1
|
Badillo-Alvarado AH, Martín-Tovar EA, Molina-Salinas GM, Sandoval-Méndez AC, Sarricolea-Puch A. Association between the cardiac contact distance and the maximum dose at the left anterior descending coronary artery in post mastectomized patients. RADIATION AND ENVIRONMENTAL BIOPHYSICS 2022; 61:407-423. [PMID: 35819511 DOI: 10.1007/s00411-022-00983-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/20/2021] [Accepted: 06/26/2022] [Indexed: 06/15/2023]
Abstract
The clinical information on the relationship between the cardiac contact distance (CCD), the maximum dose (Dmax) delivered to the left anterior descending (LAD) coronary artery and the mean heart dose has mostly focused on patients with breast-conserving surgery (BCS), being scarce in postmastectomy patients. The aim of this study is to determine the association between the CCD and the Dmax delivered to the LAD. The secondary objective was to evaluate the dosimetric results of comparing three-dimensional conformal radiotherapy (3D-CRT) to intensity-modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT) techniques for post mastectomized breast cancer patients with irradiation to the left chest wall. 53 cases of women who received adjuvant standard fractionated postmastectomy radiotherapy (PMRT) were used. Three types of plans were created for each patient: 3D-CRT, seven equidistant IMRT fields, and four partial VMAT arcs. Correlations were evaluated using Pearson's correlation coefficient. Plans made with IMRT and VMAT showed improved homogeneity and conformity. Associations between CCD and Dmax to LAD were positive for all three plan types. Compared to 3D-CRT, the modulated intensity plans obtained better dose homogeneity and conformity to the target volume. The LAD and heart doses were significantly lower for IMRT and VMAT plans. The CCD can be used as a predictor of the maximum and mean doses of the LAD. Modulated intensity techniques allow for better dose distribution and dose reduction to the heart and LAD.
Collapse
Affiliation(s)
- A H Badillo-Alvarado
- División de Oncología y Uronefrología, Departamento de Radioterapia, Unidad Médica de Alta Especialidad, Hospital de Especialidades del Centro Médico Nacional "Ignacio García Téllez", Instituto Mexicano del Seguro Social, CP 97150, Mérida, Yucatán, México
| | - E A Martín-Tovar
- División de Oncología y Uronefrología, Departamento de Radioterapia, Unidad Médica de Alta Especialidad, Hospital de Especialidades del Centro Médico Nacional "Ignacio García Téllez", Instituto Mexicano del Seguro Social, CP 97150, Mérida, Yucatán, México.
| | - G M Molina-Salinas
- Unidad de Investigación Médica Yucatán, Unidad Médica de Alta Especialidad Hospital de Especialidades 1 Mérida, Yucatán, Instituto Mexicano del Seguro Social, CP 97150, Mérida, Yucatán, México
| | - A C Sandoval-Méndez
- División de Oncología y Uronefrología, Departamento de Radioterapia, Unidad Médica de Alta Especialidad, Hospital de Especialidades del Centro Médico Nacional "Ignacio García Téllez", Instituto Mexicano del Seguro Social, CP 97150, Mérida, Yucatán, México
| | - A Sarricolea-Puch
- División de Oncología y Uronefrología, Departamento de Radioterapia, Unidad Médica de Alta Especialidad, Hospital de Especialidades del Centro Médico Nacional "Ignacio García Téllez", Instituto Mexicano del Seguro Social, CP 97150, Mérida, Yucatán, México
| |
Collapse
|
2
|
Hoppe RT, Advani RH, Ai WZ, Ambinder RF, Armand P, Bello CM, Benitez CM, Chen W, Dabaja B, Daly ME, Gordon LI, Hansen N, Herrera AF, Hochberg EP, Johnston PB, Kaminski MS, Kelsey CR, Kenkre VP, Khan N, Lynch RC, Maddocks K, McConathy J, Metzger M, Morgan D, Mulroney C, Pullarkat ST, Rabinovitch R, Rosenspire KC, Seropian S, Tao R, Torka P, Winter JN, Yahalom J, Yang JC, Burns JL, Campbell M, Sundar H. NCCN Guidelines® Insights: Hodgkin Lymphoma, Version 2.2022. J Natl Compr Canc Netw 2022; 20:322-334. [PMID: 35390768 DOI: 10.6004/jnccn.2022.0021] [Citation(s) in RCA: 37] [Impact Index Per Article: 18.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Hodgkin lymphoma (HL) is an uncommon malignancy of B-cell origin. Classical HL (cHL) and nodular lymphocyte-predominant HL are the 2 main types of HL. The cure rates for HL have increased so markedly with the advent of modern treatment options that overriding treatment considerations often relate to long-term toxicity. These NCCN Guidelines Insights discuss the recent updates to the NCCN Guidelines for HL focusing on (1) radiation therapy dose constraints in the management of patients with HL, and (2) the management of advanced-stage and relapsed or refractory cHL.
