Thyroid nodule rupture after radiofrequency ablation: case report and literature review.

Purpose: Radiofrequency ablation (RFA) is an effective and safe modality for the treatment of thyroid nodules. Nodule rupture is a major complication of RFA. There is little known on the natural history of nodule rupture due to a lack of clinical experience and no consensus on its management. A comprehensive review of nodule rupture presentation, diagnosis, and management is needed. Methods: We report a case of nodule rupture and conduct a literature review. A total of 33 patients experiencing nodule rupture after RFA were included, and their clinical presentation, management, and outcomes were collected and analyzed. Results: Nodule rupture presents with acute swelling (90.3%) and pain (77.4%) within 7 months of RFA procedure, most commonly due to disruption of the anterior thyroid capsule (87%), and can be diagnosed with ultrasonography. Most ruptures can be managed conservatively, exemplified by our reported case. There are no reported cases of long-term sequalae. Conclusion: Nodule rupture is the second most common major complication of RFA. Based on the available evidence, we propose a treatment algorithm for nodule rupture and recommendations for future data collection to address gaps in our understanding of rupture etiology and effective management.

Percutaneous pulsed radiofrequency ablation of articular nerves of the hip joint in patients with chronic hip pain refractory to conventional analgesics.

OBJECTIVES: Total Hip Arthroplasty (THA) may be a risky proposition in patients with comorbidities, and they may require systemic analgesics for chronic hip pain (CHP). Since traditional pain medications may not provide complete pain relief or carry prohibitive adverse effects, pulsed radiofrequency (PRF) treatment of the hip articular nerves (HAN) has been proposed for effective clinical outcomes. We determined the efficacy of PRF-HAN in improvement in CHP compared to baseline pain on conventional systemic analgesics. METHODS: Between August 2015 and December 2021, 31 adult patients with severe comorbid conditions and excruciating chronic hip pain were subjected to a PRF-HAN procedure following a diagnostic block. All 31 patients received PRF of the articular branches of the femoral and obturator nerves. Demographic parameters, numerical rating scale (NRS), Harris Hip Score (HHS), WOMAC scores, the change of these scores from baseline, and any adverse effects were recorded before treatment and on day 1, 1st week, 6 weeks, and 6 months after treatment. RESULTS: All the patients who underwent the PRF-HAN reported a significant improvement in NRS, HHS, and WOMAC scores compared to the baseline values on day 1, at the end of the 1st week, and the 6th week (p<0.001). No adverse events were documented in the study post-procedure until the end of 6 months. CONCLUSION: PRF-HAN is a strong alternative for chronic pain management and augments physical functioning and a return to daily activity in patients who would be deprived of arthroplasty considering associated comorbid conditions.

Does radiofrequency ablation procedural data improve the accuracy of identifying atrial fibrillation recurrence?

Radiofrequency ablation (RFA) using the CARTO 3D mapping system is a common approach for pulmonary vein isolation to treat atrial fibrillation (AF). Linkage between CARTO procedural data and patients' electronical health records (EHR) provides an opportunity to identify the ablation-related parameters that would predict AF recurrence. The objective of this study is to assess the incremental accuracy of RFA procedural data to predict post-ablation AF recurrence using machine learning model. Procedural data generated during RFA procedure were downloaded from CARTONET and linked to deidentified Mercy Health EHR data. Data were divided into train (70%) and test (30%) data for model development and validation. Automate machine learning (AutoML) was used to predict 1 year AF recurrence, defined as a composite of repeat ablation, electrical cardioversion, and AF hospitalization. At first, AutoML model only included Patients' demographic and clinical characteristics. Second, an AutoML model with procedural variables and demographical/clinical variables was developed. Area under receiver operating characteristic curve (AUROC) and net reclassification improvement (NRI) were used to compare model performances using test data. Among 306 patients, 67 (21.9%) patients experienced 1-year AF recurrence. AUROC increased from 0.66 to 0.78 after adding procedural data in the AutoML model based on test data. For patients with AF recurrence, NRI was 32% for model with procedural data. Nine of 10 important predictive features were CARTO procedural data. From CARTO procedural data, patients with lower contact force in right inferior site, long ablation duration, and low number of left inferior and right roof lesions had a higher risk of AF recurrence. Patients with persistent AF were more likely to have AF recurrence. The machine learning model with procedural data better predicted 1-year AF recurrence than the model without procedural data. The model could be used for identification of patients with high risk of AF recurrence post ablation.

