Citations

e15722 Background: Despite overall improvements in colorectal cancer (CRC) outcomes, concerning trends have emerged in younger populations. We examined two decades of US mortality data to characterize age-specific trajectory differences and identify inflection points in the epidemiologic landscape of CRC. Methods: Using CDC WONDER data (1999–2020), we analyzed age-adjusted CRC mortality rates (ICD-10: C18–C20) stratified by age: early-onset (≤44 years) versus late-onset (≥45 years). Joinpoint regression analysis (Version 5.4.0.0) with permutation testing identified significant trend changes. Annual Percent Change (APC) estimates with 95% confidence intervals assessed temporal patterns, with statistical significance set at α = 0.05. Results: Late-onset CRC (≥45 years): Mortality rates declined substantially from 69.26 to 40.49 per 100,000, representing a 41.6% reduction. A critical inflection point occurred in 2014 (95% CI: 2011–2015), marking a deceleration in the rate of improvement. The pre-2014 period showed robust decline (APC: −3.06%; 95% CI: −3.18 to −2.93; p < 0.000001), which slowed significantly post-2014 (APC: −1.61%; 95% CI: −2.12 to −1.09; p = 0.000006)—a 47% reduction in the pace of mortality improvement.Early-onset CRC (≤44 years): In stark contrast, mortality rates increased from 0.92 to 1.13 per 100,000, representing a 22.8% rise. No inflection points were identified; instead, a persistent upward trajectory characterized the entire 22-year period (APC: +0.78%; 95% CI: +0.54 to +1.02; p = 0.000001). This yielded a continuous, unabated increase in deaths among young adults. Conclusions: This analysis reveals a troubling paradox in US colorectal cancer mortality: while older adults experienced substantial but decelerating improvements, young adults faced steadily worsening outcomes throughout the study period. The 2014 inflection point in older adults, coinciding with slowed screening expansion and potential changes in risk factor prevalence, coupled with the relentless rise in early-onset mortality, signals an urgent need to reassess prevention strategies, lower screening age thresholds, and investigate biological and environmental drivers of early-onset disease. The nearly 23% increase in mortality among those ≤44 years represents a growing public health crisis demanding immediate action.

e13082 Background: Human epidermal growth factor receptor 2 (HER2)–low breast cancer, defined as HER2 immunohistochemistry (IHC) 1+ or IHC 2+/in situ hybridization–negative, represents a newly targetable subtype comprising nearly half of all breast cancers. Brain metastases are a common and morbid complication of metastatic breast cancer, yet patients with active central nervous system (CNS) disease are frequently excluded from clinical trials. Trastuzumab deruxtecan (T-DXd), an antibody–drug conjugate with a cleavable linker and potent topoisomerase I inhibitor payload, has demonstrated substantial intracranial activity in HER2-positive disease. However, the intracranial efficacy of T-DXd in patients with HER2-low breast cancer remains incompletely characterized. Methods: A systematic literature search was conducted across PubMed/MEDLINE, Embase, CENTRAL, ClinicalTrials.gov, and Web of Science from database inception through January 1, 2025. A total of 2,275 records were identified and screened. Eligible studies included randomized controlled trials and prospective or retrospective clinical studies evaluating trastuzumab deruxtecan in patients with HER2-low metastatic breast cancer and measurable brain metastases. Studies were required to report intracranial objective response rate (IC-ORR), defined as complete or partial intracranial response among CNS-evaluable patients, assessed by study-defined criteria (RECIST 1.1 or RANO-BM). Results: Five studies comprising 62 patients with HER2-low metastatic breast cancer and brain metastases were included. Using a random-effects proportional meta-analysis with Freeman–Tukey double arcsine transformation, the pooled intracranial objective response