Objective Growing interest in new radiotherapy strategies for early-stage glottic cancer highlights the importance of reviewing current treatment outcomes. This nationwide study presents the incidence, survival, recurrences, and laryngectomies for these patients.Methods Patients diagnosed with cT1-2N0M0 glottic squamous cell carcinoma (SCC) between 2015 and 2021 in the Netherlands were included. Patients diagnosed between 2015 and 2019 were analyzed for survival, recurrences, and laryngectomies after radiotherapy treatment.Results A total of 2214 patients were diagnosed with early-stage glottic SCC. A total of 826 patients were treated with radiotherapy between 2015 and 2019. The 5-year overall survival, relative survival, and recurrence-free survival after radiotherapy were 75%, 88%, and 86%, respectively. Of the 826 patients, 47 (6%) underwent laryngectomy. Only four (0.5%) patients had a laryngectomy due to severe radiation toxicity.Conclusion This nationwide study demonstrates that radiotherapy for early-stage glottic SCC results in excellent oncological outcomes. Radiation-induced laryngectomies for this treatment are extremely rare.

Salivary gland tumors are rare and morphologically diverse, posing both diagnostic and scientific challenges. This study presents the first phase of the SALV-Dataset Registry; a nationwide, expertly curated, and fully digitized clinicopathological resource, designed to support research and develop artificial intelligence (AI) tools assisting in salivary gland tumor pathology diagnostics. Salivary gland tumor resections diagnosed at the Leiden University Medical Center (1999–2024) were collected through the Dutch national network and registry for histo- and cytopathology (PALGA). In total, 685 cases were included. Hematoxylin- and eosin-stained slides were digitized and independently reviewed by three teams of head and neck pathologists, in line with the 2023 WHO Classification of Head and Neck Tumours. Discordant and ambiguous cases were resolved in consensus meetings, with access to immunohistochemistry, molecular analysis, and clinical data. Interobserver agreement among the three teams was quantified (Fleiss’ kappa), and agreement between the original and consensus diagnosis was determined (Cohen’s kappa). Of the 685 tumors, 75

Abstract Accurate, reproducible interpretation of kidney allograft biopsies is critical for the diagnosis of graft injury and for informing prognosis and clinical management. The international Banff classification is a consensus diagnostic system based on semiquantitative histological lesion scoring according to either lesion extent or severity in kidney transplant biopsies. However, pathologist scoring is limited by interobserver variability, constrained scalability, and the inherent nature of the scoring system itself. Here we present BanffNET, a weakly supervised, probabilistic deep learning framework that combines self-supervised feature extraction with a novel Bayesian multiple-instance learning framework to predict (continuously) the full spectrum of Banff lesion scores directly from whole-slide images (WSIs). Using lesion-specific aggregation functions tailored to localized (modeling severity) and diffuse histological lesions (modeling extent), BanffNET generates interpretable, patch-level probability maps and calibrated slide-level scores. BanffNET’s performance was assessed relative to consensus, biological correlates of rejection and clinical outcome, demonstrating superior consistency, transportability and generalization. Trained on 7,533 WSIs from three cohorts, BanffNET demonstrates consistent performance on 12,687 WSIs across five external validation cohorts, matching or surpassing individual expert pathologists across lesion assessments. BanffNET scores align more closely than pathologist Banff scores with molecular profiles of rejection, offering an objective, transparent, biologically grounded framework for computational pathology with relevance beyond kidney transplantation.

