Ultrasound is one of the most commonly used imaging modalities for the screening and diagnosis of liver nodules. However, its diagnostic accuracy is highly dependent on operator expertise, and atypical or small lesions are prone to missed diagnosis or misdiagnosis. In recent years, artificial intelligence (AI) has achieved remarkable progress in medical image analysis, offering novel solutions to improve the objectivity, accuracy, and efficiency of liver ultrasound diagnosis. This review systematically summarizes the current status and advances of AI in the ultrasound diagnosis of liver nodules, with a focus on B-mode and contrast-enhanced ultrasound (CEUS). We detail AI applications in automatic nodule detection and localization, benign–malignant differentiation, multi-class classification (e.g., hepatocellular carcinoma [HCC], cholangiocarcinoma [CCA], hemangioma [HH], metastasis [HM]), and prediction of key pathological biomarkers (e.g., microvascular invasion [MVI], pathological grading, Ki-67, vessels encapsulating tumor clusters [VETC]), analyzes the current research status and summarizes the main limitations of existing studies. By reviewing methodological characteristics such as cohort size, validation strategies, and machine learning algorithms, this paper provides insights into future research directions and promotes the development of clinically translatable AI models, with the ultimate goal of advancing standardization and broad clinical adoption of AI-assisted diagnosis in liver ultrasound.
- Article type
- Year
- Co-author
Open Access
Review Article
Issue
To preliminarily investigate the safety and efficacy of percutaneous microwave ablation (MWA) in patients with advanced breast cancer involving the skin or nipple-areola complex (NAC).
This study included breast cancer patients with skin or NAC involvement treated at the Fifth Medical Center of the Chinese PLA General Hospital from January 2011 to August 2024.Patients underwent percutaneous MWA with water isolation technique to protect surrounding tissues.Clinical data were retrospectively collected, and the technical success rate, complications, prognosis, patient satisfaction with breast aesthetics, and qualityof life improvement were analyzed.
A total of 19 patients (24 lesions) meeting the inclusion and exclusion criteria were analyzed.The cases included 4 with T4N0M0, 2 with T4N1M0, 3 with T4N2M0, 1 with T4N3M0, 1 with T4N2M1, and 8 with T4N3M1.The average diameter of the 24 lesions was (4.9±3.4) cm, with an average of (1.6±0.6) ablation sessions per lesion.The median ablation time was 36.9(26.1, 61.7) minutes, and the median ablation energy was 84.2(45.6, 149.2) kJ.The technical success rate was 100%.Postoperatively, 7 patients (7/19, 36.8%) experienced skin burns around the lesion or nipple shedding, all of which healed naturally.The median overall survival was 35.0(17.0, 45.5) months, and the median recurrence-free survival was 17.0(11.0, 38.5) months.Patient satisfaction with post-treatment breast aesthetics was 89.5%, and all patients reported significant improvement in their quality of life.
Percutaneous microwave ablation for breast cancer involving the skin or NAC was preliminary demonstrates to be safe and effective, suggesting its potential as a viable treatment option for patients with inoperable breast cancer.
Open Access
Original Research
Issue
Drug-induced liver injury (DILI) is one of the most challenging forms of liver disorder. We aimed to use ultrasound dual elastography, by combining strain and shear wave imaging, to noninvasively assess liver inflammation and injury severity of DILI.
291 DILI patients were included in the prospective multicenter study and divided into training and validation cohorts. All patients received liver biopsy and dual elastography examination. Liver inflammation grading (G0-4) and fibrosis staging (F0-4) were considered as the gold standard of liver injury and G+F ≥ 5 was defined as severe liver injury. Indexes of dual elastography and serological indicators (DESI) were selected and analyzed with multivariable logistic regression to build DESI models for evaluating liver inflammation, and the C score model was built with the same method for diagnosing severe liver injury.
Areas under the receiver operating characteristic curve (AUCs) of the DESI model to assess liver inflammation ≥ G2 were 0.887 and 0.868 in training and validation cohorts, respectively. AUCs of the DESI model in diagnosing ≥ G3 were 0.893 and 0.896 in the two cohorts, respectively. The C score accurately assessed severe liver injury with AUCs of 0.909 and 0.885 in two cohorts. Of the 87 patients with mild clinical severity, 10 (11.49%) had severe pathological injury, which could be identified by C score.
Dual elastography demonstrated high performance in diagnosing liver inflammation and identifying severe pathological liver injury of DILI, making up for the deficiency of serological indicators alone for evaluating DILI severity.
