Background/Objective: Cardiac innervation plays a critical role in regulating myocardial function and enabling the heart to adapt to physiological and pathological conditions. Although the general features of sympathetic and parasympathetic innervation of the myocardium are well described, the spatial organisation of nerve fibres within the cardiac muscle remains incompletely characterised. This study aimed to develop and validate the SKUF (Slice–Keep–Unwrap–Fuse) protocol, a multimodal framework for mapping myocardial innervation through the integration of histological data and magnetic resonance imaging (MRI). Methods: The study was performed on the heart of a 7-year-old patient who died from rupture of a cerebral vascular malformation without evidence of cardiovascular disease. Prior to histological processing, post-mortem MRI was performed to provide a precise anatomical reference. The heart was sectioned into sequential transverse rings of 4 mm thickness, yielding 71 paraffin blocks. Histological sections (3 μm) were immunostained with antibodies against UCHL-1 to visualise nerve fibres and scanned using an Aperio AT2 system (20× magnification). Automated image analysis was conducted using the SVSSlide Processor module, which included tissue segmentation, colour-based nerve fibre detection, and sliding-window density mapping. Heatmaps were assembled into ring-based myocardial reconstructions and co-registered with MRI slices using combined rigid and deformable registration, followed by three-dimensional reconstruction of innervation patterns. Results: A higher density of nerve fibres was observed in the right ventricular myocardium compared with the left ventricle, whereas larger nerve trunks were identified in the epicardium of the left ventricle. Quantitative analysis revealed a pronounced longitudinal gradient of innervation, with minimal density in the apical region and progressive increases towards the mid-ventricular segments, where maximal density and spatial organisation of neural structures were observed. The atrioventricular groove exhibited the greatest heterogeneity of innervation due to the presence of large nerve trunks and ganglionated plexuses. Integration of histological maps with MRI enabled three-dimensional visualisation of spatial clusters of nerve fibres. Conclusions: The SKUF protocol provides a robust framework for integrating histological and MRI data to generate three-dimensional maps of myocardial innervation. This approach may facilitate the development of high-resolution anatomical atlases of cardiac innervation and support future studies of neurocardiac mechanisms of arrhythmogenesis and targeted neuromodulation.

Background/Objectives: Orthotopic heart transplantation results in complete surgical denervation of the donor heart. Although partial functional reinnervation has been reported in some recipients, the histopathological features of intracardiac innervation in long-term failing cardiac allografts remain poorly characterized. We present a unique case of a cardiac allograft explanted 11 years after transplantation that enabled detailed histological and digital assessment of neural remodeling. Case Description: An explanted cardiac allograft obtained after retransplantation for chronic graft dysfunction was examined using whole-heart histopathological reconstruction and immunohistochemistry (CD3, CD68, C3, C4d, HLA-DR, NLRP3, VEGF, and UCHL-1). Digital quantitative analysis of UCHL-1-positive nerve fibers, including spatial density mapping and comparison with a reference non-diseased myocardium, demonstrated profound and heterogeneous loss of intracardiac innervation. Marked denervation was observed not only within fibrotic and infarcted regions but also in the morphologically preserved myocardium. Neural injury was associated with perineural and endoneurial inflammatory infiltrates, complement deposition, HLA-DR expression within nerve fibers and reduced perivascular and epicardial adipose tissue innervation. Distinct regional patterns of denervation and neural remodeling were also identified in the aortic segments of the transplantation complex. Conclusions: This case demonstrates that chronic cardiac allograft dysfunction may involve extensive injury of the intracardiac nervous system extending beyond areas of ischemic myocardial damage. The findings suggest that immune-mediated inflammation, complement activation, and chronic ischemia contribute to progressive neural remodeling in the transplanted heart. Histopathological evaluation of intracardiac innervation may provide additional insight into mechanisms of long-term graft failure and represents an underrecognized component of cardiac allograft pathology.