SMARCB1-deficient sinonasal carcinoma (SDSC) is a rare, highly aggressive malignancy with limited therapeutic options and no established preclinical models. Here, single-nucleus RNA sequencing (snRNAseq), spatial transcriptomics, and ex vivo patient-derived tissue slice culture (TSC) were combined to resolve intratumoral heterogeneity, niche organization, and treatment vulnerabilities in an index SDSC. snRNAseq identified three malignant subpopulations, including two specialized states marked by ALDH1A1 and NTN4. Spatial profiling mapped these states to distinct niches. The ALDH1A1+ compartment localized to a basal-associated niche with intermingled p63-positive basal cells adjacent to stroma, showed reduced proliferative activity, and displayed stem-like transcriptional features. Ex vivo drug testing revealed a striking response: the mTOR inhibitor Sapanisertib induced extensive tumor necrosis and was associated with near-complete depletion of ALDH1A1+ and NTN4+ states, accompanied by strong stress/apoptosis signatures and reduced endothelial cells. In an additional retrospective cohort of 12 SDSC, ALDH1A1 was present in all cases with heterogeneous spatial patterns and higher levels in recurrences. Mesothelin was expressed in the index case and a subset of tumors, supporting mesothelin-directed therapeutic strategies.

Cutaneous melanocytic tumors with concomitant NRAS Q61 and IDH1 R132C mutations have been described as intermediate-grade melanocytomas with characteristic biphasic morphology, but the malignant end of this genotype-defined spectrum remains poorly characterized. We assessed histopathologic, immunohistochemical, molecular, and clinical features of 16 primary cutaneous melanocytic tumors harboring both mutations. Following integrated review, 7 tumors were classified as melanocytoma and 9 as melanoma. Melanocytomas showed reproducible biphasic architecture with congenital nevus-like features, a biphasic HMB-45 pattern, low Ki-67, PRAME negativity, retained p16, and minimal copy number variations (CNVs). Melanomas retained partial morphologic overlap in a subset but were distinguished by higher-grade cytology, immunohistochemical features supportive of malignancy, and progression-associated genomic alterations, including TERT promoter mutation (9/9), 9p21/CDKN2A loss (4/7), and higher CNV burden. NRAS and IDH1 variant allele frequencies were strongly concordant (r = 0.83, P < 0.001), supporting their presence in the same dominant clone. Clinically, two patients presented with stage IIIB disease, but no distant metastasis or melanoma-related death occurred during a median melanoma follow-up of 3.9 years (IQR, 2.5-5.1). In exploratory analyses, moderate-to-severe atypia (RR, 6.2; 95% CI, 1.0-38.8; P = .009), Ki-67 ≥10% (RR, 4.4; 95% CI, 1.1-18.4; P = .003), lymphocytic infiltrate (RR, 2.4; 95% CI, 1.1-5.3; P = .03), absence of the typical biphasic pattern (RR, 2.4; 95% CI, 1.1-5.3; P = .03), and complete p16 loss (RR, 2.4; 95% CI, 1.1-5.3; P = .03) were associated with molecular or clinical progression to melanoma, defined as the presence of at least one of the following: TERT promoter mutation, pathogenic CDKN2A mutation, 9p21/CDKN2A loss, ≥3 genome-wide segmental CNVs, or any metastasis. These findings support the existence of NRAS/IDH1 co-mutated melanoma as the malignant counterpart of NRAS/IDH1-mutated melanocytoma within a single genotype-defined spectrum.

INTRODUCTION:Readily available predictive biomarkers for immune checkpoint inhibitor (ICI) response in advanced melanoma are limited. This study evaluates the predictive value of AI-based histopathology analysis. METHODS:Patients with advanced cutaneous melanoma treated with first-line anti-PD1 ±anti-CTLA4 between 2016 and 2023 across 11 Dutch centers were retrospectively identified using prospectively collected registry data. Pre-treatment H&E-stained metastatic slides were collected from 30 pathology labs and analyzed using 14 foundation models combined with attention-based or clustering-constrained multiple-instance learning. Primary outcome was best overall response (ORR) (RECIST 1.1) assessed through leave-one-hospital-out cross-validation. Response probabilities were added to a clinical model built with AIC-based backward selection (including WHO performance status, liver metastases, LDH, ICI-type, AJCC stage, brain metastases). Feature embedding clusters were labelled by three pathologists blinded to outcomes to assess histology driving predictions. RESULTS:Of 1935 patients, 1177 had a pre-treatment metastatic specimen available, most commonly lymph node or skin/soft tissue; 35.3% was treated with anti-PD1 +anti-CTLA4 combination therapy. ORR was 56.7% (n = 667/1177). The best AI-based model achieved an AUROC of 0.63 (95% CI:0.60-0.66) with overestimated risk. Combining the AI-based analysis with clinical information increased AUROC to 0.66 (95% CI:0.63-0.69) with improved calibration. Model predictions were driven by immune infiltration and epithelioid morphology for response, and by spindle-cell morphology, and necrosis for non-response. CONCLUSION:AI-based analysis of diagnostic pre-treatment metastatic melanoma samples predicts ICI outcomes by using explainable histological features, such as immune infiltration, cell morphology, and necrosis. The predictive performance of the AI-based analysis improves further upon addition of clinical information.

