Citations

Abstract Background: Survivor plots permit adjustment by baseline demographics and clinical characteristics; log-normal survival analysis may be more robust than a Cox model under departures from model assumptions. We depicted distant disease-free survival (DDFS) for statistically standardized quantitated ER, PgR, and HER2. Methods: We utilized CCTG MA.27 (NCT00066573), an adjuvant phase III trial of exemestane versus anastrozole in postmenopausal women with ER+ and/or PgR+ tumours. IHC ER, PgR, and HER2 HSCORE were centrally assessed by machine image quantitation, and statistically standardized to mean of 0, standard deviation (SD) of 1 following Box-Cox variance stabilization transformations of square for ER, natural logarithm (ln) and square root for PgR, and ln for HER2. For the ln transformation, 0.1 was added to 0 HSCOREs for a stable transformation. The primary endpoint was DDFS at the longest trial follow-up of 4.1 years. For log-normal survival analysis, ln(time) is a linear function of covariates and had a normal distribution; the Cox models were log-linear for covariates. Survival was depicted with log-normal and Cox survivor plots adjusted at the means of age, T and N stage, grade, lymphovascular invasion, treatment, and baseline patient demographics. We examined ER and PgR ASCO/CAP cut-points at (0; >0), HER2 cut-points at (IHC 0, 0 stain; IHC 0, (0,10%] stain; IHC 1+; IHC 2+; IHC 3+), and ER/PgR/HER2 standardized cut-points at standard deviations about mean of 0 (<-1; (-1,0]; (0,1]; >1). P was based on the likelihood ratio criterion (∼Χ2 (1)) for the addition of ER/PgR/HER2 to the model of baseline covariates, and had nominal significance if P<0.05. Log-normal and Cox multivariable regressions with unstandardized and standardized categorical, and continuous, ER, PgR, and HER2 were adjusted by baseline covariates; 2-sided Wald tests had nominal significance if P<0.05. Results: Of 7576 MA.27 patients, 2325 patients had quantitated image analysis assessments for ER, PgR, and HER2; 113 of 2325 (4.9%) patients experienced a DDFS event during follow-up. Multivariable log-normal survival analysis indicated DDFS was significantly longer for patients with T1 (p=0.01), N0 (p=.002), and grade 1/2 tumors (p=0.01); similar significance levels were found with a Cox model. Log-normal survivor plots were smooth, while Cox survivor plots were step-wise discontinuous at events. Adjusted log-normal survivor plots indicated similar 5-year DDFS for patients by standardized ER categories (p=0.43): 95.4% for those with ER <-1.0 (n=401); 95.8%, for (-1.0,0.0] (n=737); 96.1%, for (0.0,1.0] (n=737); and 96.4%, for >1.0 (n=450). The log-normal standardized PgR survivor plots indicated patients had significantly different 5-year DDFS (p<.001) by categories, with both ln and square root transformations of HSCORE: with a ln transformation, 93.7% for <-1.0 (n=607); 95.4%, for (-1.0,0.0] (n=390); 96.8%, for (0.0,1.0] (n=826); and 97.8%, for >1.0 (n=502). Patients had similar 5-year DDFS by standardized HER2 categories (p=0.71): 96.2% for <-1.0 (n=83); 96.0%, for (-1.0,0.0] (n=1201); 95.9%, for (0.0,1.0] (n=527); and 95.7%, for >1.0 (n=514). In full fit multivariable log-normal survival analyses, DDFS was not significantly different for ER (p=0.51-0.89) and HER2 (p=0.12-0.98); higher PgR was associated with significantly better DDFS (p=0.01 to <.001). Adjusted Cox survival analyses had similar results. Conclusions: Survivor plots adjusted for baseline demographic and clinical characteristics provided similar indications of significance for standardized ER, PgR, and HER2 as those seen in multivariable models with both log-normal and Cox survival analyses. Higher PgR was associated with significantly better DDFS. Citation Format: J. W. Chapman, J. Bayani, S. SenGupta, J. M. S. Bartlett, T. Piper, M. A. Quintayo, S. Virk, P. E. Goss, J. N. Ingle, M. J. Ellis, G. W. Sledge, G. T. Budd, M. Rabaglio, R. H. Ansari, R. Tozer, D. P. D'Souza, H. Chalchal, S. Spadafora, V. Stearns, E. A. Perez, K. A. Gelmon, T. J. Whelan, C. Elliott, L. E. Shepherd, B. E. Chen, K. J. Taylor. Survivor plots for quantitated adjunctive statistically standardized ER, PgR, and HER2 in adjuvant postmenopausal breast cancer: Canadian Cancer Trials Group MA.27 trial of exemestane versus anastrozole [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS3-07-23.

