首页|Chinese Academy of Sciences Reports Findings in Lung Cancer (A machine learning- based approach to predict energy layer for each field in spot-scanning proton ar c therapy for lung cancer: A feasibility study)
Chinese Academy of Sciences Reports Findings in Lung Cancer (A machine learning- based approach to predict energy layer for each field in spot-scanning proton ar c therapy for lung cancer: A feasibility study)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology - Lung Cancer is the subject of a report. According to news reporting out of Lanzhou, People' s Republic of China, by NewsRx editors, research stated, "Determining the optima l energy layer (EL) for each field, under considering both dose constraints and delivery efficiency, is crucial to promoting the development of proton arc thera py (PAT) technology. This study aimed to explore the feasibility and potential c linical benefits of utilizing machine learning (ML) technique to automatically s elect EL for each field in PAT plans of lung cancer." Our news journalists obtained a quote from the research from the Chinese Academy of Sciences, "Proton Bragg peak position (BPP) was employed to characterize EL. The ground truth BPPs for each field were determined using the modified ELO-SPA T framework. Features in geometric, water-equivalent thicknesses (WET) and beaml et were defined and extracted. By analyzing the relationship between the extract ed features and ground truth, a polynomial regression model with L2-norm regular ization (Ridge regression) was constructed and trained. The performance of the r egression model was reported as an error between the predictions and the ground truth. Besides, the predictions were used to make PAT plans (PAT_PR ED). These plans were compared with those using the ground truth BPPs (PAT_ TRUTH) and the mid- WET of the target volumes (PAT_MID) in terms of relative biological effectiveness-weighted dose (RWD) distributions. One hundred ten patients with lung cancer, a total of 7920 samples, were enrolled retrospec tively, with 5940 cases randomly selected as the training set and the remaining 1980 cases as the testing set. Nine patients (648 samples) were collected additi onally to evaluate the regression model in terms of plan quality and robustness. With regard to the prediction errors, the root mean squared errors and mean abs olute errors between the ML-predicted and ground truth BPPs for the testing set were 9.165 and 6.572 mm, respectively, indicating differences of approximately t wo to three ELs. As for plan quality, the PAT_TRUTH and PAT_ PRED plans performed similarly in terms of plan robustness, target coverage and organs at risk (OARs) protection, with differences smaller than 0.5 Gy(RBE). Thi s trend was also observed for dose conformity and uniformity. The PAT_ MID plans produced the lowest robustness index and lowest doses to OARs, along w ith the highest heterogeneity index, indicating better protection for OARs, impr oved plan robustness, but compromised dose homogeneity. Additionally, for relati vely small tumor sizes, the PAT_MID plan demonstrated a notably poo r dose conformity index."
LanzhouPeople's Republic of ChinaAsi aCancerCyborgsEmerging TechnologiesHealth and MedicineLung CancerLun g Diseases and ConditionsLung NeoplasmsMachine LearningOncology
NETL
NSTL