BACKGROUND:Sinonasal adenoid cystic carcinoma (AdCC) has a limited prognosis. This study assesses its incidence and prognostic factors in The Netherlands, focusing on histopathological features. METHODS:Adult patients diagnosed during 2008-2022 were retrieved through the Netherlands Cancer Registry and the Dutch Pathology Registry. Prognostic factors were assessed using survival analyses. RESULTS:Ninety-nine patients were included. The yearly incidence fluctuated between 3 and 14 cases (RESR: 0.02-0.08 per 100 000 person-years). Five-year overall, relative, and progression-free survival were 51%, 55%, and 62%. Multivariable analysis showed solid growth and non-surgical treatment to be independently associated with poorer overall and relative survival after correction for age, tumor location, and T stage. Non-surgical treatment was mainly used for advanced disease and was mainly palliative when intent was recorded. No significant survival differences were found among the different T stages. Sex, perineural invasion, and (lympho)vascular invasion did not impact survival. CONCLUSION:The presence of any solid growth can be used as a prognostic indicator. The absence of survival differences between T stages may indicate that sinonasal AdCC's behavior does not fully align with the standard TNM classification, with factors such as solid growth potentially being more prognostically relevant.

STUDY AIM:Cancer of the nasal vestibule (CNV) is an underrecognized head and neck malignancy, lacking a distinct ICD-O-3 topography code, and a specific T classification. The goal of this study was to assess which of the currently used T classifications provides the most accurate predictive and discriminatory accuracy. METHODS:The four currently used classifications (UICC Sinonasal, UICC NMSC, Wang and Rome) were assessed in a retrospective multicenter cohort established within the Head & Neck and Skin Groupe Européen de Curiethérapie / European SocieTy for Radiotherapy & Oncology Working Group. Through multivariable disease-specific and recurrence-free survival analyses, it was evaluated which staging system was most valuable. RESULTS:609 CNV cases were retrieved from 21 tertiary care centers. Only the Wang and New Rome systems provided accurate prognostic stratification as they showed diminishing survival rates and increasing hazards of disease-specific death and disease recurrence with each successive T category. Compared to Wang, the New Rome system employs more objective criteria and, since it includes four T categories, it can easily be integrated with cN stage to obtain a specific clinical staging for the CNV, which has also resulted superior compared to the current UICC/AJCC systems in this study. CONCLUSION:The New Rome classification exhibits a superior predictive and descriptive precision compared to the Wang and both UICC/AJCC systems. The New Rome's T category structure would allow an integration into the wider UICC/AJCC system once the nasal vestibule is acknowledged as a different subsite.

Background Ultrasound-guided fine-needle aspiration cytology (US-FNAC) is commonly used in the diagnostic work-up of head and neck cancer, but its ability to detect occult lymph node metastases in early-stage oral squamous cell carcinoma (OSCC) with a clinically negative neck remains unclear.Methods A retrospective analysis was performed in 578 patients with early-stage OSCC (cT1-3N0) who underwent US-FNAC prior to surgery. Histopathology, sentinel lymph node biopsy, and follow-up were used as reference standards.Results Occult nodal metastases were found in 179 patients (31.0%). US-FNAC showed low sensitivity (15.9%) and a negative predictive value of 72.9%, resulting in 149 false-negative cases (25.8%). Specificity (99.5%) and positive predictive value (90.3%) were high, with only 2 false-positive results.Conclusions In patients with early-stage oral cavity squamous cell carcinoma and a clinically negative neck, US-FNAC demonstrates high specificity but limited sensitivity and negative predictive value. These findings indicate that US-FNAC alone is insufficient to exclude occult nodal metastases and should be regarded as an adjunctive diagnostic tool rather than a stand-alone nodal staging strategy.