rate (IC-ORR) was 46% (95% CI, 27–65%). Between-study heterogeneity was moderate (I² = 47.7%, p = 0.11), with consistent directionality of intracranial activity observed across included cohorts. Conclusions: Across five studies, T-DXd demonstrated clinically meaningful intracranial activity in HER2-low metastatic breast cancer with brain metastases, yielding a pooled IC-ORR of 46%. This provides one of the first quantitative benchmarks of CNS response in HER2-low disease, where evidence has been limited to small, heterogeneous cohorts. These findings support dedicated prospective trials in HER2-low patients with active CNS disease and standardized intracranial endpoints to refine patient selection and expected benefit. Summary of outcomes. Study Year CNS-Evaluable Patients (N) Intracranial Responders (CR+PR) IC-ORR (%) Zhou et al. 2025 15 7 46.7 (21.0–73.0) Batista et al. 2024 6 3 50.0 (12.0–88.0) Lazaratos et al. 2024 6 4 66.7 (22.0–96.0) Duan et al. 2025 9 6 66.7 (30.0–93.0) Burnside et al. 2024 26 6 23.1 (9.0–44.0) Pooled estimate (random effects) — 62 26 46.0 (27.0–65.0)*

e12749 Background: Breast cancer (BC) survivors are at higher risk for recurrence or new primary disease and often require complex surveillance imaging. Use of contrast enhanced surveillance imaging modalities with contrast-enhanced digital mammography (CEM) and magnetic resonance imaging (MRI) has increased in recent years. This study evaluates characteristics of those BC survivors who receive contrast enhanced imaging and whether the addition of contrast enhanced imaging affects biopsy outcomes in BC survivors. Methods: An IRB-approved retrospective chart review identified female BC survivors who underwent breast surgery and subsequent surveillance imaging at a single academic center between 2016 and 2025. Surveillance episodes were categorized as mammography alone versus mammography with addition of CEM and/or MRI. Multivariable generalized estimating equations were used to compare patient and tumor characteristics associated with enhanced imaging modality use. Similarly rates of biopsy and cancer were evaluated with enhanced imaging use. Results: A total of 4,050 surveillance imaging episodes in 861 patients were identified and 54 resulted in biopsy-proven malignancy. Mammography alone was performed in 3,459 episodes, while enhanced imaging with CEM or MRI was used in 591 (14.6%) episodes. Use of CEM or MRI for surveillance imaging increased over time. In 2016, surveillance imaging consisted predominantly of mammography alone (93.3%) with 6.6% incorporating MRI or CEM. By 2025, mammography only surveillance decreased to 78.4% while use of MRI or CEM increased to 21.6%. Use of contrast enhanced imaging was associated with higher incidence rate ratios (IRR) for dense breast tissue [IRR 2.33; 95% CI 1.92, 2.82), p < 0.001] and less frequently used among patients aged 65–79 years [IRR 0.60, 95% CI 0.49, 0.74; p < 0.0001] and > = 80 years of age [IRR 0.40; 95% CI 0.24, 0.66; p < 0.001]. Ductal carcinoma in situ (DCIS) (IRR 3.09, p = 0.0061), and immunotherapy use (IRR 2.56, p = 0.0006) also were associated with increased use of CEM/MRI enhanced imaging. Biopsies were performed in 146 (4.2%) mammography alone episodes and 55 (9.3%) enhanced imaging episodes [IRR 2.20; 95% CI 1.63, 2.96; p < 0.001]. Surveillance with mammography yielded malignant biopsy results in 39 (1.1%) episodes, compared with 15 (2.5%) episodes using enhanced imaging [IRR 2.25; 95% CI 1.25, 4.06; p = 0.007). Conclusions: In breast cancer surveillance at our institution, the addition of contrast enhanced imaging modalities were utilized in a minority of surveillance episodes but did increase over time and were higher in patients with dense breasts. CEM or MRI usage demonstrated higher biopsy rates and increased malignancy detection compared with mammography alone, but the incidence of a positive biopsy was low. These findings suggest and are in keeping with 2023 ACR guidelines that enhanced imaging may improve cancer detection in select breast cancer survivors.

