Histopathological Classification Research Articles

Diagnosis and Treatment of Renal ANCA Vasculitis: A Summary of the Consensus Document of the Catalan Group for the Study of Glomerular Diseases (GLOMCAT)

The document provides a comprehensive overview of the diagnosis, monitoring, and treatment of anti-neutrophil cytoplasmic antibody-associated vasculitis (AAV) with renal involvement, focusing on granulomatosis with polyangiitis (GPA) and microscopic polyangiitis (MPA). It outlines the definitions, clinical presentation, histopathological classification, monitoring strategies, induction and maintenance treatments, as well as special considerations for relapsing, refractory, and frail patients with renal AAV. The document was prepared by the Catalan Group for the Study of Glomerular Diseases (GLOMCAT), which comprises nephrologists with extensive experience in the diagnosis and treatment of AAV patients. Several virtual and face-to-face meetings were held for coordination, section assignments, and content discussion. An exhaustive and systematic search of the literature was carried out, which included, among others, the following databases: PubMed, EMBASE, Cochrane Library, Google Scholar, and ClinicalTrials.gov, as well as the abstract books of national and international congresses. Overall, the document provides a comprehensive guide for clinicians managing patients with renal AAV, offering evidence-based recommendations for diagnosis, monitoring, and treatment across various clinical scenarios.

Reevaluating the variation of cesarean scar defect.

The increasing incidence of cesarean sections has led to a higher prevalence of cesarean scar defects (CSDs), predominantly characterized by postmenstrual bleeding in affected women. CSD manifests in various forms, including isolated myometrial defects, intrauterine cystic protrusions, and extrauterine cystic extensions. The pathophysiological mechanisms underpinning CSD and its associated symptoms remain insufficiently understood. This review explores the pathogenesis of CSD, highlights its morphological characteristics with an emphasis on variable clinical diversity, and addresses the challenges for future research. A comprehensive narrative review was conducted using electronic databases, including PubMed and Google Scholar, to identify 41 relevant literatures published up to December 31, 2023. The myometrium comprises two distinct layers-the inner and outer myometrium-with differences in their origin, structure, and function. Disruptions within these layers contribute to CSD development. Histopathologically, symptomatic CSD may be linked to uterine scar endometriosis, cystic adenomyosis, or endometrial cysts, suggesting that CSD, particularly those necessitating surgical intervention, are not limited to myometrial defects but may also involve iatrogenic endometriosis or adenomyosis, thereby exacerbating clinical symptoms. This review provides an updated understanding of the histopathological features and classification of CSD, with an emphasis on elucidating its underlying pathogenesis.

Real-time segmentation and classification of whole-slide images for tumor biomarker scoring

Histopathology image segmentation and classification are essential for diagnosing and treating breast cancer. This study introduced a highly accurate segmentation and classification for histopathology images using a single architecture. We utilized the famous segmentation architectures, SegNet and U-Net, and modified the decoder to attach ResNet, VGG and DenseNet to perform classification tasks. These hybrid models are integrated with Stardist as the backbone, and implemented in a real-time pathologist workflow with a graphical user interface. These models were trained and tested offline using the ER-IHC-stained private and H&E-stained public datasets (MoNuSeg). For real-time evaluation, the proposed model was evaluated using PR-IHC-stained glass slides. It achieved the highest segmentation pixel-based F1-score of 0.902 and 0.903 for private and public datasets respectively, and a classification-based F1-score of 0.833 for private dataset. The experiment shows the robustness of our method where a model trained on ER-IHC dataset able to perform well on real-time microscopy of PR-IHC slides on both 20x and 40x magnification. This will help the pathologists with a quick decision-making process.

Efficient feature selection for histopathological image classification with improved multi-objective WOA

The difficulty of selecting features efficiently in histopathology image analysis remains unresolved. Furthermore, the majority of current approaches have approached feature selection as a single objective issue. This research presents an enhanced multi-objective whale optimisation algorithm-based feature selection technique as a solution. To mine optimal feature sets, the suggested technique makes use of a unique variation known as the enhanced multi-objective whale optimisation algorithm. To verify the optimisation capability, the suggested variation has been evaluated on 10 common multi-objective CEC2009 benchmark functions. Furthermore, by comparing five classifiers in terms of accuracy, mean number of selected features, and calculation time, the effectiveness of the suggested strategy is verified against three other feature-selection techniques already in use. The experimental findings show that, when compared to the other approaches under consideration, the suggested method performed better on the assessed parameters.

