RESUMO
AIM: The present study was to evaluated the clinical value of anatomical thermal ablation to treat hepatocellular carcinoma compared with routine thermal ablation. METHODS: Hepatocellular carcinoma patients with tumor diameter ≤50 mm treated by thermal ablation at our center were retrospectively enrolled from October 2015 to December 2018. Enrolled patients were grouped into the anatomical ablation group and routine ablation group, respectively. To minimize the effects of potential confounders from selection bias, a propensity score matching was carried out. Technical efficacy, recurrence and survivals rates were compared. RESULTS: Altogether 101 patients (119 lesions) were grouped into the anatomical ablation group and 101 patients (131 lesions) into the routine ablation group. The ablation zone volume of the anatomical ablation group was 36.8 (2.5-176.9) ml, significantly larger than that of the routine ablation group (28.5 [28.5 (2.8-184.3) ml] (p = 0.005)). Adjusted with propensity score matching, The 1-, 2-, and 3-year local recurrence rates were 0.0%, 0.0%, and 0.0% for the anatomical ablation group and 6.9%, 10.1%, and 10.1% for the routine ablation group, respectively (p = 0.013). The cumulative 1-, 2-, and 3-year progression-free survival rates were 93.4%, 82.7%, and 79.0% for the anatomical ablation group, 74.2%, 56.9%, and 51.6% for the routine ablation group (p = 0.001). CONCLUSIONS: Anatomical ablation could be a favorable ablation strategy to improve therapeutic effect of thermal ablation for HCC with visible feeding vessels and reserved liver function.
RESUMO
The treatment outcomes of ultrasound-guided percutaneous thermal ablation of hepatocellular carcinoma in the caudate lobe with and without fusion imaging (FI) assistance were evaluated and compared. Twenty-six patients with 28 tumors in the FI group and 8 patients with 8 tumors in the non-FI group were included. Although a higher number of tumors measured >20 mm in the FI group, the technique efficacy and local tumor progression were similar between the 2 groups (P > .99 and P = .45, respectively). FI aided in the detection, guidance, and treatment monitoring of thermal ablation for caudate lobe hepatocellular carcinomas, especially for tumors measuring >20 mm.
Assuntos
Carcinoma Hepatocelular , Ablação por Cateter , Neoplasias Hepáticas , Ablação por Radiofrequência , Carcinoma Hepatocelular/diagnóstico por imagem , Carcinoma Hepatocelular/cirurgia , Humanos , Neoplasias Hepáticas/diagnóstico por imagem , Neoplasias Hepáticas/cirurgia , Resultado do Tratamento , UltrassonografiaRESUMO
PURPOSE: The aim was to assess the value of intra-procedural CT/MR-ultrasound (CT/MR-US) fusion imaging in the management of thermal ablation for hepatocellular carcinoma (HCC). MATERIALS AND METHODS: This retrospective study was approved by the institutional review board. From May 2010 to October 2016, 543 HCC nodules in 440 patients (387 men and 53 women; age range: 25-84 years) that met the Milan Criteria were treated by percutaneous thermal ablation using intra-procedural CT/MR-US fusion imaging. The HCC nodules were divided into subgroups and compared (≤â3âcm and >â3âcm, or high-risk and low-risk location, or inconspicuous and conspicuous, respectively). Technique efficacy and major complication were calculated. Cumulative local tumor progression (LTP), tumor-free and overall survival rates were estimated with the Kaplan-Meier method. RESULTS: CT/MR-US fusion imaging was successfully registered in 419 patients with 502 nodules. The technique efficacy rate of thermal ablation was 99.4â%. The major complication rate was 1.9â%. The cumulative LTP rates were 3.2â%, 5.6â% and 7.2â% at 1, 3, and 5 years, respectively. There were no significant differences for the comparisons of cumulative LTP rates between different subgroups (Pâ=â0.541, 0.314, 0.329). The cumulative tumor-free survival rates were 74.8â%, 54.0â% and 37.5â% at 1, 3, and 5 years, respectively. The cumulative overall survival rates were 97.8â%, 87.1â% and 81.7â% at 1, 3, and 5 years, respectively. CONCLUSION: Intra-procedural CT/MR-ultrasound fusion imaging is a useful technique for percutaneous liver thermal ablation. It could help to achieve satisfying survival outcomes for HCC patients who meet the Milan Criteria.