Tuberculosis remains a serious infectious disease that causes over 1.3 million deaths annually. Following the COVID-19 pandemic, the global incidence of tuberculosis has increased to 10.8 million cases. Pregnant women represent a particularly vulnerable population requiring tailored approaches to the prevention, diagnosis, and treatment of tuberculosis. SARS-CoV-2 infection may have impacted existing clinical protocols. Implementing updated methods of tuberculosis prevention, diagnosis, and treatment in pregnant women could help reduce adverse maternal and fetal outcomes. The aim of this review was to explore potential modifications in tuberculosis management among pregnant women in the post-COVID-19 era, including co-infection with SARS-CoV-2. Methods: A review was conducted, incorporating a systematic literature search across major international databases, including Medline, PubMed, Web of Science, Scopus, and Google Scholar. The search covered publications released between December 2019 and September 2024 and used targeted keywords such as “COVID-19” OR “SARS-CoV-2”, “tuberculosis” OR “TB” OR “latent tuberculosis infection” OR “pulmonary tuberculosis”, and “pregnancy” OR “pregnant women”. Results: Pregnant women living with HIV are at increased risk of developing tuberculosis, which can negatively affect both maternal and perinatal outcomes. Screening for tuberculosis is recommended for all HIV-positive pregnant women, even in the absence of clinical symptoms. Notably, immunological testing before and during pregnancy facilitates the timely and safe detection of tuberculosis infection, enabling preventive and therapeutic interventions during any stage of gestation and the early postpartum period, for the benefit of both mother and child. Drug–drug interactions play a significant role in tuberculosis management, both among anti-tuberculosis agents and with medications for comorbid conditions. Current knowledge of the pharmacokinetics and pharmacodynamics of antituberculosis agents, coupled with therapeutic drug monitoring, supports the development of individualized and effective treatment regimens, which are particularly critical for pregnant patients. Recommendations for managing tuberculosis in pregnant women after COVID-19 infection include measuring D-dimer levels, performing echocardiography, and consulting cardiologists to prevent treatment-related complications. Conclusions: Pregnant women represent a distinct subgroup of tuberculosis patients requiring individualized management. Changes observed in tuberculosis progression and treatment responses in pregnant women before and after SARS-CoV-2 infection should inform therapeutic choices, especially in cases of drug-resistant tuberculosis treated with bedaquiline. COVID-19 has been associated with increased cardiovascular risk, which may heighten the likelihood of adverse drug reactions in this population, especially given the limited therapeutic options. Further research is required to assess the long-term outcomes of latent tuberculosis infection in pregnant women and to evaluate the safety and efficacy of novel regimens for drug-resistant TB during pregnancy.

The review provides a current view of the anatomy, histology, immunohistochemistry, electron microscopy, and electron immunocytochemistry of the cardiac conduction system (CCS) based on literature data and the author's own research over more than 30 years. The article describes a new specialized x-structure of the CCS, discovered by the author and published in 2014, and another type of cells that are part of the sinus and atrioventricular nodes — telocytes, capable of generating and conducting an electrical impulse. Based on layer-by-layer dissection and serial histological sections performed on more than 400 adult hearts, the topographic anatomy of the atrial muscular framework is given. The article also describes the atrial innervation.

Background: Segmenting nerve fibres in histological images is a tricky job because of how much the tissue looks can change. Modern neural network architectures, including U-Net and transformers, demonstrate varying degrees of effectiveness in this area. The aim of this study is to conduct a comparative analysis of the SegFormer, VGG-UNet, and FabE-Net models in terms of segmentation quality and speed. Methods: The training sample consisted of more than 75,000 pairs of images of different tissues (original slice and corresponding mask), scaled from 1024 × 1024 to 224 × 224 pixels to optimise computations. Three neural network architectures were used: the classic VGG-UNet, FabE-Net with attention and global context perception blocks, and the SegFormer transformer model. For an objective assessment of the quality of the models, expert validation was carried out with the participation of four independent pathologists, who evaluated the quality of segmentation according to specified criteria. Quality metrics (precision, recall, F1-score, accuracy) were calculated as averages based on the assessments of all experts, which made it possible to take into account variability in interpretation and increase the reliability of the results. Results: SegFormer achieved stable stabilisation of the loss function faster than the other models—by the 20–30th epoch, compared to 45–60 epochs for VGG-UNet and FabE-Net. Despite taking longer to train per epoch, SegFormer produced the best segmentation quality, with the following metrics: precision 0.84, recall 0.99, F1-score 0.91 and accuracy 0.89. It also annotated a complete histological section in the fastest time. Visual analysis revealed that, compared to other models, which tended to produce incomplete or excessive segmentation, SegFormer more accurately and completely highlights nerve structures. Conclusions: Using attention mechanisms in SegFormer compensates for morphological variability in tissues, resulting in faster and higher-quality segmentation. Image scaling does not impair training quality while significantly accelerating computational processes. These results confirm the potential of SegFormer for practical use in digital pathology, while also highlighting the need for high-precision, immunohistochemistry-informed labelling to improve segmentation accuracy.

