1
|
Xie L, Zhang L, Hu T, Li G, Yi Z. Neural Network Model Based on Branch Architecture for the Quality Assurance of Volumetric Modulated Arc Therapy. Bioengineering (Basel) 2024; 11:362. [PMID: 38671783 PMCID: PMC11048630 DOI: 10.3390/bioengineering11040362] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Revised: 04/06/2024] [Accepted: 04/09/2024] [Indexed: 04/28/2024] Open
Abstract
Radiation therapy relies on quality assurance (QA) to verify dose delivery accuracy. However, current QA methods suffer from operation lag as well as inaccurate performance. Hence, to address these shortcomings, this paper proposes a QA neural network model based on branch architecture, which is based on the analysis of the category features of the QA complexity metrics. The designed branch network focuses on category features, which effectively improves the feature extraction capability for complexity metrics. The branch features extracted by the model are fused to predict the GPR for more accurate QA. The performance of the proposed method was validated on the collected dataset. The experiments show that the prediction performance of the model outperforms other QA methods; the average prediction errors for the test set are 2.12% (2%/2 mm), 1.69% (3%/2 mm), and 1.30% (3%/3 mm). Moreover, the results indicate that two-thirds of the validation samples' model predictions perform better than the clinical evaluation results, suggesting that the proposed model can assist physicists in the clinic.
Collapse
Affiliation(s)
- Lizhang Xie
- Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu 610065, China (Z.Y.)
| | - Lei Zhang
- Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu 610065, China (Z.Y.)
| | - Ting Hu
- Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu 610065, China (Z.Y.)
| | - Guangjun Li
- Cancer Center and State Key Laboratory of Biotherapy, Department of Radiation Oncology, West China Hospital, Sichuan University, Chengdu 610041, China
| | - Zhang Yi
- Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu 610065, China (Z.Y.)
| |
Collapse
|
2
|
Steenbakkers RJHM, van Rijn-Dekker MI, Stokman MA, Kierkels RGJ, van der Schaaf A, van den Hoek JGM, Bijl HP, Kramer MCA, Coppes RP, Langendijk JA, van Luijk P. Parotid Gland Stem Cell Sparing Radiation Therapy for Patients With Head and Neck Cancer: A Double-Blind Randomized Controlled Trial. Int J Radiat Oncol Biol Phys 2022; 112:306-316. [PMID: 34563635 DOI: 10.1016/j.ijrobp.2021.09.023] [Citation(s) in RCA: 24] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2021] [Revised: 09/08/2021] [Accepted: 09/13/2021] [Indexed: 02/08/2023]
Abstract
PURPOSE Radiation therapy for head and neck cancer frequently leads to salivary gland damage and subsequent xerostomia. The radiation response of the parotid glands of rats, mice, and patients critically depends on dose to parotid gland stem cells, mainly located in the gland's main ducts (stem cell rich [SCR] region). Therefore, this double-blind randomized controlled trial aimed to test the hypothesis that parotid gland stem cell sparing radiation therapy preserves parotid gland function better than currently used whole parotid gland sparing radiation therapy. METHODS AND MATERIALS Patients with head and neck cancer (n = 102) treated with definitive radiation therapy were randomized between standard parotid-sparing and stem cell sparing (SCS) techniques. The primary endpoint was >75% reduction in parotid gland saliva production compared with pretreatment production (FLOW12M). Secondary endpoints were several aspects of xerostomia 12 months after treatment. RESULTS Fifty-four patients were assigned to the standard arm and 48 to the SCS arm. Only dose to the SCR regions (contralateral 16 and 11 Gy [P = .004] and ipsilateral 26 and 16 Gy [P = .001] in the standard and SCS arm, respectively) and pretreatment patient-rated daytime xerostomia (35% and 13% [P = .01] in the standard and SCS arm, respectively) differed significantly between the arms. In the SCS arm, 1 patient (2.8%) experienced FLOW12M compared with 2 (4.9%) in the standard arm (P = 1.00). However, a trend toward better relative parotid gland salivary function in favor of SCS radiation therapy was shown. Moreover, multivariable analysis showed that mean contralateral SCR region dose was the strongest dosimetric predictor for moderate-to-severe patient-rated daytime xerostomia and grade ≥2 physician-rated xerostomia, the latter including reported alteration in diet. CONCLUSIONS No significantly better parotid function was observed in SCS radiation therapy. However, additional multivariable analysis showed that dose to the SCR region was more predictive of the development of parotid gland function-related xerostomia endpoints than dose to the entire parotid gland.
Collapse
Affiliation(s)
- Roel J H M Steenbakkers
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
| | - Maria I van Rijn-Dekker
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Monique A Stokman
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Roel G J Kierkels
- Department of Radiation Oncology, Radiotherapiegroep, Deventer, The Netherlands
| | - Arjen van der Schaaf
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Johanna G M van den Hoek
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Hendrik P Bijl
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Maria C A Kramer
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Robert P Coppes
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands; Department of Biomedical Sciences of Cell and Systems, Section Molecular Cell Biology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Johannes A Langendijk
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Peter van Luijk
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
| |
Collapse
|
3
|
Han P, Lee SH, Noro K, Haller JW, Nakatsugawa M, Sugiyama S, Bowers M, Lakshminarayanan P, Hoff J, Friedes C, Hu C, McNutt TR, Voong KR, Lee J, Hales RK. Improving Early Identification of Significant Weight Loss Using Clinical Decision Support System in Lung Cancer Radiation Therapy. JCO Clin Cancer Inform 2021; 5:944-952. [PMID: 34473547 DOI: 10.1200/cci.20.00189] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
PURPOSE Early identification of patients who may be at high risk of significant weight loss (SWL) is important for timely clinical intervention in lung cancer radiotherapy (RT). A clinical decision support system (CDSS) for SWL prediction was implemented within the routine clinical workflow and assessed on a prospective cohort of patients. MATERIALS AND METHODS CDSS incorporated a machine learning prediction model on the basis of radiomics and dosiomics image features and was connected to a web-based dashboard for streamlined patient enrollment, feature extraction, SWL prediction, and physicians' evaluation processes. Patients with lung cancer (N = 37) treated with definitive RT without prior RT were prospectively enrolled in the study. Radiomics and dosiomics features were extracted from CT and 3D dose volume, and SWL probability (≥ 0.5 considered as SWL) was predicted. Two physicians predicted whether the patient would have SWL before and after reviewing the CDSS prediction. The physician's prediction performance without and with CDSS and prediction changes before and after using CDSS were compared. RESULTS CDSS showed significantly better prediction accuracy than physicians (0.73 v 0.54) with higher specificity (0.81 v 0.50) but with lower sensitivity (0.55 v 0.64). Physicians changed their original prediction after reviewing CDSS prediction for four cases (three correctly and one incorrectly), for all of which CDSS prediction was correct. Physicians' prediction was improved with CDSS in accuracy (0.54-0.59), sensitivity (0.64-0.73), specificity (0.50-0.54), positive predictive value (0.35-0.40), and negative predictive value (0.76-0.82). CONCLUSION Machine learning-based CDSS showed the potential to improve SWL prediction in lung cancer RT. More investigation on a larger patient cohort is needed to properly interpret CDSS prediction performance and its benefit in clinical decision making.
Collapse
Affiliation(s)
- Peijin Han
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | - Sang Ho Lee
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | | | | | | | | | - Michael Bowers
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | - Pranav Lakshminarayanan
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | - Jeffrey Hoff
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | - Cole Friedes
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | - Chen Hu
- Department of Oncology Biostatistics and Bioinformatics, Johns Hopkins University, Baltimore, MD
| | - Todd R McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | - K Ranh Voong
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | - Junghoon Lee
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| | - Russell K Hales
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD
| |
Collapse
|
4
|
Pozoulakis EC, Cheng Z, Han P, Quon H. Radiation-Induced Skin Dermatitis: Treatment With CamWell® Herb to Soothe® Cream in Patients With Head and Neck Cancer Receiving Radiation Therapy. Clin J Oncol Nurs 2021; 25:E44-E49. [PMID: 34269339 DOI: 10.1188/21.cjon.e44-e49] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
BACKGROUND Radiation-induced skin dermatitis (RISD) is a common outcome experienced by adult patients with head and neck cancer (HNC) who have undergone radiation therapy. There is no standardized recommended agent for the prevention or management of RISD. OBJECTIVES The primary objective of this study was to retrospectively evaluate for effectiveness of a botanical topical agent, CamWell® Herb to Soothe® cream, on RISD. METHODS 112 patients with HNC undergoing radiation therapy self-reported their RISD topical skin care agent during treatment as standard of care, CamWell used prophylactically, or CamWell use started after the first week of treatment. The primary endpoint was impact of RISD on the patient, as measured by mean Skindex-16 score throughout treatment. Measures were completed weekly. FINDINGS The mean Skindex score was statistically significantly lower for the prophylactic group than for the standard-of-care group. CamWell may have played a role in managing RISD when compared to standard-of-care agents.
