1
|
den Boer R, Siang KNW, Yuen M, Borggreve A, Defize I, van Lier A, Ruurda J, van Hillegersberg R, Mook S, Meijer G. A robust semi-automatic delineation workflow using denoised diffusion weighted magnetic resonance imaging for response assessment of patients with esophageal cancer treated with neoadjuvant chemoradiotherapy. Phys Imaging Radiat Oncol 2023; 28:100489. [PMID: 37822533 PMCID: PMC10562188 DOI: 10.1016/j.phro.2023.100489] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2023] [Revised: 08/24/2023] [Accepted: 08/25/2023] [Indexed: 10/13/2023] Open
Abstract
Background and Purpose Diffusion weighted magnetic resonance imaging (DW-MRI) can be prognostic for response to neoadjuvant chemotherapy (nCRT) in patients with esophageal cancer. However, manual tumor delineation is labor intensive and subjective. Furthermore, noise in DW-MRI images will propagate into the corresponding apparent diffusion coefficient (ADC) signal. In this study a workflow is investigated that combines a denoising algorithm with semi-automatic segmentation for quantifying ADC changes. Materials and Methods Twenty patients with esophageal cancer who underwent nCRT before esophagectomy were included. One baseline and five weekly DW-MRI scans were acquired for every patient during nCRT. A self-supervised learning denoising algorithm, Patch2Self, was used to denoise the DWI-MRI images. A semi-automatic delineation workflow (SADW) was next developed and compared with a manually adjusted workflow (MAW). The agreement between workflows was determined using the Dice coefficients and Brand Altman plots. The prognostic value of ADCmean increases (%/week) for pathologic complete response (pCR) was assessed using c-statistics. Results The median Dice coefficient between the SADW and MAW was 0.64 (interquartile range 0.20). For the MAW, the c-statistic for predicting pCR was 0.80 (95% confidence interval (CI):0.56-1.00). The SADW showed a c-statistic of 0.84 (95%CI:0.63-1.00) after denoising. No statistically significant differences in c-statistics were observed between the workflows or after applying denoising. Conclusions The SADW resulted in non-inferior prognostic value for pCR compared to the more laborious MAW, allowing broad scale applications. The effect of denoising on the prognostic value for pCR needs to be investigated in larger cohorts.
Collapse
Affiliation(s)
- Robin den Boer
- University Medical Center Utrecht, Department of Radiation Oncology, Utrecht, The Netherlands
| | - Kelvin Ng Wei Siang
- Erasmus MC Cancer Institute, University Medical Center Rotterdam, Department of Radiotherapy, Rotterdam, The Netherlands
- Holland Proton Therapy Center, Department of Medical Physics & Informatics, Delft, The Netherlands
| | - Mandy Yuen
- University Medical Center Utrecht, Department of Radiation Oncology, Utrecht, The Netherlands
| | - Alicia Borggreve
- University Medical Center Utrecht, Department of Radiation Oncology, Utrecht, The Netherlands
| | - Ingmar Defize
- University Medical Center Utrecht, Department of Radiation Oncology, Utrecht, The Netherlands
| | - Astrid van Lier
- University Medical Center Utrecht, Department of Radiation Oncology, Utrecht, The Netherlands
| | - Jelle Ruurda
- University Medical Center Utrecht, Department of Surgery, Utrecht, The Netherlands
| | | | - Stella Mook
- University Medical Center Utrecht, Department of Radiation Oncology, Utrecht, The Netherlands
| | - Gert Meijer
- University Medical Center Utrecht, Department of Radiation Oncology, Utrecht, The Netherlands
| |
Collapse
|
2
|
Bisgaard ALH, Keesman R, van Lier ALHMW, Coolens C, van Houdt PJ, Tree A, Wetscherek A, Romesser PB, Tyagi N, Lo Russo M, Habrich J, Vesprini D, Lau AZ, Mook S, Chung P, Kerkmeijer LGW, Gouw ZAR, Lorenzen EL, van der Heide UA, Schytte T, Brink C, Mahmood F. Recommendations for improved reproducibility of ADC derivation on behalf of the Elekta MRI-linac consortium image analysis working group. Radiother Oncol 2023; 186:109803. [PMID: 37437609 DOI: 10.1016/j.radonc.2023.109803] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2023] [Revised: 06/30/2023] [Accepted: 07/06/2023] [Indexed: 07/14/2023]
