The Gleason score is an important predictor of prognosis in prostate cancer. However, its subjective nature can result in over- or under-grading. Our objective was to train an artificial intelligence (AI)-based algorithm to grade prostate cancer in specimens from patients who underwent radical prostatectomy (RP) and to assess the correlation of AI-estimated proportions of different Gleason patterns with biochemical recurrence-free survival (RFS), metastasis-free survival (MFS), and overall survival (OS). Training and validation of algorithms for cancer detection and grading were completed with three large datasets containing a total of 580 whole-mount prostate slides from 191 RP patients at two centers and 6218 annotated needle biopsy slides from the publicly available Prostate Cancer Grading Assessment dataset. A cancer detection model was trained using MobileNetV3 on 0.5 mm × 0.5 mm cancer areas (tiles) captured at 10× magnification. For cancer grading, a Gleason pattern detector was trained on tiles using a ResNet50 convolutional neural network and a selective CutMix training strategy involving a mixture of real and artificial examples. This strategy resulted in improved model generalizability in the test set compared with three different control experiments when evaluated on both needle biopsy slides and whole-mount prostate slides from different centers. In an additional test cohort of RP patients who were clinically followed over 30 years, quantitative Gleason pattern AI estimates achieved concordance indexes of 0.69, 0.72, and 0.64 for predicting RFS, MFS, and OS times, outperforming the control experiments and International Society of Urological Pathology system (ISUP) grading by pathologists. Finally, unsupervised clustering of test RP patient specimens into low-, medium-, and high-risk groups based on AI-estimated proportions of each Gleason pattern resulted in significantly improved RFS and MFS stratification compared with ISUP grading. In summary, deep learning-based quantitative Gleason scoring using a selective CutMix training strategy may improve prognostication after prostate cancer surgery.

While digitization and artificial intelligence represent the future of our specialty, future is also constrained by global warming and overstepping of planetary limits, threatening human health and the functioning of the healthcare system. The report by the Délégation ministérielle du numérique en santé and the French government\'s ecological planning of the healthcare system confirm the need to control the environmental impact of digital technology. Indeed, despite the promises of dematerialization, digital technology is a very material industry, generating greenhouse gas emissions, problematic consumption of water and mineral resources, and social impacts. The digital sector is impacting at every stage: (i) manufacture of equipment; (ii) use; and (iii) end-of-life of equipment, which, when recycled, can only be recycled to a very limited extent. This is a fast-growing sector, and the digitization of our specialty is part of its acceleration and its impact. Understanding the consequences of digitalization and artificial intelligence, and phenomena such as the rebound effect, is an essential prerequisite for the implementation of a sober, responsible, and sustainable digital pathology. The aim of this update is to help pathologists better understand the environmental impact of digital technology. As healthcare professionals, we have a responsibility to combine technological advances with an awareness of their impact, within a systemic vision of human health.

Triple-negative breast cancer (TNBC) is the most challenging breast cancer subtype. Molecular stratification and target therapy bring clinical benefit for TNBC patients, but it is difficult to implement comprehensive molecular testing in clinical practice. Here, using our multi-omics TNBC cohort (N = 425), a deep learning-based framework was devised and validated for comprehensive predictions of molecular features, subtypes and prognosis from pathological whole slide images. The framework first incorporated a neural network to decompose the tissue on WSIs, followed by a second one which was trained based on certain tissue types for predicting different targets. Multi-omics molecular features were analyzed including somatic mutations, copy number alterations, germline mutations, biological pathway activities, metabolomics features and immunotherapy biomarkers. It was shown that the molecular features with therapeutic implications can be predicted including the somatic PIK3CA mutation, germline BRCA2 mutation and PD-L1 protein expression (area under the curve [AUC]: 0.78, 0.79 and 0.74 respectively). The molecular subtypes of TNBC can be identified (AUC: 0.84, 0.85, 0.93 and 0.73 for the basal-like immune-suppressed, immunomodulatory, luminal androgen receptor, and mesenchymal-like subtypes respectively) and their distinctive morphological patterns were revealed, which provided novel insights into the heterogeneity of TNBC. A neural network integrating image features and clinical covariates stratified patients into groups with different survival outcomes (log-rank P < 0.001). Our prediction framework and neural network models were externally validated on the TNBC cases from TCGA (N = 143) and appeared robust to the changes in patient population. For potential clinical translation, we built a novel online platform, where we modularized and deployed our framework along with the validated models. It can realize real-time one-stop prediction for new cases. In summary, using only pathological WSIs, our proposed framework can enable comprehensive stratifications of TNBC patients and provide valuable information for therapeutic decision-making. It had the potential to be clinically implemented and promote the personalized management of TNBC.

Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens.

BACKGROUND: Intraoperative frozen sections (FS) are frequently used to establish the diagnosis of lung cancer when preoperative examinations are not conclusive. The downside of FS is its resource-intensive nature and the risk of tissue depletion when small lesions are assessed. Ex vivo fluorescence confocal microscopy (FCM) is a novel microimaging method for loss-free examinations of native materials. We tested its suitability for the intraoperative diagnosis of lung tumors.
METHODS: Samples from 59 lung resection specimens containing 45 carcinomas were examined in the FCM. The diagnostic performance in the evaluation of malignancy and histological typing of lung tumors was evaluated in comparison with FS and the final diagnosis.
RESULTS: A total of 44/45 (98%) carcinomas were correctly identified as malignant in the FCM. A total of 33/44 (75%) carcinomas were correctly subtyped, which was comparable with the results of FS and conventional histology. Our tests documented the excellent visualization of cytological features of normal tissues and tumors. Compared to FS, FCM was technically less demanding and less personnel intensive.
CONCLUSIONS: The ex vivo FCM is a fast, effective, and safe method for diagnosing and subtyping lung cancer and is, therefore, a promising alternative to FS. The method preserves the tissue without loss for subsequent examinations, which is an advantage in the diagnosis of small tumors and for biobanking.