Spitz tumors are diagnostically challenging due to overlap in atypical histological features with conventional melanomas. We investigated to what extent artificial intelligence (AI) models, using histological and/or clinical features, can: (1) distinguish Spitz tumors from conventional melanomas; (2) predict the underlying genetic aberration of Spitz tumors; and (3) predict the diagnostic category of Spitz tumors. The AI models were developed and validated using a retrospective cohort from the University Medical Center Utrecht, the Netherlands. The dataset consisted of 393 Spitz tumors and 379 conventional melanomas. Predictive performance was measured using the area under the receiver operating characteristic curve (AUROC) and the accuracy. The performance of the AI models was compared with that of four experienced pathologists in a reader study. Moreover, a simulation experiment was conducted to investigate the impact of implementing AI-based recommendations for ancillary diagnostic testing on the workflow of the pathology department. The best AI model based on UNI features reached an AUROC of 0.95 (95% CI, 0.92–0.98) and an accuracy of 0.86 (95% CI, 0.81–0.91) in differentiating Spitz tumors from conventional melanomas. The genetic aberration was predicted with an accuracy of 0.55 (95% CI, 0.46–0.64) compared to 0.25 for randomly guessing. The diagnostic category was predicted with an accuracy of 0.51 (95% CI, 0.40–0.60), where random chance-level accuracy equaled 0.33. On all three tasks, the AI models performed better than the four pathologists, although differences were not statistically significant for most individual comparisons. Based on the simulation experiment, implementing AI-based recommendations for ancillary diagnostic testing could reduce material costs, turnaround times, and examinations. In conclusion, the AI models achieved a strong predictive performance in distinguishing between Spitz tumors and conventional melanomas. On the more challenging tasks of predicting the genetic aberration and the diagnostic category of Spitz tumors, the AI models performed better than random chance.

BACKGROUND:Primary cutaneous melanocytic tumours harbouring MAP2K1 mutations without second-hit genomic alterations represent a subclass of neoplasms with poorly understood biological behaviour. This study aimed to investigate the clinical outcomes and genomic characteristics of these tumours. METHODS:This cohort study included primary cutaneous melanocytic tumours with MAP2K1 mutations from patients at two academic centres (Leiden University Medical Centre and University Medical Centre Utrecht). These mutations were categorised into three functional classes: Class I (RAF-dependent), Class II (RAF-regulated), and Class III (RAF-independent). Tumours underwent histopathological evaluation, next-generation sequencing (NGS), and copy number variation (CNV) analysis and were categorised as non-melanoma or melanoma. Clinical outcomes were assessed for each mutation class during follow-up visits and through the Dutch Pathology Database (PALGA) using the composite outcome of metastatic melanoma (recurrence, metastasis, or melanoma-related death). FINDINGS:A total of 102 patients were included, with tumours classified as melanoma in 52 (51%) and non-melanoma in 50 (49%). The tumours displayed spitzoid histomorphology in over two-thirds of cases and harboured 31 distinct MAP2K1 mutations: 20 Class I (19.6%), 56 Class II (54.9%), and 26 Class III (25.5%). Class I mutations exclusively co-occurred with BRAF or NRAS mutations, while Class II and III mutations often acted as sole tumour drivers. Of the tumours with Class I mutations, 95% were classified as melanoma, which was less frequently the case for Class II (risk ratio [RR] 0.43 [95% CI: 0.31-0.60], p < 0.001) and Class III mutations (RR 0.40 [95% CI: 0.25-0.67], p < 0.001). MAP2K1 mutation Class and TERT-p mutation status were independent predictors for the composite outcome. Compared to Class I mutations, Class II mutations were negatively associated with the composite outcome (odds ratio [OR] 0.16 [95% CI: 0.03-0.75], p = 0.03), whereas Class III mutations were not associated (OR 0.31 [95% CI: 0.05-1.54], p = 0.16). TERT-p mutations were positively associated with the composite outcome (OR 23.1, 95% CI: 3.99-439.8, p < 0.005). INTERPRETATION:Class I MAP2K1 mutations typically occur alongside other MAPK pathway mutations and may contribute to aggressive melanoma behaviour. In contrast, Class II and III MAP2K1 mutations can independently drive melanocytic tumourigenesis with a potential for metastasis, aligning with conventional melanomagenesis pathways, despite their frequent spitzoid histomorphology. FUNDING:This research was supported by the Hanarth Fund.