Collapse
|
5
|
Ebert MA, Gulliford S, Acosta O, de Crevoisier R, McNutt T, Heemsbergen WD, Witte M, Palma G, Rancati T, Fiorino C. Spatial descriptions of radiotherapy dose: normal tissue complication models and statistical associations. Phys Med Biol 2021; 66:12TR01. [PMID: 34049304 DOI: 10.1088/1361-6560/ac0681] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2021] [Accepted: 05/28/2021] [Indexed: 12/20/2022]
Abstract
For decades, dose-volume information for segmented anatomy has provided the essential data for correlating radiotherapy dosimetry with treatment-induced complications. Dose-volume information has formed the basis for modelling those associations via normal tissue complication probability (NTCP) models and for driving treatment planning. Limitations to this approach have been identified. Many studies have emerged demonstrating that the incorporation of information describing the spatial nature of the dose distribution, and potentially its correlation with anatomy, can provide more robust associations with toxicity and seed more general NTCP models. Such approaches are culminating in the application of computationally intensive processes such as machine learning and the application of neural networks. The opportunities these approaches have for individualising treatment, predicting toxicity and expanding the solution space for radiation therapy are substantial and have clearly widespread and disruptive potential. Impediments to reaching that potential include issues associated with data collection, model generalisation and validation. This review examines the role of spatial models of complication and summarises relevant published studies. Sources of data for these studies, appropriate statistical methodology frameworks for processing spatial dose information and extracting relevant features are described. Spatial complication modelling is consolidated as a pathway to guiding future developments towards effective, complication-free radiotherapy treatment.
Collapse
Affiliation(s)
- Martin A Ebert
- School of Physics, Mathematics and Computing, University of Western Australia, Crawley, Western Australia, Australia
- Department of Radiation Oncology, Sir Charles Gairdner Hospital, Nedlands, Western Australia, Australia
- 5D Clinics, Claremont, Western Australia, Australia
| | - Sarah Gulliford
- Department of Radiotherapy Physics, University College Hospitals London, United Kingdom
- Department of Medical Physics and Bioengineering, University College London, United Kingdom
| | - Oscar Acosta
- Univ Rennes, CLCC Eugène Marquis, INSERM, LTSI-UMR 1099, F-35000 Rennes, France
| | | | - Todd McNutt
- Johns Hopkins University, Baltimore, Maryland, United States of America
| | | | - Marnix Witte
- The Netherlands Cancer Institute, Amsterdam, The Netherlands
| | - Giuseppe Palma
- Institute of Biostructures and Bioimaging, National Research Council, Napoli, Italy
| | - Tiziana Rancati
- Prostate Cancer Program, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
| | - Claudio Fiorino
- Medical Physics, San Raffaele Scientific Institute, Milano, Italy
| |
Collapse
|
6
|
Mallick I, Saha S, Arunsingh MA. A Web-based Dose-volume Histogram Dashboard for Library-based Individualized Dose-constraints and Clinical Plan Evaluation. J Med Syst 2021; 45:62. [PMID: 33903983 DOI: 10.1007/s10916-021-01740-9] [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: 03/03/2021] [Accepted: 04/21/2021] [Indexed: 11/25/2022]
Abstract
Traditional methods of treatment planning and plan evaluation involve the use of generic dose-constraints. We aimed to build a web-based application to generate individualized dose-constraints and plan evaluation against a library of prior approved plan dose-volume histograms (DVH).A prototype was built for intensity modulated radiation therapy (IMRT) plans for prostate cancer. Using exported DVH files from the Varian and Accuray treatment planning systems, a library of plan DVHs was built by data extraction. Given structure volumes of a patient to be planned, a web based application was built to derive individual dose-constraints of the planning target volume (PTV) and organs-at-risk (OAR) based on achieved doses in a library of prior approved plans with similar anatomical volumes, selected using an interactive dashboard. A second web application was built to compare the achieved DVHs of the newly created plan against a library of plans of similar patients.These web application prototypes are a proof of principle that simple freely available tools can be built for library based planning and review.
Collapse
Affiliation(s)
- Indranil Mallick
- Department of Radiation Oncology, Tata Medical Center, 14 MAR (EW) Newtown, Kolkata, 700160, India.
| | - Saheli Saha
- Department of Radiation Oncology, Tata Medical Center, 14 MAR (EW) Newtown, Kolkata, 700160, India
| | - Moses A Arunsingh
- Department of Radiation Oncology, Tata Medical Center, 14 MAR (EW) Newtown, Kolkata, 700160, India
| |
Collapse
|
7
|
Voshart DC, Wiedemann J, van Luijk P, Barazzuol L. Regional Responses in Radiation-Induced Normal Tissue Damage. Cancers (Basel) 2021; 13:cancers13030367. [PMID: 33498403 PMCID: PMC7864176 DOI: 10.3390/cancers13030367] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2020] [Revised: 01/16/2021] [Accepted: 01/18/2021] [Indexed: 12/16/2022] Open
Abstract
Normal tissue side effects remain a major concern in radiotherapy. The improved precision of radiation dose delivery of recent technological developments in radiotherapy has the potential to reduce the radiation dose to organ regions that contribute the most to the development of side effects. This review discusses the contribution of regional variation in radiation responses in several organs. In the brain, various regions were found to contribute to radiation-induced neurocognitive dysfunction. In the parotid gland, the region containing the major ducts was found to be critical in hyposalivation. The heart and lung were each found to exhibit regional responses while also mutually affecting each other's response to radiation. Sub-structures critical for the development of side effects were identified in the pancreas and bladder. The presence of these regional responses is based on a non-uniform distribution of target cells or sub-structures critical for organ function. These characteristics are common to most organs in the body and we therefore hypothesize that regional responses in radiation-induced normal tissue damage may be a shared occurrence. Further investigations will offer new opportunities to reduce normal tissue side effects of radiotherapy using modern and high-precision technologies.
Collapse
Affiliation(s)
- Daniëlle C. Voshart
- Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, The Netherlands; (D.C.V.); (J.W.)
- Department of Biomedical Sciences of Cells & Systems–Section Molecular Cell Biology, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, The Netherlands
| | - Julia Wiedemann
- Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, The Netherlands; (D.C.V.); (J.W.)
- Department of Biomedical Sciences of Cells & Systems–Section Molecular Cell Biology, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, The Netherlands
| | - Peter van Luijk
- Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, The Netherlands; (D.C.V.); (J.W.)
- Department of Biomedical Sciences of Cells & Systems–Section Molecular Cell Biology, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, The Netherlands
- Correspondence: (P.v.L.); (L.B.)
| | - Lara Barazzuol
- Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, The Netherlands; (D.C.V.); (J.W.)
- Department of Biomedical Sciences of Cells & Systems–Section Molecular Cell Biology, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, The Netherlands
- Correspondence: (P.v.L.); (L.B.)
| |
Collapse
|
8
|
Cheng Z, Nakatsugawa M, Zhou XC, Hu C, Greco S, Kiess A, Page B, Alcorn S, Haller J, Utsunomiya K, Sugiyama S, Fu W, Wong J, Lee J, McNutt T, Quon H. Utility of a Clinical Decision Support System in Weight Loss Prediction After Head and Neck Cancer Radiotherapy. JCO Clin Cancer Inform 2020; 3:1-11. [PMID: 30860866 DOI: 10.1200/cci.18.00058] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
PURPOSE To evaluate the utility of a clinical decision support system (CDSS) using a weight loss prediction model. METHODS A prediction model for significant weight loss (loss of greater than or equal to 7.5% of body mass at 3-month post radiotherapy) was created with clinical, dosimetric, and radiomics predictors from 63 patients in an independent training data set (accuracy, 0.78; area under the curve [AUC], 0.81) using least absolute shrinkage and selection operator logistic regression. Four physicians with varying experience levels were then recruited to evaluate 100 patients in an independent validation data set of head and neck cancer twice (ie, a pre-post design): first without and then with the aid of a CDSS derived from the prediction model. At both evaluations, physicians were asked to predict the development (yes/no) and probability of significant weight loss for each patient on the basis of patient characteristics, including pretreatment dysphagia and weight loss and information from the treatment plan. At the second evaluation, physicians were also provided with the prediction model's results for weight loss probability. Physicians' predictions were compared with actual weight loss, and accuracy and AUC were investigated between the two evaluations. RESULTS The mean accuracy of the physicians' ability to identify patients who will experience significant weight loss (yes/no) increased from 0.58 (range, 0.47 to 0.63) to 0.63 (range, 0.58 to 0.72) with the CDSS ( P = .06). The AUC of weight loss probability predicted by physicians significantly increased from 0.56 (range, 0.46 to 0.64) to 0.69 (range, 0.63 to 0.73) with the aid of the CDSS ( P < .05). Specifically, more improvement was observed among less-experienced physicians ( P < .01). CONCLUSION Our preliminary results demonstrate that physicians' decisions may be improved by a weight loss CDSS model, especially among less-experienced physicians. Additional study with a larger cohort of patients and more participating physicians is thus warranted for understanding the usefulness of CDSSs.
