The development of a deep learning model for automated segmentation of the robotic pancreaticojejunostomy.

BACKGROUND: Minimally invasive surgery provides an unprecedented opportunity to review video for assessing surgical performance. Surgical video analysis is time-consuming and expensive. Deep learning provides an alternative for analysis. Robotic pancreaticoduodenectomy (RPD) is a complex and morbid operation. Surgeon technical performance of pancreaticojejunostomy (PJ) has been associated with postoperative pancreatic fistula. In this work, we aimed to utilize deep learning to automatically segment PJ RPD videos. METHODS: This was a retrospective review of prospectively collected videos from 2011 to 2022 that were in libraries at tertiary referral centers, including 111 PJ videos. Each frame of a robotic PJ video was categorized based on 6 tasks. A 3D convolutional neural network was trained for frame-level visual feature extraction and classification. All the videos were manually annotated for the start and end of each task. RESULTS: Of the 100 videos assessed, 60 videos were used for the training the model, 10 for hyperparameter optimization, and 30 for the testing of performance. All the frames were extracted (6 frames/second) and annotated. The accuracy and mean per-class F1 scores were 88.01% and 85.34% for tasks. CONCLUSION: The deep learning model performed well for automated segmentation of PJ videos. Future work will focus on skills assessment and outcome prediction.

Proficiency Levels and Validity Evidence for Scoring Metrics for a Virtual Reality and Inanimate Robotic Surgery Simulation Curriculum.

OBJECTIVE: Our institution recently implemented a virtual reality (VR) skills curriculum for general surgery residents using the SimNow simulator. Based on a content alignment study, we revised the curriculum to include only 20 of 33 VR tasks and we added 3 previously validated inanimate tasks. The purpose of this study was to establish expert-derived proficiency levels for all tasks and to evaluate the validity of the scoring for the VR tasks. DESIGN: Two expert robotic surgeons performed 5 repetitions of each VR and inanimate task. The trimmed mean (lowest scoring attempt and outliers [>2 standard deviations] were eliminated) was defined as the expert level for each task. For the VR tasks, expert levels were compared to resident performance to evaluate validity. SETTING: This study was conducted at the University of Texas Southwestern Medical Center (Dallas, TX), a tertiary care academic teaching hospital. PARTICIPANTS: Two expert robotic surgeons participated in this study. The data from 42 residents (PGY2-4) who completed the original curriculum was used to represent novice performance. RESULTS: Comparison of expert levels and resident performance was statistically significant for 15 VR tasks (supporting validity) and approached significance (p = 0.06, 0.09) for 2 VR tasks; expert levels were designated as proficiency levels for these 17 tasks. Group comparisons were clearly not significant (p = 0.2-0.8) for 3 VR tasks; 2 of these 3 tasks were retained as introductory exercises (with 3 repetitions required) and 1 was excluded. For the 3 inanimate tasks, expert levels minus 2 standard deviations were designated as proficiency levels. CONCLUSIONS: This analysis generated validity evidence for 15 VR tasks and established expert-derived proficiency levels for 17 VR tasks and 3 inanimate tasks. Our proposed curriculum now consists of 19 VR and 3 inanimate tasks using the selected proficiency levels. We anticipate that this design will maximize curriculum efficiency and effectiveness.

Safety and Feasibility of Single-Port Robotic-Assisted Nipple-Sparing Mastectomy.