A case report of atrial septal puncture "mistakenly" penetrated the aorta during left bypass radiofrequency ablation.

INTRODUCTION: Transseptal punctures (TSPs) are widely used in left atrium and left ventricle surgery. Accidental puncture of the puncture needle into the aorta is a rare complication that is rarely reported but has serious consequences. The appropriate management of this complication remains unclear. PATIENT CONCERNS: This report describes a case of a male with the chief complaint: paroxysmal palpitation for 1 year, aggravated for 1 month. DIAGNOSIS: The electrophysiological diagnosis was atrioventricular reentrant tachycardia caused by left-side bypass. INTERVENTIONS: Radiofrequency ablation of the heart was a necessary treatment and a TSP operation was needed, in which a puncture was mistakenly believed to have entered the aorta, a series of measures were taken urgently. Although the surgical procedure in this case was a false alarm, we still initiated a series of emergency plans. Emergency measures to address the complications were effectively implemented, and the emergency measures were promptly terminated after it was clear that complications had been misjudged. OUTCOMES: At last, it was confirmed that the angiogram was a pulmonary artery image, not an aorta image. Then the atrial septal puncture operation was successfully completed, and under the guidance of the Carto system, the ablation was successfully completed. Postoperative fluoroscopy showed no complications, such as pericardial effusion. After 2 years of follow-up, there was no reoccurrence of tachycardia, and there were no complications. It is crucial that emergency procedures are terminated in a timely manner after a clear miscarriage of performance. Although accidental puncture into the aorta is urgent and serious, performing a blockage or even thoracotomy in an emergency if complications are not clearly confirmed can cause further damage to the patient and would be a definitively wrong strategy. CONCLUSION: Strict and standardized TSP operations can avoid complications. Correct judgment of the authenticity of complications is crucial, and remedial measures that may cause further damage should not be blindly adopted. The retention of the aortic guide wire can provide convenient access for further differential diagnosis and remedial treatment.

Efficacy and safety of radiofrequency ablation versus surgical sympathectomy in palmar hyperhidrosis.

Radiofrequency ablation (RFA) comparative efficacy of treatments using video-assisted thoracoscopic sympathectomy (VATS) in the long term remains uncertain in patients with palmar hyperhidrosis (PHH). This study aimed to compare the efficacy and safety of RFA and VATS in patients with PHH. We recruited patients aged ≥ 14 years with diagnosed PHH from 14 centres in China. The treatment options of RFA or VATS were assigned to two cohort in patients with PHH. The primary outcome was the efficacy at 1-year. A total of 807 patients were enrolled. After propensity score matching, the rate of complete remission was lower in RFA group than VATS group (95% CI 0.21-0.57; p < 0.001). However, the rates of palmar dryness (95% CI 0.38-0.92; p = 0.020), postoperative pain (95% CI 0.13-0.33; p < 0.001), and surgery-related complications (95% CI 0.19-0.85; p = 0.020) were lower in RFA group than in VATS group, but skin temperature rise was more common in RFA group (95% CI 1.84-3.58; p < 0.001). RFA had a lower success rate than VATS for the complete remission of PHH. However, the symptom burden and cost are lower in patients undergoing RFA compared to those undergoing VATS.Trial Registration: ChiCTR2000039576, URL: http://www.chictr.org.cn/index.aspx .

Predictive value of estimated plasma volume for postoperative hypotension in percutaneous intramyocardial septal radiofrequency ablation treating for hypertrophic obstructive cardiomyopathy.

BACKGROUND: Estimated plasma volume status (ePVS) estimated by the Duarte formula is associated with clinical outcomes in patients with heart failure. It remains unclear the predictive value of the ePVS to the postoperative hypotension (POH) in percutaneous intramyocardial septal radiofrequency ablation (PIMSRA) treating hypertrophic obstructive cardiomyopathy (HOCM). METHODS: Data of HOCM patients who underwent PIMSRA were retrospectively collected. Preoperative ePVS was calculated using the Duarte formulas which derived from hemoglobin and hematocrit ratios. Clinical variables including physical assessment, biological and echocardiographic parameters were recorded. Patients were labeled with or without POH according to the medical record in the hospital. Univariable and multivariable logistic regression were performed to evaluate the association between ePVS and POH. Using different thresholds derived from quartiles and the best cutoff value of the receiver operating characteristic curve, the diagnostic performance of ePVS was quantified. RESULTS: Among the 405 patients included in this study, 53 (13.1%) patients were observed with symptomatic POH. Median (IQR) of ePVS in overall patients was 3.77 (3.27~4.40) mL/g and in patients with POH were higher than those without POH. The ePVS was associated with POH, with the odds ratio of 1.669 (95% CI 1.299 ~ 2.144) per mL/g. After adjusted by potential confounders, ePVS remained independently associated with POH, with the approximate odds ratio in different models. CONCLUSION: The preoperative ePVS derived from the Duarte formulas was independently associated with postoperative hypotension in HOCM patients who underwent PIMSRA and showed prognostic value to the risk stratification of postoperative management. TRIAL REGISTRATION: NCT06003478 (22/08/2023).