Aim. To evaluate the effect of angiotensin II receptor blocker (ARB) therapy on the expression of transforming growth factor-β (TGF-β) in the myxomatous mitral valve, on the serum levels of TGF-β1/TGF-β2 and the left ventricular (LV) systolic function in patients with mitral valve prolapse (MVP).Material and methods. The retrospective non-randomized single-center study included 233 patients who underwent surgical treatment of severe mitral regurgitation due to MVP. Preoperative drug therapy was assessed using case records. Transthoracic echocardiography was performed in all patients before surgery. Pathological and immunohistochemical analysis of mitral valve fragments removed during surgery were performed. The serum content of TGF-β1 and TGF-β2 was determined by the enzyme immunoassay.Results. According to echocardiography, mitral valve leaflets were significantly longer and thicker in patients in the control group than in the ARB group. These data were confirmed by pathological study — most patients in the control group had excessive myxomatous mitral valve leaflets (χ2=7,9; p=0,005). In the ARB group, the expression of type III collagen in the mitral valve leaflets was lower compared to the control group and the expression of fibulin-5 did not differ. Also, in the main group, an increased density of valvular interstitial cells was found, including those expressing TGF-β1 and TGF-β2 compared to the control group. The serum level of TGF-β1 and TGF-β2 was significantly higher in the control group than in the ARB group.Despite the absence of differences in LV ejection fraction between the groups, global longitudinal systolic strain and strain rate were significantly higher in the main group.Conclusion. This is the first study to reveal a positive effect of ARB therapy on myxomatous mitral valve degeneration and LV function due to inhibition of the TGF-β signaling pathway, which opens up potential for pathogenetic therapy in patients with MVP.

Hypertrophic cardiomyopathy (HCM) progressing to end-stage heart failure and heart transplantation (HT) is a rare clinical scenario with an insufficiently explored genetic background. In this single-center retrospective cohort study, we aimed to characterize the genetic spectrum, variants of HCM adverse remodeling, and aspects of molecular pathogenesis of this subgroup. The study included 14 patients (9 females), among whom 10 developed a dilated/hypokinetic phenotype and 4 a restrictive phenotype. In 13 patients (93%), at least one pathogenic or likely pathogenic genetic variant was identified. Dilated remodeling/hypokinesis was associated with loss-of-function variants in LAMP2 (3) in females, ALPK3homo (1), MYH7 (1), MYBPC3 (1), a heterozygous missense variant in TRIM63 (1), FLNCtv (1), TTNtv (2). For the latter two, electrophoretic analysis of titin isoform composition and protein content in myocardial fragments from explanted hearts confirmed the functional significance of TTN gene variants. The restrictive phenotype in the adult group was associated with carriage of multiple pathogenic sarcomere gene variants: MYL3homo (1), MYBPC3+TPM1 (1), an MYH7 converter domain variant (1), and, in one child, with a TNNT2 variant. This findings support HCM progressing to HT is characterized by a higher frequency of variants in non-sarcomeric genes and Danon disease compared to the general HCM cohort.