Importance: Robotic-assisted nipple-sparing mastectomies with multiport robots have been described in the US since 2015; however, significant hurdles to multiport robotic surgery exist in breast surgery. Objective: To demonstrate that the single-port da Vinci SP (Intuitive Surgical) robotic system is feasible in patients undergoing robotic nipple-sparing mastectomy (rNSM). Design, Setting, and Participants: An initial case series of 20 patients at a large university hospital underwent bilateral single-port robotic nipple-sparing mastectomies (SPrNSM) with tissue expander reconstruction from February 1, 2020, through January 4, 2023. Participants included women who met surgical criteria for nipple-sparing mastectomies, per standard of care. Intervention: Surgery using a single-port robot and the surgical technique of the authors. Main Outcomes and Measures: Age, indication, body mass index, breast size, operative time, conversion to open surgery, systemic complications, postoperative skin necrosis, and reported skin and nipple areolar complex (NAC) sensation. Results: Twenty women aged 29 to 63 years (median, 40 years) underwent bilateral SPrNSM. Eleven patients completed prophylactic surgery due to a high risk for breast cancer (more than 20% lifetime risk) and 9 patients had breast cancer. Breast size ranged from A through D cup with median B cup and a body mass index range of 19.7 through 27.8 (median 24.4). The total duration of the procedure from incision to skin closure for both sides ranged from 205 minutes to 351 minutes (median, 277). The median robotic time for bilateral SPrNSM was 116 minutes and varied by cup size (A cup, 95 minutes; B cup, 140 minutes; C cup, 118 minutes; D cup, 114 minutes) with no inflection point in learning curve. No cases were converted to open and no immediate complications, such as hematoma, positive margins, or recurrence, were seen. In the first 10 patients prior to routine sensation testing, 20 resected breasts had measurable NAC sensation at a range from 4 to 36 months post-index resection (65%). In the second 10 patients of the cohort, measurable NAC was preserved in 13 of 20 resected breasts 2 weeks following the index operation (65%). Conclusion and Relevance: In this case series, SPrNSM with immediate reconstruction was feasible and performed safely by an experienced breast surgeon with limited previous robotic training. Further studies confirming the preliminary data demonstrating improved NAC and skin sensation following SPrNSM are warranted. Trial Registration: ClinicalTrials.gov Identifier: NCT05245812.

Intensifying supportive care is associated with improved survival in gastric cancer patients with malignant ascites.

BACKGROUND: Gastric cancer patients with malignant ascites often have poor functional status and malnutrition that preclude receipt of systemic therapies. Thus, these patients have a very poor prognosis. Beginning in 2019, our multidisciplinary gastric cancer disease-oriented team implemented a more aggressive supportive care plan for gastric cancer patients with malignant ascites. The initiative included measures such as supplemental enteral nutrition, ascites drainage, and initiation of chemotherapy on an inpatient basis. We compared outcomes for gastric cancer patients who presented with synchronous malignant ascites treated before and after the implementation of the care plan. METHODS: We performed a retrospective review of our institutional database to identify patients diagnosed with gastric adenocarcinoma and synchronous malignant ascites between 2010 and 2022. We compared overall survival (OS) between patients diagnosed from 2010 to 2018, which will be referred to as the historical control era and patients diagnosed from 2019 to 2022, which will be called the aggressive supportive care era. RESULTS: Fifty-four patients were included in our analysis; 31 patients were treated in the historical control time frame, and 23 patients were treated during the aggressive supportive care era. Demographic, clinical, and pathologic characteristics were similar between groups. 3% of historical controls received supplemental tube feeds at diagnosis as compared to 30% of the aggressive supportive care cohort (p < 0.01). 3% of historical controls received their first cycle of chemotherapy in the inpatient setting versus 39% of patients treated during the aggressive supportive care era (p < 0.01). The median number of chemotherapy cycles received was 5 among historical controls and 9.5 among aggressive supportive care era patients (p = 0.02). There was no difference in the number of days spent as an inpatient between the two groups. The median OS for historical control patients was 5.4 months as compared with 10.4 months for patients treated during aggressive supportive care era (p = 0.04). CONCLUSIONS: Gastric cancer patients with synchronous malignant ascites treated during a timeframe when our multidisciplinary team implemented more aggressive supportive care measures had improved OS as compared with historic controls. Our results suggest that aggressive supportive measures for these patients with highly challenging clinical issues and poor prognosis can prolong survival. Specifically, initiation of chemotherapy in the inpatient setting and supplemental nutrition should be considered for patients at high risk for treatment intolerance.