Collapse
Affiliation(s)
| | | | - Weiyun Z Ai
- UCSF Helen Diller Family Comprehensive Cancer Center
| | | | | | | | | | - Weina Chen
- UT Southwestern Simmons Comprehensive Cancer Center
| | | | | | - Leo I Gordon
- Robert H. Lurie Comprehensive Cancer Center of Northwestern University
| | | | | | | | | | | | | | | | | | - Ryan C Lynch
- Fred Hutchinson Cancer Research Center/University of Washington
| | - Kami Maddocks
- The Ohio State University Comprehensive Cancer Center - James Cancer Hospital and Solove Research Institute
| | | | - Monika Metzger
- St. Jude Children's Research Hospital/The University of Tennessee Health Science Center
| | | | | | | | | | | | | | - Randa Tao
- Huntsman Cancer Institute at the University of Utah
| | | | - Jane N Winter
- Robert H. Lurie Comprehensive Cancer Center of Northwestern University
| | | | - Joanna C Yang
- Siteman Cancer Center at Barnes-Jewish Hospital and Washington University School of Medicine; and
| | | | | | | |
Collapse
|
3
|
Siciarz P, Alfaifi S, Uytven EV, Rathod S, Koul R, McCurdy B. Machine learning for dose-volume histogram based clinical decision-making support system in radiation therapy plans for brain tumors. Clin Transl Radiat Oncol 2021; 31:50-57. [PMID: 34632117 PMCID: PMC8487981 DOI: 10.1016/j.ctro.2021.09.001] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2021] [Revised: 08/27/2021] [Accepted: 09/06/2021] [Indexed: 11/17/2022] Open
Abstract
Extraction, analysis, and interpretation of historical treatment planning data is valuable but very time-consuming. Proposed machine learning model classifies radiotherapy plans based on their treatment planning objectives and trade-offs. Application of double nested cross-validation enabled to build a robust model that achieved 94% accuracy on a testing data. Model reasoning investigated with SHAP values showed consistency with clinical observations.
Purpose To create and investigate a novel, clinical decision-support system using machine learning (ML). Methods and Materials The ML model was developed based on 79 radiotherapy plans of brain tumor patients that were prescribed a total dose of 60 Gy delivered with volumetric-modulated arc therapy (VMAT). Structures considered for analysis included planning target volume (PTV), brainstem, cochleae, and optic chiasm. The model aimed to classify the target variable that included class-0 corresponding to plans for which the PTV treatment planning objective was met and class-1 that was associated with plans for which the PTV objective was not met due to the priority trade-off to meet one or more organs-at-risk constraints. Several models were evaluated using double-nested cross-validation and an area-under-the-curve (AUC) metric, with the highest performing one selected for further investigation. The model predictions were explained with Shapely additive explanation (SHAP) interaction values. Results The highest-performing model was Logistic Regression achieving an accuracy of 93.8 ± 4.1% and AUC of 0.98 ± 0.02 on the testing data. The SHAP analysis indicated that the ΔD99% metric for PTV had the greatest influence on the model predictions. The least important feature was ΔDMAX for the left and right cochleae. Conclusions The trained model achieved satisfactory accuracy and can be used by medical physicists in a data-driven quality assurance program as well as by radiation oncologists to support their decision-making process in terms of treatment plan approval and potential plan modifications. Model explanation analysis showed that the model relies on clinically valid logic when making predictions.
