Given the recent success of artificial intelligence (AI) in computer vision applications, many pathologists anticipate that AI will be able to assist them in a variety of digital pathology tasks. Simultaneously, tremendous advancements in deep learning have enabled a synergy with artificial intelligence (AI), allowing for image-based diagnosis on the background of digital pathology. There are efforts for developing AI-based tools to save pathologists time and eliminate errors. Here, we describe the elements in the development of computational pathology (CPATH), its applicability to AI development, and the challenges it faces, such as algorithm validation and interpretability, computing systems, reimbursement, ethics, and regulations. Furthermore, we present an overview of novel AI-based approaches that could be integrated into pathology laboratory workflows.

The seventh edition of the AJCC-UICC staging system for esophageal cancer is reviewed, with emphasis on appropriate use of CT, endoscopic US, and PET/CT for initial staging. Esophageal cancer is a leading cause of cancer-related deaths worldwide, and the 5-year relative survival rate remains less than 20% in the United States. The treatment of esophageal cancer should be stage specific for better clinical outcomes. Recent treatment paradigms tend to involve a multimodality approach to management, which includes surgical resection and preoperative or definitive chemoradiation therapy. Accurate pretreatment staging of esophageal cancer is integral for assessing operability and determining a suitable treatment plan. The American Joint Committee on Cancer (AJCC) and the Union for International Cancer Control (UICC) have published the seventh edition of the staging manual for cancer in the esophagus and esophagogastric junction. Unlike the sixth edition, the revised staging manual is data driven and harmonized with the staging of stomach cancer. Improvements include new definitions for the anatomic classifications Tis, T4, regional lymph node, N, and M and the addition of nonanato...

Spatial omics integrates molecular profiling with spatial tissue context, enabling high-resolution analysis of gene expression, protein interactions, and epigenetic modifications. This approach provides critical insights into disease mechanisms and therapeutic responses, with applications in cancer, neurology, and immunology. Spatial omics technologies, including spatial transcriptomics, proteomics, and epigenomics, facilitate the study of cellular heterogeneity, tissue organization, and cell–cell interactions within their native environments. Despite challenges in data complexity and integration, advancements in multi-omics pipelines and computational tools are enhancing data accuracy and biological interpretation. This review provides a comprehensive overview of key spatial omics technologies, their analytical methods, validation strategies, and clinical applications. By integrating spatially resolved molecular data with traditional omics, spatial omics is transforming precision medicine, biomarker discovery, and personalized therapy. Future research should focus on improving standardization, reproducibility, and multimodal data integration to fully realize the potential of spatial omics in clinical and translational research.

OBJECTIVE. The purposes of our study were to evaluate 18F-FDG PET findings of ground-glass opacity (GGO) nodules and to determine the value of FDG PET for the preoperative staging of lung cancer manifesting predominantly as GGO. MATERIALS AND METHODS. Eighty-nine patients (46 men and 43 women; mean [± SD] age, 62.4 ± 7.2 years [range, 33–81 years] and 61.7 ± 6.7 years [range, 34–75 years], respectively) with 134 GGO nodules (56 single and 78 multiple) who underwent CT and FDG PET before surgery were included. CT and PET findings were assessed in terms of lesion size, GGO percentage, multiplicity, and maximum standardized uptake value (SUVmax). SUVmax was correlated with lesion size and GGO percentage using linear regression. The SUVmax and hypermetabolism rates of solitary and multiple GGO nodules were compared using the Student t test or Fisher exact test. Lymph node and distant organ metastasis staging by FDG PET were correlated with histopathologic findings. RESULTS. SUVmax was positively correlated wi...

Mutations in the TERT promoter, ALK rearrangement, and the BRAF V600E mutation are associated with aggressive clinicopathologic features in thyroid cancers. However, little is known about the impact of TERT promoter mutations and ALK rearrangement in thyroid cancer patients with a high prevalence of BRAF mutations. We performed Sanger sequencing to detect BRAF V600E and TERT promoter mutations and both immunohistochemistry and fluorescence in situ hybridization to identify ALK rearrangement on 243 thyroid cancers. TERT promoter mutations were not present in 192 well-differentiated thyroid carcinomas (WDTC) without distant metastasis or in 9 medullary carcinomas. However, the mutations did occur in 40 % (12/30) of WDTC with distant metastasis, 29 % (2/7) of poorly differentiated carcinomas and 60 % (3/5) of anaplastic carcinomas. ALK rearrangement was not present in all thyroid cancers. The BRAF V600E mutation was more frequently found in WDTC without distant metastasis than in WDTC with distant metastasis (p = 0.007). In the cohort of WDTC with distant metastasis, patients with wild-type BRAF and TERT promoter had a significantly higher response rate after radioiodine therapy (p = 0.024), whereas the BRAF V600E mutation was significantly correlated with progressive disease (p = 0.025). The TERT promoter mutation is an independent predictor for distant metastasis of WDTC, but ALK testing is not useful for clinical decision-making in Korean patients with a high prevalence of the BRAF V600E mutation. Radioiodine therapy for distant metastasis of WDTC is most effective in patients without BRAF V600E and TERT promoter mutations.