Assuntos
Carcinoma Hepatocelular , Ablação por Cateter , Neoplasias Hepáticas , Adulto , Idoso , Idoso de 80 Anos ou mais , Carcinoma Hepatocelular/diagnóstico por imagem , Carcinoma Hepatocelular/cirurgia , Feminino , Humanos , Neoplasias Hepáticas/diagnóstico por imagem , Neoplasias Hepáticas/cirurgia , Masculino , Pessoa de Meia-Idade , Estudos Retrospectivos , Tomografia Computadorizada por Raios X , Resultado do TratamentoRESUMO
BACKGROUND: To evaluate the feasibility and effectiveness of artificial ascites to assist thermal ablation of liver cancer adjacent to the gastrointestinal tract in patients with previous abdominal surgery. METHODS: Thirty-nine patients with a total of 40 liver malignant tumors were enrolled between January 2016 and June 2019. All had histories of hepatectomy, splenectomy, cholecystectomy, and intestinal surgery. The distance between the tumor and the gastrointestinal tract was < 5 mm. Normal saline was used as artificial ascites to protect the gastrointestinal tract during thermal ablation. The success rate of the procedure, incidence of major complications, and the technical efficacy of ablation were recorded. Patients were followed for local tumor progression (LTP), and overall survival (OS). RESULTS: The use of artificial ascites was successful in 38 of the 40 procedures (95%). Major complications occurred in two of the 39 patients (5.1%) following the procedure. One was an intestinal fistula that occurred in a failed case and was associated with an infection. The other was a liver abscess that occurred in a successful case. The technical efficacy of ablation was 100% (40/40 procedures). The median follow-up was 16 months. The 1-, 2-, and 3-year LTP rates were 2.9, 5.7 and 5.7%. The 1-, 2-, and 3-year OS rates were 97.1, 86.8 and 69.5%. CONCLUSION: In patients with previous abdominal surgery, artificial ascites is feasible and effective for assisting thermal ablation of liver cancer adjacent to the gastrointestinal tract.
Assuntos
Carcinoma Hepatocelular/cirurgia , Ablação por Cateter/efeitos adversos , Temperatura Alta/efeitos adversos , Neoplasias Hepáticas/cirurgia , Complicações Pós-Operatórias/epidemiologia , Adulto , Idoso , Carcinoma Hepatocelular/mortalidade , Carcinoma Hepatocelular/patologia , Ablação por Cateter/instrumentação , Ablação por Cateter/métodos , Estudos de Viabilidade , Feminino , Seguimentos , Trato Gastrointestinal/diagnóstico por imagem , Hepatectomia , Humanos , Incidência , Infusões Parenterais/efeitos adversos , Infusões Parenterais/métodos , Estimativa de Kaplan-Meier , Fígado/diagnóstico por imagem , Fígado/patologia , Fígado/cirurgia , Neoplasias Hepáticas/mortalidade , Neoplasias Hepáticas/patologia , Masculino , Pessoa de Meia-Idade , Cavidade Peritoneal , Complicações Pós-Operatórias/etiologia , Complicações Pós-Operatórias/prevenção & controle , Estudos Retrospectivos , Solução Salina/administração & dosagem , Tomografia Computadorizada por Raios X , Resultado do Tratamento , UltrassonografiaRESUMO
Purpose: To investigate the feasibility, efficacy and safety of one-lung ventilation for percutaneous thermal ablation of liver tumors in the hepatic dome.Materials and methods: From 5 January 2017 to 16 April 2019, 64 patients who underwent ultrasound-guided thermal ablation with a total of 75 liver malignant tumors located in the hepatic dome were enrolled in the present study. One-lung ventilation was employed to improve the acoustic window and protect the lung and diaphragm. If the one-lung ventilation was unsuccessful, artificial pleural effusion was added. The technical efficacy was confirmed by contrast-enhanced computed tomography/magnetic resonance imaging (CT/MRI) 1 month later. After that, CT/MRI was performed every 3-6 months.Results: Among the enrolled patients, the technical success rate of one lung ventilation was 92.2% (59/64). The visibility scores of tumors were improved significantly after one-lung ventilation compared to those before one-lung ventilation (p < .001). Finally, 78.6% (55/70) of the tumors achieved clinical success of one-lung ventilation to become clearly visible and underwent thermal ablation. Fourteen of the remaining 15 tumors achieved a satisfactory acoustic window after combination of artificial pleural effusion. One lesion remained inconspicuous and partly affected by pulmonary gas. The follow-up period was 8 months (3-30 months). The technical efficacy rate was confirmed to be 100% (75/75). During the follow-up period, local tumor progression occurred in 2 patients (2/75, 2.7%). Major complications occurred in two patients (2/64, 3.1%) receiving one-lung ventilation.Conclusions: One-lung ventilation is a promising noninvasive method for the thermal ablation of hepatic dome tumors due to its efficacy and safety.
