Citations

Abstract Large language models (LLMs) and vision‐language models represent a fundamentally different category of artificial intelligence (AI) compared to prior image analysis approaches in digital pathology, which have largely been based on convolutional neural network architectures. This review from the American Society of Cytopathology Clinical Practice Committee examines the current evidence for LLM and vision‐language model applications in cytopathology, including structured reporting, diagnostic assistance, quality control, education, and workflow integration. The distinction between applications with preliminary evidence and those that remain hypothetical is described. A detailed assessment of the challenges that must be addressed before clinical deployment, including hallucination risk, limited explainability, bias, data privacy, validation gaps, and infrastructure barriers is discussed. A review of the regulatory landscape in the United States and European Union as it applies to AI‐enabled software as a medical device is provided. Recommendations addressing cytopathology‐specific benchmarks, multi‐institutional validation, transparent governance, and incremental deployment beginning with low‐risk applications are suggested. In the current environment, LLMs have the potential to augment cytopathology practice, but responsible adoption requires rigorous validation and sustained collaboration among cytopathologists, AI researchers, and regulatory bodies.

3118 Background: Improved risk stratification is critically needed across multiple cancers to guide treatment decisions. This includes reducing overtreatment in Ductal Carcinoma in Situ (DCIS), addressing late recurrence risk in estrogen receptor-positive/lymph node-negative (ER+/LN-) breast cancer (BC), and refining prognosis in head & neck squamous cell carcinomas (HNSCC), and high-grade serous ovarian carcinoma (HGSOC). Tumor-infiltrating lymphocytes (TILs) reflect anti-tumor immunity, whereas tumor-associated macrophages (TAMs) polarize toward anti-tumor M1-like (CD68+) or immunosuppressive M2-like (CD163+) phenotypes. Integrating TILs with TAM polarization markers may better capture inflammatory balance and improve outcome prediction. We developed a hematoxylin and eosin (H&E)-only AI method (VAIP) to quantify TILs and virtual CD68/CD163 TAMs to develop multi-cancer based potential prognostic models. Methods: TILs were detected on H&E with HoVer-UNet, and virtual CD68 and CD163 macrophages were inferred with VISTA. In cancer regions, we computed cell densities and immune-balance ratios and trained cancer-specific Cox models with compact feature sets (DCIS 6; HGSOC 7; ER+ 4; HNSCC 4). Prognostic stratification used disease-free survival (DFS) for DCIS (N=273), HGSOC (training N=165, independent test N=220), and ER+ BC (training N=144, test N=622), and overall survival (OS) for HNSCC (N=77), reflecting clinical endpoints. Evaluation used cross-validation for cohorts without an external test set (DCIS, HNSCC) and independent training and testing when independent cohort was available (HGSOC, ER+). Results: Risk stratification performance across cancer types is in Table 1. The DCIS model used 6 features, largely TIL-macrophage contrast ratios (TIL/M2, TIL/M1). HGSOC used 7 features with a similar ratio-heavy immune-balance signature, plus macrophage-normalized density and polarization metrics (e.g., M1/N, M/N). In contrast, ER+ BC and HNSCC achieved best performance with 4 features dominated by macrophage measures, particularly M2 density and the M1/M2 ratio. Across sites, CD163-related macrophage metrics and immune-balance ratios were consistently informative. Conclusions: Integrating H&E-visible TILs with virtual CD68/CD163 TAMs enables fully automated, H&E-only prognostic biomarkers that stratify OS and DFS across multiple cancers, demonstrating consistent prognostic value in DCIS, ER+ BC, HGSOC, and HNSCC. These findings support further study of this histomorphometric risk classifier through broader external and prospective validation. Performance across cancer types. Cancer Type Cohort C-index HR [95% CI] p-value DCIS All 0.616 1.76 [1.20-2.59] <0.001 DCIS RT/No-treatment 0.624 1.94 [1.15-3.26] 0.003 HGSOC Test 0.553 1.38 [1.02-1.87] 0.030 ER+ BC Test 0.577 1.51 [1.00-2.28] 0.004 HNSCC All 0.603 1.92 [1.03-3.36] 0.012

DEK::AFF2 fusion nonkeratinizing squamous cell carcinoma (NKSCC) is an emerging entity in the sinonasal tract, temporal bone, and skull base. However, the clinical behavior of these tumors has not been well studied. Here, we report the largest cohort of DEK::AFF2 carcinomas to determine if morphology, mitotic rate, and/or Ki-67 IHC are associated with patient outcomes, including a comparison with high-risk human papillomavirus (HPV)-associated and independent patients. We solicited cases of molecularly or AFF2 immunohistochemistry (IHC) proven DEK::AFF2 SCC from surgical pathologists to collect patient demographic, clinical, and outcome data. Using representative H&E slides, we characterized the morphology and counted mitoses. Ki-67 immunohistochemistry was performed. We also compared the DEK::AFF2 survival rates to those in a cohort of AFF2 IHC-negative HPV-associated and HPV-independent SCC. DEK::AFF2 carcinomas most commonly arose in the nasal cavity (13/30, 43%), and the average number of recurrences was 1.8 (range: 0 to 10). At the last follow-up, most patients were disease free (19/30, 63%) or were alive with disease (9/30, 30%). There was an average mitotic rate of 2 per 2 mm2 (range: 0 to 9) and Ki-67 proliferation rate of 26% (range: 3% to 60%). Local recurrence was common, but morphology, mitotic activity, and Ki-67 index were not associated with recurrence or survival. On Kaplan-Meier survival analysis, DEK::AFF2 patients had lower disease-free survival but otherwise had similar outcomes to conventional SCC patients. Our multi-institutional study shows that local recurrence is common in DEK::AFF2 fusion nonkeratinizing SCC patients, but patients have survival rates similar to conventional SCC. Despite showing a range of different features and proliferation rates, traditional grading by morphology, mitotic rate, and/or Ki-67 activity does not seem to be predictive of outcome.

