Papillary thyroid carcinoma (PTC) is biologically heterogeneous, yet its prognostic diversity is inadequately captured by conventional staging. The WHO 2022 classification introduced differentiated high-grade thyroid carcinoma (DHGTC) and mandated systematic subtyping, but institutional data from South Asian centres remain sparse. We reclassified a South Indian tertiary PTC cohort under the WHO 2022 framework; characterised preoperative ACR TI-RADS (American College of Radiology Thyroid Imaging Reporting and Data System) and TBSRTC (The Bethesda System for Reporting Thyroid Cytopathology) correlates of WHO subtype; and evaluated tumour budding, tumour-infiltrating lymphocytes (TILs), and neutrophil-to-lymphocyte ratio (NLR) as predictors of extrathyroidal extension (ETE) and lymph node metastasis. Retrospective analysis of 173 consecutive PTC cases were reclassified per WHO 2022, staged per AJCC 8th edition, and evaluated for tumour budding, TILs (peri- and intratumoural), NLR, ACR TI-RADS, and TBSRTC. Correspondence analysis, ROC curves, and binary logistic regression were performed. Classic PTC predominated (68.8
Pediatric bone tumors are increasingly sampled through image-guided biopsies. Evolution of molecular and diagnostic adjuncts have enabled diagnosis of these challenging lesions with limited diagnostic tissue. Radiologic correlation remains critical in the evaluation of these lesions and sampling quality can affect diagnostic interpretation. Our understanding of giant-cell lesions has expanded with the identification of highly specific histone mutations in giant cell tumors and chondroblastoma. Meanwhile, molecular testing has allowed validation of newer entities such as Xanthogranulomatous Epithelial tumor/Keratin-Positive Giant cell tumor while clarifying the well-defined lesions such as aneurysmal cyst. Tissue preservation and avoidance of harsh acid decalcification techniques is the mainstay to allow preservation of nucleic acids and application of newer ancillary studies. In this review, we provide an overview of the current diagnostic approach in pediatric bone tumors with key updates.
Tissue analysis is considered the gold standard for the diagnosis of a wide spectrum of disorders. However, pathologists perform labor-intensive evaluations to ensure accurate results. Computational pathology has made significant advances in the development of task-specific predictive models. Nevertheless, traditional pixel- or texture-based features often fail to capture both local and global structural patterns together with their spatial organization. This study developed TopoBoW, a computational framework to objectively characterize morphological patterns using local and global microscopy image features. We developed TopoBoW by integrating Topological Data Analysis (TDA) and Bag-of-Visual-Words (BoVW), combining it with an attention-guided multi-layer perceptron (MLP) trained to distinguish between healthy and pathological muscle tissue. TDA captures global structural features, whereas BoVW encodes local textural. We also utilized visualizations to examine the statistical behavior of feature vectors across disease classes and healthy controls, evaluating their discriminative ability. We compare TopoBoW with several baseline and deep learning models, including TDA-based models, histogram of oriented gradients (HOG), XGBoost classifiers, attention-based MLP models, and modern convolutional and transformer architectures. TopoBoW demonstrated state-of-the-art performance on muscle tissue classification within the image-level cross-validation framework applied to the present preclinical dataset, and outperformed all baselines in terms of all classification criteria, including accuracy, F1-score, and AUC. With its interpretable feature-based computational framework, TopoBoW can assist with pathological research, education, and interactive diagnostic workflows by integrating global structural and local textural information from images.
Although Wilms tumor is the most common malignant renal tumor of childhood, it is an overall rare malignancy with a variety of histological appearances. As clinical trials have sought to further identify groups of patients who can benefit from escalation or de-escalation of therapy, an increasing number of histopathological and molecular factors have become important factors in patient risk stratification. This manuscript reviews the clinical presentation and typical histologic findings in Wilms tumor. The differential diagnostic considerations are explored, with practical recommendations for immunohistochemical and molecular workup to aid in accurate diagnosis. Finally, important known and emerging elements relevant to risk stratification are outlined, including pre- and post-therapy histological classification, staging, and important molecular findings.
