1
|
Maragno D, Buti G, Birbil Şİ, Liao Z, Bortfeld T, den Hertog D, Ajdari A. Embedding machine learning based toxicity models within radiotherapy treatment plan optimization. Phys Med Biol 2024; 69:075003. [PMID: 38412530 DOI: 10.1088/1361-6560/ad2d7e] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Accepted: 02/27/2024] [Indexed: 02/29/2024]
Abstract
Objective.This study addresses radiation-induced toxicity (RIT) challenges in radiotherapy (RT) by developing a personalized treatment planning framework. It leverages patient-specific data and dosimetric information to create an optimization model that limits adverse side effects using constraints learned from historical data.Approach.The study uses the optimization with constraint learning (OCL) framework, incorporating patient-specific factors into the optimization process. It consists of three steps: optimizing the baseline treatment plan using population-wide dosimetric constraints; training a machine learning (ML) model to estimate the patient's RIT for the baseline plan; and adapting the treatment plan to minimize RIT using ML-learned patient-specific constraints. Various predictive models, including classification trees, ensembles of trees, and neural networks, are applied to predict the probability of grade 2+ radiation pneumonitis (RP2+) for non-small cell lung (NSCLC) cancer patients three months post-RT. The methodology is assessed with four high RP2+ risk NSCLC patients, with the goal of optimizing the dose distribution to constrain the RP2+ outcome below a pre-specified threshold. Conventional and OCL-enhanced plans are compared based on dosimetric parameters and predicted RP2+ risk. Sensitivity analysis on risk thresholds and data uncertainty is performed using a toy NSCLC case.Main results.Experiments show the methodology's capacity to directly incorporate all predictive models into RT treatment planning. In the four patients studied, mean lung dose and V20 were reduced by an average of 1.78 Gy and 3.66%, resulting in an average RP2+ risk reduction from 95% to 42%. Notably, this reduction maintains tumor coverage, although in two cases, sparing the lung slightly increased spinal cord max-dose (0.23 and 0.79 Gy).Significance.By integrating patient-specific information into learned constraints, the study significantly reduces adverse side effects like RP2+ without compromising target coverage. This unified framework bridges the gap between predicting toxicities and optimizing treatment plans in personalized RT decision-making.
Collapse
Affiliation(s)
- Donato Maragno
- Amsterdam Business School, University of Amsterdam, Amsterdam, The Netherlands
| | - Gregory Buti
- Massachusetts General Hospital and Harvard Medical School, Department of Radiation Oncology, Division of Radiation BioPhysics, Boston, MA, United States of America
| | - Ş İlker Birbil
- Amsterdam Business School, University of Amsterdam, Amsterdam, The Netherlands
| | - Zhongxing Liao
- University of Texas' MD Anderson Cancer Center, Department of Radiation Oncology, Division of Radiation Oncology, Houston, TX, United States of America
| | - Thomas Bortfeld
- Massachusetts General Hospital and Harvard Medical School, Department of Radiation Oncology, Division of Radiation BioPhysics, Boston, MA, United States of America
| | - Dick den Hertog
- Amsterdam Business School, University of Amsterdam, Amsterdam, The Netherlands
| | - Ali Ajdari
- Massachusetts General Hospital and Harvard Medical School, Department of Radiation Oncology, Division of Radiation BioPhysics, Boston, MA, United States of America
| |
Collapse
|
2
|
Kobayashi K, Murakami N, Takahashi K, Inaba K, Igaki H, Hamamoto R, Itami J. Tensor Regression-based Model to Investigate Heterogeneous Spatial Radiosensitivity After I-125 Seed Implantation for Prostate Cancer. In Vivo 2021; 35:489-497. [PMID: 33402501 DOI: 10.21873/invivo.12283] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2020] [Revised: 10/19/2020] [Accepted: 10/20/2020] [Indexed: 11/10/2022]
Abstract
BACKGROUND/AIM We established a data-driven method for extracting spatial patterns of dose distribution associated with radiation injuries, based on patients with prostate cancer who underwent iodine-125 (I-125) seed implantation. PATIENTS AND METHODS Seventy-five patients underwent I-125 seed implantation for prostate cancer. We modeled the severity of lower urinary tract symptoms (LUTS) to be estimated using a linear model, which is formulated as an inner product between the dose distribution D and voxel-wise radiosensitivity B inside the prostate. For the estimation, tensor regression based on a low-rank decomposition with generalized fused lasso penalty was applied. RESULTS The spatial distribution of B was visually assessed. Positive parameters appeared dominantly in the region close to the urethra and the prostate base. CONCLUSION Our tensor regression-based model can predict intra-organ radiosensitivity in a data-driven manner, providing a compelling parameter distribution associated with the development of LUTS after I-125 seed implantation for prostate cancer.
Collapse
Affiliation(s)
- Kazuma Kobayashi
- Division of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, Tokyo, Japan; .,Cancer Translational Research Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.,Department of NCC Cancer Science, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
| | - Naoya Murakami
- Department of Radiation Oncology, National Cancer Center Hospital, Tokyo, Japan
| | - Kana Takahashi
- Department of Radiation Oncology, National Cancer Center Hospital, Tokyo, Japan
| | - Koji Inaba
- Department of Radiation Oncology, National Cancer Center Hospital, Tokyo, Japan
| | - Hiroshi Igaki
- Department of Radiation Oncology, National Cancer Center Hospital, Tokyo, Japan
| | - Ryuji Hamamoto
- Division of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, Tokyo, Japan.,Cancer Translational Research Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.,Department of NCC Cancer Science, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
| | - Jun Itami
- Department of Radiation Oncology, National Cancer Center Hospital, Tokyo, Japan
| |
Collapse
|
3
|
Isaksson LJ, Pepa M, Zaffaroni M, Marvaso G, Alterio D, Volpe S, Corrao G, Augugliaro M, Starzyńska A, Leonardi MC, Orecchia R, Jereczek-Fossa BA. Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy. Front Oncol 2020; 10:790. [PMID: 32582539 PMCID: PMC7289968 DOI: 10.3389/fonc.2020.00790] [Citation(s) in RCA: 51] [Impact Index Per Article: 12.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2020] [Accepted: 04/22/2020] [Indexed: 12/20/2022] Open
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.