Sensor-Based Measurement Method to Support the Assessment of Robot-Assisted Radiofrequency Ablation.

Digital surgery technologies, such as interventional robotics and sensor systems, not only improve patient care but also aid in the development and optimization of traditional invasive treatments and methods. Atrial Fibrillation (AF) is the most common cardiac arrhythmia with critical clinical relevance today. Delayed intervention can lead to heart failure, stroke, or sudden cardiac death. Although many advances have been made in the field of radiofrequency (RF) catheter ablation (CA), it can be further developed by incorporating sensor technology to improve its efficacy and safety. Automation can be utilized to shorten the duration of RF ablation, provided that the interactions between the tissue and the RF tools are well understood and adequately modeled. Further research is needed to develop the optimal catheter design. This paper describes the systematic methodology developed to support robot-assisted RF CA characterization measurements. The article describes the custom instruments developed for the experiments, particularly the contact force limiter, the measurement procedure, and the evaluation of the results, as enablers for new results. The aim was to establish an objective, repeatable, robust measurement method and adjacent procedure.

Radiofrequency ablation for papillary thyroid microcarcinoma close to the thyroid capsule versus far from the thyroid capsule: a retrospective study.

INTRODUCTION: The aim of this study was to evaluate the safety and efficacy of ultrasound-guided radiofrequency ablation (RFA) for the management of papillary thyroid microcarcinoma (PTMC) close to the thyroid capsule. MATERIAL AND METHODS: This was a retrospective study of 202 patients with PTMC who underwent RFA close to the thyroid capsule and 80 patients with PTMC who underwent RFA far from the thyroid capsule between June 2015 and December 2022. The follow-up time after RFA, change in size of tumour, location, thyroid function, the rates of PTMC disappearance, and complications were evaluated. RESULTS: A total of 202 patients with PTMC close to the thyroid capsule and 80 patients with PTMC far from the thyroid capsule successfully treated with RFA were studied. The thyroid function including free triiodothyronine (fT3), free thyroxine (fT4), triiodothyronine (T3), thyroxine (T4), and thyroid-stimulating hormone (TSH) showed no changes after RFA for one months in both groups. The tumour size was increased at 1, 3, and 6 months after RFA compared with pre-operative RFA in both groups. The tumour size was decreased at 12 and 24 months after RFA compared with pre-operative RFA both in both group. Seventy-nine PTMC close to the thyroid capsule and 30 PTMC far from the thyroid capsule completely disappeared as assessed by ultrasound examination. Eighty-four PTMC patients close to the thyroid capsule and 34 PTMC patients far from the thyroid capsule had minor complications after RFA treatment. The complication rates between the 2 groups were similar. CONCLUSION: Ultrasound-guided RFA seems to be an effective and safe method for patients with PTMC close to the thyroid capsule.

Short time effects of two radiofrequency ablation methods on hypertrophic obstructive cardiomyopathy.

BACKGROUND: Radiofrequency ablation has been applied for the treatment of hypertrophic obstructive cardiomyopathy (HOCM). The two known procedures are percutaneous intramyocardial septal radiofrequency ablation (PIMSRA) and endocardial radiofrequency septal ablation (ERSA). METHODS: This study presents a retrospective analysis of the PIMSRA and ERSA procedures in patients with drug-refractory HOCM. A total of 28 patients participated in the study, with 12 receiving PIMSRA and 16 receiving ERSA. The objective of our study was to compare the short-term effects of these two radiofrequency ablation procedures. RESULTS: At the 30-day follow-up, the PIMSRA group demonstrated a greater reduction in left ventricular outflow tract peak gradient at rest compared to the ERSA group (22.25 [16.72] mmHg versus 47.75 [21.94] mmHg) (p < .01). The values for the PIMSRA group decreased from 99.33 (32.00) mmHg to 22.25 (16.72) mmHg (p < .01), while the ERSA group decreased from 97.75 (30.24) mmHg to 47.75 (21.94) mmHg (p < .01). Only the PIMSRA group exhibited a decrease in mitral regurgitation (MR). The area of MR decreased from 10.13 (4.12) mm2 to 3.65 (2.80) mm2 in the PIMSRA group (p < .01). Additionally, the PIMSRA group experienced reductions in left atrial diameter (LAD) and left ventricular ejection fraction (LVEF)%. The values for LAD changed from 43.58 (7.53) mm to 37.08 (6.92) mm (p = .03), and the values for LVEF% decreased from 65.75 (6.12) pg/mL to 60.83 (4.06) pg/mL (p = .03). CONCLUSION: In terms of the two types of radiofrequency ablation methods used in HOCM, it has been observed that PIMSRA demonstrates a more favorable early treatment effect compared to ERSA.