Telepathology, enabled by whole-slide imaging, digital communication, and cloud-based platforms, and artificial intelligence (AI), represents a key innovation in modern pathology practice, offering opportunities for virtual diagnosis, consultation, education, and multidisciplinary collaboration. Given the large inequity in the current distribution of pathology services in India, telepathology could play an important role in bridging the gap between urban and rural areas of the country. This narrative review aimed to present the status of telepathology in India through a description of technological advances, clinical applications, initiatives, and regulatory aspects, including the emerging role of artificial intelligence (AI) in telepathology. The search strategy used PubMed/MEDLINE, Scopus, Google Scholar, and other relevant resources identified eligible documents published in English between 1996 and 2025. Government documents and reports were also examined for relevant information regarding the study. Telepathology experiences in other low- and middle-income countries (LMICs) were also similarly reviewed and synthesized for comparative analysis. Digital pathology, driven by telepathology, is being increasingly adopted in India, both in academic and tertiary care, and select private healthcare institutions, as enabled by the Ayushman Bharat Digital Mission and similar initiatives. However, there are multiple challenges to the broader adoption of telepathology in India, including high infrastructure costs, limited accessibility in rural areas, workforce training, interoperability, and medico-legal and regulatory issues. While AI-based approaches offer great benefits in pathology, most tools need to be validated on Indian cohorts before they can be deployed in practice. Telepathology has the potential to improve equity in access to pathology services in India. Addressing the key challenges to adoption and building appropriate regulatory and workforce development frameworks will be critical to realizing the benefits of this technology in India.
Papillary thyroid carcinoma (PTC) is the most frequently encountered thyroid malignancy, yet its coexistence with intrathyroidal heterotopic bone formation (HBF) and extramedullary hematopoiesis (EMH) is exceedingly rare. This report describes, to our knowledge, the first published case of oncocytic PTC occurring alongside EMH and HBF. A literature review of previously documented cases of intrathyroidal HBF and EMH, along with a discussion on their pathophysiology, was conducted. A 49-year-old woman was presented with a calcified mass in the right thyroid lobe and an enlarged cervical lymph node. Preoperative fine-needle aspiration cytology of the lymph node suggested metastatic papillary thyroid carcinoma. The patient underwent total thyroidectomy with central neck lymph node dissection. Histopathological examination revealed multifocal PTCs on both thyroid lobes, including an oncocytic subtype adjacent to the area of mature lamellar bone with intertrabecular trilineage hematopoiesis, and multiple lymph node metastasis. Extensive lymphocytic infiltration consistent with Hashimoto thyroiditis was also observed. Our case illustrates a unique combination of pathologic findings: intrathyroidal HBF, EMH, and oncocytic PTC. It highlights the diagnostic challenges posed by these rare entities and emphasizes the importance of thorough histopathological evaluation when encountering calcified thyroid nodule on imaging study. Additionally, this report contributes to the limited literature on this phenomenon and discusses the current understanding of its pathogenesis.
Multiple giant cystic-solid hemangioblastomas arising in the cerebellopontine angle (CPA) and extending to both cerebellar hemispheres are exceedingly uncommon. We report the case of a 54-year-old female patient who was admitted with to the hospital with a two-month history of headache and hearing loss. On physical examination, the patient was alert, and Romberg’s sign was positive. Magnetic resonance imaging (MRI) revealed the presence of multiple irregular cystic-solid abnormal signal shadows in the right CPA and bilateral cerebellar hemispheres. Total tumor resection was performed via a midline suboccipital approach, resulting in marked relief of the patient’s headache symptoms and preservation of cranial nerve function. The diagnosis of hemangioblastoma was confirmed by postoperative immunohistochemical staining.
Chromosomal translocations of 5q31-33 result in rearrangement of the PDGFRB gene (platelet-derived growth factor receptor beta), leading to a unique group of myeloid neoplasms with frequent eosinophilia. More than 40 fusion partners of PDGFRB have been reported, and despite molecular and clinical heterogeneity, patients with PDGFRB rearrangement achieve rapid responses to tyrosine kinase inhibitor treatment. Therefore, detection of these fusions is of great importance for accurate diagnosis and therapeutic intervention. Here, we report a case with delayed diagnosis of myeloid neoplasm with eosinophilia and PDGFRB rearrangement as the result of a cytogenetically cryptic PCM1::PDGFRB fusion. After years of fatigue and blood count abnormalities including leukocytosis and eosinophilia, we identified a rare PCM1::PDGFRB fusion by RNA sequencing. Analysis of retrospective bone marrow samples revealed the presence of fusion transcripts up to six years prior to RNA sequencing. Upon identification of PDGFRB rearrangement, treatment was changed to imatinib (100 mg/daily) with immediate effect. After six months of imatinib treatment, the patient achieved clinical remission and a reduction in PCM1::PDGFRB fusion transcripts, and molecular remission was detected 1.5 years after treatment initiation.