Assuntos
Carcinoma Hepatocelular/radioterapia , Neoplasias Hepáticas/radioterapia , Fígado/cirurgia , Ventilação Monopulmonar/métodos , Ablação por Radiofrequência/métodos , Feminino , Humanos , Fígado/patologia , Masculino , Pessoa de Meia-IdadeRESUMO
Purpose: To evaluate whether local tumor progression (LTP) would be further reduced when contrast-enhanced ultrasound (CEUS)-CT/MR fusion imaging was used as intraprocedural assessment method in hepatocellular carcinoma (HCC) thermal ablation compared with routine CEUS. Materials and methods: This prospective non-randomized study was conducted from December 2010 to July 2012. CEUS-CT/MR fusion imaging and routine CEUS were used for treatment response assessment in the ablation procedure of 146 HCCs and 122 HCCs, respectively. Supplementary ablations were performed immediately if necessary. The primary technique efficacy rate, LTP rate and overall survival (OS) rate were calculated. Results: For CEUS-CT/MR fusion imaging and routine CEUS, the technical success rate, technique efficacy rate and supplementary ablation rate were 86.3% (126/146) and 98.4% (120/122) (p = .000), 99.2% (125/126) and 94.2% (113/120) (p = .032), and 14.3% (18/126) and 4.2% (5/120) (p = .006), respectively. The cumulative LTP rate and OS rate were not significantly different between fusion imaging group and routine CEUS group. However, for lesions that were larger than 3 cm or close to major vessels (41 lesions in fusion imaging group and 44 lesions in routine CEUS group, who received transcatheter arterial chemoembolization before ablation), the cumulative LTP rate was significantly lower in fusion imaging group than in routine CEUS group (p = .032). Conclusion: Although intraprocedural CEUS-CT/MR fusion imaging has certain limitations in application, it might provide a potential more efficient method compared with routine CEUS in reducing LTP in HCC thermal ablation, especially for difficult ablation lesions.
Assuntos
Técnicas de Ablação , Carcinoma Hepatocelular/cirurgia , Meios de Contraste/uso terapêutico , Neoplasias Hepáticas/cirurgia , Imageamento por Ressonância Magnética , Tomografia Computadorizada por Raios X , Ultrassonografia , Adulto , Idoso , Carcinoma Hepatocelular/diagnóstico por imagem , Progressão da Doença , Feminino , Humanos , Neoplasias Hepáticas/diagnóstico por imagem , Masculino , Pessoa de Meia-IdadeRESUMO
PURPOSE: To simulate the advantages of anatomical resection, a new strategy of anatomical thermal ablation was proposed. The objective of this study was to evaluate the clinical value of anatomical thermal ablation (ATA) to treat subcapsular hepatocellular carcinoma by comparing it with anatomical resection (AR) and non-anatomical resection (NAR). METHODS: This retrospective cohort study enrolled hepatocellular carcinoma patients with subcapsular tumor diameter ≤ 50 mm treated by ATA or surgical resection at our center from October 2015 to December 2018. ATA features ablation of the Glisson capsule, ablation of the liver parenchyma between the tumor and hepatic veins or inferior vena cava and then puncture from the surrounding part to the central part of the tumor. Outcome parameters were compared. RESULTS: Seventy-six patients were grouped into ATA group, 95 patients into AR group and 41 patients into NAR group. The 1-, 2-, and 3-year local recurrence rates were 0.0%, 0.0%, 0.0% for ATA group, 0.0%, 1.4%, 1.4% for the AR group and 0.0%, 0.0%, and 0.0% for the NAR group, respectively (P = 0.449). The 1-, 2-, and 3-year progression-free survival rates were 90.6%, 80.9%, and 74.6% for ATA group, 91.5%, 80.2%, and 80.2% for the AR group and 82.9%, 73.8%, and 73.8% for the NAR group, respectively (P = 0.608). The 1-, 2-, and 3-year overall survival rates were 100.0%, 95.2%, and 95.2% for the ATA group, 96.8%, 95.6%, and 95.6% for the AR group and 97.6%, 95.0%, and 95.0% for the NAR group, respectively (P = 0.970). No difference was found in major complication rate among these groups (P = 0.091). CONCLUSION: For subcapsular hepatocellular carcinoma, ATA could be an alternative to surgical resection with its comparable treatment effect and safety.
