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

Abstract

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.

Prostate Cancer Radiogenomics—From Imaging to Molecular Characterization

“…These models were already studied in a variety of cancers [ 35 , 36 , 37 , 38 , 39 ]. The recent rise in artificial intelligence (AI) and machine learning (ML) algorithms has introduced new classifications for PCa, regarding the differentiation of favorable from unfavorable disease [ 40 , 41 ]; the quantitative assessment of information predicting the tumor Gleason score [ 31 , 32 , 42 , 43 , 44 ] and biochemical recurrence (BCR)-free survival [ 45 ]; the identification of tumors through mpMRI [ 43 , 46 ]; the development of new detection features, such as advanced zoomed diffusion-weighted imaging (DWI) and conventional full-field-of-view DWI [ 47 ]; texture analysis of prostate MRI in the prostate imaging reporting and data system (PIRADS) for PI-RADS 3 score lesions [ 48 ]; the creation of frameworks for automated PCa localization and detection [ 49 ]; and, finally, the management of radiotherapy treatment and toxicity [ 50 , 51 , 52 , 53 , 54 , 55 , 56 ], and the prediction of BCR [ 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 ]. Additionally, radiomics and AI algorithms will help to limit the discrepancies between different readers [ 66 ].…”

Tenacissoside H Induces Autophagy and Radiosensitivity of Hepatocellular Carcinoma Cells by PI3K/Akt/mTOR Signaling Pathway

“… 14 - 15 Radiotherapy causes radioactive damage when rays directly act on biomolecules, indirectly damages DNA by producing free radicals to interact with biological macromolecules, blocks cell division and proliferation, and causes irreversible damage in cells, which is the first choice for treatment of locally advanced HCC. 16 However, radiation resistance is the major challenge during radiotherapy. After long-term radiation irradiation, tumors show radiation resistance similar to chemotherapy drug tolerance, which reduces the sensitivity of the tumor to radiation and causes tumor metastasis or recurrence.…”

Artificial Intelligence and Machine Learning in Prostate Cancer Patient Management—Current Trends and Future Perspectives

“…This is to improve seed identification [ 81 ] and the radiation dose calculations using CNN models to help improve the speed of those calculations [ 88 , 89 , 90 ]. The outcomes of toxicity following radiotherapy were assessed by Isaksson et al [ 91 ] in a review of PCa radiotherapy treatment in terms of genitourinary and gastrointestinal toxicity, and the publications screened only a few that showed better performance than classical models. By adding more features when training the model (the use of statin drugs and PSA (Prostate Specific Antigen) level prior to intensity, modulated radiotherapy was found to be strongly related to the toxicity outcome.…”

“…There are studies that used ML to develop methods to better localize radioactive seeds [ 81 , 87 ], using CNNs to calculate the right dose. DL based methods will be able to calculate the radio-therapeutic dose with accuracy and efficiency in order to reduce toxicity [ 91 ]. AI techniques will need future studies to better identify anatomical regions for radiotherapy, better radioactive seed implantation to cover the lesions, and dose calculations to reduce radiotherapy related toxicity.…”