Histological grading of lung adenocarcinoma is limited by interobserver variability, particularly when distinguishing noninvasive lepidic growth from invasive patterns. This distinction depends on evaluation of the alveolar elastic fiber framework, which is often insufficiently visualized on routine hematoxylin and eosin (H E) slides. We developed a deep learning framework to improve grading objectivity by computationally visualizing elastic fiber–related architecture from standard H E images. A dual-stream EfficientNet-B0 classifier was trained using spatially coregistered H E and eosin-based elastin fluorescence (EBEF) images. To enable clinical deployment without additional staining or fluorescence microscopy, a Pix2Pix-HD generative adversarial network was trained to synthesize high-fidelity virtual EBEF images from H E alone. The resulting automated pipeline classified histological patterns, quantified pattern proportions, and assigned tumor grades. Performance was evaluated on independent multicenter cohorts, with ablation analyses assessing key pipeline components. Prognostic relevance was explored using a curated TCGA lung adenocarcinoma cohort. The benchmark dual-stream model using real H E and EBEF achieved 89.3
Spinal meningioma subtype and grade still rest on haematoxylin and eosin (H E) morphology, but permanent sections become available only after fixation and embedding, and intraoperative assessment of fresh tissue relies mainly on frozen section. Dynamic cell imaging (DCI), a label-free readout from dynamic full-field optical coherence tomography, images unprocessed specimens within minutes. Whether its regional signal corresponds to H E in spinal meningioma has not been described. We imaged nine fresh ex vivo spinal meningioma specimens by DCI on an active phase modulation-assisted dynamic full-field OCT (APMD-FFOCT) platform. All specimens were transported on ice and imaged at approximately 60 min after resection: eight CNS WHO grade 1 tumours (psammomatous, n = 3; transitional, n = 2; meningothelial, n = 1; not further subtyped, n = 2) and one meningioma, CNS WHO grade 3. Every specimen had a specimen-level H E reference from the same fragment, without pixel-level co-registration. Six author-defined DCI features were recorded descriptively against conventional H E, Ki-67, and available immunohistochemistry. Selected DCI-derived virtual H E renderings were compared visually with conventional H E but were not used as diagnostic references. Diagnostic accuracy, blinded subtype assignment, reader agreement, and ROC analysis were not assessed. In all three psammomatous cases, DCI showed round or concentric signal-poor foci within whorl-like regions; specimen-level H E showed corresponding psammoma bodies and meningothelial whorls. Both transitional cases showed mixed fascicular and whorl-like patterns; meningothelial case and the two grade 1 cases without a specific histological subtype showed sheet-like, lobular, or mixed patterns. Dark fibrillar DCI signal was compatible with collagenous stroma. The grade 3 case showed disorganised hypercellular texture without whorls and a Ki-67 index of 70
Nodular fasciitis (NF) is a benign myofibroblastic tumor characterized by rapid growth, self-limiting course, and rearrangement of the USP6 gene. While NF can occur in the head and neck region, cases originating within the nasal cavity are exceedingly rare. We herein report a case of NF in the nasal vestibule of a female patient, presenting as a polypoid mass with surface erosion and bloody discharge. The lesion progressively enlarged, resulting in obstructive symptoms. Histopathological and immunohistochemical findings were diagnostic of NF despite its unusual location. Fluorescence in situ hybridization (FISH) confirmed a USP6 gene rearrangement. The patient remained free of recurrence 120 months after surgical resection. We summarize the clinicopathological features of this case along with four previously reported cases of nasal NF. Compared with NF at typical sites, nasal NF demonstrates distinctive characteristics, including a female predominance, a predilection for the right side, and a predominantly myxoid histology. Owing to its acute onset, rapid growth, high cellularity, and frequent mitotic activity in the absence of infection, NF often mimics malignant tumors and is frequently misdiagnosed as sarcoma. Given its extreme rarity, nasal NF carries a particularly high risk of being misdiagnosed as malignancy.
