Cannon, Andrew

Abstract In epilepsy patients lacking magnetic resonance imaging‐visible lesions such as focal cortical dysplasia (FCD), surgical resections target regions with abnormal electroencephalographic (EEG) activity. However, histopathological identification of subtle cortical architectural abnormalities in these specimens remains challenging. We investigated whether artificial intelligence (AI)‐based morphometric and spatial analysis of NeuN‐stained cortical sections could detect neuronal architectural disorganization in epilepsy resections, including regions without definitive histologic dysplasia. Whole slide images were generated from 83 FCD regions and 19 neurologically normal autopsy controls. Regions of interest were annotated in QuPath as FCD, FCD‐adjacent, FCD‐distant, apparently normal (abnormal EEG without histologic dysplasia), and true normal (autopsy controls). NeuN‐positive neurons were detected using QuPath (90% sensitivity, 12% false positive rate). Spatial and morphometric features—including neuronal clustering, distribution inhomogeneity, and nuclear morphology—were extracted and used to train a multinomial, Least Absolute Shrinkage and Selection Operator‐regularized regression classifier. The classifier achieved 70.6% accuracy in subregion classification and 88.2% accuracy in overall specimen diagnosis. Notably, regions with abnormal EEG but lacking histologic dysplasia exhibited quantifiable architectural disorganization similar to those seen in areas adjacent to FCD and distinct from control tissue. AI‐driven analysis of neuronal morphology and spatial distribution reveals subtle cortical disorganization in epilepsy resections, including in histologically ambiguous regions. Further investigation is warranted to determine if this methodology can enhance the diagnostic yield of neuropathological evaluation and support more precise surgical targeting in epilepsy.

Abstract Introduction Chronic myelomonocytic leukemia (CMML) is a myeloid neoplasm with overlapping features of myelodysplastic syndromes (MDS) and myeloproliferative neoplasms (MPN). Blast transformation (BT) is a frequent complication of CMML with a 3-year risk of approximately 31%. MPN driver mutations (i.e., JAK2, CALR, MPL) are known to occur in CMML but their impact on overall survival (OS) or BT remains uncertain. Methods The current study was conducted under institutional review board approved minimum risk protocols that allowed retrospective collection and analysis of patient data. Diagnostic criteria were according to the International Consensus Classification (Blood 2022; 140:1200). For survival analysis, patients were censored at the time of allogeneic stem cell transplant (ASCT). All statistical analyses were conducted using JMP Pro 17.0.0 software (SAS Institute, Cary, NC, USA) and Bluesky Statistics Software (Worldwide Headquarters, Chicago, IL, USA). Results A total of 612 CMML patients were considered (median age 71 years; 68% males). MPN driver mutations (MPNMUT) were detected in 56 (9%) patients, including 43 (77%) with JAK2, 10 (18%) MPL, and 3 (5%) CALR. The median variant allele frequencies were 44% for JAK2 (range, 0.3–100%), 49% for MPL (range, 0.3–97%), and 50% for CALR (range, 20–80%). Age and sex distributions and CMML-1 vs. CMML-2 representation were similar between CMML patients with and without MPNMUT. On the other hand, CMML patients with MPNMUT were more likely to display higher hemoglobin level (p <0.01), platelet count (p <0.01), absolute neutrophil count (p = 0.02) and leukocytosis (≥13 ×109/L; p <0.01); they were also less likely to be red blood transfusion dependent (p <0.01), display platelet counts of <100 ×109/L (p <0.01) or abnormal karyotype (p= 0.03), present with severe anemia (p= 0.03) or harbor NRAS mutation (p = 0.02). Higher Mutational frequencies of SRSF2 (median 53% vs. 41%; p = 0.01), TP53 (median 8% vs. 2%; p = 0.02) and IDH2 (median 13% vs. 4%; p = 0.01) were noted in CMML patients with MPNMUT. During a median follow-up of 23 months (inter-quantile range 11-51 months) for all 612 CMML patients, 402 (67%) deaths, 118 (19%) BT and 108 (18%) ASCT were documented. Of these, 36 (9%) deaths, 18 (15%) BT and 13 (12%) ASCT occurred in patients with MPNMUT. Median OS for the entire group (N=612) was 32 months with 1-, 2- and 3-year OS rates of 78%, 58% and 47%, respectively. There was no significant difference in OS between CMML patients with or without MPNMUT (median 41 vs 31 months; p = 0.27). Thrombotic events were reported in 53 (9%) patients after diagnosis of CMML, including 48 venous and 5 arterial events. There was no significant difference in arterial (p = 0.10) or venous (p = 0.76) thrombosis-free survival between CMML patients with or without MPNMUT. Among all 612 patients with CMML, followed for a median of 18 months for living patients, 118 (19%) experienced BT, with 1-, 3-, and 5-year BT rates of 10.8%, 23.1%, and 31%, respectively. Cumulative incidence analysis function (CIF) was calculated in order to assess the BT-free survival while accounting for death as a competing risk; 3-year CIF was 30% for CMML patients with vs. 18% for those without MPNMUT (Gray's test; p = 0.01). This observation was confirmed in univariate analysis of time to BT (HR 1.7; p=0.03) as well as the corresponding multivariable analysis involving other mutations and clinical risk factors: MPNMUT (HR 1.8; 0.036), ASXL1MUT (HR 2.3; p<0.01), DNMT3AMUT (HR 2.6; p<0.01), CMML-2 vs. CMML-1 (HR 3.4; p<0.01), and leukocyte count ≥13 ×109/L (HR 2.0; p<0.01). SRSF2, IDH2, and TP53 mutations did not impact BT. Notably, the aforementioned risk factors for BT, including ASXL1MUT and DNMT3AMUT, were no longer significant when analysis was restricted to patients with MPNMUT. Conclusions The current study suggests a higher risk of BT in CMML patients with MPNMUT, independent of other molecular or clinical risk factors for BT. On the other hand, overall and thrombosis-free survival did not appear to be similarly influenced. The differential impact of previously recognized risk factors for BT in CMML (e.g., ASXL1MUT, DNMT3AMUT, CMML-2, CMML-MP), in the presence (lost significance) vs. absence (remained significant) of MPNMUT was intriguingly noted.