Collapse
Affiliation(s)
- Pawel Siciarz
- Department of Medical Physics, CancerCare Manitoba, 675 McDermot Avenue, Winnipeg, MB R3E 0V9, Canada
- Department of Physics and Astronomy, University of Manitoba, Allen Building, Winnipeg, MB R3T 2N2, Canada
- Corresponding author at: Department of Medical Physics, CancerCare Manitoba, 675 McDermot Avenue, Winnipeg, MB R3E 0V9, Canada.
| | - Salem Alfaifi
- Radiation Oncology Resident, Department of Radiation Oncology, CancerCare Manitoba, 675 McDermot Avenue, Winnipeg, MB R3E 0V9, Canada
| | - Eric Van Uytven
- Radiation Oncology Resident, Department of Radiation Oncology, CancerCare Manitoba, 675 McDermot Avenue, Winnipeg, MB R3E 0V9, Canada
| | - Shrinivas Rathod
- Radiation Oncology Resident, Department of Radiation Oncology, CancerCare Manitoba, 675 McDermot Avenue, Winnipeg, MB R3E 0V9, Canada
- Department of Radiology, University of Manitoba, GA216-820 Sherbrook Street, Winnipeg, MB R3T 2N2, Canada
| | - Rashmi Koul
- Department of Radiology, University of Manitoba, GA216-820 Sherbrook Street, Winnipeg, MB R3T 2N2, Canada
- Medical Director and Head, Radiation Oncology Program, Department of Radiation Oncology, CancerCare Manitoba, 675 McDermot Avenue, Winnipeg, MB R3E 0V9, Canada
| | - Boyd McCurdy
- Department of Physics and Astronomy, University of Manitoba, Allen Building, Winnipeg, MB R3T 2N2, Canada
- Department of Radiology, University of Manitoba, GA216-820 Sherbrook Street, Winnipeg, MB R3T 2N2, Canada
- Head of Radiation Oncology Physics Group, Department of Medical Physics, CancerCare Manitoba, 675 McDermot Avenue, Winnipeg, MB R3E 0V9, Canada
| |
Collapse
|
4
|
Momin S, Fu Y, Lei Y, Roper J, Bradley JD, Curran WJ, Liu T, Yang X. Knowledge-based radiation treatment planning: A data-driven method survey. J Appl Clin Med Phys 2021; 22:16-44. [PMID: 34231970 PMCID: PMC8364264 DOI: 10.1002/acm2.13337] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2021] [Revised: 04/26/2021] [Accepted: 06/02/2021] [Indexed: 12/18/2022] Open
Abstract
This paper surveys the data-driven dose prediction methods investigated for knowledge-based planning (KBP) in the last decade. These methods were classified into two major categories-traditional KBP methods and deep-learning (DL) methods-according to their techniques of utilizing previous knowledge. Traditional KBP methods include studies that require geometric or anatomical features to either find the best-matched case(s) from a repository of prior treatment plans or to build dose prediction models. DL methods include studies that train neural networks to make dose predictions. A comprehensive review of each category is presented, highlighting key features, methods, and their advancements over the years. We separated the cited works according to the framework and cancer site in each category. Finally, we briefly discuss the performance of both traditional KBP methods and DL methods, then discuss future trends of both data-driven KBP methods to dose prediction.