Association of race, demographic and socioeconomic factors with failure to rescue after hepato-pancreato-biliary surgery in the United States.

BACKGROUND: We aimed to describe the association of patient-related factors such as race, socioeconomic status, and insurance on failure to rescue (FTR) after hepato-pancreato-biliary (HPB) surgeries. METHODS: Using the National Inpatient Sample, we analyzed 98,788 elective HPB surgeries between 2004 and 2017. Major and minor complications were identified using ICD9/10 codes. We evaluated mortality rates and FTR (inpatient mortality after major complications). We used multivariate logistic regression analysis to assess racial, socioeconomic, and demographic factors on FTR, adjusting for covariates. RESULTS: Overall, 43 % of patients (n = 42,256) had pancreatic operations, 36% (n = 35,526) had liver surgery, and 21% (n = 21,006) had biliary interventions. The overall major complication rate was 21% (n = 20,640), of which 8% (n = 1655) suffered FTR. Factors independently associated with increased risk for FTR were male sex, older age, higher Charlson Comorbidity Index, Hispanic ethnicity, Asian or other race, lower income quartile, Medicare insurance, and southern region hospitals. CONCLUSIONS: Medicare insurance, male gender, Hispanic ethnicity, and lower income quartile were associated with increased risk for FTR. Efforts should be made to improve the identification and subsequent treatment of complications for those at high risk of FTR.

Cost Analysis and Financial Implications of a Peritoneal Surface Malignancy Program in the USA.

BACKGROUND: We aimed to describe the financial implications of cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (CRS/HIPEC) in the USA. MATERIALS AND METHODS: We conducted a retrospective cost analysis of 100 CRS/HIPEC procedures to examine the impact of patient and procedural factors on hospital costs and reimbursement. A comparison of surgeons' work relative value units (wRVUs) between CRS/HIPEC and a representative sample of complex surgical oncology procedures was made to assess the physicians' compensation rate. Univariable and multivariable backward logistic regression was used to analyze the association between perioperative variables and high direct cost (HDCs). RESULTS: The median direct cost per CRS/HIPEC procedure was US $44,770. The median hospital reimbursement was US $43,066, while professional reimbursement was US $8608, resulting in a positive contribution margin of US $7493/procedure. However, the contribution margin significantly varied with the payer mix. Privately insured patients had a positive median contribution margin of US $23,033, whereas Medicare-insured patients had a negative contribution margin of US $13,034. Length of stay (LOS) had the most significant association with HDC, and major complications had the most significant association with LOS. Finally, CRS/HIPEC procedures generated a median of 13 wRVU/h, which is significantly lower than the wRVU/h generated by open pancreatoduodenectomies, open gastrectomies, and hepatectomies. However, higher operation complexity and multiple visceral resections help compensate for the relatively low wRVU/h. CONCLUSIONS: CRS/HIPEC is an expensive operation, and prolonged LOS has the most significant impact on the total cost of the procedure. High-quality care is essential to improve patient outcomes and maintain the economic sustainability of the procedure.

Baseline performance in a robotic virtual reality platform predicts rate of skill acquisition in a proficiency-based curriculum: a cohort study of surgical trainees.