Collapse
Affiliation(s)
- Zhi Cheng
- Johns Hopkins University, Baltimore, MD
| | | | | | - Chen Hu
- Johns Hopkins University, Baltimore, MD
| | | | - Ana Kiess
- Johns Hopkins University, Baltimore, MD
| | | | | | - John Haller
- Canon Medical Research USA, Vernon Hills, IL
| | | | | | - Wei Fu
- Johns Hopkins University, Baltimore, MD
| | - John Wong
- Johns Hopkins University, Baltimore, MD
| | | | | | | |
Collapse
|
9
|
Peng LC, Mian OY, Lakshminarayanan P, Huang P, Bae HJ, Robertson S, Habtu T, Narang A, Agarwal S, Greco S, Tran P, McNutt T, DeWeese TL, Song DY. Analysis of Spatial Dose-Volume Relationships and Decline in Sexual Function Following Permanent Brachytherapy for Prostate Cancer. Urology 2019; 135:111-116. [PMID: 31454660 DOI: 10.1016/j.urology.2019.08.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2019] [Revised: 08/01/2019] [Accepted: 08/09/2019] [Indexed: 11/19/2022]
Abstract
OBJECTIVE To explore relationships between dose to periprostatic anatomic structures and erectile dysfunction (ED) outcomes in an institutional cohort treated with prostate brachytherapy. METHODS The Sexual Health Inventory for Men (SHIM) instrument was administered for stage cT1-T2 prostate cancer patients treated with Pd-103 brachytherapy over a 10-year interval. Dose volume histograms for regional organs at risk and periprostatic regions were calculated with and without expansions to account for contouring uncertainty. Regression tree analysis clustered patients into ED risk groups. RESULTS We identified 115 men treated with definitive prostate brachytherapy who had 2 years of complete follow-up. On univariate analysis, the subapical region (SAR) caudal to prostate was the only defined region with dose volume histograms parameters significant for potency outcomes. Regression tree analysis separated patients into low ED risk (mean 2-year SHIM 20.03), medium ED risk (15.02), and high ED risk (5.54) groups. Among patients with good baseline function (SHIM ≥ 17), a dose ≥72.75 Gy to 20% of the SAR with 1 cm expansion was most predictive for 2-year potency outcome. On multivariate analysis, regression tree risk group remained significant for predicting potency outcomes even after adjustment for baseline SHIM and age. CONCLUSION Dose to the SAR immediately caudal to prostate was predictive for potency outcomes in patients with good baseline function. Minimization of dose to this region may improve potency outcomes following prostate brachytherapy.
Collapse
Affiliation(s)
- Luke C Peng
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Omar Y Mian
- Department of Radiation Oncology, Cleveland Clinic, Cleveland, OH
| | - Pranav Lakshminarayanan
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Peng Huang
- Department of Oncology, Biostatistics and Bioinformatics Division, Johns Hopkins University School of Medicine, Baltimore, MD
| | - Hee J Bae
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Scott Robertson
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Tamey Habtu
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Amol Narang
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Sameer Agarwal
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Stephen Greco
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Phuoc Tran
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Todd McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Theodore L DeWeese
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD
| | - Daniel Y Song
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Hospital, Baltimore, MD.
| |
Collapse
|
10
|
Kairn T, Crowe SB. Retrospective analysis of breast radiotherapy treatment plans: Curating the 'non-curated'. J Med Imaging Radiat Oncol 2019; 63:517-529. [PMID: 31081603 DOI: 10.1111/1754-9485.12892] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2018] [Accepted: 03/24/2019] [Indexed: 11/29/2022]
Abstract
INTRODUCTION This paper provides a demonstration of how non-curated data can be retrospectively cleaned, so that existing repositories of radiotherapy treatment planning data can be used to complete bulk retrospective analyses of dosimetric trends and other plan characteristics. METHODS A non curated archive of 1137 radiotherapy treatment plans accumulated over a 12-month period, from five radiotherapy centres operated by one institution, was used to investigate and demonstrate a process of clinical data cleansing, by: identifying and translating inconsistent structure names; correcting inconsistent lung contouring; excluding plans for treatments other than breast tangents and plans without identifiable PTV, lung and heart structures; and identifying but not excluding plans that deviated from the local planning protocol. PTV, heart and lung dose-volume metrics were evaluated, in addition to a sample of personnel and linac load indicators. RESULTS Data cleansing reduced the number of treatment plans in the sample by 35.7%. Inconsistent structure names were successfully identified and translated (e.g. 35 different names for lung). Automatically separating whole lung structures into left and right lung structures allowed the effect of contralateral and ipsilateral lung dose to be evaluated, while introducing some small uncertainties, compared to manual contouring. PTV doses were indicative of prescription doses. Breast treatment work was unevenly distributed between oncologists and between metropolitan and regional centres. CONCLUSION This paper exemplifies the data cleansing and data analysis steps that may be completed using existing treatment planning data, to provide individual radiation oncology departments with access to information on their own patient populations. Clearly, the well-planned and systematic recording of new, high quality data is the preferred solution, but the retrospective curation of non-curated data may be a useful interim solution, for radiation oncology departments where the systems for recording of new data have yet to be designed and agreed.
Collapse
Affiliation(s)
- Tanya Kairn
- Genesis Cancer Care, Auchenflower, Queensland, Australia.,Science and Engineering Faculty, Queensland University of Technology, Brisbane, Queensland, Australia
| | - Scott B Crowe
- Science and Engineering Faculty, Queensland University of Technology, Brisbane, Queensland, Australia.,Cancer Care Services, Royal Brisbane and Women's Hospital, Herston, Queensland, Australia
| |
Collapse
|
11
|
Han P, Lakshminarayanan P, Jiang W, Shpitser I, Hui X, Lee SH, Cheng Z, Guo Y, Taylor RH, Siddiqui SA, Bowers M, Sheikh K, Kiess A, Page BR, Lee J, Quon H, McNutt TR. Dose/Volume histogram patterns in Salivary Gland subvolumes influence xerostomia injury and recovery. Sci Rep 2019; 9:3616. [PMID: 30837617 PMCID: PMC6401158 DOI: 10.1038/s41598-019-40228-y] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2018] [Accepted: 01/28/2019] [Indexed: 01/29/2023] Open
Abstract
Xerostomia is a common consequence of radiotherapy in head and neck cancer. The objective was to compare the regional radiation dose distribution in patients that developed xerostomia within 6 months of radiotherapy and those recovered from xerostomia within 18 months post-radiotherapy. We developed a feature generation pipeline to extract dose volume histogram features from geometrically defined ipsilateral/contralateral parotid glands, submandibular glands, and oral cavity surrogates for each patient. Permutation tests with multiple comparisons were performed to assess the dose difference between injury vs. non-injury and recovery vs. non-recovery. Ridge logistic regression models were applied to predict injury and recovery using clinical features along with dose features (D10-D90) of the subvolumes extracted from oral cavity and salivary gland contours + 3 mm peripheral shell. Model performances were assessed by the area under the receiver operating characteristic curve (AUC) using nested cross-validation. We found that different regional dose/volume metrics patterns exist for injury vs. recovery. Compared to injury, recovery has increased importance to the subvolumes receiving lower dose. Within the subvolumes, injury tends to have increased importance towards D10 from D90. This suggests that different threshold for xerostomia injury and recovery. Injury is induced by the subvolumes receiving higher dose, and the ability to recover can be preserved by further reducing the dose to subvolumes receiving lower dose.
Collapse
Affiliation(s)
- Peijin Han
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA.
| | - Pranav Lakshminarayanan
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Wei Jiang
- Department of Civil Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Ilya Shpitser
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Xuan Hui
- Department of Public Health Sciences, University of Chicago, Chicago, IL, USA
| | - Sang Ho Lee
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Zhi Cheng
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Yue Guo
- Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA
| | - Russell H Taylor
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Sauleh A Siddiqui
- Department of Civil Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Michael Bowers
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Khadija Sheikh
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Ana Kiess
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Brandi R Page
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Junghoon Lee
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Harry Quon
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| | - Todd R McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA
| |
Collapse
|
12
|
Jiang W, Lakshminarayanan P, Hui X, Han P, Cheng Z, Bowers M, Shpitser I, Siddiqui S, Taylor RH, Quon H, McNutt T. Machine Learning Methods Uncover Radiomorphologic Dose Patterns in Salivary Glands that Predict Xerostomia in Patients with Head and Neck Cancer. Adv Radiat Oncol 2018; 4:401-412. [PMID: 31011686 PMCID: PMC6460328 DOI: 10.1016/j.adro.2018.11.008] [Citation(s) in RCA: 39] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2018] [Accepted: 11/14/2018] [Indexed: 01/06/2023] Open
Abstract
Purpose Patients with head-and-neck cancer (HNC) may experience xerostomia after radiation therapy (RT), which leads to compromised quality of life. The purpose of this study is to explore how the spatial pattern of radiation dose (radiomorphology) in the major salivary glands influences xerostomia in patients with HNC. Methods and materials A data-driven approach using spatially explicit dosimetric predictors, voxel dose (ie, actual radiation dose in voxels in parotid glands [PG] and submandibular glands [SMG]) was used to predict whether patients would develop xerostomia 3 months after RT. Using planned radiation dose data and other nondose covariates including baseline xerostomia grade of 427 patients with HNC in our database, the machine learning methods were used to investigate the influence of dose patterns across subvolumes in PG and SMG on xerostomia. Results Of the 3 supervised learning methods studied, ridge logistic regression yielded the best predictive performance. Ridge logistic regression was also preferred to evaluate the influence pattern of highly correlated dose on xerostomia, which showed a discriminative pattern of influence of doses in the PG and SMG on xerostomia. Moreover, the superior–anterior portion of the contralateral PG and medial portion of the ipsilateral PG were determined to be the most influential regions regarding dose effect on xerostomia. The area under the receiver operating characteristic curve from a 10-fold cross-validation was 0.70 ± 0.04. Conclusions Radiomorphology, combined with machine learning methods, is able to suggest patterns of dose in PG and SMG that are the most influential on xerostomia. The influence pattern identified by this data-driven approach and machine learning methods may help improve RT treatment planning and reduce xerostomia after treatment.