Nomogram to predict recurrence risk factors in patients with non-valvular paroxysmal atrial fibrillation after catheter radiofrequency ablation.

BACKGROUND: Radiofrequency catheter ablation (RFCA) is an effective method for controlling the heart rate of paroxysmal atrial fibrillation (PAF). However, recurrence is trouble under the RFCA. To gain a deeper understanding of the risk factors for recurrence in patients, we created a nomogram model to provide clinicians with treatment recommendations. METHODS: A total of two hundred thirty-three patients with PAF treated with RFCA at Guizhou Medical University Hospital between January 2021 and December 2022 were consecutively included in this study, and after 1 year of follow-up coverage, 166 patients met the nadir inclusion criteria. Patients with AF were divided into an AF recurrence group and a non-recurrence group. The nomogram was constructed using univariate and multivariate logistic regression analyses. By calculating the area under the curve, we analyzed the predictive ability of the risk scores (AUC). In addition, the performance of the nomogram in terms of calibration, discrimination, and clinical utility was evaluated. RESULTS: At the 12-month follow-up, 48 patients (28.92%) experienced a recurrence of AF after RFCA, while 118 patients (71.08%) maintained a sinus rhythm. In addition to age, sex, and TRV, LAD, and TTPG were independent predictors of recurrence of RFCA. The c-index of the nomogram predicted AF recurrence with an accuracy of .723, showing good decision curves and a calibrated nomogram, as determined by internal validation using a bootstrap sample size of 1000. CONCLUSION: We created a nomogram based on multifactorial logistic regression analysis to estimate the probability of recurrence in patients with atrial fibrillation 1 year after catheter ablation. This plot can be utilized by clinicians to predict the likelihood of recurrence.

Comparison of laparoscopic hepatectomy and percutaneous radiofrequency ablation for the treatment of small hepatocellular carcinoma: a meta-analysis.

AIM: The purpose of this study was to compare the long-term outcomes of laparoscopic hepatectomy (LH) and percutaneous radiofrequency ablation (PRFA) for the treatment of small hepatocellular carcinoma. METHODS: We systematically searched PubMed, Embase, Web of Science, and Medline from January 2000 to May 2022 for literature comparing the efficacy of LH and PRFA in the treatment of small hepatocellular carcinoma (largest tumour diameter ≤ 3 cm, number of intrahepatic tumours ≤3, or diameter of a single intrahepatic lesion ≤5 cm. ). We assessed overall survival (OS), recurrence-free survival (RFS), local recurrence and complication rates. RESULTS: A total of 1886 patients with small HCC were included in the 8 studies included in this study, of which 839 underwent LH and 1047 underwent PRAF. The results of the meta-analysis showed that the two groups had the same 3-year (HR: 0.99, 95% CI: 0.67 to 1.47) and 5-year (HR: 1.30, 95% CI: 0.90 to 1.87) OS rates, and the LH group had better 3-year (HR: 0.58, 95% CI: 0.49 to 0.68) and 5-year (HR: 0.56, 95% CI: 0.37 to 0.85) RFS rates. The LH group had a lower local recurrence rate (OR: 0.19, 95% CI: 0.12 to 0.32), but the PRFA group had a lower complication rate (OR: 2.49, 95% CI: 1.76 to 3.54). CONCLUSION: There was no difference in OS between LH and PRFA in the treatment of small HCC. LH had a higher RFS rate and a lower local recurrence rate, but PRFA had a lower complication rate. In general, the long-term efficacy of LH in the treatment of small HCC is better than that of PRFA. Considering the advantages of less trauma and a low complication rate of PRFA, a large number of RCT studies are needed for further verification in the future.

