancement of image fidelity in text-to-image tasks.
Melanoma, a malignant skin cancer arising from melanocytes, exhibits rapid metastasis and a high mortality rate, especially in advanced stages. Current treatment modalities, including surgery, radiation, and immunotherapy, offer limited success, with immunotherapy using immune checkpoint inhibitors (ICIs) being the most promising. However, the high mortality rate underscores the urgent need for robust, non-invasive biomarkers to predict patient response to adjuvant therapies. The immune microenvironment of melanoma comprises various immune cells, which influence tumor growth and immune response. Melanoma cells employ multiple mechanisms for immune escape, including defects in immune recognition and epithelial-mesenchymal transition (EMT), which collectively impact treatment efficacy. Single-cell analysis technologies, such as single-cell RNA sequencing (scRNA-seq), have revolutionized the understanding of tumor heterogeneity and immune microenvironment dynamics. These technologies facilitate the identification of rare cell populations, co-expression patterns, and regulatory networks, offering deep insights into tumor progression, immune response, and therapy resistance. In the realm of biomarker discovery for melanoma, single-cell analysis has demonstrated significant potential. It aids in uncovering cellular composition, gene profiles, and novel markers, thus advancing diagnosis, treatment, and prognosis. Additionally, tumor-associated antibodies and specific genetic and cellular markers identified through single-cell analysis hold promise as predictive biomarkers. Despite these advancements, challenges such as RNA-protein expression discrepancies and tumor heterogeneity persist, necessitating further research. Nonetheless, single-cell analysis remains a powerful tool in elucidating the mechanisms underlying therapy response and resistance, ultimately contributing to the development of personalized melanoma therapies and improved patient outcomes.
Cedric Walker, Tasneem Talawalla, Robert Toth
et al.
The discovery of patterns associated with diagnosis, prognosis, and therapy response in digital pathology images often requires intractable labeling of large quantities of histological objects. Here we release an open-source labeling tool, PatchSorter, which integrates deep learning with an intuitive web interface. Using >100,000 objects, we demonstrate a >7x improvement in labels per second over unaided labeling, with minimal impact on labeling accuracy, thus enabling high-throughput labeling of large datasets.
Marco Bertolini, Van-Khoa Le, Jake Pencharz
et al.
In pre-clinical pathology, there is a paradox between the abundance of raw data (whole slide images from many organs of many individual animals) and the lack of pixel-level slide annotations done by pathologists. Due to time constraints and requirements from regulatory authorities, diagnoses are instead stored as slide labels. Weakly supervised training is designed to take advantage of those data, and the trained models can be used by pathologists to rank slides by their probability of containing a given lesion of interest. In this work, we propose a novel contextualized eXplainable AI (XAI) framework and its application to deep learning models trained on Whole Slide Images (WSIs) in Digital Pathology. Specifically, we apply our methods to a multi-instance-learning (MIL) model, which is trained solely on slide-level labels, without the need for pixel-level annotations. We validate quantitatively our methods by quantifying the agreements of our explanations' heatmaps with pathologists' annotations, as well as with predictions from a segmentation model trained on such annotations. We demonstrate the stability of the explanations with respect to input shifts, and the fidelity with respect to increased model performance. We quantitatively evaluate the correlation between available pixel-wise annotations and explainability heatmaps. We show that the explanations on important tiles of the whole slide correlate with tissue changes between healthy regions and lesions, but do not exactly behave like a human annotator. This result is coherent with the model training strategy.
Nasibeh Hosseini-Vasoukolaei, Leila Ghavibazou, Amir Ahmad Akhavan
et al.
Background: Phlebotomine sand flies are vectors of Leishmania species, the causative agents of leishmaniasis in the world. Present study aimed to evaluate the bioecological aspects of sand flies in different ecotopes in Sari County, north of Iran.
Methods: Sand flies were collected from four villages in mountainous, forest, plain and peri-urban areas monthly using sticky traps in May–October 2016. Mounted specimens were identified using valid identification keys under optical microscope. The Arc GIS 10.5 software was applied for showing the distribution of sand flies. Shannon-Weiner, Simpson and Evenness species diversity indices were calculated.
Results: Generally, 334 specimens were captured and identified, namelly Phlebotomus kandelakii, Ph. papatasi, Ph. major, Ph. sergenti, Ph. longiductus, Ph. halepensis, Ph. tobbi, Sergentomyia dentata, Se. theodori, Se. sintoni, Se. antennata and Se. sumbarica. The most common species was Ph. kandelakii (n= 128, 38.32 %). The highest Simpson index (0.81) and abundance (N= 141) were recorded in the mountaineous area. Shannon diversity index was higher in the forest (H'= 1.53) and the highest evenness index was in the plain area (J'= 0.93). The highest richness (S= 9) and Shannon indices (H'= 1.57) were observed in June.