BACKGROUND: Residency programs must prepare to train the next generation of surgeons on the robotic platform. The purpose of this study was to determine if baseline skills of residents on a virtual reality (VR) robotic simulator before intern year predicted future performance in a proficiency-based curriculum. METHODS: Across two academic years, 21 general surgery PGY-1s underwent the robotic surgery boot camp at the University of Texas Southwestern. During boot camp, subjects completed five previously validated VR tasks, and their performance metrics (score, time, and economy of motion [EOM]) were extracted retrospectively from their Intuitive learning accounts. The same metrics were assessed during their residency until they reached previously validated proficiency benchmarks. Outcomes were defined as the score at proficiency, attempts to reach proficiency, and time to proficiency. Spearman's rho and Mann-Whitney U tests were used; median (IQR) was reported. Significance level was set at p < 0.05. RESULTS: Twenty-one residents completed at least three out of the five boot camp tasks and achieved proficiency in the former during residency. The median average score at boot camp was 12.3 (IQR: 5.14-18.5). The median average EOM at boot camp was 599.58 cm (IQR: 529.64-676.60). The average score at boot camp significantly correlated with lower time to achieve proficiency (p < 0.05). EOM at boot camp showed a significant correlation with attempts to proficiency and time to proficiency (p < 0.01). Residents with an average baseline EOM below the median showed a significant difference in attempts to proficiency (p < 0.05) and time to proficiency (p < 0.05) compared to those with EOMs above or equal to the median. CONCLUSION: Residents with an innate ability to perform tasks with better EOM may acquire robotic surgery skills faster. Future investigators could explore how these innate differences impact performance throughout residency.

Defining the Price Tag of Complications Following Pancreatic Surgery: A US National Perspective.

INTRODUCTION: Pancreatic surgery tends to have a high rate of postoperative complications due to its complex nature, significantly increasing hospital costs. Our aim was to describe the true association between complications and hospital costs in a national cohort of US patients. METHODS: The National Inpatient Sample was used to conduct a retrospective analysis of elective pancreatic resections performed between 2004 and 2017, categorizing them based on whether patients experienced major complications (MaC), minor complications (MiC), or no complications (NC). Multivariable quantile regression was used to analyze how costs varied at different percentiles of the cost curve. RESULTS: Of 37,893 patients, 45.3%, 28.6%, and 26.1% experienced NC, MiC, and MaC, respectively. Factors associated with MaC were a Charlson Comorbidity Index of ≥4, prolonged length of stay, proximal pancreatectomy, older age, male sex, and surgery performed at hospitals with a small number of beds or at urban nonteaching hospitals (all P < 0.01). Multivariable quantile regression revealed significant variation in MiC and MaC across the cost curve. At the 50th percentile, MiC increased the cost by $3352 compared to NC while MaC almost doubled the cost of the surgery, increasing it by $20,215 (both P < 0.01). The association between complications and cost was even greater at the 95th percentile, increasing the cost by $10,162 and $108,793 for MiC and MaC, respectively (P < 0.01). CONCLUSIONS: MiC and MaC were significantly associated with increased hospital costs. Furthermore, the relationship between MaC and costs was especially apparent at higher percentiles of the cost curve.

Developing a Robotic Surgery Curriculum: Selection of Virtual Reality Drills for Content Alignment.

INTRODUCTION: Despite the importance of simulation-based training for robotic surgery, there is no consensus about its training curricula. Recently, a virtual reality (VR) platform (SimNow, Intuitive, Inc) was introduced with 33 VR drills but without evidence of their validity. As part of our creating a new robotic VR curriculum, we assessed the drills' validity through content mapping and the alignment between learning goals and drill content. METHODS: Three robotically trained surgeons content-mapped all 33 drills for how well the drills incorporated 15 surgery skills and also rated the drills' difficulty, usefulness, relevance, and uniqueness. Drills were added to the new curriculum based on consensus about ratings and historic learner data. The drills were grouped according to similar skill sets and arranged in order of complexity. RESULTS: The 33 drills were judged to have 12/15 surgery skills as primary goals and 13/15 as secondary goals. Twenty of the 33 drills were selected for inclusion in the new curriculum; these had 11/15 skills as primary goals and 11/15 as secondary goals. However, skills regarding energy sources, atraumatic handling, blunt dissection, fine dissection, and running suturing were poorly represented in the drills. Three previously validated inanimate drills were added to the curriculum to address lacking skill domains. CONCLUSIONS: We identified 20 of the 33 SimNow drills as a foundation for a robotic surgery curriculum based on content-oriented evidence. We added 3 other drills to address identified gaps in drill content.