Radiofrequency ablation of hepatocellular carcinoma guided by real-time physics-based ablation simulation: a prospective study.

OBJECTIVES: To assess the safety and efficacy of radiofrequency ablation (RFA) guidance software that incorporated patient-specific physics-based simulation of each ablation volume. MATERIALS AND METHODS: Patients referred for curative ablation of hepatocellular carcinoma (HCC) of 2-5 cm diameter were prospectively enrolled. RFA was performed under general anesthesia. Procedure planning and intraprocedural modifications were guided by computer simulation of each ablation. The segmented target (tumor with 5 mm margin) was registered to and superimposed on subsequent 3D multiplanar images. The applied RF energy was used to calculate a simulated ablation volume which was displayed relative to the electrode and segmented target, to depict any untreated target tissue. After each additional ablation, the software updated the accumulated simulated ablation volume in relation to the target. The primary endpoints were technical efficacy and rate of local tumor progression (LTP). RESULTS: Sixty-eight tumors were ablated during 57 procedures in 52 patients (68.3 ± 9.2 years old, 78.8% male); 15 (26.3%) had multiple lesions and 23 (39.1%) had prior HCC treatment. The mean tumor diameter was 2.73 (±0.64) cm. The intraprocedural simulation directed additional overlapping ablations in 75.9% of tumors. Technical success and efficacy were 100% at 3-month contrast enhanced CT or MRI follow-up after the single treatment session. Cumulative incidence function estimates for 1- and 2-year LTP were 3.9% and 20.2%, respectively. CONCLUSION: This prospective study found computer-assisted guidance that simulated each ablation was both safe and efficacious. The low rate of LTP was similar to studies that employed stereotactic guidance and ablation confirmation, without requiring a second contrast enhanced study.

The Role of Genicular Radiofrequency Ablation in the Management of Persistent Pain after Total Knee Arthroplasty.

Persistent pain is one of the most frequent complications following total knee arthroplasty (TKA) and can be devastating for the patient's quality of life. The use of genicular nerve radiofrequency ablation (GNRFA) is prevalent regarding non-surgical treatment of knee osteoarthritis. However, it is controversial when employed for the management of residual pain after TKA. This study aims to evaluate the efficacy of GNRFA for the treatment of post-TKA chronic pain and to assess the potential benefits of its use. Twelve patients sustaining chronic pain after TKA underwent GNRFA treatment. The intervention included the superior medial genicular nerve, the superior lateral genicular nerve and the inferior medial genicular nerve. Visual analog scale (VAS) system was utilized for pain assessment at 1-week, 6-month, and 1-year follow-ups. Patients experiencing chronic knee pain derived from other or unspecified causes were excluded. Mean VAS score before the treatment was 8.3, while it ended up 2.3, 5.7, and 7.9 at the 1-week, 6-month, and 1-year follow-up, respectively. Some patients reported residual pain that they regarded more bearable than before the procedure at the 1-week evaluation, with no significant alterations in the 6-month reassessment. In 2 cases results at the 1-week follow-up were dissatisfying, however, this aided us in distinguishing the cause of the persistent pain. We were not able to conclude that GNRFA used for the treatment of chronic pain after TKA is as efficacious as in knee osteoarthritis pain. However, in some cases, it proved to be beneficial regarding discerning the etiology of the pain.

Predictive nomograms of repeat intrahepatic recurrence and overall survival after radiofrequency ablation of recurrent colorectal liver metastases.

OBJECTIVES: This study was conducted to develop nomograms for predicting repeat intrahepatic recurrence (rIHR) and overall survival (OS), after radiofrequency ablation (RFA), treatment in patients with recurrent colorectal liver metastases (CLMs) after hepatectomy based on clinicopathologic features. METHODS: A total of 160 consecutive patients with recurrent CLMs after hepatectomy who were treated with ultrasound-guided percutaneous RFA from 2012 to 2022 were retrospectively included. Patients were randomly divided into a training cohort and a validation cohort, with a ratio of 8:2. Potential prognostic factors associated with rIHR and OS, after RFA, were identified by using the competing-risks and Cox proportional hazard models, respectively, and were used to construct the nomogram. The nomogram was evaluated by Harrell's C-index and a calibration curve. RESULTS: The 1-, 2-, and 3-year rIHR rates after RFA were 58.8%, 70.2%, and 74.2%, respectively. The 1-, 3- and 5-year OS rates were 96.3%, 60.4%, and 38.5%, respectively. In the multivariate analysis, mutant RAS, interval from hepatectomy to intrahepatic recurrence ≤ 12 months, CEA level >5 ng/ml, and ablation margin <5 mm were the independent predictive factors for rIHR. Mutant RAS, largest CLM at hepatectomy >3 cm, CEA level >5 ng/ml, and extrahepatic disease were independent predictors of poor OS. Two nomograms for rIHR and OS were constructed using the respective significant variables. In both cohorts, the nomogram demonstrated good discrimination and calibration. CONCLUSIONS: The established nomograms can predict individual risk of rIHR and OS after RFA for recurrent CLMs and contribute to improving individualized management.

