BACKGROUND:Breast phyllodes tumours (PT) are rare biphasic neoplasms consisting of epithelial and stromal components. They are classified into benign, borderline and malignant categories. Diagnosing and grading PTs present a challenge for pathologists, as there are multiple histological parameters and their own tiers. We aim to investigate the potential role of artificial intelligence (AI) as a diagnostic aid in determining PT grade. MATERIALS AND METHODS:We investigated 15 PT whole slide images (WSIs), comprising 5 benign, 5 borderline and 5 malignant cases. We sought to classify and retrieve the most relevant WSIs by matching histological features at different patch sizes, using the Yottixel framework for WSI processing. Patches were extracted at a 20× magnification level. We then used the KimiaNet to extract feature vectors and transformed these into barcode representations. Barcodes of a query WSI were compared with those of others in the archive, allowing us to identify the most similar WSI and determine the PT grades from histological similarities. RESULTS:We utilized 'majority-n accuracy' as a measure of correctness, that is when the majority of the top-n search results have the correct diagnosis as the query patient. We achieved a maximum reported accuracy of 67%, with a 3000 × 3000 patch size when grading PT at majority voting with n = 4. CONCLUSION:Despite the small sample size and absence of fine-tuning, our study demonstrated the potential of AI-based PT grade stratification using various patch sizes through histological matching. This serves as a preliminary proof of concept, with the prospect of refinement for potential routine clinical application.
Abstract Purpose: Gastrointestinal tumors, including esophageal and gastric/gastroesophageal junction adenocarcinoma (GEA), have a high mortality rate and present significant treatment challenges. Telisotuzumab adizutecan (Temab-A, ABBV-400), a novel antibody–drug conjugate targeting the c-Met protein (also known as MET protein), has shown encouraging results in patients with advanced GEA. Patients and Methods: This phase I, open-label, multicenter study assessed the safety, efficacy, and pharmacokinetics (PK) of Temab-A monotherapy (3 mg/kg every 3 weeks intravenously) in patients with advanced GEA. Patients ≥18 years of age with advanced/metastatic GEA who had received 1 to 2 prior systemic therapies were included. The primary objectives were the evaluation of safety, PK, and efficacy; efficacy endpoints included objective response rate (ORR), duration of response (DOR), progression-free survival (PFS), and overall survival (OS). c-Met expression and MET amplification were retrospectively assessed. Results: Forty-two patients with advanced GEA were enrolled; the median age was 60 years. The median follow-up duration was 12.6 months. All patients had one or more treatment-emergent adverse events (TEAE), with 88% experiencing grade ≥3 TEAEs. The most common hematologic TEAEs were anemia (67%), nausea (52%), and decreased appetite (36%). The ORR was 29%, the clinical benefit rate was 71%, and the median DOR was 4.2 months. The median PFS was 4 months, and the median OS was 5.8 months. Exploratory biomarker analyses showed ORR enrichment in patients with higher c-Met protein expression and MET focal amplification. Conclusions: Temab-A monotherapy demonstrated antitumor activity and a manageable safety profile in patients with advanced GEA. The findings support further clinical development of Temab-A, particularly in combination with other agents to improve outcomes for patients with 2L+ GEA.
Histone methyltransferase EZH2 is essential for germinal center formation, and gain-of-function mutations of EZH2 occur in approximately 20% of follicular lymphomas (FLs). Although EZH2 inhibitors are used for relapsed/refractory EZH2-mutated (EZH2mut) FLs, their clinicopathological characteristics remain incompletely understood. We assessed the EZH2 Y646 mutation by Sanger sequencing in 301 FLs and identified mutations in 17% (50/301). Compared with EZH2 wild-type (EZH2wt), EZH2mut FL showed a significantly higher proportion aged > 60 years (p = 0.033). Pathologically, EZH2mut FL more frequently exhibited clear neoplastic follicles (p < 0.0001) and grater interfollicular tumor cell distributions highlighted by CD20 immunohistochemistry (p < 0.0001). These cases also more often showed the typical FL immunophenotype (CD10+, BCL2+, BCL6+) (p = 0.027) and BCL2 rearrangement (p = 0.0060). Gene expression profiling revealed enrichment of TNF-α/NF-κB signaling in EZH2wt FL, whereas EZH2mut FL showed upregulation of cell-cycle programs, particularly the G2/M checkpoint. Concordance of EZH2 mutation status between primary and relapsed lesions was 94% (33/35). Even at relapse, EZH2mut FL retained its characteristic pathological features, including clear follicles and high interfollicular spread of tumor cells. In conclusion, EZH2mut FL exhibits distinctive clinicopathological and molecular features that may help identify patients most likely to benefit from EZH2-targeted therapy.