Objectives: To summarize recent high-quality trials and provide an update to the original 2022 American College of Radiology Appropriate Use Criteria for Treatment of Locoregional Gastric Adenocarcinoma. This multi-specialty-led committee included gastrointestinal radiation and medical oncology, gastroenterology, radiology, and surgical oncology. Methods: Using the population, intervention, comparator, outcome, timing, and study design framework, the evidence was assessed using Cochrane and PRISMA 2020 methodology. Eligible studies included prospective Phase II/II trials and select retrospective studies published between 5/1/2020 and 8/1/2025 in the Embase, Medline, and Pubmed databases. Study type and quality were assessed. Well-established RAND-UCLA consensus methodology (modified Delphi) was used to rate the appropriateness of the treatment options. Results: ARS AUC recommendations include adjuvant FLOT chemotherapy for localized gastric adenocarcinoma after neoadjuvant FLOT and surgery, poCT or perioperative chemoimmunotherapy for localized gastric adenocarcinoma, adjuvant chemotherapy +/− CRT for localized gastric adenocarcinoma that undergoes upfront surgery, and systemic therapy alone for localized gastric adenocarcinoma in a medically inoperable patient. Conclusions: This updated ARS AUC summary provides guidelines for the multimodality treatment of resectable gastric adenocarcinoma.

Background Corticosteroid injections (CSIs) are widely employed in facet and sacroiliac joint pain. Similar to CSIs at other sites (peripheral nerve blocks, joints, epidural), these injections are associated with potential adverse events. These multisociety consensus recommendations aim to develop evidence-based statements and recommendations on the safe use of CSIs in facet joint and sacroiliac joint injections. Methods Development of the consensus recommendations was approved by the American Society of Regional Anesthesia and Pain Medicine Board of Directors and several other societies that agreed to participate. The scope of statements and recommendations was agreed on to include safety of the injection technique (landmark-guided, ultrasound, or radiology-aided injections); effect of the addition of the corticosteroid on effectiveness (vs local anesthetic or saline); and adverse events related to the injection. Experts were assigned topics to perform a comprehensive literature review and draft statements and recommendations, which were refined and voted for consensus (>75% agreement) using a modified Delphi process. A modified version of the US Preventive Services Task Force grading of evidence and strength of recommendation was followed. Results All statements and recommendations were approved by all participants after four rounds of discussion. The Practice Guidelines Committees and Boards of Directors of the participating societies also approved all statements and recommendations. Injection of corticosteroid into the facet joint in patients with joint inflammation may relieve pain and improves function. Intra-articular, extra-articular (periarticular), and combined administration are effective for sacroiliac joint injections. No dose-response studies exist, but CSIs containing 10 mg of methylprednisolone or triamcinolone per facet joint and 40 mg per sacroiliac joint (SIJ) (or their respective pharmacologic equivalents) are reasonable. Conclusions In this practice recommendation, we provide statements and recommendations on facet and sacroiliac joint CSIs, the optimal doses, and intervals and criteria for repeating the CSIs in patients with facet joint and sacroiliac joint pain.