Introduction: The contribution of SARS-CoV-2 infection to the severity of placental alterations in preeclampsia remains unclear. This study aimed to evaluate the morphological changes in placentas of women who experienced COVID-19 during pregnancy, with a focus on the presence or absence of preeclampsia. Materials and Methods: The study included placentas from: (1) patients with both COVID-19 during pregnancy and preeclampsia (n = 20, 2022); (2) patients with COVID-19 during pregnancy without preeclampsia (n = 20, 2022); (3) patients with preeclampsia but without COVID-19 (n = 5, 2019); (4) patients with physiological pregnancies without COVID-19 or gestational complications (n = 5, 2019). Histological and immunohistochemical examinations of the placentas were performed using antibodies against the SARS-CoV-2 spike protein, DPP4 (CD26), and VEGF. Results: Placentas from patients with both COVID-19 and preeclampsia demonstrated the most pronounced stromal and vascular alterations, including pseudo-infarctions and villous fibrosis. Chorangiosis, excessive fibrinoid deposition in the intervillous space, and accelerated villous maturation with an increased number of syncytial knots were more common in the preeclampsia groups, regardless of prior COVID-19 infection. Symptomatic forms of coronavirus infection were associated with more severe manifestations of malperfusion. Expression of the SARS-CoV-2 spike protein was detected in 78% of syncytiotrophoblast cells and 37% of decidual cells in 28 of 40 placentas from women with previous COVID-19, while its presence in the vascular endothelium, macrophages, and villous fibroblasts was focal, as was CD26 expression. VEGF expression did not differ significantly between patients with and without COVID-19. Conclusions: COVID-19 is associated with more pronounced stromal-vascular alterations in the placenta; however, not all of these changes are directly caused by the virus itself but rather reflect the severe course of preeclampsia. Inflammatory alterations are nonspecific for COVID-19, even though CD26 and the SARS-CoV-2 spike protein are detectable in nearly all placental structures, whereas VEGF levels remain comparable to those observed in placentas prior to the coronavirus pandemic.

Placental terminal villi have always been the focus of placental pathology research, and the automatic and precise segmentation of placental terminal villi can effectively assist doctors in reading slides. However, due to the uniqueness of placenta, data is often difficult to collect while training a highly accurate model always requires a large amount of experts' annotations. To address the challenges, we propose a new framework handling villi segmentation, given multi-center data and very few annotations. We employ Generative Adversarial Networks (GAN) for stain normalization and utilize a large volume of unlabeled data for self-supervised pre-training, which helps learning useful feature representations of placental terminal villi. To achieve high-precision segmentation while reducing the burden of annotations, we propose a weakly supervised method to finetune pre-trained model, which only required fewer annotations in the form of local rectangular boxes. We collect a dataset comprising 1659 images from three machines with stain variations. Validation involves 120 images with each data source contributing 40 images. Our method achieves high IoU of 91.14, 89.27, and 88.12 across the three data types. The results not only validate the effectiveness and precision of our method in dealing with complex placental data but also highlight the potential of our model in parsing such data. This research paves the way for future studies to further explore and understand the structure and function of placental terminal villi.

Papillary fibroelastomas are the most common tumors of the heart valves. Among all primary heart tumors, the incidence of papillary fibroelastoma is about 15 %. The clinical picture is often asymptomatic, however, it can be complicated by a transient ischemic attack, acute cerebrovascular accident, acute myocardial infarction, heart failure, pulmonary embolism, and etc. The article presents a clinical case of a 55-year-old female patient with papillary fibroelastoma of the aortic valve, which caused angina attacks and was a probable cause of several myocardial infarctions. Complex radiation diagnostics using aortic computed tomography with ECG synchronization, transthoracic and transesophageal echocardiography made it possible to visualize a formation in the commissure area between the right coronary and non-coronary aortic valve flaps as the cause of the patient’s clinical manifestations. Comprehensive diagnostics made it possible to successfully perform emergency surgical treatment.