Collapse
Affiliation(s)
- Wei Jiang
- Department of Civil Engineering, Johns Hopkins System Institute, Johns Hopkins University, Baltimore, Maryland
| | | | - Xuan Hui
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Peijin Han
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Zhi Cheng
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Michael Bowers
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Ilya Shpitser
- Department of Computer Science, Johns Hopkins University, Baltimore, Maryland
| | - Sauleh Siddiqui
- Department of Civil Engineering, Johns Hopkins System Institute, Johns Hopkins University, Baltimore, Maryland
| | - Russell H Taylor
- Department of Computer Science, Johns Hopkins University, Baltimore, Maryland
| | - Harry Quon
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Todd McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| |
Collapse
|
13
|
The Needs and Benefits of Continuous Model Updates on the Accuracy of RT-Induced Toxicity Prediction Models Within a Learning Health System. Int J Radiat Oncol Biol Phys 2018; 103:460-467. [PMID: 30300689 DOI: 10.1016/j.ijrobp.2018.09.038] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2018] [Accepted: 10/06/2018] [Indexed: 12/14/2022]
Abstract
PURPOSE Clinical data collection and development of outcome prediction models by machine learning can form the foundation for a learning health system offering precision radiation therapy. However, changes in clinical practice over time can affect the measures and patient outcomes and, hence, the collected data. We hypothesize that regular prediction model updates and continuous prospective data collection are important to prevent the degradation of a model's predication accuracy. METHODS AND MATERIALS Clinical and dosimetric data from head and neck patients receiving intensity modulated radiation therapy from 2008 to 2015 were prospectively collected as a routine clinical workflow and anonymized for this analysis. Prediction models for grade ≥2 xerostomia at 3 to 6 months of follow-up were developed by bivariate logistic regression using the dose-volume histogram of parotid and submandibular glands. A baseline prediction model was developed with a training data set from 2008 to 2009. The selected predictor variables and coefficients were updated by 4 different model updating methods. (A) The prediction model was updated by using only recent 2-year data and applied to patients in the following test year. (B) The model was updated by increasing the training data set yearly. (C) The model was updated by increasing the training data set on the condition that the area under the curve (AUC) of the recent test year was less than 0.6. (D) The model was not updated. The AUC of the test data set was compared among the 4 model updating methods. RESULTS Dose to parotid and submandibular glands and grade of xerostomia showed decreasing trends over the years (2008-2015, 297 patients; P < .001). The AUC of predicting grade ≥2 xerostomia for the initial training data set (2008-2009, 41 patients) was 0.6196. The AUC for the test data set (2010-2015, 256 patients) decreased to 0.5284 when the initial model was not updated (D). However, the AUC was significantly improved by model updates (A: 0.6164; B: 0.6084; P < .05). When the model was conditionally updated, the AUC was 0.6072 (C). CONCLUSIONS Our preliminary results demonstrate that updating prediction models with prospective data collection is effective for maintaining the performance of xerostomia prediction. This suggests that a machine learning framework can handle the dynamic changes in a radiation oncology clinical practice and may be an important component for the construction of a learning health system.
Collapse
|
14
|
Matuszak MM, Fuller CD, Yock TI, Hess CB, McNutt T, Jolly S, Gabriel P, Mayo CS, Thor M, Caissie A, Rao A, Owen D, Smith W, Palta J, Kapoor R, Hayman J, Waddle M, Rosenstein B, Miller R, Choi S, Moreno A, Herman J, Feng M. Performance/outcomes data and physician process challenges for practical big data efforts in radiation oncology. Med Phys 2018; 45:e811-e819. [PMID: 30229946 DOI: 10.1002/mp.13136] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2018] [Revised: 07/20/2018] [Accepted: 08/08/2018] [Indexed: 11/11/2022] Open
Abstract
It is an exciting time for big data efforts in radiation oncology. The use of big data to help aid both outcomes and decision-making research is becoming a reality. However, there are true challenges that exist in the space of gathering and utilizing performance and outcomes data. Here, we summarize the current state of big data in radiation oncology with respect to outcomes and discuss some of the efforts and challenges in radiation oncology big data.
Collapse
Affiliation(s)
| | | | | | | | - Todd McNutt
- Johns Hopkins University, Baltimore, MD, USA
| | | | | | | | - Maria Thor
- Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | | | - Arvind Rao
- University of Michigan, Ann Arbor, MI, USA
| | - Dawn Owen
- University of Michigan, Ann Arbor, MI, USA
| | - Wade Smith
- University of Washington, Seattle, WA, USA
| | | | | | | | | | | | | | | | - Amy Moreno
- MD Anderson Cancer Center, Houston, TX, USA
| | | | - Mary Feng
- University of California at San Francisco, San Francisco, CA, USA
| |
Collapse
|
15
|
Mayo CS, Phillips M, McNutt TR, Palta J, Dekker A, Miller RC, Xiao Y, Moran JM, Matuszak MM, Gabriel P, Ayan AS, Prisciandaro J, Thor M, Dixit N, Popple R, Killoran J, Kaleba E, Kantor M, Ruan D, Kapoor R, Kessler ML, Lawrence TS. Treatment data and technical process challenges for practical big data efforts in radiation oncology. Med Phys 2018; 45:e793-e810. [PMID: 30226286 DOI: 10.1002/mp.13114] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2017] [Revised: 06/26/2018] [Accepted: 06/26/2018] [Indexed: 12/20/2022] Open
Abstract
The term Big Data has come to encompass a number of concepts and uses within medicine. This paper lays out the relevance and application of large collections of data in the radiation oncology community. We describe the potential importance and uses in clinical practice. The important concepts are then described and how they have been or could be implemented are discussed. Impediments to progress in the collection and use of sufficient quantities of data are also described. Finally, recommendations for how the community can move forward to achieve the potential of big data in radiation oncology are provided.
Collapse
Affiliation(s)
- C S Mayo
- University of Michigan, Ann Arbor, MI, USA
| | - M Phillips
- University of Washington, Seattle, WA, USA
| | - T R McNutt
- Johns Hopkins University, Baltimore, MD, USA
| | - J Palta
- Virginia Commonwealth University, Richmond, VA, USA
| | - A Dekker
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | | | - Y Xiao
- University of Pennsylvania, Philadelphia, PA, USA
| | - J M Moran
- University of Michigan, Ann Arbor, MI, USA
| | | | - P Gabriel
- University of Pennsylvania, Philadelphia, PA, USA
| | - A S Ayan
- Ohio State University, Columbus, OH, USA
| | | | - M Thor
- Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - N Dixit
- University of California at San Francisco, San Francisco, CA, USA
| | - R Popple
- University of Alabama at Birmingham, Birmingham, AL, USA
| | | | - E Kaleba
- University of Michigan, Ann Arbor, MI, USA
| | - M Kantor
- MD Anderson Cancer Center, Houston, TX, USA
| | - D Ruan
- University of California at Los Angeles, Los Angeles, CA, USA
| | - R Kapoor
- Johns Hopkins University, Baltimore, MD, USA
| | | | | |
Collapse
|
16
|
Cheng Z, Rosati LM, Chen L, Mian OY, Cao Y, Villafania M, Nakatsugawa M, Moore JA, Robertson SP, Jackson J, Hacker-Prietz A, He J, Wolfgang CL, Weiss MJ, Herman JM, Narang AK, McNutt TR. Improving prediction of surgical resectability over current staging guidelines in patients with pancreatic cancer who receive stereotactic body radiation therapy. Adv Radiat Oncol 2018; 3:601-610. [PMID: 30370361 PMCID: PMC6200892 DOI: 10.1016/j.adro.2018.07.002] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2017] [Revised: 05/10/2018] [Accepted: 07/09/2018] [Indexed: 12/18/2022] Open
Abstract
Purpose For patients with localized pancreatic cancer (PC) with vascular involvement, prediction of resectability is critical to define optimal treatment. However, the current definitions of borderline resectable (BR) and locally advanced (LA) disease leave considerable heterogeneity in outcomes within these classifications. Moreover, factors beyond vascular involvement likely affect the ability to undergo resection. Herein, we share our experience developing a model that incorporates detailed radiologic, patient, and treatment factors to predict surgical resectability in patients with BR and LA PC who undergo stereotactic body radiation therapy (SBRT). Methods and materials Patients with BR or LA PC who were treated with SBRT between 2010 and 2016 were included. The primary endpoint was margin negative resection, and predictors included age, sex, race, treatment year, performance status, initial staging, tumor volume and location, baseline and pre-SBRT carbohydrate antigen 19-9 levels, chemotherapy regimen and duration, and radiation dose. In addition, we characterized the relationship between tumors and key arteries (superior mesenteric, celiac, and common hepatic arteries), using overlap volume histograms derived from computed tomography data. A classification and regression tree was built, and leave-one-out cross-validation was performed. Prediction of surgical resection was compared between our model and staging in accordance with the National Comprehensive Care Network guidelines using McNemar's test. Results A total of 191 patients were identified (128 patients with LA and 63 with BR), of which 87 patients (46%) underwent margin negative resection. The median total dose was 33 Gy. Predictors included the chemotherapy regimen, amount of arterial involvement, and age. Importantly, radiation dose that covers 95% of gross tumor volume (GTV D95), was a key predictor of resectability in certain subpopulations, and the model showed improved accuracy in the prediction of margin negative resection compared with National Comprehensive Care Network guideline staging (75% vs 63%; P < .05). Conclusions We demonstrate the ability to improve prediction of surgical resectabiliy beyond the current staging guidelines, which highlights the value of assessing vascular involvement in a continuous manner. In addition, we show an association between radiation dose and resectability, which suggests the potential importance of radiation to allow for resection in certain populations. External data are needed for validation and to increase the robustness of the model.
