Colorectal cancer histopathological grading relies on the accurate segmentation of glandular structures. Current deep learning–based methods depend heavily on large-scale pixel-level annotations that are labor-intensive and not amenable to clinical practice. Weakly supervised semantic segmentation offers a promising alternative; yet, existing class activation map–based weakly supervised semantic segmentation approaches often produce incomplete, low-quality pseudo-masks that overemphasize discriminative regions and fail to provide reliable supervision for unannotated glandular structures, limiting their suitability for dense histopathology segmentation under sparse supervision. We propose a novel weakly supervised teacher–student framework that leverages sparse pathologists’ annotations and an Exponential Moving Average–stabilized teacher network to generate refined pseudo-masks.

Our framework integrates confidence-based filtering, adaptive fusion of teacher predictions with limited ground truth, and curriculum-guided refinement, enabling the student network to progressively delineate and accurately segment unannotated glandular regions. We validated our framework on an institutional colorectal cancer cohort from The Ohio State University Wexner Medical Center, consisting of 60 hematoxylin and eosin-stained whole-slide images from independent patients with varying degrees of gland differentiation, as well as on public benchmarks including the Gland Segmentation dataset (derived from stage T3–T4 colorectal adenocarcinomas), TCGA-COAD, TCGA-READ, and SPIDER.

The proposed framework achieved strong performance on the institutional dataset despite limited annotations. On the Gland Segmentation dataset, it demonstrated competitive performance compared to both weakly and fully supervised approaches, achieving a mean Intersection over Union of 80.10% ± 1.52 and a mean Dice coefficient of 89.10% ± 2.10. Moreover, cross-cohort evaluations showed robust generalization on TCGA-COAD and TCGA-READ without requiring additional annotations, while reduced performance on SPIDER reflected pronounced domain shift.

Our framework provides an annotation-efficient and generalizable paradigm for accurate gland segmentation in colorectal histopathology, offering a practical pathway toward significantly reducing annotation burdens while preserving high segmentation fidelity.

End-stage liver disease (ESLD) is characterized by a dramatic deterioration of liver function, frequently accompanied by systemic inflammatory storms and multiple organ failures. Central to the onset and progression of ESLD, systemic inflammation arises from complex interactions among various inflammatory signaling molecules and immune cells within and beyond the liver. As key inflammatory modulatory molecules, bioactive oxylipins have been increasingly recognized for their complex molecular mechanisms implicated in various diseases. This review aims to summarize recent findings regarding the molecular and immunological mechanisms through which oxylipins contribute to the development of liver injury and failure, with emphasis on both substantial intrahepatic and extrahepatic immune and inflammatory dysregulation associated with ESLD. Furthermore, this review discusses the translational potential of targeting oxylipins for clinical diagnosis, prognosis, and therapeutic intervention in ESLD.

The history of screening for cervical cancer is rich with implementing cutting-edge ideas and technologies. From the very first “Pap smear” to the semi-automated and computerized systems of today, the way we screen for cervical cancer has changed dramatically in the past 75 years. With the advent of new techniques and more advanced machine learning algorithms, we sought to understand the current and future applications of artificial intelligence in clinical pathology around cervical cancer screening, diagnosis, and treatment.

A structured narrative review was conducted to examine the historical evolution and contemporary advances in cervical cancer screening, diagnosis, excisional management, and artificial intelligence applications. Peer-reviewed articles, consensus guidelines, and global policy documents published between January 1990 and March 2025 were identified through targeted searches of PubMed and review of reference lists from relevant publications. Search terms included combinations of “cervical cancer screening,” “Papanicolaou test,” “liquid-based cytology,” “HPV testing,” “colposcopy,” “loop electrosurgical excision procedure,” “digital pathology,” “deep learning,” and “artificial intelligence.” Emphasis was placed on multi-center validation studies, systematic reviews, regulatory and implementation guidance, and global health frameworks. Publications lacking methodological transparency or direct relevance to clinical or translational practice were excluded.

Through a review of the literature, we describe how innovations in conventional and liquid-based cytology, human papillomavirus testing, and organized screening programs established the current prevention framework. Building on this foundation, recent studies demonstrate promising performance of deep learning algorithms applied to conventionally prepared cervical cytology slides, with systems capable of binary normal versus abnormal classification as well as more granular diagnostic categorization. Artificial intelligence-assisted colposcopy and computer-vision approaches have also shown improved diagnostic concordance, workflow efficiency, and potential to expand screening capacity in resource-limited environments.

There has been much work done in the past several years surrounding the implementation of deep learning algorithms in regard to cervical cancer screening. The work in this field shows promise in enhancing diagnostic accuracy, streamlining diagnostic workflow, and decreasing turnaround times from specimen collection to rendering a diagnosis. However, there are still many technical, legal, and ethical questions that must be answered prior to widespread adoption of these algorithms for patient care.