Millions of melanocytic skin lesions are examined by pathologists each year, the majority of which concern common nevi (i.e., ordinary moles). While most of these lesions can be diagnosed in seconds, writing the corresponding pathology report is much more time-consuming. Automating part of the report writing could, therefore, alleviate the increasing workload of pathologists. In this work, we develop a vision-language model specifically for the pathology domain of cutaneous melanocytic lesions. The model follows the Contrastive Captioner framework and was trained and evaluated using a melanocytic lesion dataset of 42,512 H E-stained whole slide images and 19,645 corresponding pathology reports. Our results show that the quality scores of model-generated reports were on par with pathologist-written reports for common nevi, assessed by an expert pathologist in a reader study. While report generation revealed to be more difficult for rare melanocytic lesion subtypes, the cross-modal retrieval performance for these cases was considerably better.

Central giant cell granuloma (CGCG) is a rare non-neoplastic but locally destructive intraosseous lesion of the jaw. While surgical resection remains the golden standard, associated morbidity has led to exploration of pharmacological alternatives, such as denosumab. This case series evaluates the efficacy of monthly direct low-dose intralesional Prolia® (60 mg denosumab/mL) in patients with histologically confirmed CGCG. Before therapy, dental focus examination and screening blood tests were performed. Calcium carbonate/colecalciferol (1.25G/400IU) tablets were administered during treatment. Baseline and follow-up CBCT scans were performed at 3, 6, 12, and 18 months to assess mineralization and lesion volume regression. Nine patients (age range: 7-67 years, median 29 years, five males) received an average of 8 (range: 6-11) low-dose intralesional injections. Median follow-up was 18 (IQR 12) months. CBCT scans showed rapid mineralization within 3-6 months and volume regression within 6-12 months. One patient interrupted therapy due to pregnancy plans at subtotal remission but experienced recurrence, necessitating postpartum treatment. One child showed no response after six injections. Monthly direct intralesional denosumab (≥8 injections) gave complete remission in 7-9 patients after ≥8 injections and is an alternative for CGCG treatment when surgery is harmful. Note rebound hypercalcemia in children.

