Risk stratification of gallbladder masses by machine learning-based ultrasound radiomics models: a prospective and multi-institutional study.

OBJECTIVE: This study aimed to evaluate the diagnostic performance of machine learning (ML)-based ultrasound (US) radiomics models for risk stratification of gallbladder (GB) masses. METHODS: We prospectively examined 640 pathologically confirmed GB masses obtained from 640 patients between August 2019 and October 2022 at four institutions. Radiomics features were extracted from grayscale US images and germane features were selected. Subsequently, 11 ML algorithms were separately used with the selected features to construct optimum US radiomics models for risk stratification of the GB masses. Furthermore, we compared the diagnostic performance of these models with the conventional US and contrast-enhanced US (CEUS) models. RESULTS: The optimal XGBoost-based US radiomics model for discriminating neoplastic from non-neoplastic GB lesions showed higher diagnostic performance in terms of areas under the curves (AUCs) than the conventional US model (0.822-0.853 vs. 0.642-0.706, p < 0.05) and potentially decreased unnecessary cholecystectomy rate in a speculative comparison with performing cholecystectomy for lesions sized over 10 mm (2.7-13.8% vs. 53.6-64.9%, p < 0.05) in the validation and test sets. The AUCs of the XGBoost-based US radiomics model for discriminating carcinomas from benign GB lesions were higher than the conventional US model (0.904-0.979 vs. 0.706-0.766, p < 0.05). The XGBoost-US radiomics model performed better than the CEUS model in discriminating GB carcinomas (AUC: 0.995 vs. 0.902, p = 0.011). CONCLUSIONS: The proposed ML-based US radiomics models possess the potential capacity for risk stratification of GB masses and may reduce the unnecessary cholecystectomy rate and use of CEUS. CLINICAL RELEVANCE STATEMENT: The machine learning-based ultrasound radiomics models have potential for risk stratification of gallbladder masses and may potentially reduce unnecessary cholecystectomies. KEY POINTS: • The XGBoost-based US radiomics models are useful for the risk stratification of GB masses. • The XGBoost-based US radiomics model is superior to the conventional US model for discriminating neoplastic from non-neoplastic GB lesions and may potentially decrease unnecessary cholecystectomy rate for lesions sized over 10 mm in comparison with the current consensus guideline. • The XGBoost-based US radiomics model could overmatch CEUS model in discriminating GB carcinomas from benign GB lesions.

The efficacy and safety of endoscopic ultrasound-guided fine-needle biopsy in gallbladder masses.

BACKGROUND: Endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) is a widely used modality for acquiring various target samples, but its efficacy in gallbladder masses is unknown. The aim of this retrospective study was to evaluate the efficacy and safety of EUS-FNB in patients with gallbladder masses. METHODS: The study samples were composed of patients from March 2015 to July 2019 who needed to identify the nature of gallbladder masses through EUS-FNB. The outcomes of this study were the adequacy of specimens, diagnostic yields, technical feasibility, and adverse events of the EUS-FNB in gallbladder masses. RESULTS: A total of 27 consecutive patients with a median age of 58 years were included in this study. The 22-gauge FNB needle was feasible in all lesions. The median follow-up period of the patients was 294 days. The specimens sufficient for diagnosis account for 89% (24/27) and 93% (25/27) in cytology and histology, respectively. The overall diagnostic yields for malignancy showed the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 95.45% [95% confidence interval (CI): 75.12%-99.76%], 100% (95% CI: 46.29%-100%), 100% (95% CI: 80.76%-100%), 83.33% (95% CI: 36.48%-99.12%), and 96.30% (95% CI: 80.20%-99.99%), respectively. The subgroup analysis revealed that FNB could obtain sufficient specimens and high diagnostic yields in both gallbladder mass < 20.5 mm group and ≥ 20.5 mm group. One patient experienced mild abdominal pain after the procedure and recovered within one day. CONCLUSIONS: EUS-FNB is a reasonable diagnostic tool for the pretreatment diagnosis of patients with gallbladder masses, especially for patients who may miss the opportunity of surgery and need sufficient specimens to identify the pathological type so as to determine chemotherapy regimens. Further large-scale studies are needed to confirm our conclusion.

Diagnostic performance and safety of endoscopic ultrasound-guided tissue acquisition of gallbladder lesions: A systematic review with meta-analysis.

BACKGROUND: Endoscopic ultrasound (EUS)-guided tissue acquisition (TA) is widely used for various target samples, but its efficacy in gallbladder (GB) lesions is unknown. The aim of the present meta-analysis was to assess the pooled adequacy, accuracy and safety of EUS-TA of GB lesions. METHODS: A literature search from January 2000 to August 2022 was done for studies analyzing the outcome of EUS-guided TA in patients with GB lesions. Pooled event rates were expressed with summative statistics. RESULTS: The pooled rate of sample adequacy for all GB lesions and malignant GB lesions was 97.0% (95% CI: 94.5-99.4) and 96.6% (95% CI: 93.8-99.3), respectively. The pooled sensitivity and specificity for the diagnosis of malignant lesions were 90% (95% CI: 85-94; I2 = 0.0%) and 100% (95% CI: 86-100; I2 = 0.0%), respectively, with an area under the curve of 0.915. EUS-guided TA had a pooled diagnostic accuracy rate of 94.6% (95% CI: 90.5-96.6) for all GB lesions and 94.1% (95% CI: 91.0-97.2) for malignant GB lesions. There were six reported mild adverse events (acute cholecystitis = 1, self-limited bleeding = 2, self-limited episode of pain = 3) with a pooled incidence of 1.8% (95% CI: 0.0-3.8) and none of the patients had serious adverse events. CONCLUSION: EUS-guided tissue acquisition from GB lesions is a safe technique with high sample adequacy and diagnostic accuracy. EUS-TA can be an alternative when traditional sampling techniques fail or are not feasible.