Abstract Background High‐resolution MRI is essential for accurate diagnosis and treatment planning, but its clinical acquisition is often constrained by long scanning times, which increase patient discomfort and reduce scanner throughput. While super‐resolution (SR) techniques offer a post‐acquisition solution to enhance resolution, existing deep learning approaches face trade‐offs between reconstruction fidelity and computational efficiency, limiting their clinical applicability. Purpose This study aims to develop an efficient and accurate deep learning framework for MRI SR that preserves fine anatomical detail while maintaining low computational overhead, enabling practical integration into clinical workflows. Materials and Methods We propose a novel SR framework based on multi‐head selective state‐space models (MHSSM) integrated with a lightweight channel multilayer perceptron (MLP). The model employs 2D patch extraction with hybrid scanning strategies (vertical, horizontal, and diagonal) to capture long‐range dependencies while mitigating pixel forgetting. Each MambaFormer block combines MHSSM, depthwise convolutions, and gated channel mixing to balance local and global feature representation. The framework was trained and evaluated on two distinct datasets: 7T brain T1 MP2RAGE maps (142 subjects) and 1.5T prostate T2w MRI (334 subjects). Performance was compared against multiple baselines including Bicubic interpolation, GAN‐based (CycleGAN, Pix2pix, SPSR), transformer‐based (SwinIR), Mamba‐based (MambaIR), and diffusion‐based (I 2 SB, Res‐SRDiff) methods. Results The proposed model demonstrated superior performance across all evaluation metrics while maintaining exceptional computational efficiency. On the 7T brain dataset, our method achieved the highest structural similarity (SSIM: ) and peak signal‐to‐noise ratio (PSNR: dB), along with the best perceptual quality scores (LPIPS: ; GMSD: ). These results represented statistically significant improvements over all baselines (), including a 2.1% SSIM gain over SPSR and a 2.4% PSNR improvement over Res‐SRDiff. For the prostate dataset, the model similarly outperformed competing approaches, achieving SSIM of , PSNR of dB, LPIPS of , and GMSD of . Notably, our framework accomplished these results with only 0.9 million parameters and 57 GFLOPs, representing reductions of 99.8% in parameters and 97.5% in computational operations compared to Res‐SRDiff, while also substantially outperforming SwinIR and MambaIR in both accuracy and efficiency metrics. Conclusion The proposed framework provides a computationally efficient yet accurate solution for MRI SR, delivering well‐defined anatomical details and improved perceptual fidelity across anatomically distinct datasets. By significantly reducing computational demands while maintaining state‐of‐the‐art performance, the model offers strong potential for feasibility toward clinical translation and scalable integration into future imaging workflows.

9568 Background: Stage IIB/C cutaneous melanoma is associated with high recurrence risk, however stratification of risk in relation to time after surgery has not been comprehensively evaluated. We evaluated recurrence-free survival (RFS) at key time points, stratified by clinicopathologic factors, to identify patients (pts) at higher recurrence risk and personalize postoperative surveillance strategies. Methods: In this multi-institutional, international retrospective cohort study from the Sentinel Lymph Node Working Group database, we included pts with pathologic T3b/T4a/T4b and N0 disease who underwent surgical resection and sentinel node biopsy from 1994-2025. The type of first recurrence (local, regional, distant) was characterized based on time category (0-12, 12-24, 24-60, and 60+ months after surgery). Restricted mean survival time (RMST) analysis was used to measure the average survival time up to a specified time point (6-, 12-, 24-, and 60-months after surgery), and associations of clinicopathologic variables (age, sex, Breslow thickness, ulceration and lymphovascular invasion [LVI]) with RFS. Results: We included 2514 stage IIB/C pts from 19 sites in 4 countries, with a median follow-up of 53 (stage IIB) and 49 (stage IIC) months. 675 (27%) pts experienced a recurrence (92 [14%] local, 238 [35%] regional and 345 [51%] distant), and 400 (59%) recurrences occurred within 24 months. The proportion of distant recurrences as the first recurrence increased significantly with time, comprising 39%, 50%, 62%, and 59% of recurrences in the 0-12, 12-24, 24-60, and 60+ month time categories respectively (χ 2 p<0.001). No significant differences were observed for the included clinicopathologic variables for 6-month RMST estimates. At 12 months, RMST estimates for thickness ≥4 mm (11.2 vs 11.6 months for thickness 2-3.99 mm, p<0.001) and presence of LVI (10.7 vs 11.4 months, p=0.009) were significantly different. 24-month RMST estimates differed for male sex (20.7 vs 21.5 months vs females, p=0.002), thickness ≥4 mm (20.5 vs 21.9 months, p<0.001), and presence of LVI (19.0 vs 21.1 months, p<0.001). Lastly, 60-month RMST estimates differed for male sex (42.0 vs 45.2 months, p=0.001), thickness ≥4 mm (41.5 vs 46.2 months, p<0.001), LVI (36.0 vs 43.7 months, p<0.001), and age >65 years (41.5 vs 46.4 for age <42, p=0.022). Conclusions: In this real-world, multi-center analysis of pathologic stage IIB/C melanoma pts, recurrence patterns varied based on time after surgery. Breslow thickness, LVI, male sex, and age were significantly associated with earlier recurrence at different time intervals on RMST analysis. Additionally, given that >50% of first recurrences 12+ months after surgery were distant, active surveillance for distant relapses may be warranted.