Abstract
BACKGROUND AND PURPOSE The apparent diffusion coefficient (ADC), a potential imaging biomarker for radiotherapy response, needs to be reproducible before translation into clinical use. The aim of this study was to evaluate the multi-centre delineation- and calculation-related ADC variation and give recommendations to minimize it. MATERIALS AND METHODS Nine centres received identical diffusion-weighted and anatomical magnetic resonance images of different cancerous tumours (adrenal gland, pelvic oligo metastasis, pancreas, and prostate). All centres delineated the gross tumour volume (GTV), clinical target volume (CTV), and viable tumour volume (VTV), and calculated ADCs using both their local calculation methods and each of the following calculation conditions: b-values 0-500 vs. 150-500 s/mm2, region-of-interest (ROI)-based vs. voxel-based calculation, and mean vs. median. ADC variation was assessed using the mean coefficient of variation across delineations (CVD) and calculation methods (CVC). Absolute ADC differences between calculation conditions were evaluated using Friedman's test. Recommendations for ADC calculation were formulated based on observations and discussions within the Elekta MRI-linac consortium image analysis working group. RESULTS The median (range) CVD and CVC were 0.06 (0.02-0.32) and 0.17 (0.08-0.26), respectively. The ADC estimates differed 18% between b-value sets and 4% between ROI/voxel-based calculation (p-values < 0.01). No significant difference was observed between mean and median (p = 0.64). Aligning calculation conditions between centres reduced CVC to 0.04 (0.01-0.16). CVD was comparable between ROI types. CONCLUSION Overall, calculation methods had a larger impact on ADC reproducibility compared to delineation. Based on the results, significant sources of variation were identified, which should be considered when initiating new studies, in particular multi-centre investigations.
Collapse
Affiliation(s)
- Anne L H Bisgaard
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Kløvervænget 19, 5000 Odense, Denmark; Department of Clinical Research, University of Southern Denmark, J.B. Winsløws Vej 19.3, 5000 Odense Denmark.
| | - Rick Keesman
- Department of Radiation Oncology, Radboud University Medical Centre, P.O. Box 9101, 6500 HB Nijmegen, The Netherlands.
| | - Astrid L H M W van Lier
- Department of Radiotherapy, University Medical Centre Utrecht, Heidelberglaan 100, 3584 CX,Utrecht, The Netherlands.
| | - Catherine Coolens
- Department of Medical Physics, Princess Margaret Cancer Centre, University Health Network, 610 University Avenue, M5G 2M9 Toronto, ON, Canada.
| | - Petra J van Houdt
- Department of Radiation Oncology, the Netherlands Cancer Institute, Postbus 90203, 1006 BE Amsterdam, The Netherlands.
| | - Alison Tree
- Department of Urology, The Institute of Cancer Research and The Royal Marsden NHS Foundation Trust, Downs Road, Sutton, Surrey, SM2 5PT London, UK.
| | - Andreas Wetscherek
- Joint Department of Physics, The Institute of Cancer Research and The Royal Marsden NHS Foundation Trust, SM2 5NG London, UK.
| | - Paul B Romesser
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, Box 22, NY 10065, New York, USA.
| | - Neelam Tyagi
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, 545 E. 73rd street, NY 10021, New York, USA.
| | - Monica Lo Russo
- Department of Radiation Oncology, University Hospital and Medical Faculty, Eberhard Karls University, Hoppe-Seyler-Str. 3, 72076 Tübingen, Germany.
| | - Jonas Habrich
- Section for Biomedical Physics, Department of Radiation Oncology, University of Tübingen, Hoppe-Seyler-Str. 3, 72076 Tübingen, Germany.
| | - Danny Vesprini
- Department of Radiation Oncology, Sunnybrook Odette Cancer Centre, University of Toronto, 2075 Bayview Avenue, M4N 3M5 Toronto, ON, Canada.
| | - Angus Z Lau
- Physical Sciences Platform, Sunnybrook Research Institute. Department of Medical Biophysics, University of Toronto, 2075 Bayview Avenue, M4N 3M5 Toronto, ON, Canada.
