1
|
Ubaldi L, Valenti V, Borgese RF, Collura G, Fantacci ME, Ferrera G, Iacoviello G, Abbate BF, Laruina F, Tripoli A, Retico A, Marrale M. Strategies to develop radiomics and machine learning models for lung cancer stage and histology prediction using small data samples. Phys Med 2021; 90:13-22. [PMID: 34521016 DOI: 10.1016/j.ejmp.2021.08.015] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/03/2021] [Revised: 08/21/2021] [Accepted: 08/28/2021] [Indexed: 02/09/2023] Open
Abstract
Predictive models based on radiomics and machine-learning (ML) need large and annotated datasets for training, often difficult to collect. We designed an operative pipeline for model training to exploit data already available to the scientific community. The aim of this work was to explore the capability of radiomic features in predicting tumor histology and stage in patients with non-small cell lung cancer (NSCLC). We analyzed the radiotherapy planning thoracic CT scans of a proprietary sample of 47 subjects (L-RT) and integrated this dataset with a publicly available set of 130 patients from the MAASTRO NSCLC collection (Lung1). We implemented intra- and inter-sample cross-validation strategies (CV) for evaluating the ML predictive model performances with not so large datasets. We carried out two classification tasks: histology classification (3 classes) and overall stage classification (two classes: stage I and II). In the first task, the best performance was obtained by a Random Forest classifier, once the analysis has been restricted to stage I and II tumors of the Lung1 and L-RT merged dataset (AUC = 0.72 ± 0.11). For the overall stage classification, the best results were obtained when training on Lung1 and testing of L-RT dataset (AUC = 0.72 ± 0.04 for Random Forest and AUC = 0.84 ± 0.03 for linear-kernel Support Vector Machine). According to the classification task to be accomplished and to the heterogeneity of the available dataset(s), different CV strategies have to be explored and compared to make a robust assessment of the potential of a predictive model based on radiomics and ML.
Collapse
Affiliation(s)
- L Ubaldi
- Physics Department, University of Pisa, Pisa, Italy; National Institute for Nuclear Physics (INFN), Pisa Division, Pisa, Italy
| | - V Valenti
- REM Radiation Therapy Center, Viagrande (CT), I-95029 Catania, Italy
| | - R F Borgese
- Physics and Chemistry Department "Emilio Segrè", University of Palermo, Palermo, Italy; National Institute for Nuclear Physics (INFN), Catania Division, Catania, Italy
| | - G Collura
- Physics and Chemistry Department "Emilio Segrè", University of Palermo, Palermo, Italy; National Institute for Nuclear Physics (INFN), Catania Division, Catania, Italy
| | - M E Fantacci
- Physics Department, University of Pisa, Pisa, Italy; National Institute for Nuclear Physics (INFN), Pisa Division, Pisa, Italy
| | - G Ferrera
- Radiation Oncology, ARNAS-Civico Hospital, Palermo, Italy
| | - G Iacoviello
- Medical Physics Department, ARNAS-Civico Hospital, Palermo, Italy
| | - B F Abbate
- Medical Physics Department, ARNAS-Civico Hospital, Palermo, Italy
| | - F Laruina
- Physics Department, University of Pisa, Pisa, Italy; National Institute for Nuclear Physics (INFN), Pisa Division, Pisa, Italy
| | - A Tripoli
- REM Radiation Therapy Center, Viagrande (CT), I-95029 Catania, Italy
| | - A Retico
- National Institute for Nuclear Physics (INFN), Pisa Division, Pisa, Italy
| | - M Marrale
- Physics and Chemistry Department "Emilio Segrè", University of Palermo, Palermo, Italy; National Institute for Nuclear Physics (INFN), Catania Division, Catania, Italy
| |
Collapse
|
2
|
Georg D, van der Heide UA, Aznar MC, Baumann M. Tribute to David Thwaites. Radiother Oncol 2020; 153:5-6. [PMID: 33341191 DOI: 10.1016/j.radonc.2020.11.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/10/2020] [Indexed: 11/24/2022]
Affiliation(s)
- Dietmar Georg
- Division Medical Radiation Physics, Department of Radiation Oncology, Medical University of Vienna/AKH Wien, Austria
| | - Uulke A van der Heide
- Department of Radiation Oncology, The Netherlands Cancer Institute, Amsterdam, The Netherlands
| | - Marianne C Aznar
- Division of Cancer Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, The Christie NHS Foundation Trust, United Kingdom; Nuffield Department of Population Health, University of Oxford, United Kingdom