Diagnostic laparoscopy is underutilized in the staging of gastric adenocarcinoma regardless of hospital type: An US safety net collaborative analysis.

BACKGROUND: Diagnostic laparoscopy (DL) is a key component of staging for locally advanced gastric adenocarcinoma (GA). We hypothesized that utilization of DL varied between safety net (SNH) and affiliated tertiary referral centers (TRCs). METHODS: Patients diagnosed with primary GA eligible for DL were identified from the US Safety Net Collaborative database (2012-2014). Clinicopathologic factors were analyzed for association with use of DL and findings on DL. Overall survival (OS) was analyzed by Kaplan-Meier method. RESULTS: Among 233 eligible patients, 69 (30%) received DL, of which 24 (35%) were positive for metastatic disease. Forty percent of eligible SNH patients underwent DL compared to 21.5% at TRCs. Lack of insurance was significantly associated with decreased use of DL (OR 0.48, p < 0.01), while African American (OR 6.87, p = 0.02) and Asian race (OR 3.12, p ≤ 0.01), signet ring cells on biopsy (OR 3.14, p < 0.01), and distal tumors (OR 1.62, p < 0.01) were associated with increased use. Median OS of patients with a negative DL was better than those without DL or a positive DL (not reached vs. 32 vs. 12 months, p < 0.005, Figure 1). CONCLUSIONS: Results from DL are a strong predictor of OS in GA; however, the procedure is underutilized. Patients from racial minority groups were more likely to undergo DL, which likely accounts for higher DL rates among SNH patients.

Feasibility, effectiveness and transferability of a novel mastery-based virtual reality robotic training platform for general surgery residents.

BACKGROUND: The annual number of robotic surgical procedures is on the rise. Robotic surgery requires unique skills compared to other surgical approaches. Simulation allows basic robot skill acquisition and enhances patient safety. The purpose of this study was to evaluate the feasibility, effectiveness, and transferability of a mastery-based curriculum using a new virtual reality (VR) robotic simulator for surgery resident training. METHODS: Nineteen PGY2s and 22 PGY4s were enrolled. Residents completed a pretest and posttest consisting of five VR and three previously validated inanimate tasks. Training included practicing 33 VR tasks until a total score ≥ 90% ("mastery") was achieved using automated metrics (time, economy of motion). Inanimate performance was evaluated by two trained, blinded raters using video review metrics (time, errors, and modified OSATS). Outcomes were defined as: curriculum feasibility (completion rate, training time, repetitions), training effectiveness (pre/post training skill improvement), and skill transferability (skill transfer to validated inanimate drills). Wilcoxon signed-rank and Mann-Whitney U tests were used; median (IQR) reported. RESULTS: Thirty-four of 41 residents (83%) achieved mastery on all 33 VR tasks; median training time was 7 h (IQR: 5'26″-8'52″). Pretest vs. post-test performance improved (all p < 0.001) according to all VR and Inanimate metrics for both PGY2 and PGY4 residents. Significant pretest performance differences were observed between PGY2 and PGY4 residents for VR but not inanimate tasks; no PGY2 vs. PGY4 posttest performance differences were observed for both VR and inanimate tasks. CONCLUSION: This mastery-based VR curriculum was associated with a high completion rate and excellent feasibility. Significant performance improvements were noted for both the VR and inanimate tasks, supporting training effectiveness and skill transferability. Additional studies examining validity evidence may help further refine this curriculum.

Gaps in Providers' Knowledge Delays Gastric Cancer Diagnosis.