Whole-slide images (WSIs) in digital pathology are generated at gigapixel resolution, leading to substantial storage and data management demands. Lossy image compression is commonly used to mitigate these challenges. However, its impact on deep learning (DL)–based image analysis, particularly for detailed segmentation tasks, remains insufficiently characterized. DL models may be sensitive to subtle compression artifacts, underscoring the need for systematic evaluation. We evaluated JPEG2000 compression effects on tile-level tumor segmentation using lung adenocarcinoma WSIs. Eighty-six WSIs annotated by four board-certified pathologists were subdivided into nonoverlapping 512 × 512 tiles at 20× magnification. To assess architectural robustness, we trained CNN-based models (U-Net with MobileNetV3, ResNet-18, ResNet-50 encoders) and a Transformer-based model (SegFormer) exclusively on lossless PNG images. These models were evaluated on test tiles compressed using JPEG2000 at rates ranging from 1 (lossless) to 80. Segmentation performance was assessed using the Dice coefficient. Image quality was quantified using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and the no-reference Perception-based Image Quality Evaluator (PIQE). Storage efficiency was evaluated relative to uncompressed TIFF images. Segmentation performance remained stable at mild compression levels, with a marginal decrease of approximately 1.7
The development and clinical application of novel HER2-targeted antibody-drug conjugates (ADCs) have significantly improved outcomes for breast cancer patients with HER2-low expression. The efficacy of such therapies critically depends on accurate assessment of HER2-low status. However, immunohistochemical (IHC) interpretation of HER2-low breast cancer faces multiple challenges due to tumor heterogeneity and interobserver variability among pathologists. This study aimed to develop a deep learning-based framework for analyzing hematoxylin and eosin (H E) stained whole-slide images (WSIs) of breast cancer to achieve precise prediction of HER2-low status while providing interpretable evidence. We retrospectively collected 776 cases of invasive breast carcinoma diagnosed at the Affiliated Hospital of Zunyi Medical University between January 2019 and April 2023 to construct a HER2-low expression dataset. Leveraging an ImageNet-pretrained ResNet50 model for feature extraction and a CLAM (Clustering-constrained Attention Multiple Instance Learning) model with 10-fold cross-validation, our framework demonstrated robust performance on both validation and test sets. Critical HER2-low predictive regions were visualized using attention heatmaps to enhance model interpretability. The mean AUC of the model was 0.613 ± 0.118 on the validation set, and 0.608 ± 0.104 on the test set. The attention heatmap visualization provided biologically plausible explanations for model predictions, offering reliable decision-support tools for pathologists.
Bladder cancer is the most common malignancy of the urinary tract and is often treated with radical cystectomy with lymph node dissection, followed by a thorough pathological evaluation of the dissected nodes. This is crucial for both accurate prognosis and successful treatment. However, histopathological lymph node examination is labor-intensive and time-consuming. To develop a supervised deep learning model for detecting nodal metastases in bladder cancer, and to evaluate its influence on pathologists’ assessment efficiency. This study included 100 histopathological slides representing lymph nodes collected between 2015 and 2024 from the Sahlgrenska University Hospital and scanned into whole slide images, divided into training and validation/test sets. The algorithm was trained with 3437 pixelwise annotations. In the validation set, 50 regions containing normal tissue and metastasis were assessed by AI and two specialist pathologists as validators. In the test set, two pathologists reviewed entire slides and measured review times without, and then, after the washout period, with AI assistance. In the test set, the AI model achieved a sensitivity of 100
This case report describes a novel subtype of testicular sex cord-stromal tumor, termed the “inflammatory and nested testicular sex cord tumor”, which is characterized by a specific EWSR1::ATF1 gene fusion. We present the clinicopathological features of this case to enhance the understanding of this extremely rare tumor. A 45-year-old male patient presented with a right testicular mass that had been present for six years without an identifiable cause. MRI conducted revealed a round nodule in the right testicular area, measuring approximately 38 × 28 mm, with relatively well-defined margins. The tumor exhibited a nodular growth, consisting of epithelial-like cells with abundant clear cytoplasm arranged in solid nests or sheets. Fibrous connective tissue surrounded the epithelial-like tumor nests, and focal inflammatory cell infiltration was observed within the stroma and tumor periphery. Immunohistochemistry showed membranous positivity for α-inhibin in the epithelial-like component. Molecular testing revealed an EWSR1::ATF1 gene fusion, leading to a final diagnosis of inflammatory and nested testicular sex cord tumor. We report a novel subtype of testicular sex cord-stromal tumor, distinct from conventional forms, characterized by nest-like growth of clear epithelial-like tumor cells, focal inflammatory cell infiltration, and the presence of the EWSR1::ATF1 gene fusion. This case provides further evidence that supports the fusion pattern and clinicopathological basis for the newly proposed subtype of testicular sex cord-stromal tumor, inflammatory and nested testicular sex cord tumor.