Conclusions: Phlebotomus kandelakii, Ph. sergenti, Ph. tobbi, Ph. longiductus, Se. theodori, Se. antennata and Se. sumbarica were recorded for the first time in the study area. Since some species are incriminated for leishmaniasis transmission, further studies are required in the northern regions of Iran to timely control measures planning.
Laetitia Lebrun, Lara Absil, Myriam Remmelink
et al.
Abstract Introduction COVID-19-infected patients harbour neurological symptoms such as stroke and anosmia, leading to the hypothesis that there is direct invasion of the central nervous system (CNS) by SARS-CoV-2. Several studies have reported the neuropathological examination of brain samples from patients who died from COVID-19. However, there is still sparse evidence of virus replication in the human brain, suggesting that neurologic symptoms could be related to mechanisms other than CNS infection by the virus. Our objective was to provide an extensive review of the literature on the neuropathological findings of postmortem brain samples from patients who died from COVID-19 and to report our own experience with 18 postmortem brain samples. Material and methods We used microscopic examination, immunohistochemistry (using two different antibodies) and PCR-based techniques to describe the neuropathological findings and the presence of SARS-CoV-2 virus in postmortem brain samples. For comparison, similar techniques (IHC and PCR) were applied to the lung tissue samples for each patient from our cohort. The systematic literature review was conducted from the beginning of the pandemic in 2019 until June 1st, 2022. Results In our cohort, the most common neuropathological findings were perivascular haemosiderin-laden macrophages and hypoxic-ischaemic changes in neurons, which were found in all cases (n = 18). Only one brain tissue sample harboured SARS-CoV-2 viral spike and nucleocapsid protein expression, while all brain cases harboured SARS-CoV-2 RNA positivity by PCR. A colocalization immunohistochemistry study revealed that SARS-CoV-2 antigens could be located in brain perivascular macrophages. The literature review highlighted that the most frequent neuropathological findings were ischaemic and haemorrhagic lesions, including hypoxic/ischaemic alterations. However, few studies have confirmed the presence of SARS-CoV-2 antigens in brain tissue samples. Conclusion This study highlighted the lack of specific neuropathological alterations in COVID-19-infected patients. There is still no evidence of neurotropism for SARS-CoV-2 in our cohort or in the literature.
Abstract Objective This study aims to compare the feasibility and effectiveness of automatic deep learning network and radiomics models in differentiating low tumor stroma ratio (TSR) from high TSR in pancreatic ductal adenocarcinoma (PDAC). Methods A retrospective analysis was conducted on a total of 207 PDAC patients from three centers (training cohort: n = 160; test cohort: n = 47). TSR was assessed on hematoxylin and eosin-stained specimens by experienced pathologists and divided as low TSR and high TSR. Deep learning and radiomics models were developed including ShuffulNetV2, Xception, MobileNetV3, ResNet18, support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF), and logistic regression (LR). Additionally, the clinical models were constructed through univariate and multivariate logistic regression. Kaplan–Meier survival analysis and log-rank tests were conducted to compare the overall survival time between different TSR groups. Results To differentiate low TSR from high TSR, the deep learning models based on ShuffulNetV2, Xception, MobileNetV3, and ResNet18 achieved AUCs of 0.846, 0.924, 0.930, and 0.941, respectively, outperforming the radiomics models based on SVM, KNN, RF, and LR with AUCs of 0.739, 0.717, 0.763, and 0.756, respectively. Resnet 18 achieved the best predictive performance. The clinical model based on T stage alone performed worse than deep learning models and radiomics models. The survival analysis based on 142 of the 207 patients demonstrated that patients with low TSR had longer overall survival. Conclusions Deep learning models demonstrate feasibility and superiority over radiomics in differentiating TSR in PDAC. The tumor stroma ratio in the PDAC microenvironment plays a significant role in determining prognosis. Critical relevance statement The objective was to compare the feasibility and effectiveness of automatic deep learning networks and radiomics models in identifying the tumor-stroma ratio in pancreatic ductal adenocarcinoma. Our findings demonstrate deep learning models exhibited superior performance compared to traditional radiomics models. Key points • Deep learning demonstrates better performance than radiomics in differentiating tumor-stroma ratio in pancreatic ductal adenocarcinoma. • The tumor-stroma ratio in the pancreatic ductal adenocarcinoma microenvironment plays a protective role in prognosis. • Preoperative prediction of tumor-stroma ratio contributes to clinical decision-making and guiding precise medicine. Graphical Abstract
Medical physics. Medical radiology. Nuclear medicine