e13679 Background: Lymph node (LN) assessment is pivotal for guiding treatment in breast cancer (BC), head- and neck cancer (HNC) and melanoma, yet it imposes a significant workload on pathologists and sometimes involves high costs (immunohistochemical stains), making it well-suited for AI-assistance. Here, we evaluate the performance of two CE-IVD certified AI-applications (DeepPath-LYDIA© (DP) and the Metastasis-Detection-App by Visiopharm© (VP)), both inside (IIU) and outside their intended use (OIU). Methods: Both apps were tested in positive LNs of ~100 patients for HNC (both OIU) and melanoma (DP IIU, VP OIU), and for BC (both IIU) in the 59 positive sentinel LN-samples (SLN) from the CONFIDENT-B trial. DP and VP highlight suspicious areas through colored outlines (“alerts”). Sensitivity and false alerts (FAs) were assessed. For BC this was assessed in 20 random negative SLN-cases (10 with-, and 10 without prior treatment) and for HNC and melanoma in up to 3 negative slides per patient. Results: Both apps detected all macro-metastases across tumor types (Table 1). For BC, both DP and VP detected all but one case of micro-metastases, which was undetectable on HE due to heavy cauterization. In contrast, isolated tumor cells (ITC), only relevant in case of neoadjuvant therapy, were detected in 8 of 18 cases. For HNC, DP performed excellent with 100% sensitivity for all metastases, whereas VP missed one case of micro-metastases and 2 of 3 ITC cases. For melanoma, DP missed one case of micro-metastases, while VP missed three cases. ITC-detection was only moderate for both (DP: 50.0%, VP: 62.5%). FAs for both apps were comparable in HNC and melanoma (average 8-9 per slide), whereas in BC, VP showed considerably more FAs (no prior therapy: average 8.4 vs. 4.0 for DP, neoadjuvant therapy: 17.4 vs. 6.8 for DP), which can mainly be explained by the method of annotation (more detailed versus broad outlines) and subsequent counting. Conclusions: Two commercially available AI-applications from different companies performed similar in the detection of LN micro- and macro-metastases in multiple tumor types, both IIU and OIU. For ITC, with clinical relevance depending on tumor type, performance was moderate in general. This may enable implementation of a single AI-solution for a broad indication, thereby positively impacting the business case for individual pathology laboratories. Sensitivity. Breast cancer (n=59) Macro-metastases (n=17) Micro-metastases (n=24) ITC (n=18) DP (IIU) 100% (n=17) 95.8% (n=23) 44.4% (n=8) VP (IIU) 100% (n=17) 95.8% (n=23) 44.4% (n=8) Head and neck cancer (n=100) Macro-metastases (n=75) Micro-metastases (n=22) ITC (n=3) DP (OIU) 100% (n=75) 100% (n=22) 100% (n=3) VP (OIU) 100% (n=75) 95.5% (n=21) 33.3% (n=1) Melanoma (n=98) Macro-metastases (n=66) Micro-metastases (n=24) ITC (n=8) DP (OIU) 100% (n=66) 95.8% (n=23) 50% (n=4) VP (OIU) 100% (n=66) 87.5% (n=21) 62.5% (n=5)

Fibro-osseous tumors of the craniofacial bones are a heterogeneous group of lesions comprising cemento-osseous dysplasia (COD), cemento-ossifying fibroma (COF), juvenile trabecular ossifying fibroma (JTOF), psammomatoid ossifying fibroma (PsOF), fibrous dysplasia (FD), and low-grade osteosarcoma (LGOS) with overlapping clinicopathological features. However, their clinical behavior and treatment differ significantly, underlining the need for accurate diagnosis. Molecular diagnostic markers exist for subsets of these tumors, including GNAS mutations in FD, SATB2 fusions in PsOF, mutations involving the RAS-MAPK signaling pathway in COD, and MDM2 amplification in LGOS. Since DNA methylation and copy number profiling are well established for the classification of central nervous system tumors, our aim was to investigate whether this tool might be used as well for classifying fibro-osseous tumors in the craniofacial bones. We collected a well-characterized, multicenter cohort with available molecular data, including COD (n = 20), COF (n = 13), JTOF (n = 10), PsOF (n = 25), FD (n = 23), LGOS (n = 4), and high-grade osteosarcoma (HGOS; n = 11). Genome-wide DNA methylation and copy number variation data were generated using the Illumina Infinium Methylation EPIC array interrogating >850 000 CpG sites. DNA methylation profiling yielded evaluable results in 73/106 tumors, including 6 CODs, 12 COFs, 6 JTOFs, 19 PsOFs, 18 FDs, 2 LGOSs, and 10 HGOSs. Unsupervised clustering and dimensionality reduction (Uniform Manifold Approximation and Projection) revealed that FD, extragnatic PsOF, and HGOS formed distinct clusters. Surprisingly, COD, COF, JTOF, and mandibular PsOF clustered together, apart from other craniofacial bone tumors. LGOS did not form a distinct cluster, likely due to the low number of cases. Copy number analysis revealed that FD, COD, COF, JTOF, and PsOF were typically characterized by flat copy number profiles compared to LGOS with gains of chromosome 12 and HGOS with multiple heterogeneous copy number alterations. In conclusion, using DNA methylation and copy number profiles, benign fibro-osseous tumors can be separated from low-grade and high-grade osteosarcomas in the craniofacial bones, which is of diagnostic value in challenging cases with overlapping clinicopathological features.