| | | |
Collapse
|
3
|
Thwaites D. Beginnings, endings, histories and horizons. Radiother Oncol 2020; 153:1-4. [PMID: 33189761 DOI: 10.1016/j.radonc.2020.10.034] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2020] [Accepted: 10/26/2020] [Indexed: 12/19/2022]
Affiliation(s)
- David Thwaites
- Institute of Medical Physics, School of Physics, The University of Sydney, NSW 2006, Australia; Medical Physics, Leeds Institute of Cancer and Pathology, School of Medicine, The University of Leeds, UK; West Sydney Radiation Oncology Network and Cancer Research Network, Crown Princess Mary Cancer Centre, Westmead, NSW, Australia
| |
Collapse
|
4
|
Christiansen RL, Dysager L, Bertelsen AS, Hansen O, Brink C, Bernchou U. Accuracy of automatic deformable structure propagation for high-field MRI guided prostate radiotherapy. Radiat Oncol 2020; 15:32. [PMID: 32033574 PMCID: PMC7007657 DOI: 10.1186/s13014-020-1482-y] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2019] [Accepted: 01/30/2020] [Indexed: 11/25/2022] Open
Abstract
BACKGROUND In this study we have evaluated the accuracy of automatic, deformable structure propagation from planning CT and MR scans for daily online plan adaptation for MR linac (MRL) treatment, which is an important element to minimize re-planning time and reduce the risk of misrepresenting the target due to this time pressure. METHODS For 12 high-risk prostate cancer patients treated to the prostate and pelvic lymph nodes, target structures and organs at risk were delineated on both planning MR and CT scans and propagated using deformable registration to three T2 weighted MR scans acquired during the treatment course. Generated structures were evaluated against manual delineations on the repeated scans using intra-observer variation obtained on the planning MR as ground truth. RESULTS MR-to-MR propagated structures had significant less median surface distance and larger Dice similarity index compared to CT-MR propagation. The MR-MR propagation uncertainty was similar in magnitude to the intra-observer variation. Visual inspection of the deformed structures revealed that small anatomical differences between organs in source and destination image sets were generally well accounted for while large differences were not. CONCLUSION Both CT and MR based propagations require manual editing, but the current results show that MR-to-MR propagated structures require fewer corrections for high risk prostate cancer patients treated at a high-field MRL.
Collapse
Affiliation(s)
- Rasmus Lübeck Christiansen
- Department of Clinical Research, University of Southern Denmark, Winsløwparken 19 3. Sal, 5000, Odense C, Denmark.
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Kløvervænget 19, Indgang 85, Pavillion, Stuen, 5000, Odense C, Denmark.
| | - Lars Dysager
- Department of Oncology, Odense University Hospital, Kløvervænget 19 Indgang 85 Pavillion, 1. sal, 5000, Odense C, Denmark
| | - Anders Smedegaard Bertelsen
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Kløvervænget 19, Indgang 85, Pavillion, Stuen, 5000, Odense C, Denmark
| | - Olfred Hansen
- Department of Clinical Research, University of Southern Denmark, Winsløwparken 19 3. Sal, 5000, Odense C, Denmark
- Department of Oncology, Odense University Hospital, Kløvervænget 19 Indgang 85 Pavillion, 1. sal, 5000, Odense C, Denmark
| | - Carsten Brink
- Department of Clinical Research, University of Southern Denmark, Winsløwparken 19 3. Sal, 5000, Odense C, Denmark
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Kløvervænget 19, Indgang 85, Pavillion, Stuen, 5000, Odense C, Denmark
| | - Uffe Bernchou
- Department of Clinical Research, University of Southern Denmark, Winsløwparken 19 3. Sal, 5000, Odense C, Denmark
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Kløvervænget 19, Indgang 85, Pavillion, Stuen, 5000, Odense C, Denmark
| |
Collapse
|
5
|
Wohlfahrt P, Möhler C, Richter C, Greilich S. Evaluation of Stopping-Power Prediction by Dual- and Single-Energy Computed Tomography in an Anthropomorphic Ground-Truth Phantom. Int J Radiat Oncol Biol Phys 2018; 100:244-253. [DOI: 10.1016/j.ijrobp.2017.09.025] [Citation(s) in RCA: 43] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2017] [Revised: 08/28/2017] [Accepted: 09/08/2017] [Indexed: 01/31/2023]