GLUT1 and cerebral glucose hypometabolism in human focal cortical dysplasia is associated with hypermethylation of key glucose regulatory genes.

Focal cortical dysplasia (FCD) is recognized as a significant etiological factor in pharmacoresistant intractable epilepsy, linked with disturbances in neurovascular metabolism. Our study investigated regulation of glucose-transporter1 (GLUT1) and cerebral hypometabolism within FCD subtypes. Surgically excised human brain specimens underwent histopathological categorization. A subset of samples (paired with matching blood) was assessed for DNA methylation changes of glucose metabolism-related genes. We evaluated GLUT1, VEGFα, MCT2, and mTOR expression by western blot analysis, measured glucose-lactate concentrations, and established correlations with patients' demographic and clinical profiles. Furthermore, we investigated the impact of DNA methylation inhibitor decitabine and hypometabolic condition on the uptake of [ 3 H]-2-deoxyglucose and ATPase in epileptic brain endothelial cells (EPI-EC). We observed hypermethylation of GLUT1 and glucose metabolic genes in FCD brain/blood samples and could distinguish FCDIIa/b from mMCD, MOGHE and non-lesional types in brain. Low GLUT1 and glucose-lactate ratios corresponded to elevated VEGFα and MCT2 in FCDIIa/b vs non-lesional tissues, independent of age, gender, seizure-onset, or duration of epilepsy. Increased mTOR signaling in FCDIIa/b tissues was evident. Decitabine stimulation increased GLUT1, decreased VEGFα expression, restored glucose uptake and ATPase activity in EPI-ECs and reduced mTOR and MCT2 levels in HEK cells. We demonstrated: 1) hypermethylation of glucose regulatory genes distinguish FCDIIa/b from mMCD, MOGHE and non-lesional types, 2) glucose uptake reduction is due to GLUT1 suppression mediated possibly by a GLUT1-mTOR mechanism; and 3) DNA methylation regulates cellular glucose update and metabolism. Together, these studies may lead to GLUT1-mediated biomarkers, glucose metabolism and identify early intervention strategies in FCD.

Histopathological image classification of colorectal cancer using a novel supervised contrastive learning approach

Histopathological image classification of colorectal cancer using a novel supervised contrastive learning approach

A comparative study of postadrenalectomy hyperuricemia and renal impairment in patients with unilateral primary aldosteronism: does histopathology subtype matter?

BackgroundPrimary aldosteronism (PA), which is present in 5–18% of hypertensive patients, is a leading cause of secondary hypertension. Adrenalectomy is often recommended for patients with unilateral primary aldosteronism (uPA), yielding good long-term outcomes. PA patients without hyperuricemia and chronic renal failure before adrenalectomy were enrolled in this cohort study. Serum uric acid (SUA) and renal filtration were measured one year post-adrenalectomy. Their relationships with pathologic features, histopathological subtype (classical or nonclassical (HISTALDO consensus)), and vessel stiffness were explored. The aim of this cohort study is to evaluate the correlation between post-adrenalectomy serum uric acid (SUA) levels and estimated glomerular filtration rate (eGFR) with the pathologic features delineated by the HISTALDO consensus. Additionally, the study seeks to assess the impact of these biochemical markers on peripheral vessel stiffness and brachial-ankle pulse wave velocity (baPWV) at a one-year follow-up visit.MethodsThis prospective cohort study included patients (N = 100) diagnosed with uPA who underwent adrenalectomy from Jan 1, 2007 to Dec 31, 2022.ResultsAt follow-up, elevated SUA, hyperuricemia, and a > 25% eGFR decrease were significantly more common in the classical than the nonclassical group. The incidence of postoperative hyperuricemia, herein referred to as post-adrenalectomy hyperuricemia (PAHU), was 29% (29/100) overall, 34.8% (23/66) in the classical group and 17.6% (6/34) in the nonclassical group. The incidence of eGFR reduction > 25% was 33% (33/100), 43.9% (29/66), and 11.8% (4/34), respectively. baPWV decreased more in the classical group than the nonclassical group.ConclusionFor PA patients with PAHU and/or renal impairment, we suggest monitoring SUA, pH, urine uric acid, and urine crystals and performing a KUB study and peripheral vascular and renal sonography (on which pure uric acid stones in the KUB are radiolucent) to determine whether drug intervention is required for cases of asymptomatic PAHU, especially patients in male gender, classical histopathology, or renal impairment.