Assuntos
Carcinoma Hepatocelular , Ablação por Cateter , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/diagnóstico por imagem , Carcinoma Hepatocelular/cirurgia , Neoplasias Hepáticas/diagnóstico por imagem , Neoplasias Hepáticas/cirurgia , Estudos Retrospectivos , Hepatectomia , Recidiva Local de Neoplasia/cirurgia , Resultado do Tratamento , Ablação por Cateter/efeitos adversosRESUMO
We present a 60-year-old man suffering from delayed arterial hemorrhage post liver biopsy. Contrast-enhanced ultrasound was used to detect the bleeding point and to evaluate the efficacy of microwave ablation (MWA). The hemorrhage was controlled by MWA at the bedside. This is the first application of MWA for delayed hemorrhage.
RESUMO
Objective: This study intends to compare the efficacy and safety between patients undergoing invasive isolation or monitoring measures and patients undergoing intra-operative contrast-enhanced ultrasound (CEUS) monitoring who underwent radiofrequency ablation (RFA) of hepatocellular carcinomas (HCC) adjacent to the gallbladder (GB). Methods: We retrospectively assessed patients with HCC adjacent to the GB who underwent ultrasound-guided RFA. They were divided into two groups: group A was monitored under intra-operative CEUS, while group B was assisted by invasive auxiliary means. The efficacy, complications and survival were followed up and compared. Results: Thirty-eight patients with 39 HCCs were enrolled into group A and 31 patients with 35 HCCs were enrolled into group B. The technique efficacy rates were both 100% in the two groups. There were no significant differences of the cumulative 1-, 3-, and 5-year local tumor progression, tumor-free survival and overall survival between the two groups (P = 0.851, 0.081 and 0.700, respectively). There were no significant differences of major and minor complications rates between the two groups (P = 1.000, 0.994, respectively). More importantly, no GB related complications occurred in group A. Conclusion: Intra-operative CEUS monitoring without protective isolation of the GB might be also a potentially safe and effective method for the RFA of HCC adjacent to the GB, when compared with those assisted with invasive auxiliary means.
RESUMO
Purpose: The objectives were to investigate the safety and efficacy of thermal ablation as an alternative to liver transplantation for hepatocellular carcinoma patients with clinically significant portal hypertension (CSPH). Materials and Methods: From July 2016 to September 2019, hepatocellular carcinoma patients with CSPH treated by liver transplantation (N=37) or thermal ablation (N=114) were enrolled. Cumulative intrahepatic recurrence, overall survival and major complications were compared by propensity score matching. Results: In the two matched groups, the 1-, 2-, and 3-year intrahepatic recurrence rates for the ablation group (22.3%, 50.0%, and 50.0%, respectively) were significantly higher than those for the transplantation group (4.5%, 4.5%, and 4.5%, respectively) (P=0.016). The 1-, 2-, and 3-year overall survival rates were comparable between the two groups [96.1%, 88.7%, and 88.7%, respectively (ablation group) vs. 84.6%, 76.2%, and 76.2%, respectively (transplantation group)] (P=0.07). The major complication rate for the ablation group [4.8% (3/62)] was significantly lower than that for the transplantation group [36.0% (9/25)] (P<0.001). Conclusions: Thermal ablation is a safe and effective alternative for hepatocellular carcinoma patients with CSPH.