Open Access
Review Article
Issue
Interventional ultrasound (IUS) is an important branch of modern minimally invasive medicine that has been widely applied in clinical practice due to its unique techniques and advantages. As a relatively emerging field, IUS has progressed towards standardization, precision, intelligence, and cutting-edge directions alone with more than 40 years of development, which is becoming increasingly important techniques in clinical medicine. This article will briefly review the development and advancement of IUS for diagnosis and treatment in China in the era of precision medicine from the aspects of artificial intelligence, virtual navigation, molecular imaging, and nanotechnology.
Open Access
Original Article
Issue
Thermal ablation poses challenges in the surgical resection (SR) of small hepatocellular carcinoma (HCC), and its therapeutic outcomes for larger lesions remain debated.
This retrospective study evaluated 729 patients with HCC meeting the Milan criteria, who were treated with curative SR or microwave ablation (MWA) between 2008 and 2014. Overall survival (OS), cancer-specific survival (CSS), disease-free survival (DFS), and local tumor progression (LTP) were compared after propensity score matching (PSM). Co-variates associated with OS, CSS, LTP, and DFS were identified. The risk of death and tumor progression were compared.
During the median follow-up of 78.6 months, 253 patients were included in each group after PSM. For tumors ≤ 3.0 cm and 3.1-4.0 cm, MWA achieved comparable results in terms of OS, CSS, DFS, and LTP. For tumors 4.1-5.0 cm, MWA had lower OS, CSS, and DFS rates (all P < 0.05) than SR. Higher LTP rates were observed in the MWA group for tumors 4.1-5.0 cm, although the difference was not significant (P = 0.18). Complication rates (P = 0.41) were similar, but MWA led to less estimated blood loss (P < 0.01) and shorter postoperative hospitalization times (P < 0.01).
MWA achieved comparable long-term oncologic outcomes with SR for ≤ 4 cm HCC, with lower complication rates and faster recovery.
Open Access
Original Article
Issue
To explore the association between cholecystectomy and the prognostic outcomes of patients with hepatocellular carcinoma (HCC) who underwent microwave ablation (MWA).
Patients with HCC (n = 921) who underwent MWA were included and divided into cholecystectomy (n = 114) and non-cholecystectomy groups (n = 807). After propensity score matching (PSM) at a 1:2 ratio, overall survival (OS) and disease-free survival (DFS) rates were analyzed to compare prognostic outcomes between the cholecystectomy (n = 114) and non-cholecystectomy groups (n = 228). Univariate and multivariate Cox analyses were performed to assess potential risk factors for OS and DFS. Major complications were also compared between the groups.
After matching, no significant differences between groups were observed in baseline characteristics. The 1-, 3-, and 5-year OS rates were 96.5%, 82.1%, and 67.1% in the cholecystectomy group, and 97.4%, 85.2%, and 74.4% in the non-cholecystectomy group (P = 0.396); the 1-, 3-, and 5-year DFS rates were 58.4%, 34.5%, and 26.6% in the cholecystectomy group, and 73.6%, 44.7%, and 32.2% in the non-cholecystectomy group (P = 0.026), respectively. The intrahepatic distant recurrence rate in the cholecystectomy group was significantly higher than that in the non-cholecystectomy group (P = 0.026), and the local tumor recurrence and extrahepatic recurrence rates did not significantly differ between the groups (P = 0.609 and P = 0.879). Multivariate analysis revealed that cholecystectomy (HR = 1.364, 95% CI 1.023–1.819, P = 0.035), number of tumors (2 vs. 1: HR = 2.744, 95% CI 1.925–3.912, P < 0.001; 3 vs. 1: HR = 3.411, 95% CI 2.021–5.759, P < 0.001), and γ-GT levels (HR = 1.003, 95% CI 1.000–1.006, P < 0.024) were independent risk factors for DFS. The best γ-GT level cut-off value for predicting median DFS was 39.6 U/L (area under the curve = 0.600, P < 0.05). A positive correlation was observed between cholecystectomy and γ-GT level (r = 0.108, 95% CI −0.001–0.214, P = 0.047). Subgroup analysis showed that the DFS rates were significantly higher in the non-cholecystectomy group than the cholecystectomy group when γ-GT ≥39.6 U/L (P = 0.044). The 5-, 10-, 15-, 20-, and 25-year recurrence rates from the time of cholecystectomy were 2.63%, 21.93%, 42.11%, 58.77%, and 65.79%, respectively. A significant positive correlation was observed between cholecystectomy and the time from cholecystectomy to recurrence (r = 0.205, 95% CI 0.016–0.379, P = 0.029). There were no significant differences in complications between groups (P = 0.685).
Patients with HCC who underwent cholecystectomy were more likely to develop intrahepatic distant recurrence after MWA, an outcome probably associated with increased γ-GT levels. Moreover, the recurrence rates increased with time.
京公网安备11010802044758号