Abstract Background: Fatty Acid Synthase (FASN) is a key lipogenic enzyme co-regulated with HER2 and highly expressed in ER+ and HER2+ BC. Its targeting downregulates HER2 expression. Our preclinical studies revealed that FASN inhibition can sensitize or restore sensitivity to trastuzumab, paclitaxel and ET in HER2+ BC models. Denifanstat (deni, formerly TVB-2640) is a novel FASN inhibitor that demonstrated promising clinical activity and safety in a prior phase I trial as either monotherapy or in combination with paclitaxel. The primary objective of this study was to evaluate the objective tumor response rate (ORR) of deni plus trastuzumab (H) in combination with paclitaxel (T) or ET. Methods: Two independent, phase II clinical trials were initiated to assess the efficacy and safety of deni plus H in combination with T (Cohort A) or ET (Cohort B). Key inclusion criteria included HER2+ MBC resistant to HER2-directed therapy, measurable disease, unlimited ET, ≤6 prior chemotherapy or antibody drug conjugate regimens, and confirmation of HER2+ MBC on a pre-registration biopsy. Deni was administered 100 mg/m2 orally once daily. HP or H plus ET (fulvestrant or aromatase inhibitor) was administered at standard dose and schedule. Blood was collected on Cycle 1 Day 1 (C1D1), C1D8 and C2D1 for serum FASN analysis. An additional MBC tumor biopsy was collected on C2D1 for correlative studies. A 2-stage Simon design with a safety-run in was used to test the null hypothesis that the true ORR is at most 5% against the alternative it is at least 20%. With a sample size of 32 patients (pts) per cohort, if ≥4 responses are seen, this design has a 90% chance of rejecting the true ORR is <5% when the true ORR is ≥20% at a 0.10 level of significance. The decision to close both trials to enrollment early was multifactorial. Results: From August 2017 - February 2024, 33 pts with HER2+ MBC pre-registered, among which 17 were eligible and 16 were evaluable (15 pts in Cohort A and 1 pt in Cohort B). The most common reason for ineligibility was HER2-negative status on central review of the pre-registration biopsy. Median age was 57 years (range 35-80). All pts were non-Hispanic and 13 (81.3%) were White. Median prior lines of therapy was 5 (range 0 - 11). In Cohort A, there were 5 partial responses; thus, the primary endpoint was met with the ORR estimated to be 33.3% (90% CI: 14.2-57.7%). The median PFS time was 7.0 months (95 %CI: 3.7 - 11.3), and median OS was 25.7 months (95%CI: 10.2 - NE). No dose limiting toxicities were observed during the C1 safety run-in (6 pts). In Cohort A, 7 (46.7%) developed a grade 3 or 4 adverse event (AE) attributed to combination therapy. Grade ≥2 AEs regardless of attribution occurring in ≥20% of all pts included anemia, fatigue, neutropenia, palmar plantar erythrodysesthesia (PPE), and peripheral neuropathy. Treatment was discontinued due to progression (12; 80%) or AE (3; 20% - pneumonitis; neuropathy; PPE). In Cohort B, the pt maintained stable disease through 8 cycles with grade 3 ALT increase, and she remained alive 31.2 months post-registration. Median C1D1 FASN level was 32.7 ng/mL (IQR: 18.7 - 49.6 ng/mL). There was minimal association between C1D8 and C2D1 FASN levels and time to disease progression (C1D8 n=9, Spearman rank correlation coefficient (r s) = 0.040; C2D1 n=13, r s = -0.019). Analyses of changes in MBC tumor expression of FASN, phospho-AKT, and phospho-S6 are in progress. Conclusion: Deni combined with HP provided clinical antitumor activity in pts with HER2+ MBC resistant to trastuzumab. Expected paclitaxel-associated AEs were observed. Nearly half of pts experienced a grade 3 or 4 AE attributed to the combination therapy, and 20% stopped treatment due to AE. Further study of deni, H plus ET is necessary to draw safety and efficacy conclusions. Citation Format: T. C. Haddad, V. J. Suman, R. R. Roa, B. J. Ernst, R. Lupu, T. Vander Steen, M. H. Solanki, M. Keeney, D. W. Northfelt, K. S. Anderson, T. J. Hobday, S. Chumsri, J. E. Hoppenworth, J. L. Carroll, K. V. Giridhar, C. C. O’Sullivan, R. A. Leon-Ferre, M. P. Goetz. Phase II Trial of the FASN Inhibitor, Denifanstat (TVB-2640), Plus Trastuzumab in Combination with Paclitaxel or Endocrine Therapy (ET) in Patients with HER2+ Metastatic Breast Cancer (MBC) Resistant to Trastuzumab [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS5-01-16.