9524 Background: Unresectable melanoma in-transit metastases (ITM) can pose a significant clinical challenge. Our recently published data comparing first-line treatments for ITM, isolated limb infusion or perfusion (ILI/ILP), immune checkpoint inhibitors (ICI) and intralesional talimogene laherparepvec (TVEC), found superior outcomes with TVEC. However, TVEC was used more often in patients with lower disease burden and earlier stage (IIIB vs. IIIC/D). Therefore, we sought to better investigate these differences with a propensity score-matched (PSM) analysis. Methods: A multi-institutional, international IRB- approved retrospective analysis was conducted for unresectable melanoma ITM from 2016-2022. PSM analysis comparing first-line ILI/ILP, ICI, and TVEC for was performed. Patients were matched for stage, number of ITM, anatomical site, CLND status, gender and age. Kaplan-Meier curves (OS, PFS, DMFS) and Cumulative incidence function (MSS) were used to visualize time-to-event outcomes in the PSM cohort, though both methods do not account for the matched structure. Results: 274 patients were identified, 120 female/154 male; 96 treated with ILI/ILP, 111 with ICI, and 67 with TVEC. Median follow-up was 40 months (range, 1-80). PSM was performed and identified 36 TVEC–ICI pairs and 27 TVEC–ILI pairs. These were combined resulting in a final cohort of 108 observations (45 TVEC, 36 ICI and 27 ILI). The groups were well balanced. No statistical difference was found for metastasis-free survival (DMFS), progression-free survival (PFS), melanoma-specific survival (MSS), and overall survival (OS) between treatment modalities. TVEC was associated with significant improvement in local PFS (median was 2.2 years (y) for ILI/ILP, 1.5y for ICI and not reached for TVEC, p=0.048). While not statistically significant, a clinical benefit was seen in PFS being longer for TVEC (2.1y for TVEC vs. 1.2y for ILI/ILP and 1.1y for ICI; p=0.2) and OS (not reached vs 2.9y for ILI/ILP and 5.2y for ICI; p=0.2). On mixed effect Cox regression proportional hazard model using the matched data set, there were no significant differences in any of the survival and recurrence outcomes. Conclusions: When patients are propensity-matched, there were no significant differences in first-line treatment modalities for unresectable melanoma ITM. Treatment with TVEC did result in clinically meaningful improved overall and local PFS and OS. This supports that selection of ITM therapy should incorporate an individualized approach, incorporating disease distribution, stage, burden, treatment side effects and patient priorities.

9525 Background: Melanocortin-1 receptor (MC1R) is a novel target for radiopharmaceutical therapy and is highly expressed on melanoma tumor cells. VMT01 is an MC1R-targeted peptide. 203 Pb is used for patient selection via SPECT imaging. Peptide radiolabeling with 212 Pb delivers alpha-particle therapy. Here, we present data on the treatment of adult patients with MC1R-positive metastatic melanoma receiving [ 212 Pb]VMT01 either as a monotherapy or in combination with the programmed death-1 (PD-1) checkpoint inhibitor, nivolumab. Methods: This is an ongoing phase I/IIa, first-in-human, prospective, multicenter, open-label, radioactive dose-finding and dose-expansion trial. The objectives are to investigate safety, pharmacokinetics, dosimetry, and efficacy. Participants receive up to 3 treatment cycles with either [ 212 Pb]VMT01 3 mCi, 5 mCi, or 1.5 mCi monotherapy, or combination therapy with [ 212 Pb]VMT01 (1.5 mCi) + nivolumab (480 mg, Q4W) or [ 212 Pb]VMT01 (3 mCi) + nivolumab. Participants are evaluated for any DLTs for the first 6 weeks after cycle 1. Efficacy is assessed by RECIST v1.1 criteria by the investigator. Results: As of 24 December 2025, 26 participants (53.8% male; median age: 68 years [range: 27-81]) with MC1R-positive metastatic melanoma were enrolled. The median prior systemic therapies was 4. All 26 enrolled participants received ≥1 dose of [²¹²Pb]VMT01. No DLTs were reported. All SAEs (including one grade 5 SAE) were attributed to disease progression. Most TEAEs were grade 1 (19.2%) and grade 2 (34.6%). Grade 3 TEAEs occurred in 8 participants (30.8%), 5 on monotherapy and 3 on combination therapy (3 mCi + nivolumab). Of the 22 evaluable participants, 1 PR, 9 SD, and 12 PD were reported. Four participants had progression-free survival of ≥6 months. Conclusions: [ 212 Pb]VMT01 as a monotherapy and in combination with nivolumab was generally safe and well-tolerated in 26 enrolled participants, with antitumor activity observed at the 3 mCi dose level. These data may be supplemented with a more complete follow-up at the time of the meeting. Clinical trial information: NCT05655312 .