BACKGROUND: Multiple sclerosis (MS) is a clinically heterogeneous disease underpinned by inflammatory, demyelinating and neurodegenerative processes, the extent of which varies between individuals and over the course of the disease. Recognising the clinicopathological features that most strongly associate with disease outcomes will inform future efforts at patient phenotyping.
OBJECTIVE: We used a digital pathology workflow, involving high-resolution image acquisition of immunostained slides and opensource software for quantification, to investigate the relationship between clinical and neuropathological features in an autopsy cohort of progressive MS.
METHODS: Sequential sections of frontal, cingulate and occipital cortex, thalamus, brain stem (pons) and cerebellum including dentate nucleus (n = 35 progressive MS, females = 28, males = 7; age died = 53.5 years; range 38-98 years) were immunostained for myelin (anti-MOG), neurons (anti-HuC/D) and microglia/macrophages (anti-HLA). The extent of demyelination, neurodegeneration, the presence of active and/or chronic active lesions and quantification of brain and leptomeningeal inflammation was captured by digital pathology.
RESULTS: Digital analysis of tissue sections revealed the variable extent of pathology that characterises progressive MS. Microglia/macrophage activation, if found at a higher level in a single block, was typically elevated across all sampled blocks. Compartmentalised (perivascular/leptomeningeal) inflammation was associated with age-related measures of disease severity and an earlier death.
CONCLUSIONS: Digital pathology identified prognostically important clinicopathological correlations in MS. This methodology can be used to prioritise the principal pathological processes that need to be captured by future MS biomarkers.

暂无摘要。

Alzheimer\'s disease (AD) is a progressive neurological condition characterized by impaired cognitive function and behavioral alterations. While AD research historically centered around mis-folded proteins, advances in mass spectrometry techniques have triggered increased exploration of the AD lipidome with lipid dysregulation emerging as a critical player in AD pathogenesis. Gangliosides are a class of glycosphingolipids enriched within the central nervous system. Previous work has suggested a shift in a-series gangliosides from complex (GM1) to simple (GM2 and GM3) species may be related to the development of neurodegenerative disease. In addition, complex gangliosides with 20 carbon sphingosine chains have been shown to increase in the aging brain. In this study, we utilized matrix-assisted laser desorption ionization mass spectrometry imaging (MALDI-MSI) to interrogate the in situ relationship of a-series gangliosides with either 18 or 20 carbon sphingosine chains (d18:1 or d20:1, respectively) in the post-mortem human AD brain. Here, we expanded upon previous literature and demonstrated a significant decrease in the GM1 d20:1 to GM1 d18:1 ratio in regions of the dentate gyrus and entorhinal cortex in AD relative to control brain tissue. Then, we demonstrated that the MALDI-MSI profile of GM3 co-localizes with histologically confirmed amyloid beta (Aβ) plaques and found a significant increase in both GM1 and GM3 in proximity to Aβ plaques. Collectively, this study demonstrates a perturbation of the ganglioside profile in AD, and validates a pipeline for MALDI-MSI and classic histological staining in the same tissue sections. This demonstrates feasibility for integrating untargeted mass spectrometry imaging approaches into a digital pathology framework.

Recent advancements in computer-assisted diagnosis (CAD) have catalysed significant progress in pathology, particularly in the realm of urine cytopathology. This review synthesizes the latest developments and challenges in CAD for diagnosing urothelial carcinomas, addressing the limitations of traditional urinary cytology. Through a literature review, we identify and analyse CAD models and algorithms developed for urine cytopathology, highlighting their methodologies and performance metrics. We discuss the potential of CAD to improve diagnostic accuracy, efficiency and patient outcomes, emphasizing its role in streamlining workflow and reducing errors. Furthermore, CAD tools have shown potential in exploring pathological conditions, uncovering novel biomarkers and prognostic/predictive features previously unknown or unseen. Finally, we examine the practical issues surrounding the integration of CAD into clinical practice, including regulatory approval, validation and training for pathologists. Despite the promising results, challenges remain, necessitating further research and validation efforts. Overall, CAD presents a transformative opportunity to revolutionize diagnostic practices in urine cytopathology, paving the way for enhanced patient care and outcomes.

In sub-Saharan Africa, acute-onset severe malaria anaemia (SMA) is a critical challenge, particularly affecting children under five. The acute drop in haematocrit in SMA is thought to be driven by an increased phagocytotic pathological process in the spleen, leading to the presence of distinct red blood cells (RBCs) with altered morphological characteristics. We hypothesized that these RBCs could be detected systematically and at scale in peripheral blood films (PBFs) by harnessing the capabilities of deep learning models. Assessment of PBFs by a microscopist does not scale for this task and is subject to variability. Here we introduce a deep learning model, leveraging a weakly supervised Multiple Instance Learning framework, to Identify SMA (MILISMA) through the presence of morphologically changed RBCs. MILISMA achieved a classification accuracy of 83% (receiver operating characteristic area under the curve [AUC] of 87%; precision-recall AUC of 76%). More importantly, MILISMA\'s capabilities extend to identifying statistically significant morphological distinctions (p < 0.01) in RBCs descriptors. Our findings are enriched by visual analyses, which underscore the unique morphological features of SMA-affected RBCs when compared to non-SMA cells. This model aided detection and characterization of RBC alterations could enhance the understanding of SMA\'s pathology and refine SMA diagnostic and prognostic evaluation processes at scale.