Abstract Introduction: An Our Practice Advisory (OPA), formerly known as Best Practice Advisory (BPA), is an electronic health record (EHR) tool. OPAs identify key parameters to alert providers of potential interventions that could enhance quality of care. Such functionality is increasingly relevant given the rapid pace of new drug approvals. Within the Mayo Clinic system, we previously identified that amongst Mayo Clinic patients (pts) meeting the MonarchE criteria, 28% of pts did not undergo a documented discussion with their provider regarding the role of adjuvant abemaciclib (Premji, SABCS 2024). Further, a Flatiron study identified that only 40% of eligible pts received abemaciclib (Sandoval, Miami Breast 2025). To address this practice gap, in 2024 we began to implement EHR clinical decision support by creating an OPA trigger for pts eligible for an adjuvant CDK 4/6 inhibitor (CDK 4/6i). Here we report on ‘action taken’ versus not for the OPA and the most common reasons for re-prompts. Methods: The Mayo Breast Disease Group designed an OPA including pts who are within 14 months of a clinical or pathologic diagnosis of high-risk early-stage breast cancer. We leveraged structured data captured in the Epic staging forms (Epic Systems) to identify pts with clinical or pathologic T-stage, N-stage, grade, ± Ki-67/ multigene signature to identify ER+/HER2- pts eligible for adjuvant ribociclib or abemaciclib based on FDA approvals. The OPA was triggered by a patient encounter in oncology when endocrine therapy (but not CDK4/6i) was on the active medication list resulting in a hard stop. The OPA gathered limited details about whether adjuvant CDK4/6 inhibitors were discussed and whether the provider followed a link that resulted in prescribing one—considered an indicator of action taken. In this IRB-exempt quality improvement project, we describe the responses captured in the OPA trigger utilizing Epic tools. Results: The OPA went live on 1/10/2025. Over a 5-month period post OPA initiation, we identified 517 OPA alerts among 332 unique pts. Their median age was 62.5 years, and the majority were female (97%). The median time to resolve the OPA was 17.5 seconds (range 2-567 seconds). 12.6% (65/517) of the time there was ‘action taken’ by selecting the hyperlink to potentially start a treatment plan. Providers selected the following OPA pre-set responses: ‘re-prompt in one month’ 248 (48%), ‘patient not a candidate for therapy’ 48 (9%), ‘patient declines’ 69 (13%), ‘outside oncologist will prescribe’ 36 (7%), ‘not discussed’ 44 (9%), and unknown 72 (14%). The most common free text comments among the 517 OPA alerts (summarized) included: ‘revisit in future’ 108 (21%), ‘too early’ 65 (13%), ‘patient declines’ 66 (13%), ‘outside oncologist will start’ 31 (6%), ‘not a candidate’ 26 (5%), and ‘co-morbidities’ 18 (3%). Erroneous OPA prompting occurred in 14 (3%) who previously failed a CDK4/6i due to toxicity and in 18 (3%) for pts currently on a CDK4/6i. 30 (6%) OPA comments noted that they discussed or started therapy that day. Conclusion: The OPA offered clinical decision support and ensured that clinicians considered prescribing CDK 4/6i in all pts identified as eligible, and captured deferrals. Refinements are needed to ensure appropriate timing of OPA and minimize erroneous firing. The OPA remains active and captures the reason for deferral of adjuvant CDK 4/6i prescription. This data pairs real world decision making to better understand clinically meaningful application of improved invasive disease-free survival (iDFS). Citation Format: S. Premji, P. Advani, S. Chumsri, L. Mina, J. Taraba, J. Carroll, J. Hoppenworth, E. Cathcart-Rake, T. Haddad, B. Rudder, G. Choong, D. Idossa, C. O’Sullivan, S. Yadav, K. Ruddy, P. Peethambaram, T. Hobday, M. Goetz, R. Rao, B. Ernst, F. Batalini, R. Leon-Ferre, A. Tevaarwerk, K. Giridhar. Implementing an Our Practice Advisory (OPA) to provide clinical decision support for adjuvant CDK4/6 inhibitors in early-stage hormone receptor positive breast cancer: The Mayo Clinic Experience [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS5-11-10.