Collapse
Affiliation(s)
- Shadab Momin
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGAUSA
| | - Yabo Fu
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGAUSA
| | - Yang Lei
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGAUSA
| | - Justin Roper
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGAUSA
| | - Jeffrey D. Bradley
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGAUSA
| | - Walter J. Curran
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGAUSA
| | - Tian Liu
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGAUSA
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGAUSA
| |
Collapse
|
5
|
Safety Margins for the Delineation of the Left Anterior Descending Artery in Patients Treated for Breast Cancer. Int J Radiat Oncol Biol Phys 2021; 109:267-272. [DOI: 10.1016/j.ijrobp.2020.08.051] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2020] [Revised: 08/16/2020] [Accepted: 08/19/2020] [Indexed: 11/18/2022]
|
6
|
Marques C, Schiff J, Momin F, McAllister N, Jennelle RL, Bian SX, Schechter NR, Yoo SK. Technical Challenges of Heart Avoidance for Synchronous Breast and Lung Cancers in a Postmenopausal Female: A Planning Case Report From a Safety-Net Hospital. Adv Radiat Oncol 2020; 5:1076-1082. [PMID: 33083670 PMCID: PMC7557127 DOI: 10.1016/j.adro.2020.04.041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2019] [Revised: 03/21/2020] [Accepted: 04/20/2020] [Indexed: 11/03/2022] Open
|
7
|
Whole breast external beam radiotherapy in elderly patients affected by left-sided early breast cancer: a dosimetric comparison between two simple free-breathing techniques. Aging Clin Exp Res 2020; 32:1335-1341. [PMID: 31429001 DOI: 10.1007/s40520-019-01312-5] [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: 05/08/2019] [Accepted: 08/07/2019] [Indexed: 12/20/2022]
Abstract
BACKGROUND Elderly breast cancer patients are frequently affected by significant comorbidities that make sophisticated radiotherapy treatments particularly challenging. AIMS We dosimetrically analyzed two different simple free-breathing external beam radiotherapy (EBRT) techniques for the hypofractionated treatment of the left breast in elderly patients with a low compliance, to compare target coverage, and heart and left anterior descending coronary artery (LADCA) sparing. METHODS We developed radiation plans for 24 elderly patients using 3D conformal (3DCRT) field-in-field tangential technique and intensity-modulated (IMRT) tangential beam technique. Dose-Volume-Histograms (DVHs) were used to provide a quantitative comparison between plans. RESULTS The median breast volume was 645 cm3. IMRT and 3DCRT plans comparison demonstrated no significant differences in terms of organ sparing for the heart. Regarding LADCA, mean dose (10.3 ± 9.5 Gy vs 11.9 ± 9.6 Gy, p = 0.0003), maximum dose (26.1 ± 16.1 Gy vs 29.1 ± 16.1 Gy, p = 0.004) and V17 Gy (21.5% ± 26.9% vs 25.0% ± 27.2%, p = 0.002) significantly decreased using IMRT compared with 3DCRT. IMRT plans showed a better target coverage compared with 3DCRT (0.91 ± 0.05 vs 0.93 ± 0.04, p = 0.05). DISCUSSION Comparing the two different EBRT techniques, we demonstrated few, although substantial, dosimetric differences in terms of doses to the organs at risk characterized by a statistically significant dose reduction of LADCA in the IMRT plans. CONCLUSIONS Elderly patients with a low compliance to treatment might benefit from 3DCRT with field-in-field tangential arrangement or from a simple IMRT approach. IMRT should be preferred.
Collapse
|
8
|
Ge Y, Wu QJ. Knowledge-based planning for intensity-modulated radiation therapy: A review of data-driven approaches. Med Phys 2019; 46:2760-2775. [PMID: 30963580 PMCID: PMC6561807 DOI: 10.1002/mp.13526] [Citation(s) in RCA: 128] [Impact Index Per Article: 25.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2017] [Revised: 01/15/2019] [Accepted: 03/26/2019] [Indexed: 12/20/2022] Open
Abstract
Purpose Intensity‐Modulated Radiation Therapy (IMRT), including its variations (including IMRT, Volumetric Arc Therapy (VMAT), and Tomotherapy), is a widely used and critically important technology for cancer treatment. It is a knowledge‐intensive technology due not only to its own technical complexity, but also to the inherently conflicting nature of maximizing tumor control while minimizing normal organ damage. As IMRT experience and especially the carefully designed clinical plan data are accumulated during the past two decades, a new set of methods commonly termed knowledge‐based planning (KBP) have been developed that aim to improve the quality and efficiency of IMRT planning by learning from the database of past clinical plans. Some of this development has led to commercial products recently that allowed the investigation of KBP in numerous clinical applications. In this literature review, we will attempt to present a summary of published methods of knowledge‐based approaches in IMRT and recent clinical validation results. Methods In March 2018, a literature search was conducted in the NIH Medline database using the PubMed interface to identify publications that describe methods and validations related to KBP in IMRT including variations such as VMAT and Tomotherapy. The search criteria were designed to have a broad scope to capture relevant results with high sensitivity. The authors filtered down the search results according to a predefined selection criteria by reviewing the titles and abstracts first and then by reviewing the full text. A few papers were added to the list based on the references of the reviewed papers. The final set of papers was reviewed and summarized here. Results The initial search yielded a total of 740 articles. A careful review of the titles, abstracts, and eventually the full text and then adding relevant articles from reviewing the references resulted in a final list of 73 articles published between 2011 and early 2018. These articles described methods for developing knowledge models for predicting such parameters as dosimetric and dose‐volume points, voxel‐level doses, and objective function weights that improve or automate IMRT planning for various cancer sites, addressing different clinical and quality assurance needs, and using a variety of machine learning approaches. A number of articles reported carefully designed clinical studies that assessed the performance of KBP models in realistic clinical applications. Overwhelming majority of the studies demonstrated the benefits of KBP in achieving comparable and often improved quality of IMRT planning while reducing planning time and plan quality variation. Conclusions The number of KBP‐related studies has been steadily increasing since 2011 indicating a growing interest in applying this approach to clinical applications. Validation studies have generally shown KBP to produce plans with quality comparable to expert planners while reducing the time and efforts to generate plans. However, current studies are mostly retrospective and leverage relatively small datasets. Larger datasets collected through multi‐institutional collaboration will enable the development of more advanced models to further improve the performance of KBP in complex clinical cases. Prospective studies will be an important next step toward widespread adoption of this exciting technology.