INTRODUCTION: Esophageal adenocarcinoma (EAC) is an aggressive cancer with poor prognosis. Barrett's esophagus (BE) is a critical precursor of EAC. Patients with BE undergo endoscopic surveillance to monitor disease progression although only a small fraction develop EAC. These procedures are invasive and have limited accuracy in predicting BE progression. We evaluated the utility of an 8-protein mass spectrometry panel in predicting progression in patients with BE. METHODS: Eighty untreated controls and 20 cases were selected from our institutional tissue registry. Quantitative mass-spectrometry was performed on microdissected tissue sections. Data were split into 80% training and 20% test sets. We used Least Absolute Shrinkage and Selection Operator-regularized regression to train a logistic classifier on training data. Classifier performance was evaluated in test data. RESULTS: Ninety-two samples had sufficient tissue for mass spectrometry analysis (18 progressors, 74 nonprogressors). The multivariable regression model produced a sensitivity of 100% and a specificity of 39% in the overall cohort, with AUCs of 0.75 and 0.89 in the overall and test cohorts, respectively. Cox proportional hazards time-to-progression (TTP) showed a hazard ratio of 66.1 (95% CI 7.79–561, P = 0.00012) for the model prediction. DISCUSSION: The promising performance of the model generated here suggests that the test may aid in selecting patients most likely to benefit from active BE surveillance. Moreover, the association of this model's prediction with time-to-progression may offer decision support for management of patients likely to progress quickly. These results support continued development of this proteomic panel as a risk stratification tool for patients with BE.

Acute pancreatitis (AP) is among the most common hospital gastrointestinal diagnoses; understanding the mechanisms underlying the severity of AP is critical for development of new treatment options for this disease. Here, we evaluate the biological function of phosphofructo-2-kinase/fructose-2,6-biphosphatase 3 (PFKFB3) in AP pathogenesis in 2 independent genetically engineered mouse models of AP. PFKFB3 was elevated in AP and severe AP (SAP), and KO of Pfkfb3 abrogated the severity of alcoholic SAP (FAEE-SAP). Using a combination of genetic, pharmacological, and molecular studies, we defined the interaction of PFKFB3 with inositol 1,4,5-trisphosphate receptor (IP3R) as a key event mediating this phenomenon. Further analysis demonstrated that the interaction between PFKFB3 and IP3R promotes FAEE-SAP severity by altering intracellular calcium homeostasis in acinar cells. Together, our results support a PFKFB3-driven mechanism controlling AP pathobiology and define this enzyme as a therapeutic target to ameliorate the severity of this condition.

Aims Reticulin stain is used routinely in the histological evaluation of hepatocellular carcinoma (HCC). The goal of this study was to assess whether the histological reticulin proportionate area (RPA) in HCCs predicts tumour‐related outcomes. Methods and results We developed and validated a supervised artificial intelligence (AI) model that utilises a cloud‐based, deep‐learning AI platform (Aiforia Technologies, Helsinki, Finland) to specifically recognise and quantify the reticulin framework in normal livers and HCCs using routine reticulin staining. We applied this reticulin AI model to a cohort of consecutive HCC cases from patients undergoing curative resection between 2005 and 2015. A total of 101 HCC resections were included (median age = 68 years, 64 males, median follow‐up time = 49.9 months). AI model RPA reduction of > 50% (compared to normal liver tissue) was predictive of metastasis [hazard ratio (HR) = 3.76, P = 0.004, disease‐free survival (DFS, HR = 2.48, P < 0.001) and overall survival (OS), HR = 2.80, P = 0.001]. In a Cox regression model, which included clinical and pathological variables, RPA decrease was an independent predictor of DFS and OS and the only independent predictor of metastasis. Similar results were found in the moderately differentiated HCC subgroup (WHO grade 2), in which reticulin quantitative analysis was an independent predictor of metastasis, DFS and OS. Conclusion Our data indicate that decreased RPA is a strong predictor of various HCC‐related outcomes, including within the moderately differentiated subgroup. Reticulin, therefore, may represent a novel and important prognostic HCC marker, to be further explored and validated.