Enhancing breast cancer histopathological image classification using attention-based high order covariance pooling

Enhancing breast cancer histopathological image classification using attention-based high order covariance pooling

Distinct copy number signatures between residual benign and transformed areas of carcinoma ex pleomorphic adenoma

The mechanisms involved with the pathogenesis of carcinoma ex pleomorphic adenoma (CXPA) seem to be associated with the accumulation of molecular alterations in the pleomorphic adenoma (PA). In this sense, using array-based comparative genomic hybridization (aCGH) a rare series of 27 cases of CXPA and 14 residual PA (rPA) adjacent to the transformation area, we investigated the profile of the copy number alterations (CNAs) comparing benign residual and transformed areas. The main findings were correlated with the histopathological classification by histologic subtype and degree of invasion. The distribution of losses (p = 0.187) and amplifications (p = 0.172) was not statistically different between rPA and CXPA. The number of gains was increased in the transformed areas compared to the benign residual areas (p = 0.005). PLAG1 gain was maintained along the malignant transformation, as it was observed in both residual PA and CXPA samples, likely being an earlier event during transformation. The amplification of GRB7 and ERBB2 may also be an initial step in the malignant transformation of PA to CXPA (salivary duct carcinoma subtype). Furthermore, the amplification of HMGA2 and RPSAP52 were the most prevalent alterations among the studied samples. It was noteworthy that amplified genes in the transformed areas of the tumors were enriched for biological processes related to immune signaling. In conclusion, our results underscored for the first-time crucial CNAs in CXPA, some of them shared with the residual benign area adjacent to the transformation site. These CNAs included PLAG1 gain, as well as amplification of GRB7, ERBB2, HMGA2, and RPSAP52.

Aggressiveness evaluation of borderline serous ovarian tumors by analysis of Psammoma bodies present in cancer tissues using micro-FTIR spectroscopy

Borderline ovarian tumor is a type of tumor with generally low malignant potential. However, these tumors pose diagnostic challenges with benign and malignant epithelial ovarian tumors because the clinical symptoms are similar and investigation procedures for specific diagnosis are still debated. In addition, a small number of borderlines transform into high-grade serous ovarian carcinoma with a poor prognosis. Therefore, tools improving a better characterization of high-risk subtypes of borderline tumors to enable understanding of possible unfavorable evolution are essential for patients’ management. Psammoma bodies (PBs) are microcalcifications found both in serous epithelial ovarian cancer and serous borderline tumors with possible correlation with disease progressionIn this work, the chemical composition of PBs found in the tissues of borderline, high-grade and low-grade ovarian tumors was evaluated using micro-FTIR spectroscopy. Applying principal component analysis to spectral data, it was observed that among the borderline tumors analyzed (1-bl,2-bland3-bl), the PBs of3-blshowed a different chemical content from that of the PBs of the high-grade and low-grade tumors, while the PBs of1-bland2-blappeared to have similar chemical content to the PBs of high- and low-grade tumors. The discriminating wavenumbers were found to be those related to carbonate CO32− (1454, 1413 cm−1and 872 cm−1) and phosphate PO43−(1018 cm−1and 960 cm−1) present in microcalcifications. A higher ratio between peak intensities at 1413 cm−1and 1018 cm−1(I1413/I1018) was observed in the PBs of3-blcompared with those of high- and low-grade ovarian carcinoma patients, which correlates with higher CO32− content. On the other hand, the PBs of1-bland2-blshowed a CO32−level close to that of the PBs of high- and low-grade patients. Several studies on microcalcifications in breast carcinoma have reported that increased carbonate content is related to decreased tumor aggressiveness. Therefore, case bl-3 appeared to be the less aggressive. The results obtained from FTIR analysis were in agreement with histopathological tumor classification and molecular analysis for BRAFV600E. The FTIR technique could become a reliable tool for identifying borderline low- and high-risk tumors.