Collapse
Affiliation(s)
- Yaorong Ge
- Department of Software and Information Systems, University of North Carolina at Charlotte, Charlotte, NC, 28223, USA
| | - Q Jackie Wu
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, 27710, USA
| |
Collapse
|
9
|
Ueda Y, Gerber NK, Das IJ. Model-based cardiac dose estimation in radiation treatment of left breast cancer. Br J Radiol 2018; 91:20180287. [PMID: 30044144 DOI: 10.1259/bjr.20180287] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
OBJECTIVE: To develop a mathematical model for cardiac dose estimation for patients who have been treated for left-sided breast cancer without CT data. METHODS: After obtaining institutional review board approvals, 147 patients with left-sided breast cancer were selected that were treated supine with opposed tangents. The heart blocks from the tangential fields were removed and dose calculations were performed with 6 MV beams using an advanced algorithm. This study was performed with CT data with DRR to represent a radiographic simulator image of yesteryear treatments. The beam's eye-view images showing delineated breast, lung and heart were created to represent views on radiograph. The maximum heart distance (MHD) was recorded and irradiated heart area (AREA) was computed by combination of triangles and rectangles. Based on accurate 3D dose calculation, mean dose (Dmean) and V10 to V50 of heart were analyzed with respect to MHD and AREA for dosimetric parameters using linear and quadratic fit. RESULTS: The treatment parameters calculated by MHD and segments using 2D radiographs were within 2% of the actual dosimetric parameters computed from the 3D planning system. The MHD and AREA vs Dmean, V10, V20, V30 and V50 showed very good correlation with linear model (R2 > 0.91); however the correlation was significantly better with quadratic model (R2 > 0.92). The analysis of the dosimetric error with our linear and quadratic model is remarkable within <3% error for most cases. CONCLUSION: The proposed mathematical model for the cardiac dose estimation is accurate within ±3% using a radiograph without CT data. This provides avenues for patient pooling in future studies related to radiation dose and cardiac toxicity. These results will help in estimating cardiac dose analysis accurately from previous studies as well as in centers still using 2D planning. ADVANCES IN KNOWLEDGE: The evidence of cardiac risk following radiotherapy continues to be one of the important considerations for the management of left-sided breast cancer patients. One of the problem in the estimation of dose-risk effects is the reconstruction of heart dose for pre-CT treatments. In this study, a simple mathematical model is presented that could estimate cardiac dose within ±3% in left breast cancer treatment from 2D radiograph where CT data do not exist.
Collapse
Affiliation(s)
- Yoshihiro Ueda
- 1 Department of Radiation Oncology, Osaka International Cancer Institute , Osaka , Japan
| | - Naamit K Gerber
- 2 Department of Radiation Oncology, New York University Health & Laura and Isaac Perlmutter Cancer Center , New York, NY , USA
| | - Indra J Das
- 2 Department of Radiation Oncology, New York University Health & Laura and Isaac Perlmutter Cancer Center , New York, NY , USA
| |
Collapse
|