The increasing diagnostic workload in pathology, driven by rising cancer incidences, highlights the need for scalable, cost effective solutions. Artificial intelligence (AI) has shown promise in supporting lymph node (LN) metastasis detection, a key prognostic factor in cancer staging. However, the current Conformité Européene In Vitro Diagnostics--certified AI tools are often limited to specific tumor types, reducing their cost efficiency and clinical use. This study evaluates the performance of 2 Conformité Européene In Vitro Diagnostics-certified AI tools—Visiopharm Metastasis Detection App (VMD) and DeepPath LYDIA (DPL)—for multipurpose LN metastasis detection across 6 tumor types, both within and beyond their intended use. We retrospectively analyzed whole-slide images from 455 patients with LN metastases from melanoma, colorectal, head and neck, lung, vulvar, and breast cancer. Both sentinel and nonsentinel LNs were included, with expert pathologists establishing the reference standard, according to clinical practice. Sensitivity was calculated per case and stratified based on metastasis size. False-positive alerts (FPAs) were assessed in 1012 tumor-negative slides. Both applications demonstrated excellent sensitivity for macrometastases across tumor types. DPL showed slightly higher sensitivity for micrometastases and isolated tumor cells compared with VMD, particularly in lung cancer and melanoma. FPA rates were substantial for both tools, with VMD generally producing more alerts, especially in lung and breast cancer. Our findings suggest that a single AI tool may be suitable for LN metastasis detection across multiple tumor types, even beyond its intended use. However, high FPA rates—particularly in lung cancer (inside intended use for DPL)—may limit practical use. Prospective studies are needed to confirm workflow efficiency gains and define optimal implementation strategies. These results support a broader, pragmatic approach to AI validation and regulatory approval, potentially improving the business case for AI adoption in pathology laboratories.

PurposeAmeloblastic fibro-odontoma (AFO) is a rare benign mixed odontogenic tumor that, after being classified for years as a distinct entity, was redefined as a "developing odontoma" in the 2017 World Health Organization classification. This article presents a unique case of an AFO with an FGFR1 mutation.MethodsWe present a case of an 8-year-old child with a slowly progressive swelling in the lower left mandible. Next-generation sequencing (TSO500 panel) was performed.ResultsPanoramic radiography revealed an odontogenic tumor; therefore, a transoral enucleation was performed. Pathological microscopic examination confirmed the diagnosis of AFO, and next-generation sequencing detected an FGFR1 mutation.ConclusionThe presence of an FGFR1 mutation in an AFO may suggest a closer biological relationship between ameloblastic fibroma and AFO, potentially distinguishing it from odontomas. Further research, including genetic studies, is needed to enhance our understanding and refine the classification of these tumors.

The tongue is essential for swallowing, taste perception, and mechanosensation. The anterior and posterior parts of the tongue have region-specific developmental origins and are maintained by adult epithelial stem/progenitor cells. In vitro models that can be used to investigate anterior tongue biology have been lacking. Here, a protocol is developed to generate a long-term expanding organoid model from the adult mouse dorsal anterior tongue. Anterior tongue organoids consist of Lgr6+ cells, Sox2+ stem/progenitor cells, and Hoxc13+ filiform papillae progenitor cells. Furthermore, anterior tongue organoids share region-specific transcriptomic profiles, gene regulatory networks, and signaling pathways with anterior tongue tissue. Anterior tongue organoids can be differentiated into various epithelial cell types, including Merkel-like cells, keratinocytes, and taste bud cells. Gene regulatory network analysis reveals transcriptional programs associated with Krt8+ cell and Krt23+/Sbsn+ keratinocyte differentiation in the organoids. Together, this study provides an in vitro model of mouse dorsal tongue epithelium.