Collapse
Affiliation(s)
- Zhi Cheng
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
- Corresponding author. Johns Hopkins University, Radiation Oncology, 401 North Broadway, Suite B163, Baltimore, MD 21231
| | - Lauren M. Rosati
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Linda Chen
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Omar Y. Mian
- Translational Hematology and Oncology Research Department, Cleveland Clinic, Cleveland, Ohio
| | - Yilin Cao
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | | | | | - Joseph A. Moore
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Scott P. Robertson
- Department of Radiation Oncology, York Medical Center, York, Pennsylvania
| | - Juan Jackson
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Amy Hacker-Prietz
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Jin He
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | | | - Matthew J. Weiss
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Joseph M. Herman
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Amol K. Narang
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Todd R. McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland
| |
Collapse
|
17
|
Anacleto A, Dias J. Data Analysis in Radiotherapy Treatments. INTERNATIONAL JOURNAL OF E-HEALTH AND MEDICAL COMMUNICATIONS 2018. [DOI: 10.4018/ijehmc.2018070103] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Radiotherapy is one of the main cancer treatments available today, together with chemotherapy and surgery. Radiotherapy treatments have to be planned for each patient in an individualized manner. The knowledge acquired from one single treatment can be used to improve the treatment planning and outcome of several other patients. In the last years, attention has been drawn to the added value of using data analysis for radiotherapy treatment planning, prediction of treatment outcomes, survival analysis and quality assurance. In this article, existing literature is reviewed.
Collapse
Affiliation(s)
- Ana Anacleto
- Faculty of Economics, University of Coimbra, Coimbra, Portugal
| | - Joana Dias
- Inesc-Coimbra, CeBER, Faculty of Economics, University of Coimbra, Coimbra, Portugal
| |
Collapse
|
18
|
Cheng Z, Nakatsugawa M, Hu C, Robertson SP, Hui X, Moore JA, Bowers MR, Kiess AP, Page BR, Burns L, Muse M, Choflet A, Sakaue K, Sugiyama S, Utsunomiya K, Wong JW, McNutt TR, Quon H. Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy. Adv Radiat Oncol 2018; 3:346-355. [PMID: 30197940 PMCID: PMC6127872 DOI: 10.1016/j.adro.2017.11.006] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2017] [Revised: 10/02/2017] [Accepted: 11/30/2017] [Indexed: 11/05/2022] Open
Abstract
OBJECTIVE We explore whether a knowledge-discovery approach building a Classification and Regression Tree (CART) prediction model for weight loss (WL) in head and neck cancer (HNC) patients treated with radiation therapy (RT) is feasible. METHODS AND MATERIALS HNC patients from 2007 to 2015 were identified from a prospectively collected database Oncospace. Two prediction models at different time points were developed to predict weight loss ≥5 kg at 3 months post-RT by CART algorithm: (1) during RT planning using patient demographic, delineated dose data, planning target volume-organs at risk shape relationships data and (2) at the end of treatment (EOT) using additional on-treatment toxicities and quality of life data. RESULTS Among 391 patients identified, WL predictors during RT planning were International Classification of Diseases diagnosis; dose to masticatory and superior constrictor muscles, larynx, and parotid; and age. At EOT, patient-reported oral intake, diagnosis, N stage, nausea, pain, dose to larynx, parotid, and low-dose planning target volume-larynx distance were significant predictive factors. The area under the curve during RT and EOT was 0.773 and 0.821, respectively. CONCLUSIONS We demonstrate the feasibility and potential value of an informatics infrastructure that has facilitated insight into the prediction of WL using the CART algorithm. The prediction accuracy significantly improved with the inclusion of additional treatment-related data and has the potential to be leveraged as a strategy to develop a learning health system.
Collapse
Affiliation(s)
- Zhi Cheng
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Minoru Nakatsugawa
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
- Toshiba America Research, Inc., Baltimore, Maryland
| | - Chen Hu
- Oncology Center—Biostatistics/Bioinformatics, Johns Hopkins University, Baltimore, Maryland
| | - Scott P. Robertson
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Xuan Hui
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Joseph A. Moore
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Michael R. Bowers
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Ana P. Kiess
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Brandi R. Page
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Laura Burns
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Mariah Muse
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Amanda Choflet
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | | | | | | | - John W. Wong
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Todd R. McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Harry Quon
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| |
Collapse
|
19
|
McNutt TR, Benedict SH, Low DA, Moore K, Shpitser I, Jiang W, Lakshminarayanan P, Cheng Z, Han P, Hui X, Nakatsugawa M, Lee J, Moore JA, Robertson SP, Shah V, Taylor R, Quon H, Wong J, DeWeese T. Using Big Data Analytics to Advance Precision Radiation Oncology. Int J Radiat Oncol Biol Phys 2018; 101:285-291. [DOI: 10.1016/j.ijrobp.2018.02.028] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2017] [Revised: 02/13/2018] [Accepted: 02/20/2018] [Indexed: 11/25/2022]
|
20
|
Interian Y, Rideout V, Kearney VP, Gennatas E, Morin O, Cheung J, Solberg T, Valdes G. Deep nets vs expert designed features in medical physics: An IMRT QA case study. Med Phys 2018; 45:2672-2680. [PMID: 29603278 DOI: 10.1002/mp.12890] [Citation(s) in RCA: 83] [Impact Index Per Article: 13.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2017] [Revised: 01/09/2018] [Accepted: 01/09/2018] [Indexed: 11/12/2022] Open
Abstract
PURPOSE The purpose of this study was to compare the performance of Deep Neural Networks against a technique designed by domain experts in the prediction of gamma passing rates for Intensity Modulated Radiation Therapy Quality Assurance (IMRT QA). METHOD A total of 498 IMRT plans across all treatment sites were planned in Eclipse version 11 and delivered using a dynamic sliding window technique on Clinac iX or TrueBeam Linacs. Measurements were performed using a commercial 2D diode array, and passing rates for 3%/3 mm local dose/distance-to-agreement (DTA) were recorded. Separately, fluence maps calculated for each plan were used as inputs to a convolution neural network (CNN). The CNNs were trained to predict IMRT QA gamma passing rates using TensorFlow and Keras. A set of model architectures, inspired by the convolutional blocks of the VGG-16 ImageNet model, were constructed and implemented. Synthetic data, created by rotating and translating the fluence maps during training, was created to boost the performance of the CNNs. Dropout, batch normalization, and data augmentation were utilized to help train the model. The performance of the CNNs was compared to a generalized Poisson regression model, previously developed for this application, which used 78 expert designed features. RESULTS Deep Neural Networks without domain knowledge achieved comparable performance to a baseline system designed by domain experts in the prediction of 3%/3 mm Local gamma passing rates. An ensemble of neural nets resulted in a mean absolute error (MAE) of 0.70 ± 0.05 and the domain expert model resulted in a 0.74 ± 0.06. CONCLUSIONS Convolutional neural networks (CNNs) with transfer learning can predict IMRT QA passing rates by automatically designing features from the fluence maps without human expert supervision. Predictions from CNNs are comparable to a system carefully designed by physicist experts.
Collapse
Affiliation(s)
- Yannet Interian
- MS in Analytics Program, University of San Francisco, San Francisco, CA, USA
| | - Vincent Rideout
- MS in Analytics Program, University of San Francisco, San Francisco, CA, USA
| | - Vasant P Kearney
- Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA
| | - Efstathios Gennatas
- Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA
| | - Olivier Morin
- Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA
| | - Joey Cheung
- Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA
| | - Timothy Solberg
- Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA
| | - Gilmer Valdes
- Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA
| |
Collapse
|
21
|
Takagi R, Komiya Y, Sutherland KL, Shirato H, Date H, Mizuta M. Comparison of the average surviving fraction model with the integral biologically effective dose model for an optimal irradiation scheme. JOURNAL OF RADIATION RESEARCH 2018; 59:i32-i39. [PMID: 29309670 PMCID: PMC5868211 DOI: 10.1093/jrr/rrx084] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/12/2017] [Revised: 11/14/2017] [Indexed: 06/07/2023]
Abstract
In this paper, we compare two radiation effect models: the average surviving fraction (ASF) model and the integral biologically effective dose (IBED) model for deriving the optimal irradiation scheme and show the superiority of ASF. Minimizing the effect on an organ at risk (OAR) is important in radiotherapy. The biologically effective dose (BED) model is widely used to estimate the effect on the tumor or on the OAR, for a fixed value of dose. However, this is not always appropriate because the dose is not a single value but is distributed. The IBED and ASF models are proposed under the assumption that the irradiation is distributed. Although the IBED and ASF models are essentially equivalent for deriving the optimal irradiation scheme in the case of uniform distribution, they are not equivalent in the case of non-uniform distribution. We evaluate the differences between them for two types of cancers: high α/β ratio cancer (e.g. lung) and low α/β ratio cancer (e.g. prostate), and for various distributions i.e. various dose-volume histograms. When we adopt the IBED model, the optimal number of fractions for low α/β ratio cancers is reasonable, but for high α/β ratio cancers or for some DVHs it is extremely large. However, for the ASF model, the results keep within the range used in clinical practice for both low and high α/β ratio cancers and for most DVHs. These results indicate that the ASF model is more robust for constructing the optimal irradiation regimen than the IBED model.