Few-shot learning based histopathological image classification of colorectal cancer

Background Colorectal cancer is a prevalent and deadly disease worldwide, posing significant diagnostic challenges. Traditional histopathologic images classification is often inefficient and subjective. Although some histopathologists use computer-aided diagnosis (CAD) to improve efficiency, these methods depend heavily on extensive data and specific annotations, limiting their development. To address these challenges, this paper proposes a method based on few-shot learning. Methods This study introduces a few-shot learning approach that combines transfer learning and contrastive learning to classify colorectal cancer histopathology images into benign and malignant categories. The model comprises modules for feature extraction, dimensionality reduction, and classification, trained using a combination of contrast loss and cross-entropy loss. In this paper, we detail the setup of hyperparameters:n-way, k-shot, β and the creation of support, query, and test datasets. Results Our method achieved over 98% accuracy on a query dataset with 35 samples per category using only 10 training samples per category. We documented the model’s loss, accuracy, and the confusion matrix of the results. Additionally, we employed the t-SNE algorithm to analyze and assess the model’s classification performance. Conclusion The proposed model demonstrates significant advantages in accuracy and minimal data dependency, performing robustly across all tested n-way, k-shot scenarios. It consistently achieved over 93% accuracy on comprehensive test datasets, including 1916 samples, confirming its high classification accuracy and strong generalization capability. Our research advances the use of few-shot learning in medical diagnostics, and also lays the groundwork for extending it to deal with rare, difficult-to-diagnose cases.

Histopathological and immunohistochemical investigation of mammary tumors in female cats in Northeast Algeria

Cancer is a leading cause of feline mortality globally. This study focuses on delineating mammary gland tumor prevalence and anatomopathological characteristics in cats from northeastern Algeria. Encompassing the period from January 2021 to March 2022, the research included 50 cats from Constantine and Annaba provinces, revealing an overall 20% feline mammary tumors (FMT) prevalence. Siamese cats exhibited a higher rate compared to crossbred cats, with a mean age of positively diagnosed cats at 9±0.3 years. Histopathological classification identified 20% of tumors as malignant, specifically squamous cell carcinoma, cribriform carcinoma, and comedocarcinoma. In conclusion, further epidemiological investigations are essential to understand the risk factors in the initiation and progression of these health issues. In contrast to canine species, FMTs are less diverse, predominantly simple malignant tumors. Benign FMTs are infrequent, and the existence of complex and mixed tumors in felines remains unclear. This study selected three FMT types for immunohistochemical analyses, revealing unusual histological characteristics. A set of three malignant tumors exhibited an epithelial/myoepithelial population, with consistent myoepithelial immunohistochemical signatures. All Grade I malignant tumors resulted in subjects surviving one-year post-diagnosis. Morphologically, we propose categorizing them as feline ductal/canalicular adenoma/carcinoma and feline intracanalicular papillary adenoma/carcinoma, respectively. These findings contribute novel insights to FMT classification and are valuable for prognostic studies.

Histopathologic classification of actinic keratosis severity is associated with burden of keratinocyte carcinoma

Histopathologic classification of actinic keratosis severity is associated with burden of keratinocyte carcinoma

Transformer based on multi-scale local feature for colon cancer histopathological image classification

Colon cancer histopathological image recognition is an important method in the early screening of colon cancer. At present, most whole slide images (WSIs) classification models only consider the features of a single patch, and do not consider the features of the WSIs region. To expand the receptive field of the patches and obtain its surrounding pathological information, this paper proposes a transformer based on multi-scale local feature for colon cancer histopathological image classification model. The model samples patches based on farthest point sampling (FPS). A multi-scale grouping scheme is also proposed to capture WSI local regions. Then the classification labels, feature information and local area information of sampled patches are embedded into the transformer encoder. In addition, the focal loss function is adopted to solve the problem of unbalanced categories of colon cancer histopathological images. Experimental results demonstrate that our model surpasses competing methods in performance on both hospital colon cancer datasets and The Cancer Genome Atlas(TCGA) colon cancer datasets.