RESUMO
Objective: To evaluate the diagnostic accuracy of fusion imaging contrast-enhanced ultrasound (FI-CEUS) of magnetic resonance imaging (MRI) LI-RADS-indeterminate (LR-3/4) and conventional ultrasound undetected focal liver lesions (FLLs) in patients at risk for hepatocellular carcinoma (HCC). Methods: Between February 2020 and July 2021, 71 FLLs in 63 patients were registered for diagnostic performance evaluation respectively for ultrasound-guided thermal ablation evaluation in this retrospective study. Diagnostic performance regarding FLLs was compared between FI-CEUS and contrast-enhanced MRI (CE-MRI). Results: For diagnostic performance evaluation, among 71 lesions in 63 patients, the diagnostic efficacy of FI-CEUS with LI-RADS was significantly higher than that of CE-MRI (P < 0.05) in both overall and hierarchical comparison (except for the group with lesion diameter ≥2 cm). For malignant lesions, the proportion of arterial phase hyperenhancement (APHE) and washout on FI-CEUS was higher than that on CE-MRI (P < 0.05). Conclusion: FI-CEUS has a high value in the precise qualitative diagnosis of small FLLs (<2 cm) of MRI LI-RADS-indeterminate diagnosis (LR-3/4) that are undetected by conventional ultrasound in patients at risk for HCC and can be a good supplementary CE-MRI diagnostic method for thermal ablation evaluation.
RESUMO
Background: To assess the frequency of major complications after thermal ablation of liver tumours and to determine risk factors for adverse events. Methods: A retrospective study was conducted between January 2015 and January 2021. A total of 2,084 thermal ablation sessions in 1,592 patients with primary and metastatic liver tumours were evaluated. The frequency of major complications was evaluated according to the Society of Interventional Radiology Standards, and putative predictors of adverse events were analysed using simple and multivariate logistic regression. Results: Thermal ablation-related mortality was 0.1% (2/2,084), with an overall major complication rate of 5.6% (117/2,084). The most frequent major complication was symptomatic pleural effusion (2.9%, 60/2,084). Multivariate logistic regression analysis revealed that a total maximum diameter of lesions >3â cm, microwave ablation (MWA) and MWA combined with radiofrequency ablation, intrahepatic cholangiocarcinoma and postoperative systemic inflammatory response syndrome were independent prognostic factors for major complications. Conclusions: Thermal ablation of liver tumours is a safe procedure with an acceptable incidence of major complications. The risk factors identified in this study will help to stratify high-risk patients.
RESUMO
PURPOSE: To assess the feasibility of ablation planning based on fusion imaging of three-dimensional ultrasound/contrast-enhanced ultrasound (3D US/CEUS) with real-time US/CEUS for liver tumor thermal ablation. MATERIALS AND METHODS: Between January 2017 and December 2018, 85 hepatic tumors from 82 patients who underwent percutaneous ablation were included. First, intraprocedural 3D US/CEUS imaging was performed for ablation planning. Then, fusion imaging of 3D US/CEUS with real-time US/CEUS was used to guide the implementation of the plan, immediately evaluate the technical success and indicate the need for supplemental ablation. In addition, contrast-enhanced CT/MR imaging was performed 1 month after the procedure to evaluate the presence of residual tumors, and follow-up scans were repeated every 3 months. RESULTS: The average liver tumor diameter was 28 ± 9 mm (range, 10-55 mm). 3D US/CEUS-based planning was successfully conducted in all 85 tumors with a 100% technical success rate of planning. The immediate evaluation by 3D CEUS/US-CEUS fusion imaging showed a 100% technical success rate of ablation. The 1-month CT/MR scans found a residual tumor in one intrahepatic cholangiocarcinoma patient; the technique efficacy rate was 98.8%. The median follow-up period was 21.5 months (IQR: 4-36 months). During the follow-up period, the local tumor progression rate was 5.9% (5/84), and no major procedure-related complications occurred. CONCLUSIONS: Ablation planning based on 3D US/CEUS-US/CEUS fusion imaging is feasible for liver tumors.