BACKGROUND: Previous studies have suggested that symptomatic cancer patients often experience delays in diagnosis (DD). However, DD of gastric cancer within the USA and etiology of those delays are not understood. Our study quantifies the proportion of gastric cancer patients experiencing DD and contributing barriers of care. METHODS: We conducted a single institution retrospective review of 256 gastric cancer patients treated between 2015 and 2020. Patients with an interval from symptom onset to diagnosis of > 90 days were classified as having DD and categorized into one of the following barriers of care: access, provider knowledge/skills, and patient factors. Chi-square tests were used to analyze categorical group differences. Non-pooled t-tests and ANOVA were used to compare differences in group means. RESULTS: A total of 59 patients (23%) had DD. Among patients with DD, the mean time from symptom onset to diagnosis was 229 days vs 30 days in the non-delayed group (p < 0.0001). The most common barrier of care was provider knowledge/skills gaps (44%), followed by access (36%) and patient-related factors (20%). Only 5% of patients who experienced delays reported abdominal pain alone, with the remaining 95% of patients reporting more than one symptom including obstruction, gastrointestinal bleeding, or weight loss. CONCLUSION: Patients often face lengthy delays in gastric cancer diagnosis which arise from healthcare system factors such as access barriers or gaps in provider knowledge/skills. Understanding concerning alarm symptoms and addressing identified barriers will expedite patient diagnosis and are prime opportunities to improve outcomes for gastric cancer patients.

Socioeconomic and racial/ethnic disparities in receipt of palliative care among patients with metastatic hepatocellular carcinoma.

BACKGROUND: Patients with metastatic hepatocellular carcinoma (HCC) suffer symptoms of both end-stage liver disease and cancer. Palliative care (PC) enhances the quality of life via symptom control and even improves survival for some cancers. Our study characterized rates of PC utilization among metastatic HCC patients and determined factors associated with PC receipt. METHODS: We conducted a retrospective review of adult National Cancer Database patients diagnosed with metastatic HCC between 2004 and 2016. Chi-square tests were used to analyze two cohorts: those who received PC and those who did not. Logistic regression was performed to assess the impact of clinicodemographic factors on the likelihood of receiving PC. RESULTS: PC utilization was low at just 17%. Later year of diagnosis, insured status, and higher education level were associated with an increased likelihood of receiving PC. Treatment at academic centers or integrated network cancer programs increased the likelihood of receiving PC compared to treatment at a community center (odds ratio [OR] = 1.17, 95% confidence interval [CI] = 1.03-1.33 and OR = 1.25, 95% CI = 1.07-1.45; respectively). Hispanics were significantly less likely to received PC than non-Hispanic Whites (OR = 0.73, 95% CI = 0.64-0.82). CONCLUSIONS: PC utilization among patients with metastatic HCC remains low. Targeted efforts should be enacted to increase the delivery of PC in this group.

Clinical Presentation Patterns and Survival Outcomes of Hispanic Patients With Gastric Cancer.

BACKGROUND: Hispanic patients have a higher incidence of gastric cancer when compared to non-Hispanics. Outlining clinicodemographic characteristics and assessing the impact of ethnicity on stage-specific survival may identify opportunities to improve gastric cancer care for this population. METHODS: Patients with gastric cancer in the US Safety Net Collaborative (2012-2014) were retrospectively reviewed. Demographics, clinicopathologic characteristics, operative details, and outcomes were compared between Hispanic and non-Hispanic patients. Early onset gastric cancer was defined as age <50 years. Kaplan-Meier and Cox proportional-hazards models were used to identify the impact of ethnicity on disease-specific survival (DSS). RESULTS: Seven hundred and ninety-seven patients were included, of which 219 (28%) were Hispanic. Hispanic patients were more likely to seek care at safety-net hospitals (66 vs 39%) and be uninsured (36 vs 17%), and less likely to have a primary care provider (PCP) (46 vs 75%; all P<0.05). Hispanic patients were twice as likely to present with early onset gastric cancer (28 vs 15%) and were more frequently diagnosed in the emergency room (54 vs 37%) with both abdominal pain and weight loss (44 vs 31%; all P <0.05). Treatment paradigms, operative outcomes, and DSS were similar between Hispanic and non-Hispanic patients when accounting for cancer stage. Cancer stage, pathologically positive nodes, and negative surgical margins were independently associated with DSS. CONCLUSIONS: A diagnosis of gastric cancer must be considered in previously healthy Hispanic patients who present to the emergency room with both abdominal pain and weight loss. Fewer than 50% of Hispanic patients have a PCP, indicating poor outpatient support. Efforts to improve outpatient support and screening may improve gastric cancer outcomes in this vulnerable population.