Abstract Background: BRCA2 variants with partially aberrant RNA splicing have been associated with a relatively lower breast cancer risk (reduced penetrance) relative to canonical pathogenic variants. However, the existence of partial loss of function (hypomorphic) missense variants, conferring reduced penetrance, is less certain. Identification and assessment of the clinical relevance of such reduced penetrance pathogenic variants (RPPVs) is needed to provide accurate risk estimates. Methods: Comprehensive functional characterization of hypomorphic missense variants (n=70) in the BRCA2 DNA-binding domain, initially identified through homology-directed DNA repair (HDR) assays, was conducted through multiple independent functional assays, including HDR, CRISPR/Cas9-based endogenous targeting, RAD51 foci formation assay, and Poly(ADP-ribose) polymerase (PARP) inhibitor response assay. Risk estimates were obtained using two large datasets from patients referred for hereditary cancer testing. A ClinGen/ACMG/AMP model was used for clinical classification. Results: The variants consistently demonstrated hypomorphic HDR activity and endogenous survival in HAP1 targeted cells, decreased RAD51 foci formation, and increased sensitivity to PARP inhibitors. These variants were associated with a moderate increase in breast cancer risk, as shown in two independent studies: one using multivariable logistic analysis adjusted for age, ancestry and family history (OR=2.41, 95%CI=1.51-3.85) and another comparing frequencies of variants in breast cancer cases to public reference controls adjusted for ancestry (OR=2.09, 95% CI=1.16-4.08). The mean age of breast cancer diagnosis for carriers of hypomorphic variants was 57 years, which was significantly older than the mean age of diagnosis of 51 years for carriers of protein truncating variants. Functional data were combined with other evidence sources in a ClinGen/ACMG/AMP model to classify 14 variants as “likely pathogenic”. Conclusions: We identified partially functional, hypomorphic missense variants associated with reduced penetrance for breast cancer. Cancer risk management guidelines for this new category of variants should be revisited given that the associated breast cancer risks warrant high risk screening but do not meet the threshold at which risk reducing mastectomy is offered. This study supports a shift in paradigm to considering variant-based risks on a continuum, with implications for risk-appropriate cancer risk management. Citation Format: H. Huang, C. Hu, J. Na, M. Kucera, T. Simmons, E. Mundt, C. C. Young, Z. Heidari, P. C. Lyra, Y. Y. Tan, K. L. Nathanson, T. Pal, R. Karam, T. Pesaran, S. Yadav, S. M. Domchek, A. N. Monteiro, E. Hughes, N. Boddicker, W. Chen, M. E. Richardson, F. J. Couch. Partially functional (hypomorphic) missense variants in BRCA2 are reduced penetrance pathogenic variants [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PD4-05.

Abstract Background: TheTAILORx trial established that adjuvant endocrine therapy (ET) is non-inferiorto chemotherapy plus ET (CET) in T1-2N0 HR+/HER2-negative early breast cancer(EBC) with an Oncotype DX (ODX) 21-gene recurrence score (RS) of 11-25, RS 0-10is associated with low distant recurrence (DR) rates with ET alone, and RS26-100 is associated with higher DR rates despite CET. Although ODX isprognostic for 10-year DR, it has limited value for late DR >5 years. Inorder to develop improved DR risk prognostication, we developed multimodal AImodels integrating clinical, molecular, and histopathology features to provideprognostic information for early (<5years), late (>5 years), and overall DR at 15 years using primary tumorsamples and clinical data from volunteers who participated in TAILORx. Methods: DigitizedH&E slides were generated and nucleic acids extracted and sequenced from∼5000 primary tumor samples using Caris MI Tumor Seek-Hybrid, of which 2,808(56%) were used for model training and 5-fold nested cross validation (60/20/20split). Models included single-modality (clinical [C], image [I], molecular [M:ODX genes]), dual-modality (CM, IC), and multimodal (ICM). An expandedmolecular model (M+) model was also derived from expanded molecular inputsderived from whole transcriptome sequencing (WTS) data, including 5 commercialgene signatures (ODX, MammaPrint, Prosigna, EndoPredict, BCI) and 57 high-variancegenes; only EndoPredict, BCI, and ODX gene signatures were retained for model M+.Model-CM+ combined clinical plus expanded molecular features, while ICM/ICM+integrated image, clinical, and (expanded) molecular inputs. Risk scores were dichotomized into high vs. low risk groups usingthresholds chosen to yield risk group proportions closely matching thosedefined by the ODX RS cutoff of 25 for distinguishing high vs. low genomicrisk. Theprimary endpoint was distant recurrence (DR). Prognostic performance wasassessed using truncated concordance index (C-index, 90th percentile of eventtimes), hazard ratios (HRs), and log-rank tests. DNA-level whole exomesequencing (WES) features were also tested but did not provide additionalprognostic information and thus excluded from final models. Results: Theactual ODX continuous RS achieved a C-index of 0.625 for overall DR and 0.743early DR, but no prognostic value for late DR (0.52). Similar results for theC-index were observed for ODX+C for overall DR (0.619), early DR (0.724), andlate DR (0.514). Of all modelsevaluated, model-ICM+ gave the best overall prognostic accuracy for overall DR (C-index0.713; hazard ratio [HR] 3.56 for comparison of high vs. low risk, p<0.001)and late DR (C-index 0.655; HR 2.36, p<0.001), and ranked second for earlyDR (C-index 0.772; HR 6.59, p<0.001) behind the CM+ model (C-index 0.782). Amongsingle-modality models, Model-M+ improved early DR prognostication comparedwith a molecular model including only ODX genes(C-index 0.767 vs 0.744 for M),whereas Model-I was strongest for late DR prognostication (C-index 0.635). Conclusions: Molecularfeatures primarily drove prognostic accuracy for early DR within 5 years,whereas histopathology features strengthened the prognostic accuracy for lateDR after 5 years. Multimodal models captured these complementary signals, withICM+ giving the best overall accuracy for individualized prognostic assessment.Additional validation of the optimized ICM+ model and other models is beingperformed in an intendent validation sample of 2000 TAILORx volunteers, withresults to be presented at the meeting.Supported by the Breast CancerResearch Foundation and the U.S. NIH/NCI U10CA180820 and 5U24CA196172, and theU.S. Postal Service Breast Cancer Stamp Fund. Citation Format: J. A. Sparano, V. Wang, R. J. Gray, D. F. Makower, K. S. Albain, D. F. Hayes, C. E. Geyer, E. C. Dees, M. P. Goetz, J. A. Olson, S. S. Badve, T. J. Saphner, T. J. Whelan, M. Radovich, V. G. Kaklamani, G. W. Sledge. Multimodal artificial intelligence (AI) models integrating image, clinical, and molecular data for predicting early and late breast cancer recurrence in TAILORx [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr GS1-08.