Interobserver variability in the histopathological classification and grading of dysplasia in elevated colon lesions in the city of Lima

Colonic polyp refers to lesions that exhibit a protrusion of the mucosa, regardless of histology. The most recent WHO classification is based on a better understanding of these lesions; however, its application in daily practice could be subject to interobserver variability biases that could have clinical implications. Objectives: To determine the interobserver variability in the histopathological reporting and grading of dysplasia of samples obtained from elevated colon lesions in a private laboratory in the city of Lima. Materials and methods: Observational, descriptive, and prospective study: Case series type. All biopsies of elevated colon lesions received over a period of 3 months were evaluated by two observers without clinical information of the cases, to diagnose the lesions according to the WHO classification. In cases of diagnostic differences, the cases were evaluated together to reach a consensus. Results: A Kappa coefficient value of 0.458 was obtained in the diagnostic classification of elevated colon lesions, while a Kappa value of 0.416 in the evaluation of dysplasia; indicating moderate agreement. Conclusions: Despite achieving moderate agreement between evaluators, this work demonstrates the importance of not only relying on morphological criteria for diagnostic classification, but also including criteria of location and size of these lesions to increase diagnostic accuracy.

Grade 1, 2, and 3 Multifocal Type 1 Gastric Neuroendocrine Tumor In The Same Patient, Case Report.

Objective: Gastric neuroendocrine tumors (GNETs) are a rare but increasingly recognized subset of neuroendocrine tumors, primarily due to advancements in diagnostic techniques. These tumors exhibit varied clinical presentations and prognoses, necessitating precise histopathological classification for appropriate management. GNETs are classified into four types, with Type 1 being the most common and often associated with autoimmune atrophic gastritis. Case: This case report presents a 41-year-old male diagnosed with multifocal, grade 2 GNET, initially misclassified as grade 3 at an external facility. Despite the usual indolent nature of Type 1 GNETs, total gastrectomy and D1-D2 lymph node dissection were performed due to the multifocal nature of the tumors and positive margins from previous resections. Immunohistochemical analysis confirmed the diagnosis, with a Ki-67 index of <1%. Despite initial aggressive histological features, the patient showed no recurrence at the 5-month follow-up. Conclusion: This case highlights the challenges in grading and managing GNETs, emphasizing the importance of multidisciplinary approaches and careful pathological examination to guide treatment.

Histopathologic classification and immunohistochemical features of papillary renal neoplasm with potential therapeutic targets.

Papillary renal cell carcinoma (pRCC) is the second most common histological subtype of renal cell carcinoma and is considered a morphologically and molecularly heterogeneous tumor. Accurate classification and assessment of the immunohistochemical features of possible therapeutic targets are needed for precise patient care. We aimed to evaluate immunohistochemical features and possible therapeutic targets of papillary renal neoplasms. We collected 140 papillary renal neoplasms from three different hospitals and conducted immunohistochemical studies on tissue microarray slides. We performed succinate dehydrogenase B, fumarate hydratase, and transcription factor E3 immunohistochemical studies for differential diagnosis and re-classified five cases (3.6%) of papillary renal neoplasms. In addition, we conducted c-MET, p16, c-Myc, Ki-67, p53, and stimulator of interferon genes (STING) immunohistochemical studies to evaluate their pathogenesis and value for therapeutic targets. We found that c-MET expression was more common in pRCC (classic) (p = .021) among papillary renal neoplasms and Ki-67 proliferation index was higher in pRCC (not otherwise specified, NOS) compared to that of pRCC (classic) and papillary neoplasm with reverse polarity (marginal significance, p = .080). Small subsets of cases with p16 block positivity (4.5%) (pRCC [NOS] only) and c-Myc expression (7.1%) (pRCC [classic] only) were found. Also, there were some cases showing STING expression and those cases were associated with increased Ki-67 proliferation index (marginal significance, p = .063). Our findings suggested that there are subsets of pRCC with c-MET, p16, c-MYC, and STING expression and those cases could be potential candidates for targeted therapy.