Attrition during neoadjuvant chemotherapy for gastric adenocarcinoma is associated with decreased survival: A United States Safety-Net Collaborative analysis.

BACKGROUND: Neoadjuvant chemotherapy (NAC) is standard management for localized gastric cancer (GC). Attrition during NAC due to treatment-related toxicity or functional decline is considered a surrogate for worse biologic outcomes; however, data supporting this paradigm are lacking. We investigated factors predicting attrition and its association with overall survival (OS) in GC. METHODS: Patients with nonmetastatic GC initiating NAC were identified from the US Safety-Net Collaborative (2012-2014). Patient/treatment-related characteristics were compared between attrition/nonattrition cohorts. Cox models determined factors associated with OS. RESULTS: Of 116 patients initiating NAC, attrition during prescribed NAC occurred in 24%. No differences were observed in performance status, comorbidities, treatment at safety-net hospital, or clinicopathologic factors between cohorts. Despite absence of distinguishing factors, attrition was associated with worse OS (median: 11 vs. 37 months; p = 0.01) and was an independent predictor of mortality (hazard ratio [HR]: 4.7, 95% confidence interval [CI]: 1.5-15.2; p = 0.02). Fewer patients with attrition underwent curative-intent surgery (39% vs. 89%; p < 0.001). Even in patients undergoing surgical exploration (n = 89), NAC attrition remained an independent predictor of worse OS (HR: 50.8, 95% CI: 3.6-717.8; p = 0.004) despite similar receipt of adjuvant chemotherapy. CONCLUSION: Attrition during NAC for nonmetastatic GC is independently associated with worse OS, even in patients undergoing surgery. Attrition during NAC may reflect unfavorable tumor biology not captured by conventional staging metrics.

Is there a difference in utilization of a perioperative treatment approach for gastric cancer between safety net hospitals and tertiary referral centers?

BACKGROUND AND OBJECTIVES: Perioperative therapy is a favored treatment strategy for gastric cancer. We sought to assess utilization of this approach at safety net hospitals (SNH) and tertiary referral centers (TRC). MATERIALS AND METHODS: Patients in the US Safety Net Collaborative (2012-2014) with resectable gastric cancer across five SNH and their sister TRC were included. Primary outcomes were receipt of neoadjuvant chemotherapy (NAC) and perioperative therapy. RESULTS: Of 284 patients, 36% and 64% received care at SNH and TRC. The distribution of Stage II/III resectable disease was similar across facilities. Receipt of NAC at SNH and TRC was similar (56% vs. 46%, p = 0.27). Compared with overall clinical stage, 38% and 36% were pathologically downstaged at SNH and TRC, respectively. Among patients who received NAC, those who also received adjuvant chemotherapy at SNH and TRC were similar (66% vs. 60%, p = 0.50). Asian race and higher clinical stage were associated with receipt of perioperative therapy (both p < 0.05) while treatment facility type was not. CONCLUSIONS: There was no difference in utilization of a perioperative treatment strategy between facility types for patients with gastric cancer. Pathologic downstaging from NAC was similar across treatment facilities, suggesting similar quality and duration of therapy. Treatment at an SNH is not a barrier to receiving standard-of-care perioperative therapy for gastric cancer.