Diagnostic errors in pathology remain a significant contributor to patient harm despite advances in laboratory automation and quality management systems. Failure Mode and Effects Analysis (FMEA) provides a structured approach to the prospective identification and prioritization of workflow risks, while artificial intelligence (AI) offers emerging capabilities in image analysis, data validation, and workflow monitoring. In this study, we surveyed 43 pathologists to characterize commonly encountered diagnostic errors across the pathology workflow and found that errors were most prevalent in the pre-examination phase. These findings informed an FMEA-based risk assessment that identified high-priority failure modes. Building on these insights, we propose a conceptual framework that integrates agentic AI with FMEA-driven quality management. In this model, AI systems can enhance error detection, reduce failures, and enable continuous recalibration of risk through dynamic data feedback. This work is intended as a hypothesis-generating and conceptual contribution. Prospective validation, standardized performance metrics, and real-world implementation studies will be necessary to determine the clinical and operational impact of such integrated systems.
Accurate classification of Isocitrate Dehydrogenase (IDH) mutation status is crucial for the diagnosis and treatment of adult-type diffuse gliomas as defined by the 2021 World Health Organization (WHO) Classification. However, conventional histological and molecular diagnostics are time-consuming, labor-intensive, costly, and often limited in accessibility. Recent advances in artificial intelligence have enabled automated and unbiased glioma classification directly from histopathological images, but challenges remain in capturing complex pathological and molecular features effectively. In this study, we propose FOCUS (Feature Optimization and Cascaded Unified Screening), an integrated framework for IDH mutation status classification in gliomas using glioma pathology slides. The histopathological images are divided into patches, from which a Vision Transformer (ViT) extracts interpretable features related to nuclear morphology and tumor progression–associated protein expression. A Patch-based Graph Convolutional Network (PatchGCN) further aggregates spatial context to capture both local morphology and global tumor heterogeneity. A cascaded feature selection strategy is employed to refine biomarker identification, followed by a machine learning classifier for final classification. Using the proposed framework, the Support Vector Machine (SVM) demonstrated promising performance on a dataset of 73 patients (accuracy = 0.902, AUC = 0.909). These results highlight the potential of the FOCUS framework as a robust and interpretable tool for IDH mutation status classification, providing a computational approach to distinguish IDH-mutant (astrocytoma and oligodendroglioma) from IDH-wildtype (glioblastoma) tumors.
To investigate the CT and MRI features of pancreatic colloid carcinoma (PCC) and to correlate imaging findings with histopathological characteristics. The CT and MRI images and clinical data of 15 patients with PCC confirmed by surgical resection and histopathological examination from August 2009 to October 2023 were retrospectively analyzed. All 15 PCC lesions presented as single masses, occurring in 8 males and 7 females (mean age 66 ± 8.4 years). The majority of lesions (73
Primary pulmonary lymphoepithelial carcinoma (PPLEC) is a rare Epstein–Barr virus (EBV)-associated subtype of lung cancer classified under pulmonary squamous cell carcinoma (PSCC) in the fifth WHO classification of thoracic tumors. However, its clinicopathological features remain poorly defined. This study compared the histomorphological characteristics and prognostic outcomes of PPLEC and conventional non-keratinizing PSCC, a morphologically mimicking tumor entity. We retrospectively analyzed 103 Epstein-Barr virus-encoded small RNA (EBER)-positive PPLEC cases and 86 PSCC cases diagnosed at Shanghai Pulmonary Hospital from October 2014 to August 2023. Based on tumor morphology and tumor-infiltrating lymphocyte (TIL) density, lesions were categorized as stromal lymphocyte-rich or lymphocyte-poor subtypes. Clinicopathological features, immunohistochemistry, molecular profiles, and survival outcomes were evaluated. Compared with patients with PSCC, PPLEC cases presented a higher female proportion (37.9
