Interstitial lung disease encompasses diverse pulmonary disorders with varied prognoses. Current pathological diagnoses suffer from interobserver variability, necessitating more standardized approaches. We developed an ensemble cryobiopsy artificial intelligence model (CRAIO) to analyze transbronchial lung cryobiopsy specimens and predict patient outcomes. CRAIO comprises 7 modules for detecting histological features, generating 17 pathologically significant findings. A downstream XGBoost classifier was developed to predict disease progression using these findings. The model's performance was evaluated using respiratory function changes and survival analysis in cross-validation and external test cohorts. In the internal cross-validation (135 cases), the model predicted 105 cases without disease progression and 30 cases with disease progression. The annual absolute change in % forced vital capacity was - 1.293 in the nonprogressive group versus - 5.198 in the progressive group, a difference that was significant for CRAIO, while only 5 of 19 pathologists achieved significant differentiation using usual interstitial pneumonia diagnosis. Survival analysis demonstrated significantly shorter survival times in the progressive group (P = .038). CRAIO provides a comprehensive, interpretable approach to analyzing transbronchial lung cryobiopsy specimens, offering potential for standardizing interstitial lung disease diagnosis and predicting disease progression. The model could facilitate early identification of progressive cases and guide personalized therapeutic interventions. (c) 2026 THE AUTHORS. Published by Elsevier Inc. on behalf of the United States & Canadian Academy of Pathology. This is an open access article under the CC BY license (http:// creativecommons.org/licenses/by/4.0/).
Introduction Achalasia has been proposed as a muscle-predominant variant of eosinophilic or lymphocytic oesophagitis. Peroral endoscopic myotomy (POEM) enables direct biopsy of the oesophageal muscular layer. We assessed eosinophilic and lymphocytic infiltration in the distal oesophageal muscle.Methods We retrospectively analysed POEM patients without mucosal eosinophilia who underwent lower oesophageal sphincter biopsies over 42 months. Eosinophils (EOs) were quantified per mm & sup2;; lymphocytes and nerve tissue were assessed by CD3 and S-100 staining. Seven patients with proximal oesophageal cancer served as controls.Results Among 141 patients (52.4% male; mean age 47.5 years), mean EO density was 0.4/mm & sup2;; 10.6% had >= 1 EO/mm & sup2;. CD3 staining was absent or minimal in most, with mild increases in 5.7%. Lymphocyte density correlated with achalasia subtype (p=0.03), but not with EOs or outcomes. Controls showed negligible inflammation.Conclusion Lower oesophageal sphincter biopsies showed no significant eosinophilic or lymphocytic infiltration, arguing against an inflammatory myopathy as the basis of achalasia.
Castleman disease (CD) represents a heterogeneous group of lymphoproliferative disorders, with the idiopathic multicentric CD (iMCD) subtype associated with thrombocytopenia, anasarca, fever, reticulin fibrosis/renal dysfunction, and organomegaly (TAFRO) syndrome (iMCD-TAFRO) posing significant research challenges because of its severity and tissue scarcity. This study used integrated bulk and spatial proteomics to characterize protein expression profiles in lymph node samples across clinical and pathological subtypes. Bulk proteomics revealed subtype-specific molecular signatures, including distinct protein profiles for hyaline vascular vs plasmacytic variants, systemic complement activation distinguishing iMCD from unicentric CD, and molecular evidence supporting the classification of iMCD-idiopathic plasmacytic lymphadenopathy as a distinct entity. Specifically, iMCD-TAFRO exhibited upregulation of angiogenesis drivers (PDGFR(3 and NOTCH3), interferon signaling proteins (STAT1/ISG15), and fibrosis markers (COL3A1/LOXL1). Spatial proteomics, through laser capture microdissection of follicular and vascular niches, delineated compartmentalized pathogenesis in iMCD-TAFRO. Intrafollicular vessels showed enrichment of myofibroblast markers (ACTA2) and programmed cell death regulators (eg, GSDMD and TFRC), whereas interfollicular regions displayed TGF-(3/SMAD3-mediated upregulation of LOXL1 linked to fibrosis. Follicular zones demonstrated complement activation (CFHR1/CFHR2) and M2 macrophage infiltration. Our integrated approach delineated the molecular heterogeneity of CD, revealed spatially resolved pathogenic drivers in iMCD-TAFRO, and provided insights into its unique vascular-fibroinflammatory pathology, offering a foundation for advancing precision diagnostics and targeted therapies. (c) 2026 THE AUTHORS. Published by Elsevier Inc. on behalf of the United States & Canadian Academy of Pathology. This is an open access article under the CC BY-NC-ND license (http:// creativecommons.org/licenses/by-nc-nd/4.0/).