|
6
|
Medical physics in radiation Oncology: New challenges, needs and roles. Radiother Oncol 2017; 125:375-378. [PMID: 29150160 DOI: 10.1016/j.radonc.2017.10.035] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2017] [Accepted: 10/30/2017] [Indexed: 12/21/2022]
|
7
|
Beasley WJ, McWilliam A, Slevin NJ, Mackay RI, van Herk M. An automated workflow for patient-specific quality control of contour propagation. Phys Med Biol 2016; 61:8577-8586. [DOI: 10.1088/1361-6560/61/24/8577] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
|
8
|
Huynh E, Coroller TP, Narayan V, Agrawal V, Hou Y, Romano J, Franco I, Mak RH, Aerts HJWL. CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer. Radiother Oncol 2016; 120:258-66. [PMID: 27296412 DOI: 10.1016/j.radonc.2016.05.024] [Citation(s) in RCA: 140] [Impact Index Per Article: 17.5] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2015] [Revised: 05/23/2016] [Accepted: 05/24/2016] [Indexed: 02/07/2023]
Abstract
BACKGROUND Radiomics uses a large number of quantitative imaging features that describe the tumor phenotype to develop imaging biomarkers for clinical outcomes. Radiomic analysis of pre-treatment computed-tomography (CT) scans was investigated to identify imaging predictors of clinical outcomes in early stage non-small cell lung cancer (NSCLC) patients treated with stereotactic body radiation therapy (SBRT). MATERIALS AND METHODS CT images of 113 stage I-II NSCLC patients treated with SBRT were analyzed. Twelve radiomic features were selected based on stability and variance. The association of features with clinical outcomes and their prognostic value (using the concordance index (CI)) was evaluated. Radiomic features were compared with conventional imaging metrics (tumor volume and diameter) and clinical parameters. RESULTS Overall survival was associated with two conventional features (volume and diameter) and two radiomic features (LoG 3D run low gray level short run emphasis and stats median). One radiomic feature (Wavelet LLH stats range) was significantly prognostic for distant metastasis (CI=0.67, q-value<0.1), while none of the conventional and clinical parameters were. Three conventional and four radiomic features were prognostic for overall survival. CONCLUSION This exploratory analysis demonstrates that radiomic features have potential to be prognostic for some outcomes that conventional imaging metrics cannot predict in SBRT patients.
Collapse
Affiliation(s)
- Elizabeth Huynh
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA.
| | - Thibaud P Coroller
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Vivek Narayan
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Vishesh Agrawal
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Ying Hou
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - John Romano
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Idalid Franco
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Raymond H Mak
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Hugo J W L Aerts
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA; Department of Radiology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| |
Collapse
|
9
|
Baumann M, Overgaard J. Bridging the valley of death: The new Radiotherapy & Oncology section “First in man – Translational innovations in radiation oncology”. Radiother Oncol 2016; 118:217-9. [DOI: 10.1016/j.radonc.2016.02.005] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2016] [Accepted: 02/03/2016] [Indexed: 12/31/2022]
|
10
|
Richter C, Pausch G, Barczyk S, Priegnitz M, Keitz I, Thiele J, Smeets J, Stappen FV, Bombelli L, Fiorini C, Hotoiu L, Perali I, Prieels D, Enghardt W, Baumann M. First clinical application of a prompt gamma based in vivo proton range verification system. Radiother Oncol 2016; 118:232-7. [DOI: 10.1016/j.radonc.2016.01.004] [Citation(s) in RCA: 169] [Impact Index Per Article: 21.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2015] [Revised: 12/13/2015] [Accepted: 01/05/2016] [Indexed: 12/25/2022]
|
11
|
Muren LP, Jornet N, Georg D, Garcia R, Thwaites DI. Improving radiotherapy through medical physics developments. Radiother Oncol 2015; 117:403-6. [DOI: 10.1016/j.radonc.2015.11.008] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2015] [Accepted: 11/19/2015] [Indexed: 01/21/2023]
|
12
|
|