Search

To determine the pathologic response of computed tomography-guided percutaneous microwave ablation as bridging therapy for patients with hepatocellular carcinoma awaiting liver transplant, and its subsequent effect on survival. A single-center retrospective analysis was conducted on 62 patients (M:F = 50:12) with mean age of 59.6 years ± 7.2 months (SD). Sixty-four total MWA procedures were performed for hepatocellular carcinomas within Milan criteria as bridging therapy to subsequent orthotopic liver transplant between August 2014 and September 2018. The pathology reports of the explanted livers were reviewed to assess for residual disease. Residual disease was categorized as complete or incomplete necrosis. Patient demographics, tumor/procedural characteristics, and laboratory values were evaluated. Survival from time of ablation and time of transplantation were recorded and compared between cohorts using log rank tests. The mean tumor size was 2.4 cm ± 0.7 cm (SD), (range = 1–4.6 cm). 32 (50%) cases required hydrodissection. Histopathologic necrosis was seen in 66% of cases at time of liver transplantation. Median time to liver transplant post-MWA was 12.6 months. [IQR = 8.6–14.8 months]. The median survival from ablation was 60.8 months [IQR = 45.5–73.7 months], and the median survival from transplant was 49.3 months [IQR = 33.7–60.1 months]. There was no significant difference in survival for patients with complete versus incomplete necrosis from ablation or liver transplant (p = 0.49, p = 0.46, respectively). Computed tomography-guided percutaneous microwave ablation is an effective bridge to orthotopic liver transplantation for patients with hepatocellular carcinoma. Level 3, non-randomized controlled cohort study/follow-up study.

To assess the performance of pre-ablation computed tomography texture features of adrenal metastases to predict post-treatment local progression and survival in patients who underwent ablation using machine learning as a prediction tool. This is a pilot retrospective study of patients with adrenal metastases undergoing ablation. Clinical variables were collected. Thirty-two texture features were extracted from manually segmented adrenal tumors. A univariate cox proportional hazard model was used for prediction of local progression and survival. A linear support vector machine (SVM) learning technique was applied to the texture features and clinical variables, with leave-one-out cross-validation. Receiver operating characteristic analysis and the area under the curve (AUC) were used to assess performance between using clinical variables only versus clinical variables and texture features. Twenty-one patients (61% male, age 64.1 ± 10.3 years) were included. Mean time to local progression was 29.8 months. Five texture features exhibited association with progression (p

The purpose of this review is to highlight the current role of machine learning and artificial intelligence and in the field of interventional oncology. With advancements in technology, there is a significant amount of research regarding the application of artificial intelligence and machine learning in medicine. Interventional oncology is a field that can benefit greatly from this research through enhanced image analysis and intraprocedural guidance. These software developments can increase detection of cancers through routine screening and improve diagnostic accuracy in classifying tumors. They may also aid in selecting the most effective treatment for the patient by predicting outcomes based on a combination of both clinical and radiologic factors. Furthermore, machine learning and artificial intelligence can advance intraprocedural guidance for the interventional oncologist through more accurate needle tracking and image fusion technology. This minimizes damage to nearby healthy tissue and maximizes treatment of the tumor. While there are several exciting developments, this review also discusses limitations before incorporating machine learning and artificial intelligence in the field of interventional oncology. These include data capture and processing, lack of transparency among developers, validating models, integrating workflow, and ethical challenged. In summary, machine learning and artificial intelligence have the potential to positively impact interventional oncologists and how they provide cancer care treatments.

To assess the feasibility, safety and clinical outcomes of image-guided percutaneous thermal ablation as salvage therapy for local recurrence of renal cell carcinoma (RCC) in patients initially treated surgically with curative intent. A retrospective review of 11 consecutive patients (M/F = 8:3, mean age = 76 years) who underwent computed tomography (CT)-guided thermal ablation for locally recurrent RCC after partial (72%, 8/11) or radical nephrectomy (28%, 3/11) with a mean time to recurrence of 48 months (range 2–156). Assessment of technical success, complication (peri- and post-procedural), oncological outcome and survival analysis were performed. Patient baseline and follow-up renal function surrogates including creatinine level (Cr) and estimated glomerular filtration rate (eGFR) were statistically compared. Eleven biopsy-proven recurrent RCC measuring 1.4–3.9 cm (mean = 2.8 cm) were treated with CT-guided thermal ablation. Technical success was achieved in 100% (11/11) of the cases. There were no major complications except for one (9%) asymptomatic hemorrhage (Clavien–Dindo grade I complication). Complete response, local progression-free and overall survival rate were 91, 91 and 82% during the mean follow-up time of 2.5 years (range 0.1–7.1). Renal function was overall stable without significant change at 1 month and last follow-up (p = 0.21; GFR, p = 0.10; creatinine). Image-guided percutaneous thermal ablation is a feasible, safe and effective for local recurrence after nephrectomy, representing a non-surgical alternative for unresectable disease.

The purpose of the study was to compare the quality of stomach and small bowel marking/labeling using 1,350 ml of low-density barium alone (VoLumen) with 900 ml of low-density barium and 450 ml of water for 16-MDCT scans of the abdomen and pelvis and assess cost benefits with the two protocols. In this IRB approved study, 80 consecutive patients scheduled for routine CECT (contrast-enhanced CT) of the abdomen-pelvis were studied. Patients were randomized into two groups and were administered either 1,350 ml of VoLumen (two bottles at 20-min intervals, one half bottle at 50 min and the last half on the table) or 900 ml of VoLumen (two bottles at 20-min intervals and 450 ml water on the table). Portal venous phase scanning (detector collimation = 0.625 mm, speed = 18.75 mm, thickness = 5 mm) was subsequently performed. Images were reconstructed in axial and coronal plane at the CT console. Two blinded readers used a pre-designed template to assess distension and wall characteristics of the stomach and small bowel on a 5-point scale. Median scores with the two protocols were compared using the Wilcoxon rank sum test. The stomach and small bowel labeling was rated fair to optimal in all patients and did not differ significantly in the two protocols. The mean scores for distension of the small bowel and stomach were comparable. Inter-observer agreement for bowel labeling was found to be excellent (k 0.81). With the use of coronal images there was increased reader confidence in tracing the small bowel with both protocols. Acceptance for two bottles of VoLumen and water was greater among patients as compared to three bottles of VoLumen. Use of two bottles of VoLumen and water combination cost less than three bottles of VoLumen. Stomach and small bowel labeling with administration of 900 ml of VoLumen followed by 450 ml of water is cost effective and compares well to 1,350 ml of VoLumen alone.