Work

Artificial intelligence system assists doctors to improve the treatment effect of microwave ablation on hepatocellular carcinoma: A prospective cohort study

Year: 2025

Type: article

Abstract: Background Treatment effect of hepatocellular carcinoma (HCC) through ablation is highly dependent on doctors’ experience. Purpose To develop an artificial intelligence-assisted microwave ablation planning system (MWA-PS) to improve ablation treatment effect. Methods Pre-ablative image, clinical information and ablation parameters were collected to build MWA-PS. MWA-PS was consisted by three modules: analyze image module, predictive ablation energy module, and output parameter module which can output: ablation time, power, needle number, needle type, and needle distance. HCCs from four centers were collected as prospective cohort to compare the local tumor progression (LTP), technical effective, complication and mean ablation energy among experienced-doctor (ED), less-experienced-doctor (LED) and less-experienced-doctor with MWA-PS (MWA-PS) groups. Results 875 HCCs were divided into training (n=788) and validation (n=87) sets, and the mean relative error of MWA-PS on ablation energy was 8.0% and 8.2%, respectively. 388 HCCs were randomly divided into ED (n=130), LED (n=128) and MWA-PS (n=130) groups. With a 15.3 months median follow-up, MWA-PS group showed lower LTP than LED group (4.7% vs 11.6%, p=0.041) and comparable LTP to ED group (4.7% vs 5.5%, p=0.770). For HCCs adjacent to capsule/vessels, MWA-PS group showed relatively lower LTP than LED group (6.3% vs 20.7%, p=0.096) and comparable to ED group (6.3% vs 9.7%, p=0.600). Three groups achieved comparable technical effective and complication rate, and mean ablation energy of MWA-PS group was lower than LED and ED groups (28±10kJ vs 38±26kJ, p<0.001; 28±10kJ vs 34±16kJ, p<0.001). Conclusions MWA-PS can help less-experienced doctors achieve comparable local tumor control effect to experienced doctors.

Source: Digital engineering.

DOI: 10.1016/j.dte.2025.100054