Assuntos
Carcinoma Hepatocelular , Ablação por Cateter , Neoplasias Hepáticas , Carcinoma Hepatocelular/cirurgia , Meios de Contraste , Estudos de Viabilidade , Humanos , Neoplasias Hepáticas/diagnóstico por imagem , Neoplasias Hepáticas/cirurgia , Estudos Retrospectivos , UltrassonografiaRESUMO
OBJECTIVE: To explore the value of ultrasound fusion imaging for the thermal ablation of medium-sized hepatocellular carcinomas (HCCs). MATERIALS AND METHODS: From December 2010 to June 2018, patients with medium-sized (3.1-5.0cm) HCCs who underwent radiofrequency ablation (RFA) or microwave ablation (MWA) with the assistance of ultrasound fusion imaging were enrolled in this retrospective study. Technical efficacy, local tumor progression (LTP), intrahepatic distant recurrence (IDR), overall survival (OS), tumor-free survival (TFS) and major complications were evaluated during the follow-up period. The therapeutic outcomes were compared between the RFA/MWA combined with trans-arterial chemoembolization (TACE) group and the RFA/MWA alone group with propensity-score matching (PSM) analysis. RESULTS: A total of 112 patients with 115 medium-sized HCCs were finally enrolled in this study. The median duration of follow-up was 33 months (range, 2-104 months). The technique efficacy was 100% (115/115). The 1-, 3-, 5-year OS rates and TFS rates were 95.5%, 76.7%, 71.5% and 74.1%, 48.7%, 41.8%, respectively. The corresponding LTP rates and IDR rates were 5.4%, 7.3%, 7.3% and 21.8%, 46.9%, 50.3%, respectively. The incidence of major complications was 5.4% (6/112). After PSM analysis (19 patients in each group), the therapeutic outcomes, including the OS, TFS, and LTP rates, were comparable in the two groups (P > 0.05). CONCLUSIONS: With the assistance of ultrasound fusion imaging, thermal ablation of medium-sized HCC could achieve a satisfactory local control rate and long-term survival. The outcomes were comparable in the stratified analysis between the RFA/MWA alone group and the RFA/MWA+TACE group after PSM analysis.
Assuntos
Carcinoma Hepatocelular , Ablação por Cateter , Neoplasias Hepáticas , Carcinoma Hepatocelular/diagnóstico por imagem , Carcinoma Hepatocelular/cirurgia , Humanos , Neoplasias Hepáticas/diagnóstico por imagem , Neoplasias Hepáticas/cirurgia , Pontuação de Propensão , Estudos Retrospectivos , Resultado do Tratamento , Ultrassonografia de IntervençãoRESUMO
OBJECTIVE: To explore the best ablative margin (AM) for single hepatocellular carcinoma (HCC) patients with image-guided percutaneous thermal ablation (IPTA) based on MRI-MRI fusion imaging, and to develop and validate a local tumor progression (LTP) predictive model based on the recommended AM. METHODS: Between March 2014 and August 2019, 444 treatment-naïve patients with single HCC (diameter ≤3 cm) who underwent IPTA as first-line treatment from three hospitals were included, which were randomly divided into training (n= 296) and validation (n = 148) cohorts. We measured the ablative margin (AM) by MRI-MRI fusion imaging based on pre-ablation and post-ablation images. Then, we followed up their LPT and verified the optimal AM. Risk factors related to LTP were explored through Cox regression models, the nomogram was developed to predict the LTP risk base on the risk factors, and subsequently validated. The predictive performance and discrimination were assessed and compared with conventional indices. RESULTS: The median follow-up was 19.9 months (95% CI 18.0-21.8) for the entire cohort. The results revealed that the tumor size (HR: 2.16; 95% CI 1.25-3.72; P = 0.003) and AM (HR: 0.72; 95% CI, 0.61-0.85; P < 0.001) were independent prognostic factors for LTP. The AM had a pronounced nonlinear impact on LTP, and a cut-off value of 5-mm was optimal. We developed and validated an LTP predictive model based on the linear tumor size and nonlinear AM. The model showed good predictive accuracy and discrimination (training set, concordance index [C-index] of 0.751; validation set, C-index of 0.756) and outperformed other conventional indices. CONCLUSION: The 5-mm AM is recommended for the best IPTA candidates with single HCC (diameter ≤3 cm). We provided an LTP predictive model that exhibited adequate performance for individualized prediction and risk stratification.