Collapse
Affiliation(s)
- Ryo Takagi
- Graduate School of Information Science and Technology, Hokkaido University, Kita-14, Nishi-9, Kita-ku, Sapporo, 060-0814, Japan
| | - Yuriko Komiya
- Laboratory of Advanced Data Science, Information Initiative Center, Hokkaido University, Kita-11, Nishi-5, Kita-ku, Sapporo, 060-0811, Japan
| | - Kenneth L Sutherland
- Global Station for Quantum Medical Science and Engineering, Global Institution for Collaborative Research and Education (GI-CoRE), Hokkaido University, Kita-15, Nishi-8, Kita-ku, Sapporo, 060-0815, Japan
| | - Hiroki Shirato
- Global Station for Quantum Medical Science and Engineering, Global Institution for Collaborative Research and Education (GI-CoRE), Hokkaido University, Kita-15, Nishi-8, Kita-ku, Sapporo, 060-0815, Japan
- Department of Radiation Medicine, Faculty of Medicine, Hokkaido University, Kita-15, Nishi-7, Kita-ku, Sapporo, 060-8638, Japan
| | - Hiroyuki Date
- Faculty of Health Sciences, Hokkaido University, Kita-12, Nishi-5, Kita-ku, Sapporo, 060-0812, Japan
| | - Masahiro Mizuta
- Laboratory of Advanced Data Science, Information Initiative Center, Hokkaido University, Kita-11, Nishi-5, Kita-ku, Sapporo, 060-0811, Japan
| |
Collapse
|
22
|
Les big data , généralités et intégration en radiothérapie. Cancer Radiother 2018; 22:73-84. [DOI: 10.1016/j.canrad.2017.04.013] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2017] [Revised: 04/11/2017] [Accepted: 04/19/2017] [Indexed: 12/25/2022]
|
23
|
Benedict SH, Hoffman K, Martel MK, Abernethy AP, Asher AL, Capala J, Chen RC, Chera B, Couch J, Deye J, Efstathiou JA, Ford E, Fraass BA, Gabriel PE, Huser V, Kavanagh BD, Khuntia D, Marks LB, Mayo C, McNutt T, Miller RS, Moore KL, Prior F, Roelofs E, Rosenstein BS, Sloan J, Theriault A, Vikram B. Overview of the American Society for Radiation Oncology-National Institutes of Health-American Association of Physicists in Medicine Workshop 2015: Exploring Opportunities for Radiation Oncology in the Era of Big Data. Int J Radiat Oncol Biol Phys 2017; 95:873-879. [PMID: 27302503 DOI: 10.1016/j.ijrobp.2016.03.006] [Citation(s) in RCA: 24] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2016] [Revised: 03/03/2016] [Accepted: 03/08/2016] [Indexed: 01/24/2023]
Affiliation(s)
| | - Karen Hoffman
- University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Mary K Martel
- University of Texas MD Anderson Cancer Center, Houston, Texas
| | | | - Anthony L Asher
- American Association of Neurological Surgeons, Rolling Meadows, Illinois
| | - Jacek Capala
- Clinical Radiation Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Ronald C Chen
- University of North Carolina School of Medicine, Chapel Hill, North Carolina
| | - Bhisham Chera
- University of North Carolina School of Medicine, Chapel Hill, North Carolina
| | - Jennifer Couch
- National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - James Deye
- National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Jason A Efstathiou
- Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Eric Ford
- University of Washington, Seattle, Washington
| | | | - Peter E Gabriel
- Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Vojtech Huser
- Lister Hill National Center for Biomedical Communications, National Library of Medicine, National Institutes of Health, Bethesda, Maryland
| | | | | | - Lawrence B Marks
- University of North Carolina School of Medicine, Chapel Hill, North Carolina
| | | | - Todd McNutt
- The Johns Hopkins University School of Medicine, Baltimore, Maryland
| | | | - Kevin L Moore
- University of California, San Diego, La Jolla, California
| | - Fred Prior
- University of Arkansas for Medical Sciences, Little Rock, Arkansas
| | - Erik Roelofs
- Department of Radiation Oncology (MAASTRO), GROW - School for Oncology and Developmental Biology, Maastricht University Medical Center, Maastricht, the Netherlands
| | | | | | | | - Bhadrasain Vikram
- National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| |
Collapse
|
24
|
Valdes G, Chan MF, Lim SB, Scheuermann R, Deasy JO, Solberg TD. IMRT QA using machine learning: A multi-institutional validation. J Appl Clin Med Phys 2017; 18:279-284. [PMID: 28815994 PMCID: PMC5874948 DOI: 10.1002/acm2.12161] [Citation(s) in RCA: 93] [Impact Index Per Article: 13.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2017] [Revised: 06/30/2017] [Accepted: 07/10/2017] [Indexed: 02/04/2023] Open
Abstract
Purpose To validate a machine learning approach to Virtual intensity‐modulated radiation therapy (IMRT) quality assurance (QA) for accurately predicting gamma passing rates using different measurement approaches at different institutions. Methods A Virtual IMRT QA framework was previously developed using a machine learning algorithm based on 498 IMRT plans, in which QA measurements were performed using diode‐array detectors and a 3%local/3 mm with 10% threshold at Institution 1. An independent set of 139 IMRT measurements from a different institution, Institution 2, with QA data based on portal dosimetry using the same gamma index, was used to test the mathematical framework. Only pixels with ≥10% of the maximum calibrated units (CU) or dose were included in the comparison. Plans were characterized by 90 different complexity metrics. A weighted poison regression with Lasso regularization was trained to predict passing rates using the complexity metrics as input. Results The methodology predicted passing rates within 3% accuracy for all composite plans measured using diode‐array detectors at Institution 1, and within 3.5% for 120 of 139 plans using portal dosimetry measurements performed on a per‐beam basis at Institution 2. The remaining measurements (19) had large areas of low CU, where portal dosimetry has a larger disagreement with the calculated dose and as such, the failure was expected. These beams need further modeling in the treatment planning system to correct the under‐response in low‐dose regions. Important features selected by Lasso to predict gamma passing rates were as follows: complete irradiated area outline (CIAO), jaw position, fraction of MLC leafs with gaps smaller than 20 or 5 mm, fraction of area receiving less than 50% of the total CU, fraction of the area receiving dose from penumbra, weighted average irregularity factor, and duty cycle. Conclusions We have demonstrated that Virtual IMRT QA can predict passing rates using different measurement techniques and across multiple institutions. Prediction of QA passing rates can have profound implications on the current IMRT process.
Collapse
Affiliation(s)
- Gilmer Valdes
- Department of Radiation Oncology, University of California San Francisco Medical Center, San Francisco, CA, USA.,Department of Radiation Oncology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Maria F Chan
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Seng Boh Lim
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Ryan Scheuermann
- Department of Radiation Oncology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Joseph O Deasy
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Timothy D Solberg
- Department of Radiation Oncology, University of California San Francisco Medical Center, San Francisco, CA, USA.,Department of Radiation Oncology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| |
Collapse
|
25
|
Quon H, Hui X, Cheng Z, Robertson S, Peng L, Bowers M, Moore J, Choflet A, Thompson A, Muse M, Kiess A, Page B, Fakhry C, Gourin C, O'Hare J, Graham P, Szczesniak M, Maclean J, Cook I, McNutt T. Quantitative Evaluation of Head and Neck Cancer Treatment-Related Dysphagia in the Development of a Personalized Treatment Deintensification Paradigm. Int J Radiat Oncol Biol Phys 2017; 99:1271-1278. [PMID: 29165287 DOI: 10.1016/j.ijrobp.2017.08.004] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2017] [Revised: 06/09/2017] [Accepted: 08/07/2017] [Indexed: 01/01/2023]
Abstract
PURPOSE To test the hypothesis that quantifying swallow function with multiple patient-reported outcome (PRO) instruments is an important strategy to yield insights in the development of personalized deintensified therapies seeking to reduce the risk of head and neck cancer (HNC) treatment-related dysphagia (HNCTD). METHODS AND MATERIALS Irradiated HNC subjects seen in follow-up care (April 2015 to December 2015) who prospectively completed the Sydney Swallow Questionnaire (SSQ) and the MD Anderson Dysphagia Inventory (MDADI) concurrently on the web interface to our Oncospace database were evaluated. A correlation matrix quantified the relationship between the SSQ and MDADI. Machine-learning unsupervised cluster analysis using the elbow criterion and CLUSPLOT analysis to establish its validity was performed. RESULTS We identified 89 subjects. The MDADI and SSQ scores were moderately but significantly correlated (correlation coefficient -0.69). K-means cluster analysis demonstrated that 3 unique statistical cohorts (elbow criterion) could be identified with CLUSPLOT analysis, confirming that 100% of variances were accounted for. Correlation coefficients between the individual items in the SSQ and the MDADI demonstrated weak to moderate negative correlation, except for SSQ17 (quality of life question). CONCLUSIONS Pilot analysis demonstrates that the MDADI and SSQ are complementary. Three unique clusters of patients can be defined, suggesting that a unique dysphagia signature for HNCTD may be definable. Longitudinal studies relying on only a single PRO, such as MDADI, may be inadequate for classifying HNCTD.