Cardiac contractility modulation (CCM) is based on electrical stimulation of the heart without alteration of action potential and mechanical activation, the data on its fundamental molecular mechanisms are limited. Here we demonstrate clinical and physiological effect of 12 months CCM in 29 patients along with transcriptomic molecular data. Based on the CCM effect the patients were divided into two groups: responders (n = 13) and non-responders (n = 16). RNA-seq data were collected for 6 patients before and after CCM including 3 responders and 3 non-responders. The overall effect of CCM on gene expression was mainly provided by samples from the responder group and included the upregulation of the genes involved in the maintenance of proteostasis and mitochondrial structure and function. Using pathway enrichment analysis, we found that baseline myocardial tissue samples from responder group were characterized by upregulation of mitochondrial matrix-related genes, Z disc-protein encoding genes and muscle contraction-related genes. In summary, twelve months of ССM led to changes in signaling pathways associated with cellular respiration, apoptosis, and autophagy. The pattern of myocardial remodeling after CCM is associated with initial expression level of myocardial contractile proteins, adaptation reserves associated with mitochondria and low expression level of inflammatory molecules.

Gastric precancerous conditions are closely linked to the development of gastric cancer. However, the detection of gastric precancerous lesions (GPL) is limited by the indistinct symptoms and the low detection rate of microscope images. This paper proposes an RGB and Hyperspectral Dual-modality imaging Feature Fusion Network (DuFF-Net) to improve the classification accuracy of GPL. To fully exploit information of different modality images, we customize a dual-stream ResNet-based model for feature sharing and fusion. Skip-Connections are added between inter-path of networks to achieve information interaction. In the decision step, we adopt the SEbased attention module and Pearson Correlation to highlight and select effective features. Experimental results show that the DuFF-Net increases the screening accuracy to 96.15 % for two types of gastric precancerous tissues with high morphological similarity. Furthermore, our approach reduces the labeling workload for classification tasks by approximately 50 %. These findings provide valuable guidance for the screening and subsequent lesion segmentation of GPLs.

Gastric precancerous lesions (GPL) significantly elevate the risk of gastric cancer, and precise diagnosis and timely intervention are critical for patient survival. Due to the elusive pathological features of precancerous lesions, the early detection rate is less than 10%, which hinders lesion localization and diagnosis. In this paper, we provide a GPL pathological dataset and propose a novel method for improving the segmentation accuracy on a limited-scale dataset, namely RGB and Hyperspectral dual-modal pathological image Cross-attention U-Net (CrossU-Net). Specifically, we present a self-supervised pre-training model for hyperspectral images to serve downstream segmentation tasks. Secondly, we design a dual-stream U-Net-based network to extract features from different modal images. To promote information exchange between spatial information in RGB images and spectral information in hyperspectral images, we customize the cross-attention mechanism between the two networks. Furthermore, we use an intermediate agent in this mechanism to improve computational efficiency. Finally, we add a distillation loss to align predicted results for both branches, improving network generalization. Experimental results show that our CrossU-Net achieves accuracy and Dice of 96.53% and 91.62%, respectively, for GPL lesion segmentation, providing a promising spectral research approach for the localization and subsequent quantitative analysis of pathological features in early diagnosis.

Histiocytoses are rare diseases characterised by infiltration of affected organs by myeloid cells with a monocyte or dendritic cell phenotype. Symptoms can range from self-resolving localised forms to multisystemic lesions requiring specific treatment. To demonstrate extremely rare cases of CD68-negative cardiac histiocytosis with expression of SARS-CoV-2 antigen in infiltrate cells. We demonstrated a case of Erdheim–Chester disease in a 67-year-old man with pericardial involvement and positive dynamics with vemurafenib treatment, an autopsy case of xanthogranulomatous myopericarditis in a 63-year-old man, surgical material of xanthogranulomatous constrictive pericarditis in a 57-year-old man, and an autopsy case of xanthogranulomatosis in a 1-month-old girl. In all cases, xanthogranuloma cells expressed CD163, many of them spike protein SARS-CoV-2, while CD68 expression was detected only in single cells. In this article, we demonstrated four cases of extremely rare CD68-negative cardiac xanthogranulomatosis in three adults and one child with expression of the spike protein SARS-CoV-2 in M2 macrophages. This potential indirect association between COVID-19 and the development of histiocytosis in these patients warrants further investigation. To substantiate this hypothesis, more extensive research is needed.