9007 Background: Since transition to virtual interviews, application and interview inflation have increased the work burden of GME recruitment. In 2021, AAMC ERAS implemented a process that allows applicants to assign signals to top programs of interest. There is a paucity of guidance on optimal use of ERAS signals (ES), resulting in apprehension and uncertainty amongst applicants and program directors (PD). For the 2026 ERAS cycle, Hematology/Oncology programs (HOP) had the option to participate in ES, in which applicants are provided 5 gold (G) signals and 15 silver (S) signals. First-hand knowledge on how ES was utilized by HOP, as well as PD perceptions about ES, may guide best practices on ES. Methods: During the ASCO Oncology Training Program Leadership Retreat in November 2025, an anonymous survey, assessing HOP utilization and perception of ES, and the impact of ES on recruitment practices, was launched. One PD from each HOP was invited to complete the survey while onsite. Results: 88 HOP (46% of ACGME HOP) are represented. 97% (n=85) utilized ES. Of HOP who used ES, 74% are academic. 32% are small (1-9 fellows), 43% medium (10-19 fellows), and 25% large (20+ fellows). 79% received 400+ applications. 69% reviewed applications without signals but gave higher consideration to signaled applicants. 25% only reviewed applications with signals. 28% used ES when creating rank list; 45% think ES utilization is appropriate during ranking. 85% reported ES did not alter their approach to applicants requiring visa sponsorship. 78% felt ES made the interview selection process easier. 66% were more satisfied with this year’s recruitment process compared to years without ES. The most requested change to ES was reduction of allowed signals, especially silver. 98% will use ES next year. Conclusions: Despite limited knowledge on ES impact on recruitment, nearly all surveyed HOP participated in ES this past year and will continue. Most HOP view ES positively though many desire changes, particularly with the number of signals. Most HOP consider all applications regardless of ES. However, some HOP with larger applicant pool are using ES as inclusion criteria for interview consideration. Signals are a strong predictor for interview invitation when internal selection criteria are met. The “borderline” applicant may be the greatest benefactor from ES, viewed similarly to the non-signaled applicant who meets internal selection criteria. Sharing PD perspectives and real-life data from this year’s ES process breeds opportunities for further improvement and increased confidence with ES. Likelihood HOP offer interview invitation based on quality of application and signals (%, n=85). Internal Selection Criteria Signal Extremely Likely Likely Neutral Unlikely Extremely Unlikely Met G 73 22 5 0 0 S 42 47 8 2 1 None 8 27 24 22 19 Nearly met G 4 35 39 19 3 S 0 9 52 28 11 Not met G 0 2 12 41 45 S 1 1 6 30 62

8597 Background: Lorlatinib improves outcomes in NSCLC but commonly causes marked hyperlipidemia, prompting initiation of lipid-lowering therapy (LLT). Beyond lipid control, LLT may be associated with vascular events; however, its association with thromboembolism, healthcare utilization, and mortality among lorlatinib-treated patients has not been characterized in real-world cohorts. Methods: Using TriNetX, we identified adults with NSCLC who received lorlatinib (index = first lorlatinib record). Patients were grouped by early LLT initiation within 30 days of index versus no LLT within 30 days. LLT included statins, ezetimibe, PCSK9 inhibitors, or fibrates. Cohorts were balanced 1:1 using propensity score matching on demographics and baseline comorbidities. Outcomes were assessed through 365 days; patients with prior outcome documentation were excluded. Results: After matching, 387 patients per cohort were analyzed. Early LLT was associated with lower all-cause mortality at 365 days (16.1% vs 26.4%; risk ratio [RR] 0.61, 95% CI 0.46-0.81; p=0.0004) and improved time to death (hazard ratio 0.60, 95% CI 0.44-0.82). Early LLT was also associated with lower venous thromboembolism (6.2% vs 