Collapse
Affiliation(s)
- Harry Quon
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland; Department of Otolaryngology-Head and Neck Surgery, Johns Hopkins University, Baltimore, Maryland.
| | - Xuan Hui
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Zhi Cheng
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Scott Robertson
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Luke Peng
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Michael Bowers
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Joseph Moore
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Amanda Choflet
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Alex Thompson
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Mariah Muse
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Ana Kiess
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Brandi Page
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Carole Fakhry
- Department of Otolaryngology-Head and Neck Surgery, Johns Hopkins University, Baltimore, Maryland
| | - Christine Gourin
- Department of Otolaryngology-Head and Neck Surgery, Johns Hopkins University, Baltimore, Maryland
| | - Jolyne O'Hare
- Department of Radiation Oncology, St. George Hospital, University of New South Wales, Sydney, New South Wales, Australia
| | - Peter Graham
- Department of Radiation Oncology, St. George Hospital, University of New South Wales, Sydney, New South Wales, Australia
| | - Michal Szczesniak
- Department of Gastroenterology and Hepatology, St. George Hospital, University of New South Wales, Sydney, New South Wales, Australia
| | - Julia Maclean
- Department of Gastroenterology and Hepatology, St. George Hospital, University of New South Wales, Sydney, New South Wales, Australia
| | - Ian Cook
- Department of Gastroenterology and Hepatology, St. George Hospital, University of New South Wales, Sydney, New South Wales, Australia
| | - Todd McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| |
Collapse
|
26
|
Incorporating big data into treatment plan evaluation: Development of statistical DVH metrics and visualization dashboards. Adv Radiat Oncol 2017; 2:503-514. [PMID: 29114619 PMCID: PMC5605288 DOI: 10.1016/j.adro.2017.04.005] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2016] [Revised: 03/01/2017] [Accepted: 04/14/2017] [Indexed: 11/20/2022] Open
Abstract
Purpose To develop statistical dose-volume histogram (DVH)–based metrics and a visualization method to quantify the comparison of treatment plans with historical experience and among different institutions. Methods and materials The descriptive statistical summary (ie, median, first and third quartiles, and 95% confidence intervals) of volume-normalized DVH curve sets of past experiences was visualized through the creation of statistical DVH plots. Detailed distribution parameters were calculated and stored in JavaScript Object Notation files to facilitate management, including transfer and potential multi-institutional comparisons. In the treatment plan evaluation, structure DVH curves were scored against computed statistical DVHs and weighted experience scores (WESs). Individual, clinically used, DVH-based metrics were integrated into a generalized evaluation metric (GEM) as a priority-weighted sum of normalized incomplete gamma functions. Historical treatment plans for 351 patients with head and neck cancer, 104 with prostate cancer who were treated with conventional fractionation, and 94 with liver cancer who were treated with stereotactic body radiation therapy were analyzed to demonstrate the usage of statistical DVH, WES, and GEM in a plan evaluation. A shareable dashboard plugin was created to display statistical DVHs and integrate GEM and WES scores into a clinical plan evaluation within the treatment planning system. Benchmarking with normal tissue complication probability scores was carried out to compare the behavior of GEM and WES scores. Results DVH curves from historical treatment plans were characterized and presented, with difficult-to-spare structures (ie, frequently compromised organs at risk) identified. Quantitative evaluations by GEM and/or WES compared favorably with the normal tissue complication probability Lyman-Kutcher-Burman model, transforming a set of discrete threshold-priority limits into a continuous model reflecting physician objectives and historical experience. Conclusions Statistical DVH offers an easy-to-read, detailed, and comprehensive way to visualize the quantitative comparison with historical experiences and among institutions. WES and GEM metrics offer a flexible means of incorporating discrete threshold-prioritizations and historic context into a set of standardized scoring metrics. Together, they provide a practical approach for incorporating big data into clinical practice for treatment plan evaluations.
Collapse
|
27
|
Predicting liver SBRT eligibility and plan quality for VMAT and 4π plans. Radiat Oncol 2017; 12:70. [PMID: 28438215 PMCID: PMC5404690 DOI: 10.1186/s13014-017-0806-z] [Citation(s) in RCA: 26] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2016] [Accepted: 04/12/2017] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND It is useful to predict planned dosimetry and determine the eligibility of a liver cancer patient for SBRT treatment using knowledge based planning (KBP). We compare the predictive accuracy using the overlap volume histogram (OVH) and statistical voxel dose learning (SVDL) KBP prediction models for coplanar VMAT to non-coplanar 4π radiotherapy plans. METHODS In this study, 21 liver SBRT cases were selected, which were initially treated using coplanar VMAT plans. They were then re-planned using 4π IMRT plans with 20 inversely optimized non-coplanar beams. OVH was calculated by expanding the planning target volume (PTV) and then plotting the percent overlap volume v with the liver vs. r v , the expansion distance. SVDL calculated the distance to the PTV for all liver voxels and bins the voxels of the same distance. Their dose information is approximated by either taking the median or using a skew-normal or non-parametric fit, which was then applied to voxels of unknown dose for each patient in a leave-one-out test. The liver volume receiving less than 15 Gy (V<15Gy), DVHs, and 3D dose distributions were predicted and compared between the prediction models and planning methods. RESULTS On average, V<15Gy was predicted within 5%. SVDL was more accurate than OVH and able to predict DVH and 3D dose distributions. Median SVDL yielded predictive errors similar or lower than the fitting methods and is more computationally efficient. Prediction of the 4π dose was more accurate compared to VMAT for all prediction methods, with significant (p < 0.05) results except for OVH predicting liver V<15Gy (p = 0.063). CONCLUSIONS In addition to evaluating plan quality, KBP is useful to automatically determine the patient eligibility for liver SBRT and quantify the dosimetric gains from non-coplanar 4π plans. The two here analyzed dose prediction methods performed more accurately for the 4π plans than VMAT.
Collapse
|
28
|
Guihard S, Thariat J, Clavier JB. [Big data and their perspectives in radiation therapy]. Bull Cancer 2016; 104:147-156. [PMID: 27914589 DOI: 10.1016/j.bulcan.2016.10.018] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2016] [Revised: 10/21/2016] [Accepted: 10/21/2016] [Indexed: 12/15/2022]
Abstract
The concept of big data indicates a change of scale in the use of data and data aggregation into large databases through improved computer technology. One of the current challenges in the creation of big data in the context of radiation therapy is the transformation of routine care items into dark data, i.e. data not yet collected, and the fusion of databases collecting different types of information (dose-volume histograms and toxicity data for example). Processes and infrastructures devoted to big data collection should not impact negatively on the doctor-patient relationship, the general process of care or the quality of the data collected. The use of big data requires a collective effort of physicians, physicists, software manufacturers and health authorities to create, organize and exploit big data in radiotherapy and, beyond, oncology. Big data involve a new culture to build an appropriate infrastructure legally and ethically. Processes and issues are discussed in this article.
Collapse
Affiliation(s)
- Sébastien Guihard
- Centre Paul-Strauss, service de radiothérapie, 3, rue de la Porte-de-l'Hôpital, BP 30042, 67065 Strasbourg cedex, France.
| | - Juliette Thariat
- Centre Lacassagne, service de radiothérapie, 227, avenue de la Lanterne, 06200 Nice, France
| | - Jean-Baptiste Clavier
- Centre Paul-Strauss, service de radiothérapie, 3, rue de la Porte-de-l'Hôpital, BP 30042, 67065 Strasbourg cedex, France
| |
Collapse
|
29
|
Moran JM, Feng M, Benedetti LA, Marsh R, Griffith KA, Matuszak MM, Hess M, McMullen M, Fisher JH, Nurushev T, Grubb M, Gardner S, Nielsen D, Jagsi R, Hayman JA, Pierce LJ. Development of a model web-based system to support a statewide quality consortium in radiation oncology. Pract Radiat Oncol 2016; 7:e205-e213. [PMID: 28196607 DOI: 10.1016/j.prro.2016.10.002] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2016] [Revised: 09/23/2016] [Accepted: 10/10/2016] [Indexed: 12/25/2022]
Abstract
PURPOSE A database in which patient data are compiled allows analytic opportunities for continuous improvements in treatment quality and comparative effectiveness research. We describe the development of a novel, web-based system that supports the collection of complex radiation treatment planning information from centers that use diverse techniques, software, and hardware for radiation oncology care in a statewide quality collaborative, the Michigan Radiation Oncology Quality Consortium (MROQC). METHODS AND MATERIALS The MROQC database seeks to enable assessment of physician- and patient-reported outcomes and quality improvement as a function of treatment planning and delivery techniques for breast and lung cancer patients. We created tools to collect anonymized data based on all plans. RESULTS The MROQC system representing 24 institutions has been successfully deployed in the state of Michigan. Since 2012, dose-volume histogram and Digital Imaging and Communications in Medicine-radiation therapy plan data and information on simulation, planning, and delivery techniques have been collected. Audits indicated >90% accurate data submission and spurred refinements to data collection methodology. CONCLUSIONS This model web-based system captures detailed, high-quality radiation therapy dosimetry data along with patient- and physician-reported outcomes and clinical data for a radiation therapy collaborative quality initiative. The collaborative nature of the project has been integral to its success. Our methodology can be applied to setting up analogous consortiums and databases.