Aim. To determine the prevalence and profile of rare variants of the filamin C gene (FLNC) among patients with hypertrophic obstructive cardiomyopathy (HCM) referred for septal myectomy, and to provide a clinical description of HCM occurring with these variants.Material and methods. Ninety-eight adult patients with HCM who underwent septal myectomy underwent genetic testing by next-generation sequencing using a targeted cardiac panel (39-gene panel in 58 patients and 17-gene panel in 40 patients). In patients with rare FLNC variants (with a minor allele frequency <0,01%), the data of anamnesis, echocardiography, electrocardiography, Holter monitoring, and myocardial histological examination were analyzed.Results. Four patients with rare FLNC variants (two men and two women) were identified, which amounted to 4% (Pro1774Ser, Thr1317Pro and His1834Tyr, the latter was detected twice). These variants were missenses and classified as variants of uncertain clinical significance. The FLNC p.Thr1317Pro variant in one patient was combined with a pathogenic variant p.Val606Leu in MYH7 gene. All patients received diagnosis of HCM after age of 40 years. Clinical course was represented by mild symptoms of heart failure and class II stable angina. Episodes of non-sustained ventricular tachycardia, atrial fibrillation or clinically significant conduction block were not registered. One patient with p.His1834Tyr FLNC variant had reverse curve interventricular septum morphology, whereas other patients had predominant hypertrophy of basal segment of interventricular septum. Diastolic dysfunction did not exceed grade 1-2 in all four patients.Conclusion. The clinical characteristics of carriers of rare FLNC variants in our study did not differ from the majority of patients with HCM who underwent septal myectomy. Rare FLNC variants can act as causative or modifying factors of HCM course. Functional and population-based studies using segregation analysis should clarify the pathogenicity of rare FLNC variants.

Stain variations pose a major challenge to deep learning segmentation algorithms in histopathology images. Current unsupervised domain adaptation methods show promise in improving model generalization across diverse staining appearances but demand abundant accurately labeled source domain data. This paper assumes a novel scenario, namely, unsupervised domain adaptation based segmentation task with incompletely labeled source data. This paper propose a Stain-Adaptive Segmentation Network with Incomplete Labels (SASN-IL). Specifically, the algorithm consists of two stages. The first stage is an incomplete label correction stage, involving reliable model selection and label correction to rectify false-negative regions in incomplete labels. The second stage is the unsupervised domain adaptation stage, achieving segmentation on the target domain. In this stage, we introduce an adaptive stain transformation module, which adjusts the degree of transformation based on segmentation performance. We evaluate our method on a gastric cancer dataset, demonstrating significant improvements, with a 10.01% increase in Dice coefficient compared to the baseline and competitive performance relative to existing methods.

The development of drug therapy for the pathological calcification of the aortic valve is still an open issue due to the lack of effective treatment strategies. Currently, the only option for treating this condition is surgical correction and symptom management. The search for models to study the safety and efficacy of anti-calcifying drugs requires them to not only be as close as possible to in vivo conditions, but also to be flexible with regard to the molecular studies that can be applied to them. The ex vivo model has several advantages, including the ability to study the effect of a drug on human cells while preserving the original structure of the valve. This allows for a better understanding of how different cell types interact within the valve, including non-dividing cells. The aim of this study was to develop a reproducible ex vivo calcification model based on valves from patients with calcific aortic stenosis. We aimed to induce spontaneous calcification in valve tissue fragments under osteogenic conditions, and to demonstrate the possibility of significantly suppressing it using a calcification inhibitor. To validate the model, we tested a Notch inhibitor Crenigacestat (LY3039478), which has been previously shown to have an anti-calcifying effect on interstitial cell of the aortic valve. We demonstrate here an approach to testing calcification inhibitors using an ex vivo model of cultured human aortic valve tissue fragments. Thus, we propose that ex vivo models may warrant further investigation for their utility in studying aortic valve disease and performing pre-clinical assessment of drug efficacy.