12.1%; RR 0.51, 95% CI 0.30-0.86; p=0.0093) and fewer inpatient hospitalizations (14.6% vs 23.6%; RR 0.62, 95% CI 0.40-0.97; p=0.0320). Emergency department visits were numerically lower (8.3% vs 13.9%; RR 0.59, 95% CI 0.35-1.00; p=0.0467). No significant differences were observed for acute kidney injury or major adverse cardiovascular events. Conclusions: In a real-world propensity-matched cohort of lorlatinib-treated NSCLC patients, LLT initiated within 30 days was associated with lower 1-year mortality, venous thromboembolism, and hospitalization. Given the frequency of lorlatinib-associated dyslipidemia, these findings support early lipid monitoring and timely LLT initiation in practice. Prospective studies are warranted to confirm these associations. 365-day outcomes after matching. Outcome Early LLT (n=387) No early LLT (n=387) RR (95% CI) HR (95% CI) p All-cause mortality 16.1% 26.4% 0.608 (0.458-0.806) 0.597 (0.435-0.818) 0.0004; log-rank 0.001 Venous thromboembolism 6.2% 12.1% 0.509 (0.302-0.857) — 0.0093 Inpatient hospitalization 14.6% 23.6% 0.619 (0.396-0.967) — 0.0320 ED visit 8.3% 13.9% 0.593 (0.352-1.001) — 0.0467 Acute kidney injury 5.4% 7.1% 0.769 (0.429-1.378) — 0.3758 MACE 4.6% 4.6% 1.006 (0.511-1.979) — 0.9868

8579 Background: LOH may provide a means to target tumor versus normal cells, to augment the efficacy and safety of MSLN-targeted programs (Hecht et al. JCO . 2022). A2B694 is an autologous, logic-gated, Tmod CAR T therapy designed to improve tumor selectivity and decrease toxicity by integrating an MSLN CAR activator with an HLA-A*02 blocker (Hamburger et al. Mol Imm. 2020). Methods: The first-in-human, open-label, phase 1/2 EVEREST-2 (NCT06051695) study of A2B694 in patients with recurrent/metastatic MSLN-expressing cancers with tumor-associated HLA-A*02 LOH. The prescreening study BASECAMP-1 (NCT04981119) identifies eligible patients and cryopreserves leukapheresis product. Upon progression, A2B694 is manufactured and administered after lymphodepletion. Phase 1 primary objective: evaluate the safety and tolerability of A2B694 and identify a recommended phase 2 dose. Results: As of 05 January 2026, 13 patients were enrolled: 8 women/5 men, median age 59 years, 11 non-Hispanic White/2 Hispanic with unknown race. Tumor types included colorectal (n = 4), ovarian (n = 3), pancreatic (n = 3), non–small cell lung adenocarcinoma (NSCLC), gastro-esophageal, and mesothelioma (n = 1 each). A2B694 dose level (DL) groups were: DL1: 1×10 8 cells (n = 3), DL2: 2×10 8 cells (n = 4), DL3: 4×10 8 cells (n = 5), and DL4: 6×10 8 cells plus low-dose IL-2 (n = 1). Lymphodepletion prior to administration of A2B694 was well-tolerated, with expected, transient cytopenias. The only adverse event reported in more than 1 patient was grade 3 neutropenia. One patient had grade 3 ICANS and 1 patient had grade 1 CRS. There were no dose-limiting toxicities or new safety signals after up to 17 months follow-up. All 13 patients received A2B694, were efficacy-evaluable, and had A2B694 detected post-infusion in peripheral blood. While A2B694 was not detected in tumor biopsies collected in patients treated at DL1 (0/2), all patients treated at DL2-DL4 with available biopsies (3/3) had detectable A2B694 in the tumor microenvironment. A patient with KRAS G12V /STK11 co-mutated NSCLC who had progressed on carboplatin, pemetrexed, and pembrolizumab achieved a complete response (CR) at D90 post-infusion per RECIST 1.1 by central review and had a confirmed CR at D180. In addition, PET-CT scan and ctDNA on D190 demonstrated no evidence of disease. On D243, the patient had a CNS relapse, with an ongoing non-CNS CR per RANO-BM at D284. At M12, the patient's CT showed no new findings and persistence of A2B694 in the blood was confirmed by ddPCR. Conclusions: We report the first patient with NSCLC to have a CR after CAR T. Overall, A2B694 demonstrated manageable safety and tolerability in patients with advanced solid MSLN-expressing tumors with tumor-associated HLA-A*02 LOH. The maximum tolerated dose has not been reached; dose-escalation continues. Clinical trial information: NCT06051695 .