Abstract Background: The dysregulation of polycomb repressive complex 2 (PRC2) promotes tumorigenesis and progression. Two therapeutic agents targeting enhancer of zeste homolog (EZH) 2 or EZH1/2, the catalytic subunits of PRC2, have been approved in several cancer types. HH2853 is a novel selective EZH1/2 dual inhibitor, which has demonstrated superior anti-tumor efficacy to tazemetostat (EZH2 inhibitor approved by FDA) in various preclinical models. Methods: This is a first-in-human, open-label, multi-center, phase (Ph) I/II study of HH2853 in patients (pts) with relapsed/refractory (r/r) non-Hodgkin lymphomas (NHLs) or advanced solid tumors. HH2853 was administered orally twice daily (BID) on a continuous 28-day treatment cycle. Ph I consist of two parts: dose escalation part adopting accelerated titration followed by a Bayesian optimal interval design and dose extension part. Dose limiting toxicity (DLT) was evaluated during the 1st cycle in dose escalation. Safety, tolerability, pharmacokinetics (PK), pharmacodynamics (PD) and preliminary anti-tumor activity of HH2853 were explored in this Ph I study. Results: As of Oct 19, 2022, a total of 57 pts, including 50 pts with solid tumors and 7 pts with r/r follicular lymphoma (FL), were enrolled from 12 sites in China and the US. Twenty-five (43.9%) pts received ≥3 lines of prior systemic therapies. Six dose levels(50 mg, 100 mg, 200 mg, 400 mg, 600 mg and 800 mg)were evaluated. DLTs were observed in 2 of 8 DLT evaluable pts at 800 mg: one grade 3 platelet count decreased and one grade 3 diarrhea. A conclusive maximal tolerated dose was not reached. The most common treatment-related adverse events (TRAE) were diarrhea (45.6%), blood bilirubin increased (35.1%), white blood cell count (WBC) decreased (26.3%), platelet count decreased (26.3%), rash (24.6%) and anemia (22.8%). The most common ≥grade 3 TRAEs included anemia (8.8%), platelet count decreased (7.0%), WBC decreased (5.3%) and diarrhea (5.3%). TRAEs leading to dose interruption or reduction were reported in 17.5% and 8.8% pts respectively. No TRAE led to dose discontinuation or death. PK data indicated dose-related increase in exposure from 50 to 600 mg. PD data showed a significant inhibition (maximum reached &gt;90%) of H3K27me3 in granulocytes and monocytes at 400-800 mg. Tumor responses were observed in 7 pts from 200 to 800 mg in multiple tumor types, including complete response in 1 patient with FL, partial response in 3 pts with epithelioid sarcoma, 2 pts with FL and 1 patient with malignant rhabdoid tumor of pancreas. Conclusions: This first-in-human study of HH2853 showed a manageable safety profile and promising anti-tumor activity in multiple tumor types, supporting further exploration in NHLs and solid tumors after recommended Ph II dose is determined.Clinical trial information: NCT04390737 Citation Format: Zhengfu Fan, Jin Wang, Meiyu Fang, Johnston Patrick, Tun Han, David Sommerhalder, Jifang Gong, Jilong Yang, Yun Yang, Javier Munoz, Yuqin Song, Zhiming Li, Xian'an Li, Qiuying Ma, Jinming Han, Lin Shen, Jun Zhu. Preliminary results from the Phase I part of a first-in-human Phase I/II study of HH2853, an EZH1/2 inhibitor, in patients with relapsed/refractory non-Hodgkin lymphomas or advanced solid tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr CT105.

microRNAs associate with Argonaute proteins, forming the microRNA-induced silencing complex (miRISC), to repress target gene expression post-transcriptionally. Although microRNAs are critical regulators in mammalian cell differentiation, our understanding of how microRNA machinery, such as the miRISC, are regulated during development is still limited. We previously showed that repressing the production of one Argonaute protein, Ago2, by Trim71 is important for mouse embryonic stem cells (mESCs) self-renewal (Liu et al., 2021). Here, we show that among the four Argonaute proteins in mammals, Ago2 is the major developmentally regulated Argonaute protein in mESCs. Moreover, in pluripotency, besides the Trim71-mediated regulation of Ago2 (Liu et al., 2021), Mir182/Mir183 also repress Ago2 . Specific inhibition of this microRNA-mediated repression results in stemness defects and accelerated differentiation through the let-7 microRNA pathway. These results reveal a microRNA-mediated regulatory circuit on microRNA machinery that is critical to maintaining pluripotency.

The regulation of stem cell fate is poorly understood. Genetic studies in Caenorhabditis elegans lead to the hypothesis that a conserved cytoplasmic double-negative feedback loop consisting of the RNA-binding protein Trim71 and the let-7 microRNA controls the pluripotency and differentiation of stem cells. Although let-7-microRNA-mediated inhibition of Trim71 promotes differentiation, whether and how Trim71 regulates pluripotency and inhibits the let-7 microRNA are still unknown. Here, we show that Trim71 represses Ago2 mRNA translation in mouse embryonic stem cells. Blocking this repression leads to a specific post-transcriptional increase of mature let-7 microRNAs, resulting in let-7-dependent stemness defects and accelerated differentiation in the stem cells. These results not only support the Trim71-let-7-microRNA bi-stable switch model in controlling stem cell fate, but also reveal that repressing the conserved pro-differentiation let-7 microRNAs at the mature microRNA level by Ago2 availability is critical to maintaining pluripotency.