The development of acute humoral rejection (AMR) in transplanted organs remains a highly relevant and unresolved issue. This study presents a clinical case of heart transplantation (HT) in a patient with hypertrophic cardiomyopathy transitioning to a restrictive phenotype amid chronic lymphocytic myocarditis. Following HT, the patient developed nosocomial pneumonia, necessitating a reduction in immunosuppressive therapy. On the 12th day post-transplantation, the patient experienced a sudden hemodynamic collapse, which proved fatal. Autopsy examination revealed acute humoral rejection with a predominance of CD16+ cells in the infiltrate, exhibiting high expression of the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) Spike protein on the endothelium and CD16+ cells. Further investigation is required to clarify the role of SARS-CoV-2 in potentially exacerbating AMR development.

Myocardial fibrosis is an important factor in the progression of cardiovascular diseases. However, there is still no universal lifetime method of myocardial fibrosis assessment that has a high prognostic significance. The aim of the study was to determine the significance of ventricular endomyocardial biopsies for the assessment of myocardial fibrosis and to identify the severity of myocardial fibrosis in different cardiovascular diseases. Material and Methods: Endomyocardial biopsies (EMBs) of 20 patients with chronic lymphocytic myocarditis (CM), endomyocardial fragments obtained during septal reduction of 21 patients with hypertrophic cardiomyopathy (HCM), and 36 patients with a long history of hypertensive and ischemic heart disease (HHD + IHD) were included in the study. The control group was formed from EMBs taken on 12–14 days after heart transplantation (n = 28). Also, for one patient without clinical and morphological data for cardiovascular pathology, postmortem myocardial fragments were taken from typical EMB and septal reduction sites. The relative area of fibrosis was calculated as the ratio of the total area of collagen fibers to the area of the whole biopsy. Endocardium and subendocardial fibrosis were not included in the total biopsy area. Results: The relative fibrosis area in the EMBs in the CM patient group was 5.6 [3.3; 12.6]%, 11.1 [6.6; 15.9]% in the HHD + IHD patient group, 13.4 [8.8; 16.7]% in the HCM patient group, and 2.7 [1.5; 4.6]% in the control group. When comparing the fibrosis area of the CM patients in repeat EMBs, it was found that the fibrosis area in the first EMBs was 7.6 [4.8; 12.0]%, and in repeat EMBs, it was 5.3 [3.2; 7.6]%. No statistically significant differences were found between the primary and repeat EMBs (p = 0.15). In ROC analysis, the area of fibrosis in the myocardium of 1.1% (or lower than one) was found to be highly specific for the control group of patients compared to the study patients. Conclusions: EMB in the assessment of myocardial fibrosis has a questionable role because of the heterogeneity of fibrotic changes in the myocardium.

Segmenting terminal villous structures as separable instances is a prerequisite task for quantitative and explainable analysis of placental histopathology. Inspired by the fact that villous structure is typically surrounded by syncytiotrophoblast cells which yield critical hints for segmentation, we focus on designing a contour-based instance segmentation method. Previous contour-based methods usually utilize the confidence of object localization (or classification) as the instance score, without contour scores which explicitly measure the contour refinement quality ( i.e. , the distance discrepancy between the predicted contour and its ground truth). In this paper, we propose an augmented contour Scoring Snake framework, termed as SSnake, which learns both contour deformation and refinement quality estimation. To form contour quality measurement, we devise an axis-aware size-adaptive smooth function mapping from predicted contours to normalized scores in point resolution. Besides, to estimate scores of long-distance cases and strengthen the score learning process, a contour-augmented training scheme is designed for initial box contours. Our method recalibrates instance scores using contour quality by prioritizing instances with finer contours. Experimental results on the inhouse separable villi segmentation dataset and a public cell nucleus segmentation dataset demonstrate that our proposed method significantly outperforms all competitors including state-of-the-art approaches. In villi segmentation dataset, our proposed SSnake achieves 3.7% improvements in COCO APm m over the baseline DeepSnake. The source code is available at https://github.com/Psilym/SSnake.