Assessment of safety margin after microwave ablation of stage I NSCLC with three-dimensional reconstruction technique using CT imaging

Yan, Peng; Tong, Anna; Nie, Xiuli; Ma, Minge

doi:10.1186/s12880-021-00626-z

Cited by 11 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A radiomics signature, composed of multiple features, serves as a robust prognostic biomarker that could complement clinical data [ 38 ]. The overestimation of the completely necrotic region as GGO on CT [ 39 ] indicates the need to ablate peritumoral lung parenchyma within 5 to 10 mm for complete ablation [ 9 , 40 ]. Previous studies have highlighted the utility of combining intra- and peritumoral radiomics features for improved treatment response prediction [ 16 , 19 ].…”

Section: Discussionmentioning

confidence: 99%

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

Huang,

Chen,

Zheng

et al. 2024

Cancer Imaging

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Huang,

Chen,

Zheng

et al. 2024

Cancer Imaging

View full text Add to dashboard Cite

show abstract

“…Our method has several important potential clinical applications [43,44]. Pre-procedure planning with our model can be used to establish applicator trajectory, power, and duration.…”

Section: Discussionmentioning

confidence: 99%

“…The segmented ablation zones on follow-up scans were used as ground truth for training since they are the clinical standard for assessing lung ablation zones and treatment margins [25,26]. We utilized the sum of cross entropy and the Dice co-efficient between the predicted and ground truth as the loss function to train the network [27].…”

Section: Trainingmentioning

confidence: 99%

Pre-operative lung ablation prediction using deep learning

Keshavamurthy,

Eickhoff,

Ziv

2024

Eur Radiol

View full text Add to dashboard Cite

Objective Microwave lung ablation (MWA) is a minimally invasive and inexpensive alternative cancer treatment for patients who are not candidates for surgery/radiotherapy. However, a major challenge for MWA is its relatively high tumor recurrence rates, due to incomplete treatment as a result of inaccurate planning. We introduce a patient-specific, deep-learning model to accurately predict post-treatment ablation zones to aid planning and enable effective treatments. Materials and methods Our IRB-approved retrospective study consisted of ablations with a single applicator/burn/vendor between 01/2015 and 01/2019. The input data included pre-procedure computerized tomography (CT), ablation power/time, and applicator position. The ground truth ablation zone was segmented from follow-up CT post-treatment. Novel deformable image registration optimized for ablation scans and an applicator-centric co-ordinate system for data analysis were applied. Our prediction model was based on the U-net architecture. The registrations were evaluated using target registration error (TRE) and predictions using Bland-Altman plots, Dice co-efficient, precision, and recall, compared against the applicator vendor’s estimates. Results The data included 113 unique ablations from 72 patients (median age 57, interquartile range (IQR) (49–67); 41 women). We obtained a TRE ≤ 2 mm on 52 ablations. Our prediction had no bias from ground truth ablation volumes (p = 0.169) unlike the vendor’s estimate (p < 0.001) and had smaller limits of agreement (p < 0.001). An 11% improvement was achieved in the Dice score. The ability to account for patient-specific in-vivo anatomical effects due to vessels, chest wall, heart, lung boundaries, and fissures was shown. Conclusions We demonstrated a patient-specific deep-learning model to predict the ablation treatment effect prior to the procedure, with the potential for improved planning, achieving complete treatments, and reduce tumor recurrence. Clinical relevance statement Our method addresses the current lack of reliable tools to estimate ablation extents, required for ensuring successful ablation treatments. The potential clinical implications include improved treatment planning, ensuring complete treatments, and reducing tumor recurrence.

show abstract

“…Tumor size represents tumor burden and is usually associated with poor treatment outcomes. In non-small cell lung cancer, a diameter of tumor >3 cm was positively correlated with local tumor progression after MWA [ 22 ]. Largest ablated tumor diameter ≥4 cm was associated with worse recurrence-free survival of hepatocellular cancer patients after MWA [ 23 ].…”

Section: Discussionmentioning

confidence: 99%

Complications and local recurrence of malignant liver tumor after ablation in risk areas: a retrospective analysis

Yan

Yang

Zhu

et al. 2023

European Journal of Gastroenterology &Amp; Hepatology

View full text Add to dashboard Cite

Introduction Microwave ablation (MWA) is an effective local treatment for malignant liver tumors; however, its efficacy and safety for liver tumors adjacent to important organs are debatable. Patients and methods Forty-three cases with liver tumors adjacent to important organs were the risk group and 66 cases were the control group. The complications between two groups were compared by chi-square test and t-test. Local tumor recurrence (LTR) was analyzed by log-rank test. Factors affecting complications were analyzed by logistic regression and Spearman analyses. Factors affecting LTR were analyzed by Cox regression analysis. A receiver operating characteristic curve predicted pain treated with drugs and LTR. Results We found no significant difference in complications and LTR between two groups. The risk group experienced lower ablation energy and more antennas per tumor than control group. Necrosis volume after MWA was positively correlated with pain; necrosis volume and ablation time were positively correlated with recovery duration. Major diameter of tumor >3 cm increased risk of LTR by 3.319-fold, good lipiodol deposition decreased risk of LTR by 73.4%. The area under the curve (AUC) for necrosis volume in predicting pain was 0.74, with a 69.1 cm 3 cutoff. AUC for major diameter of tumor in predicting LTR was 0.68, with a 27.02 mm cutoff. Conclusion MWA on liver tumors in at-risk areas is safe and effective, this is largely affected by proper ablation energy, antennas per tumor, and experienced doctors. LTR is primarily determined by major diameter of tumor and lipiodol deposition status.

show abstract

Assessment of safety margin after microwave ablation of stage I NSCLC with three-dimensional reconstruction technique using CT imaging

Cited by 11 publications

References 30 publications

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

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

Pre-operative lung ablation prediction using deep learning

Complications and local recurrence of malignant liver tumor after ablation in risk areas: a retrospective analysis

Contact Info

Product

Resources

About