RESUMO
PURPOSE: To develop a radiomics model based on dynamic contrast-enhanced ultrasound (CEUS) to predict early and late recurrence in patients with a single HCC lesion ≤ 5 cm in diameter after thermal ablation. PROCEDURES: We enrolled patients who underwent thermal ablation for HCC in our hospital from April 2004 to April 2017. Radiomics based on two branch convolution recurrent network was utilized to analyze preoperative dynamic CEUS image of HCC lesions to establish CEUS model, in comparison to the conventional ultrasound (US), clinical, and combined models. Clinical follow-up of HCC recurrence after ablation were taken as reference standard to evaluate the predicted performance of CEUS model and other models. RESULTS: We finally analyzed 318 patients (training cohort: test cohort = 255:63). The combined model showed better performance for early recurrence than CUES (in training cohort, AUC, 0.89 vs. 0.84, P < 0.001; in test cohort, AUC, 0.84 vs. 0.83, P = 0.272), US (P < 0.001), or clinical model (P < 0.001). For late recurrence prediction, the combined model showed the best performance than the CEUS (C-index, in training cohort, 0.77 vs. 0.76, P = 0.009; in test cohort, 0.77 vs. 0.68, P < 0.001), US (P < 0.001), or clinical model (P < 0.001). CONCLUSIONS: The CEUS model based on dynamic CEUS radiomics performed well in predicting early HCC recurrence after ablation. The combined model combining CEUS, US radiomics, and clinical factors could stratify the high risk of late recurrence.
Assuntos
Hipertermia Induzida/métodos , Neoplasias Hepáticas/diagnóstico por imagem , Recidiva Local de Neoplasia/diagnóstico por imagem , Ultrassonografia/métodos , Carcinoma Hepatocelular/diagnóstico por imagem , Carcinoma Hepatocelular/patologia , Carcinoma Hepatocelular/cirurgia , Meios de Contraste , Feminino , Seguimentos , Humanos , Neoplasias Hepáticas/patologia , Neoplasias Hepáticas/cirurgia , Masculino , Pessoa de Meia-Idade , Recidiva Local de Neoplasia/patologia , Recidiva Local de Neoplasia/cirurgia , Prognóstico , Estudos Retrospectivos , Taxa de SobrevidaRESUMO
BACKGROUND: To date, the missed diagnosis rate of pulmonary hypertension (PH) was high, and there has been limited development of a rapid, simple, and effective way to screen the disease. The purpose of this study is to develop a deep learning approach to achieve rapid detection of possible abnormalities in chest radiographs suggesting PH for screening patients suspected of PH. METHODS: We retrospectively collected frontal chest radiographs and the pulmonary artery systolic pressure (PASP) value measured by Doppler transthoracic echocardiography from 762 patients (357 healthy controls and 405 with PH) from three institutes in China from January 2013 to May 2019. The wohle sample comprised 762 images (641 for training, 80 for internal test, and 41 for external test). We firstly performed a 8-fold cross-validation on the 641 images selected for training (561 for pre-training, 80 for validation), then decided to tune learning rate to 0.0008 according to the best score on validation data. Finally, we used all the pre-training and validation data (561+80 = 641) to train our models (Resnet50, Xception, and Inception V3), evaluated them on internal and external test dataset to classify the images as having manifestations of PH or healthy according to the area under the receiver operating characteristic curve (AUC/ROC). After that, the three deep learning models were further used for prediction of PASP using regression algorithm. Moreover, we invited an experienced chest radiologist to classify the images in the test dataset as having PH or not, and compared the prediction accuracy performed by deep learing models with that of manual classification. RESULTS: The AUC performed by the best model (Inception V3) achieved 0.970 in the internal test, and slightly declined in the external test (0.967) when using deep learning algorithms to classify PH from normal based on chest X-rays. The mean absolute error (MAE) of the best model for prediction of PASP value was smaller in the internal test (7.45) compared to 9.95 in the external test. Manual classification of PH based on chest X-rays showed much lower AUCs compared to that performed by deep learning models both in the internal and external test. CONCLUSIONS: The present study used deep learning algorithms to classify abnormalities suggesting PH in chest radiographs with high accuracy and good generalizability. Once tested prospectively in clinical settings, the technology could provide a non-invasive and easy-to-use method to screen patients suspected of having PH.