Collapse
Affiliation(s)
- Lars J Isaksson
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Matteo Pepa
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Mattia Zaffaroni
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Giulia Marvaso
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy.,Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | - Daniela Alterio
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Stefania Volpe
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Giulia Corrao
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy.,Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | - Matteo Augugliaro
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Anna Starzyńska
- Department of Oral Surgery, Medical University of Gdańsk, Gdańsk, Poland
| | - Maria C Leonardi
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Roberto Orecchia
- Scientific Directorate, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Barbara A Jereczek-Fossa
- Division of Radiotherapy, IEO European Institute of Oncology IRCCS, Milan, Italy.,Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| |
Collapse
|
4
|
Independent component analysis for rectal bleeding prediction following prostate cancer radiotherapy. Radiother Oncol 2017; 126:263-269. [PMID: 29203291 DOI: 10.1016/j.radonc.2017.11.011] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2016] [Revised: 11/18/2017] [Accepted: 11/20/2017] [Indexed: 11/22/2022]
Abstract
BACKGROUND AND PURPOSE To evaluate the benefit of independent component analysis (ICA)-based models for predicting rectal bleeding (RB) following prostate cancer radiotherapy. MATERIALS AND METHODS A total of 593 irradiated prostate cancer patients were prospectively analyzed for Grade ≥2 RB. ICA was used to extract two informative subspaces (presenting RB or not) from the rectal DVHs, enabling a set of new pICA parameters to be estimated. These DVH-based parameters, along with others from the principal component analysis (PCA) and functional PCA, were compared to "standard" features (patient/treatment characteristics and DVH bins) using the Cox proportional hazards model for RB prediction. The whole cohort was divided into: (i) training (N = 339) for ICA-based subspace identification and Cox regression model identification and (ii) validation (N = 254) for RB prediction capability evaluation using the C-index and the area under the receiving operating curve (AUC), by comparing predicted and observed toxicity probabilities. RESULTS In the training cohort, multivariate Cox analysis retained pICA and PC as significant parameters of RB with 0.65 C-index. For the validation cohort, the C-index increased from 0.64 when pICA was not included in the Cox model to 0.78 when including pICA parameters. When pICA was not included, the AUC for 3-, 5-, and 8-year RB prediction were 0.68, 0.66, and 0.64, respectively. When included, the AUC increased to 0.83, 0.80, and 0.78, respectively. CONCLUSION Among the many various extracted or calculated features, ICA parameters improved RB prediction following prostate cancer radiotherapy.
Collapse
|
5
|
Ospina JD, Fargeas A, Dréan G, Simon A, Acosta O, de Crevoisier R. Recent advancements in toxicity prediction following prostate cancer radiotherapy. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2016; 2015:5231-4. [PMID: 26737471 DOI: 10.1109/embc.2015.7319571] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
In external beam radiotherapy for prostate cancer limiting toxicities for dose escalation are bladder and rectum toxicities. Normal tissue complication probability models aim at quantifying the risk of developping adverse events following radiotherapy. These models, originally proposed in the context of uniform irradiation, have evolved to implementations based on the state-of-the-art classification methods which are trained using empirical data. Recently, the use of image processing techniques combined with population analysis methods has led to a new generation of models to understand the risk of normal tissue complications following radiotherapy. This paper overviews those methods in the case of prostate cancer radiation therapy and propose some lines of future research.
Collapse
|
6
|
Liu L, Kachenoura A, Fargeas A, Dréan G, Lafond C, De Crevoisier R, Acosta O, Albera L. Discriminant nonnegative matrix factorization for classification of rectal bleeding in prostate cancer radiotherapy. Ing Rech Biomed 2015. [DOI: 10.1016/j.irbm.2015.10.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
7
|
Fargeas A, Arango JDO, Kachenoura A, Costet N, Albera L, Lafond C, Acosta O, De Crevoisier R. A new parameter computed with independent component analysis to predict rectal toxicity following prostate cancer radiotherapy. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2015; 2015:2657-2660. [PMID: 26736838 DOI: 10.1109/embc.2015.7318938] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
The main challenge in prostate cancer radiotherapy is to deliver the prescribed dose to the clinical target while minimizing the dose to the neighboring organs at risk and thus avoiding subsequent toxicity-related events. With the aim of improving toxicity prediction following prostate cancer radiotherapy, the goal of our work is to propose a new predictive variable computed with independent component analysis to predict late rectal toxicity, and to compare its performance to other models (logistic regression, normal tissue complication probability model and recent principal component analysis approach). Clinical data and dose-volume histograms were collected from 216 patients having received 3D conformal radiation for prostate cancer with at least two years of follow-up. Independent component analysis was trained to predict the risk of 3-year rectal bleeding Grade ≥ 2. The performance of all the models was assessed by computing the area under the receiving operating characteristic curve. Clinical parameters combined with the new variable were found to be predictors of rectal bleeding. The mean area under the receiving operating curve for our proposed approach was 0:75. The AUC values for the logistic regression, the Lyman-Kutcher-Burman model and the recent principal component analysis approach were 0:62, 0:53 and 0:62, respectively. Our proposed new variable may be an useful new tool in predicting late rectal toxicity. It appears as a strong predictive variable to improve classical models.
Collapse
|