| | - Stella Mook
- Department of Radiotherapy, University Medical Centre Utrecht, Heidelberglaan 100, 3584 CX,Utrecht, The Netherlands.
| | - Peter Chung
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network. Department of Radiation Oncology, University of Toronto, 610 University Avenue, M5G 2M9 Toronto, ON, Canada.
| | - Linda G W Kerkmeijer
- Department of Radiation Oncology, Radboud University Medical Centre, P.O. Box 9101, 6500 HB Nijmegen, The Netherlands.
| | - Zeno A R Gouw
- Department of Radiation Oncology, the Netherlands Cancer Institute, Postbus 90203, 1006 BE Amsterdam, The Netherlands.
| | - Ebbe L Lorenzen
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Kløvervænget 19, 5000 Odense, Denmark.
| | - Uulke A van der Heide
- Department of Radiation Oncology, the Netherlands Cancer Institute, Postbus 90203, 1006 BE Amsterdam, The Netherlands.
| | - Tine Schytte
- Department of Clinical Research, University of Southern Denmark, J.B. Winsløws Vej 19.3, 5000 Odense Denmark; Department of Oncology, Odense University Hospital, Kløvervænget 19, 5000 Odense, Denmark.
| | - Carsten Brink
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Kløvervænget 19, 5000 Odense, Denmark; Department of Clinical Research, University of Southern Denmark, J.B. Winsløws Vej 19.3, 5000 Odense Denmark.
| | - Faisal Mahmood
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Kløvervænget 19, 5000 Odense, Denmark; Department of Clinical Research, University of Southern Denmark, J.B. Winsløws Vej 19.3, 5000 Odense Denmark.
| |
Collapse
|
3
|
Knuth F, Groendahl AR, Winter RM, Torheim T, Negård A, Holmedal SH, Bakke KM, Meltzer S, Futsæther CM, Redalen KR. Semi-automatic tumor segmentation of rectal cancer based on functional magnetic resonance imaging. Phys Imaging Radiat Oncol 2022; 22:77-84. [PMID: 35602548 PMCID: PMC9114680 DOI: 10.1016/j.phro.2022.05.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2021] [Revised: 05/01/2022] [Accepted: 05/02/2022] [Indexed: 11/25/2022] Open
Abstract
Machine learning on magnetic resonance images (MRI) was used for tumor segmentation. Voxelwise machine learning with morphological post-processing achieved good segmentation results. Combining T2-weighted with functional MRI improved semi-automatic tumor segmentation. Dynamic contrast enhanced MRI was the most valuable functional MRI information. Tumor volume and interobserver variation were linked to measured segmentation quality.
Background and purpose Tumor delineation is required both for radiotherapy planning and quantitative imaging biomarker purposes. It is a manual, time- and labor-intensive process prone to inter- and intraobserver variations. Semi or fully automatic segmentation could provide better efficiency and consistency. This study aimed to investigate the influence of including and combining functional with anatomical magnetic resonance imaging (MRI) sequences on the quality of automatic segmentations. Materials and methods T2-weighted (T2w), diffusion weighted, multi-echo T2*-weighted, and contrast enhanced dynamic multi-echo (DME) MR images of eighty-one patients with rectal cancer were used in the analysis. Four classical machine learning algorithms; adaptive boosting (ADA), linear and quadratic discriminant analysis and support vector machines, were trained for automatic segmentation of tumor and normal tissue using different combinations of the MR images as input, followed by semi-automatic morphological post-processing. Manual delineations from two experts served as ground truth. The Sørensen-Dice similarity coefficient (DICE) and mean symmetric surface distance (MSD) were used as performance metric in leave-one-out cross validation. Results Using T2w images alone, ADA outperformed the other algorithms, yielding a median per patient DICE of 0.67 and MSD of 3.6 mm. The performance improved when functional images were added and was highest for models based on either T2w and DME images (DICE: 0.72, MSD: 2.7 mm) or all four MRI sequences (DICE: 0.72, MSD: 2.5 mm). Conclusion Machine learning models using functional MRI, in particular DME, have the potential to improve automatic segmentation of rectal cancer relative to models using T2w MRI alone.
Collapse
|