Patient Specific Characteristics Are an Important Factor That Determines the Risk of Acute Grade ≥ 2 Rectal Toxicity in Patients Treated for Prostate Cancer with IMRT and Daily Image Guidance Based on Implanted Gold Markers

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

In order to limit radiotherapy (RT)-related side effects, effective toxicity prediction and assessment schemes are essential. In recent years, the growing interest toward artificial intelligence and machine learning (ML) within the science community has led to the implementation of innovative tools in RT. Several researchers have demonstrated the high performance of ML-based models in predicting toxicity, but the application of these approaches in clinics is still lagging, partly due to their low interpretability. Therefore, an overview of contemporary research is needed in order to familiarize practitioners with common methods and strategies. Here, we present a review of ML-based models for predicting and classifying RT-induced complications from both a methodological and a clinical standpoint, focusing on the type of features considered, the ML methods used, and the main results achieved. Our work overviews published research in multiple cancer sites, including brain, breast, esophagus, gynecological, head and neck, liver, lung, and prostate cancers. The aim is to define the current state of the art and main achievements within the field for both researchers and clinicians.

Modeling of Acute Rectal Toxicity to Compare Two Patient Positioning Methods for Prostate Cancer Radiotherapy: Can Toxicity Modeling be Used for Quality Assurance?

Purpose:

Intensity Modulated Radiation Therapy (IMRT) allows for significant dose reductions to organs at risk in prostate cancer patients. However, the accurate delivery of IMRT plans can be compromised by patient positioning errors. The purpose of this study was to determine if the modeling of grade ≥ 2 acute rectal toxicity could be used to monitor the quality of IMRT protocols.

Materials and Methods:

79 patients treated with Image and Fiducial Markers Guided IMRT (FMIGRT) and 302 patients treated with trans-abdominal ultrasound guided IMRT (USGRT) was selected for this study. Treatment plans were available for the FMIGRT group, and hand recorded dosimetric indices were available for both groups. We modeled toxicity in the FMIGRT group using the Lyman Kutcher Burman (LKB) and Univariate Logistic Regression (ULR) models, and we modeled toxicity in USGRT group using the ULR model. We performed Receiver Operating Characteristics (ROC) analysis on all of the models and compared the Area under the ROC curve (AUC) for the FMIGRT and the USGRT groups.

Results:

The observed Incidence of grade ≥ 2 rectal toxicity was 20% in FMIGRT patients and 54% in USGRT patients. LKB model parameters in the FMIGRT group were TD₅₀=56.8 Gy, slope m=0.093, and exponent n=0.131. The most predictive indices in the ULR model for the FMIGRT group were D_25% and V_{50 Gy}. AUC for both models in the FMIGRT group was similar (AUC=0.67). The FMIGRT URL model predicted less than a 37% incidence of grade ≥ 2 acute rectal toxicity in the USGRT group. A fit of the ULR model to USGRT data did not yield a predictive model (AUC=0.5).

Conclusion:

Modeling of acute rectal toxicity provided a quantitative measure of the correlation between planning dosimetry and this clinical endpoint. Our study suggests that an unusually weak correlation may indicate a persistent patient positioning error.

Strategies for prediction and mitigation of radiation-induced liver toxicity

Although well described in the 1960s, liver toxicity secondary to radiation therapy, commonly known as radiation-induced liver disease (RILD), remains a major challenge. RILD encompasses two distinct clinical entities, a 'classic' form, composed of anicteric hepatomegaly, ascites and elevated alkaline phosphatase; and a 'non-classic' form, with liver transaminases elevated to more than five times the reference value, or worsening of liver metabolic function represented as an increase of 2 or more points in the Child-Pugh score classification. The risk of occurrence of RILD has historically limited the applicability of radiation for the treatment of liver malignancies. With the development of 3D conformal radiation therapy, which allowed for partial organ irradiation based on computed tomography treatment planning, there has been a resurgence of interest in the use of liver irradiation. Since then, a large body of evidence regarding the liver tolerance to conventionally fractionated radiation has been produced, but severe liver toxicities has continued to be reported. More recently, improvements in diagnostic imaging, radiation treatment planning technology and delivery systems have prompted the development of stereotactic body radiotherapy (SBRT), by which high doses of radiation can be delivered with high target accuracy and a steep dose gradient at the tumor - normal tissue interface, offering an opportunity of decreasing toxicity rates while improving tumor control. Here, we present an overview of the role SBRT has played in the management of liver tumors, addressing the challenges and opportunities to reduce the incidence of RILD, such as adaptive approaches and machine-learning-based predictive models.