Data Augmentation in Histopathological Classification: An Analysis Exploring GANs with XAI and Vision Transformers

Generative adversarial networks (GANs) create images by pitting a generator (G) against a discriminator (D) network, aiming to find a balance between the networks. However, achieving this balance is difficult because G is trained based on just one value representing D’s prediction, and only D can access image features. We introduce a novel approach for training GANs using explainable artificial intelligence (XAI) to enhance the quality and diversity of generated images in histopathological datasets. We leverage XAI to extract feature information from D and incorporate it into G via the loss function, a unique strategy not previously explored in this context. We demonstrate that this approach enriches the training with relevant information and promotes improved quality and more variability in the artificial images, decreasing the FID by up to 32.7% compared to traditional methods. In the data augmentation task, these images improve the classification accuracy of Transformer models by up to 3.81% compared to models without data augmentation and up to 3.01% compared to traditional GAN data augmentation. The Saliency method provides G with the most informative feature information. Overall, our work highlights the potential of XAI for enhancing GAN training and suggests avenues for further exploration in this field.

Pathology diagnosis of intraoperative frozen thyroid lesions assisted by deep learning

BackgroundThyroid cancer is a common thyroid malignancy. The majority of thyroid lesion needs intraoperative frozen pathology diagnosis, which provides important information for precision operation. As digital whole slide images (WSIs) develop, deep learning methods for histopathological classification of the thyroid gland (paraffin sections) have achieved outstanding results. Our current study is to clarify whether deep learning assists pathology diagnosis for intraoperative frozen thyroid lesions or not.MethodsWe propose an artificial intelligence-assisted diagnostic system for frozen thyroid lesions that applies prior knowledge in tandem with a dichotomous judgment of whether the lesion is cancerous or not and a quadratic judgment of the type of cancerous lesion to categorize the frozen thyroid lesions into five categories: papillary thyroid carcinoma, medullary thyroid carcinoma, anaplastic thyroid carcinoma, follicular thyroid tumor, and non-cancerous lesion. We obtained 4409 frozen digital pathology sections (WSI) of thyroid from the First Affiliated Hospital of Sun Yat-sen University (SYSUFH) to train and test the model, and the performance was validated by a six-fold cross validation, 101 papillary microcarcinoma sections of thyroid were used to validate the system’s sensitivity, and 1388 WSIs of thyroid were used for the evaluation of the external dataset. The deep learning models were compared in terms of several metrics such as accuracy, F1 score, recall, precision and AUC (Area Under Curve).ResultsWe developed the first deep learning-based frozen thyroid diagnostic classifier for histopathological WSI classification of papillary carcinoma, medullary carcinoma, follicular tumor, anaplastic carcinoma, and non-carcinoma lesion. On test slides, the system had an accuracy of 0.9459, a precision of 0.9475, and an AUC of 0.9955. In the papillary carcinoma test slides, the system was able to accurately predict even lesions as small as 2 mm in diameter. Tested with the acceleration component, the cut processing can be performed in 346.12 s and the visual inference prediction results can be obtained in 98.61 s, thus meeting the time requirements for intraoperative diagnosis. Our study employs a deep learning approach for high-precision classification of intraoperative frozen thyroid lesion distribution in the clinical setting, which has potential clinical implications for assisting pathologists and precision surgery of thyroid lesions.

Translating biological insights into improved management of endometrial cancer.

Endometrial cancer (EC) is the most common gynaecological cancer among women in high-income countries, with both incidence and mortality continuing to increase. The complexity of the management of patients with EC has evolved with greater comprehension of the underlying biology and heterogeneity of this disease. With a growing number of novel therapeutic agents available, emerging treatment regimens seem to have the potential to helpto address the concerning trends in EC-related mortality. In this Review, we describe the epidemiology, histopathology and molecular classification of EC as well as the role of the new (2023) International Federation of Gynecologists and Obstetricians (FIGO) staging model. Furthermore, we provide an overview of disease management in the first-line and recurrent disease settings. With increasing use of molecular profiling and updates in treatment paradigms, we also summarize new developments in this rapidly changing treatment landscape.