Abstract Intravital imaging studies have provided insights into the spatial and temporal variations of platelet activation and thrombin generation that occur during hemostasis; however, these studies are generally limited to small vessels due to the practical limitations of imaging in thicker tissues. Recent advances in cleared tissue fluorescence imaging as well as volume electron microscopy (vEM) coupled with machine learning–based image segmentation provide an opportunity for analysis of the 3-dimensional structure of complex tissues. We utilized these technologies to examine hemostatic plugs from murine jugular veins and carotid arteries to investigate the spatial distribution of platelet activation and biochemical responses in these disparate physiologic contexts. Both venous and arterial hemostatic plugs had a heterogeneous structure with regions of sparsely and densely packed platelets. Despite similar injury sizes, arterial hemostatic plugs were at least an order of magnitude larger than venous plugs. The difference in plug size was primarily due to a 19-fold increase in the population of densely packed platelets in the extravascular compartment. Venous plugs displayed significant platelet aggregation extending into the vessel lumen and developed distinctive fibrin and red blood cell–filled cavities. Complementary fluorescence microscopy revealed that platelet activation was spatially heterogeneous in both contexts, with α-granule secretion and phosphatidylserine exposure confined to specific microenvironments, highlighting tightly regulated thrombin activity. Overall, our findings reveal both conserved and distinct mechanisms of hemostatic thrombus formation in different physiologic contexts. They also demonstrate the power of vEM coupled with machine learning–based image segmentation for the quantitative analysis of large imaging data sets from complex tissues.

Abstract INTRODUCTION The Centiloid scale is the standard for amyloid (Aβ) PET quantification in research and clinical settings. However, variability between tracers and scanners remains a challenge. METHODS This study introduces DeepSUVR, a deep learning method to correct Centiloid quantification, by penalizing implausible longitudinal trajectories during training. The model was trained using data from 2,129 participants (7,149 Aβ positron emission tomography [PET] scans) in the Australian Imaging, Biomarkers and Lifestyle Study of ageing (AIBL)/Alzheimer's Disease Neuroimaging Initiative (ADNI) and validated using 15,807 Aβ PET scans from 10,543 participants across 10 external datasets. RESULTS DeepSUVR increased correlation between tracers, and reduced variability in the Aß‐negatives. It showed significantly stronger association with cognition, visual reads, neuropathology, and increased longitudinal consistency between studies. DeepSUVR also increased the effect size for detecting small treatment related slowing of amyloid accumulation in the A4 study. DISCUSSION DeepSUVR substantially advances Aβ PET quantification, outperforming all standard approaches, which is particularly important for clinical decision making and to detect subtle or early changes in Aβ. Highlights Novel artificial intelligence (AI)‐method that penalizes biologically implausible longitudinal trajectories, enabling the model to learn standardized uptake value ratios (SUVR) correction factors without requiring longitudinal data at inference time. Improves Centiloid consistency across tracers and studies, significantly enhancing cross‐sectional and longitudinal amyloid positron emission tomography (PET) quantification. DeepSUVR‐derived Centiloids show stronger associations with cognition, visual reads, and neuropathology. Longitudinal variability is reduced three‐ to five‐fold, enabling more reliable tracking of amyloid accumulation and better detection of treatment effects. Novel reference and target masks derived from DeepSUVR replicate most of the model's performance, offering a practical alternative for integration into existing pipelines.