[Guidelines for image-guided ablation of primary liver cancer (2023 version)].

Image-guided ablation for primary liver cancer has many advantages, including high efficacy, minimal invasion, easy operation, high tolerance, short hospitalization, fast recovery, and few complications. Percutaneous radiofrequency and microwave ablation are the most mature technologies, which have been recognized by many domestic and foreign guidelines as the first-line treatment for small liver cancers. As a large country with large numbers of liver cancers, Chinese doctors have accumulated rich experience in ablation therapy for liver cancer and achieved systematic research results. This guideline focused on the standardization of the puncture path, guidance techniques, indications, preoperative preparation, operation methods, postoperative treatment and follow-up, and complication prevention and treatment strategies for liver cancer ablation, and elaborates on the technical comparisons of image-guided ablation modalities and their status in comprehensive management of primary liver cancer.

Can Machine Learning Predict Favorable Outcome After Radiofrequency Ablation of Hepatocellular Carcinoma?

PURPOSE: The standard practice for limited-stage hepatocellular carcinoma (HCC) is the resection or the use of local ablative techniques, such as radiofrequency ablation (RFA). The outcome after RFA depends on a complex interaction between the patient's general condition, hepatic function, and disease stage. In this study, we aimed to explore using a machine learning model to predict the response. PATIENTS AND METHODS: A retrospective study was conducted for patients with RFA for a localized HCC between 2018 and 2022. The collected clinical, radiologic, and laboratory data were explored using Python and XGBoost. They were split into a training set (70%) and a validation set (30%). The primary end point of this study was to predict the probability of achieving favorable outcomes 12 months after RFA. Favorable outcomes were defined as the patient was alive and HCC was controlled. RESULTS: One hundred and eleven patients were eligible for the study. Males were 78 (70.3%) with a median age of 57 (range of 43-81) years. Favorable outcome was seen in 62 (55.9%) of the patients. The 1-year survival rate and control rate were 94.6%, and 61.3%, respectively. The final model harbored an accuracy and an AUC of 90.6% and 0.95, respectively, for the training set, while they were 78.9% and 0.80, respectively, for the validation set. CONCLUSION: Machine learning can be a predictive tool for the outcome after RFA in patients with HCC. Further validation by a larger study is necessary.

Habitat-based radiomics analysis for evaluating immediate response in colorectal cancer lung metastases treated by radiofrequency ablation.

PURPOSE: To create radiomics signatures based on habitat to assess the instant response in lung metastases of colorectal cancer (CRC) after radiofrequency ablation (RFA). METHODS: Between August 2016 and June 2019, we retrospectively included 515 lung metastases in 233 CRC patients who received RFA (412 in the training group and 103 in the test group). Multivariable analysis was performed to identify independent risk factors for developing the clinical model. Tumor and ablation regions of interest (ROI) were split into three spatial habitats through K-means clustering and dilated with 5 mm and 10 mm thicknesses. Radiomics signatures of intratumor, peritumor, and habitat were developed using the features extracted from intraoperative CT data. The performance of these signatures was primarily evaluated using the area under the receiver operating characteristics curve (AUC) via the DeLong test, calibration curves through the Hosmer-Lemeshow test, and decision curve analysis. RESULTS: A total of 412 out of 515 metastases (80%) achieved complete response. Four clinical variables (cancer antigen 19-9, simultaneous systemic treatment, site of lung metastases, and electrode type) were utilized to construct the clinical model. The Habitat signature was combined with the Peri-5 signature, which achieved a higher AUC than the Peri-10 signature in the test set (0.825 vs. 0.816). The Habitat+Peri-5 signature notably surpassed the clinical and intratumor radiomics signatures (AUC: 0.870 in the test set; both, p < 0.05), displaying improved calibration and clinical practicality. CONCLUSIONS: The habitat-based radiomics signature can offer precise predictions and valuable assistance to physicians in developing personalized treatment strategies.