Collapse
Affiliation(s)
- Jean M Moran
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan.
| | - Mary Feng
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Lisa A Benedetti
- Department of Radiation Oncology, William Beaumont Hospital, Royal Oak, Michigan
| | - Robin Marsh
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Kent A Griffith
- Department of Biostatistics, University of Michigan, Ann Arbor, Michigan
| | - Martha M Matuszak
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Michael Hess
- School of Information, University of Michigan, Ann Arbor, Michigan
| | - Matthew McMullen
- Radiation Oncology, St. Joseph Mercy Hospital, Ypsilanti, Michigan
| | - Jennifer H Fisher
- Johnson Family Center for Cancer Care, Mercy Health Partners, Muskegon, Michigan
| | | | - Margaret Grubb
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Stephen Gardner
- Radiation Oncology Department, Henry Ford Health System, Detroit, Michigan
| | - Daniel Nielsen
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Reshma Jagsi
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - James A Hayman
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Lori J Pierce
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | | |
Collapse
|
30
|
Mayo CS, Kessler ML, Eisbruch A, Weyburne G, Feng M, Hayman JA, Jolly S, El Naqa I, Moran JM, Matuszak MM, Anderson CJ, Holevinski LP, McShan DL, Merkel SM, Machnak SL, Lawrence TS, Ten Haken RK. The big data effort in radiation oncology: Data mining or data farming? Adv Radiat Oncol 2016; 1:260-271. [PMID: 28740896 PMCID: PMC5514231 DOI: 10.1016/j.adro.2016.10.001] [Citation(s) in RCA: 40] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2016] [Revised: 09/23/2016] [Accepted: 10/05/2016] [Indexed: 12/01/2022] Open
Abstract
Although large volumes of information are entered into our electronic health care records, radiation oncology information systems and treatment planning systems on a daily basis, the goal of extracting and using this big data has been slow to emerge. Development of strategies to meet this goal is aided by examining issues with a data farming instead of a data mining conceptualization. Using this model, a vision of key data elements, clinical process changes, technology issues and solutions, and role for professional societies is presented. With a better view of technology, process and standardization factors, definition and prioritization of efforts can be more effectively directed.
Collapse
Affiliation(s)
- Charles S Mayo
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Marc L Kessler
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Avraham Eisbruch
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Grant Weyburne
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Mary Feng
- Department of Radiation Oncology, University of California at San Francisco, San Francisco, California
| | - James A Hayman
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Shruti Jolly
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Issam El Naqa
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Jean M Moran
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Martha M Matuszak
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Carlos J Anderson
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Lynn P Holevinski
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Daniel L McShan
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Sue M Merkel
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Sherry L Machnak
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Theodore S Lawrence
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Randall K Ten Haken
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| |
Collapse
|
31
|
Bibault JE, Giraud P, Burgun A. Big Data and machine learning in radiation oncology: State of the art and future prospects. Cancer Lett 2016; 382:110-117. [PMID: 27241666 DOI: 10.1016/j.canlet.2016.05.033] [Citation(s) in RCA: 171] [Impact Index Per Article: 21.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2016] [Revised: 05/26/2016] [Accepted: 05/26/2016] [Indexed: 12/13/2022]
Abstract
Precision medicine relies on an increasing amount of heterogeneous data. Advances in radiation oncology, through the use of CT Scan, dosimetry and imaging performed before each fraction, have generated a considerable flow of data that needs to be integrated. In the same time, Electronic Health Records now provide phenotypic profiles of large cohorts of patients that could be correlated to this information. In this review, we describe methods that could be used to create integrative predictive models in radiation oncology. Potential uses of machine learning methods such as support vector machine, artificial neural networks, and deep learning are also discussed.
Collapse
Affiliation(s)
- Jean-Emmanuel Bibault
- Radiation Oncology Department, Georges Pompidou European Hospital, Assistance Publique - Hôpitaux de Paris, Paris Descartes University, Paris Sorbonne Cité, Paris, France; INSERM UMR 1138 Team 22: Information Sciences to support Personalized Medicine, Paris Descartes University, Sorbonne Paris Cité, Paris, France.
| | - Philippe Giraud
- Radiation Oncology Department, Georges Pompidou European Hospital, Assistance Publique - Hôpitaux de Paris, Paris Descartes University, Paris Sorbonne Cité, Paris, France
| | - Anita Burgun
- INSERM UMR 1138 Team 22: Information Sciences to support Personalized Medicine, Paris Descartes University, Sorbonne Paris Cité, Paris, France; Biomedical Informatics and Public Health Department, Georges Pompidou European Hospital, Assistance Publique - Hôpitaux de Paris, Paris Descartes University, Paris Sorbonne Cité, Paris, France
| |
Collapse
|
32
|
Mayo CS, Pisansky TM, Petersen IA, Yan ES, Davis BJ, Stafford SL, Garces YI, Miller RC, Martenson JA, Mutter RW, Choo R, Hallemeier CL, Laack NN, Park SS, Ma DJ, Olivier KR, Keole SR, Fatyga M, Foote RL, Haddock MG. Establishment of practice standards in nomenclature and prescription to enable construction of software and databases for knowledge-based practice review. Pract Radiat Oncol 2016; 6:e117-e126. [PMID: 26825250 DOI: 10.1016/j.prro.2015.11.001] [Citation(s) in RCA: 18] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2015] [Revised: 09/05/2015] [Accepted: 11/02/2015] [Indexed: 12/25/2022]
Abstract
INTRODUCTION Establishment of standards within a practice and across disease site groups for nomenclatures, prescription formatting, and measured dose-volume histogram (DVH) metrics is a key enabling step for creating software and database solutions to make routine aggregation of dosimetric data for all patients treated in a practice, practical. A process of physician-driven, iterative dialogs coupled with development of technical tools is required to implement the cultural and procedural changes. The cumulative reward for this effort is a database that can be used for defining practice norms, benchmarking against national standards, and tracking dosimetric effects of longitudinal practice pattern changes. METHODS AND MATERIALS A 4-year project was carried out to develop and introduce standardizations, modify processes, and develop computer-based tools for reporting, aggregation, and analysis of prescription and DVH metrics. Physician disease site groups developed 42 target and 81 normal tissue templates. From the database of 32,002 DVH metrics, benchmarking was illustrated for a subgroup of breast (281) and prostate (324) patients treated with conventional fractionation over a 16-month period. Breast patients were segregated according to prescription template used: simple (S, tangents only) vs complex (C, tangents + supraclavicular ± intramammary nodes) and left (S-L or C-L) versus right (S-R or C-R). RESULTS Prostate patients' median and 50% confidence intervals (CIs) for bladder, stated according to the nomenclature: the percentage of bladder volume receiving doses of ≥40 Gy (V40[%]), V65Gy[%], V70Gy[%], V75Gy[%], and V80Gy[%] were 45.5 (24.9-57.0), 15.6 (9.0-23.8), 7.6 (3.3-13.6), 2.0 (0.0-7.9), and 0.0 (0.0-1.4), respectively. Values for rectum: V50Gy[%], V60 Gy[%], V65Gy[%], V70Gy[%], and V75Gy[%] were 37.1 (27.8-43.5), 21.8 (15.6-25.5), 14.6 (9.6-18.0), 7.7 (1.9-12.3), and 1.0 (0-7.0), respectively. For breast patients, heart:mean Gray values were 1.5 (1.0-2.0), 3.1 (2.2-4.8), 0.4 (0.3-0.7), and 1.1 (0.8-2.2) for S-L, C-L, S-R, and C-R, respectively. Longitudinal, moving window plots of median, 50% CI, and 90% CI for 6-month periods demonstrated the effect of practice changes to reduce heart doses. CONCLUSIONS Standardization was challenging as a practice change, but has resulted in significant improvements for both our clinical and research efforts.
Collapse
Affiliation(s)
- Charles S Mayo
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota.
| | | | - Ivy A Petersen
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - Elizabeth S Yan
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - Brian J Davis
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - Scott L Stafford
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - Yolanda I Garces
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - Robert C Miller
- Department of Radiation Oncology, Mayo Clinic, Jacksonville, Florida
| | | | - Robert W Mutter
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - Richard Choo
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | | | - Nadia N Laack
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - Sean S Park
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | - Daniel J Ma
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | | | - Sameer R Keole
- Department of Radiation Oncology, Mayo Clinic, Phoenix, Arizona
| | - Mirek Fatyga
- Department of Radiation Oncology, Mayo Clinic, Phoenix, Arizona
| | - Robert L Foote
- Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota
| | | |
Collapse
|
33
|
How Can We Effect Culture Change Toward Data-Driven Medicine? Int J Radiat Oncol Biol Phys 2015; 95:916-921. [PMID: 27302507 DOI: 10.1016/j.ijrobp.2015.12.355] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2015] [Revised: 12/04/2015] [Accepted: 12/14/2015] [Indexed: 11/23/2022]
|
34
|
McNutt TR, Moore KL, Quon H. Needs and Challenges for Big Data in Radiation Oncology. Int J Radiat Oncol Biol Phys 2015; 95:909-915. [PMID: 27302506 DOI: 10.1016/j.ijrobp.2015.11.032] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2015] [Revised: 11/13/2015] [Accepted: 11/20/2015] [Indexed: 01/15/2023]
Affiliation(s)
- Todd R McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland.
| | - Kevin L Moore
- Department of Radiation Oncology, University of California - San Diego, La Jolla, California
| | - Harry Quon
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| |
Collapse
|
35
|
Chen RC, Gabriel PE, Kavanagh BD, McNutt TR. How Will Big Data Impact Clinical Decision Making and Precision Medicine in Radiation Therapy? Int J Radiat Oncol Biol Phys 2015; 95:880-884. [PMID: 26797536 DOI: 10.1016/j.ijrobp.2015.10.052] [Citation(s) in RCA: 18] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2015] [Revised: 10/09/2015] [Accepted: 10/26/2015] [Indexed: 11/25/2022]
Affiliation(s)
- Ronald C Chen
- Department of Radiation Oncology, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina.
| | - Peter E Gabriel
- Department of Radiation Oncology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, Pennsylvania
| | - Brian D Kavanagh
- Department of Radiation Oncology, University of Colorado School of Medicine, Aurora, Colorado
| | - Todd R McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland
| |
Collapse
|