Alpinia calcarata (A. calcarata) Roscoe (Family: Zingiberaceae) is a rhizomatous perennial herb used in traditional medicine to treat inflammatory conditions. This study aimed to develop a topical emulgel dosage form by incorporating the essential oil of A. calcarata rhizome and to investigate it’s in vitro anti-inflammatory activity. A thin-layer chromatographic fingerprint of the essential oil of A. calcarata rhizome was developed. Then, an emulsion base containing plant oil was formulated and incorporated within a Carbopol gel base. The physical characteristics of this formulation were evaluated subsequently. The anti-inflammatory mechanism of the emulgel was determined by in vitro blood cell membrane stabilization assay and thrombolytic activity assay. The results were statistically analyzed by one-way analysis of variance. The thin-layer chromatographic fingerprint of the test oil demonstrated several bands with unique retention factor values. The formulated herbal emulgel was white, viscous, and homogeneous in appearance. The spreadability was 118 g·cm/M, and the pH of the emulgel was 6.30 at 25°C. The A. calcarata emulgel significantly (p < 0.05) inhibited heat-induced in vitro hemolysis, with the highest activity at a 50 µg/mL dose (87.68 ± 0.35%) compared to the placebo. Furthermore, this activity was found to be dependent on the essential oil concentration (r2 = 0.99) of the emulgel. Therefore, it was concluded that the essential oil of A. calcarata rhizome is an effective active ingredient to be used in a topical emulgel formulation, whereas the diverse phytochemicals present in the essential oil would be the underlying source of its anti-inflammatory activity.

Congenital portosystemic shunts (CPSS) are rare vascular anomalies characterized by abnormal communication between the portal and systemic venous systems, resulting in partial or complete diversion of portal blood away from the liver. These shunts can give rise to a broad spectrum of clinical manifestations, including hyperammonemia (with or without encephalopathy), hepatopulmonary syndrome, and portopulmonary hypertension. Notably, these complications often occur in the absence of portal hypertension. Advances in diagnostic imaging, particularly Doppler ultrasound, computed tomographic angiography, and magnetic resonance imaging, have enhanced the early detection and classification of CPSS. Treatment approaches vary depending on shunt type and clinical severity and may include interventional closure via embolization or surgical ligation. Most persistent or symptomatic shunts require immediate intervention. Recent studies have also identified potential genetic and embryological mechanisms contributing to CPSS development, offering new insights into their pathogenesis. This review aims to summarize current knowledge on the epidemiology, pathophysiology, clinical presentation, diagnostic evaluation, and management of CPSS, and to highlight their consideration in patients with hepatic encephalopathy or unexplained liver disease.

Cirrhotic ascites develops when portal hypertension and arterial under-filling chronically activate neuro-hormonal pathways that drive renal sodium-water retention. Augmented proximal tubular sodium reabsorption, predominantly mediated by the apical sodium/hydrogen exchanger 3 (NHE3), plays a fundamental role in this process. Given the spatial coupling of NHE3 and the sodium-glucose cotransporter 2 (SGLT2), selective SGLT2 inhibition reduces NHE3 activity via functional suppression within the apical microdomain. The increased sodium chloride delivery to the macula densa augments tubuloglomerular feedback and modulates the renin–angiotensin–aldosterone system. Early clinical investigations, ranging from case reports and retrospective analyses to pilot randomized trials, indicated potential benefits in controlling ascites and reducing decompensation events. However, their limited sample size, heterogeneous endpoints, and predominantly observational design constrain the generalizability of the findings. This review concentrates on the molecular mechanisms and emerging clinical evidence supporting the therapeutic potential of SGLT2 inhibitors in the management of cirrhotic ascites.

PVT is a harmful event in cirrhosis, and the prevention and treatment of PVT are important in the management of cirrhosis and portal hypertension. The study aimed to observe the efficacy of Danggui Buxue Decoction (DBD) on portal vein thrombosis (PVT) in cirrhosis and to elucidate the related mechanism using a modified animal model.

A model of PVT in cirrhosis was established by partial portal vein ligation and intraperitoneal injection of CCl4 in rats, which showed obvious PVT with intra- and extravenous thrombosis as well as liver cirrhosis. Rats were randomly assigned into four groups and received intragastric administration of DBD (12 g/kg/day) or rivaroxaban (20 mg/kg/day) for 6 weeks.

DBD attenuated collagen deposition and reduced thrombus formation in model livers, increased portal vein blood flow, expanded the portal vein diameter, and reduced prothrombin time and international normalized ratio in the model rats. In addition, DBD reduced hepatic von Willebrand factor and plasminogen activator inhibitor-1 expression and increased hepatic fibrin degradation product content in the liver tissues of model rats.

We modified a model of cirrhotic PVT in rats and found that DBD had a good effect on PVT and liver fibrosis, with the mechanisms related to the enhancement of portal vein blood flow and the protection against endothelial cell injury.