Dedicated <scp>MRI</scp> simulation for cervical cancer radiation treatment planning: Assessing the impact on clinical target volume delineation

Veera, Jacqueline; Lim, Karen; Dowling, Jason; O’Connor, Chelsie; Holloway, Lois; Vinod, Shalini

doi:10.1111/1754-9485.12831

Cited by 9 publications

(16 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, in radiation oncology, gross tumor volumes (GTVs) are sometimes derived from MRI for more accurate delineations [54]. The examples of GTVs of MRIs and CTs are shown in [55] and [56]. Within a treatment planning system (TPS), the radiation oncologist initially identifies the target volumes and OARs.…”

Section: Radiotherapy Treatment (Rt) Planning and Optimizationmentioning

confidence: 99%

Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges

et al. 2021

View full text Add to dashboard Cite

The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing. DL provides grounds for technological development of computer-aided diagnosis and segmentation in radiology and radiation oncology. Amongst the anatomical locations where recent auto-segmentation algorithms have been employed, the pelvis remains one of the most challenging due to large intra- and inter-patient soft-tissue variabilities. This review provides a comprehensive, non-systematic and clinically-oriented overview of 74 DL-based segmentation studies, published between January 2016 and December 2020, for bladder, prostate, cervical and rectal cancers on computed tomography (CT) and magnetic resonance imaging (MRI), highlighting the key findings, challenges and limitations.

show abstract

Section: Radiotherapy Treatment (Rt) Planning and Optimizationmentioning

confidence: 99%

Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Data from a previous study assessing the impact of MRI on target volume delineation for cervical cancer 4 were used for this study. Study population included 18 patients with Stage IB-IV cervical cancer with a macroscopic pelvic tumour, undergoing primary radiation therapy.…”

Section: Methods and Materials Study Population And Imagingmentioning

confidence: 99%

“…The delineation process, outlining comparison methods and CTV delineation results have been reported previously 4 and is outlined briefly. Three experienced radiation oncologists specialising in gynaecological cancer independently delineated a pelvic CT and MRI data set for each patient.…”

Section: Delineation Processmentioning

confidence: 99%

“…Interobserver variability in target delineation has been quantified and reported for many tumour sites, 2 including cervical cancer. 3,4 Several studies have addressed the consequences of interobserver contouring variability on the resulting dose delivered to the patient. This has been addressed for external beam radiotherapy (EBRT) [5][6][7][8][9] and brachytherapy [10][11][12] for many tumour sites.…”

Section: Introductionmentioning

confidence: 99%

“…Our previous work to quantify differences in delineated CTVs between CT and MRI showed significantly smaller CTV on MRI. 4 As an extension of this previous work, we planned to quantify the dosimetric impact of the delineation variation. We hypothesised that MRI-based target volume is associated with radiotherapy plans with a better therapeutic ratio (better target volume coverage and lower OAR doses).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Impact of dosimetric differences between CT and MRI derived target volumes for external beam cervical cancer radiotherapy

Batumalai

Burke

Roach

et al. 2020

The British Journal of Radiology

Self Cite

View full text Add to dashboard Cite

Objectives: The use of MRI is becoming more prevalent in cervical cancer external beam radiotherapy (RT). The aim of this study was to investigate the impact of dosimetric differences between CT and MRI-derived target volumes for cervical cancer external beam RT. Methods: An automated planning technique for volumetric modulated arc therapy was developed. Two automated planning plans were generated for 18 cervical cancer patients where planning target volumes (PTVs) were generated based on CT or MRI data alone. Dose metrics for planning target volumes and organs at risk (OARs) were compared to analyse any differences based on imaging modality. Results: All treatment plans were clinically acceptable. Bladder doses (V40) were lower in MRI-based plans (p = 0.04, 53.6 ± 17.2 % vs 60.3 ± 13.1 % for MRI vs CT, respectively). The maximum dose for left iliac crest showed lower doses in CT-based plans (p = 0.02, 47.8 ± 0.7 Gy vs 47.4 ± 0.4 Gy MRI vs CT, respectively). No significant differences were seen for other OARs. Conclusions: The dosimetric differences of CT- and MRI-based contouring variability for this study was small. CT remains the standard imaging modality for volume delineation for these patients. Advances in knowledge: This is the first study to evaluate the dosimetric implications of imaging modality on target and OAR doses in cervical cancer external beam RT.

show abstract

Automatic segmentation of tumour and organs at risk in 3D MRI for cervical cancer radiation therapy with anatomical variations

Leung,

Chandra,

Lim

et al. 2024

Phys Eng Sci Med

Self Cite

View full text Add to dashboard Cite

Cervical cancer is a common cancer in women globally, with treatment usually involving radiation therapy (RT). Accurate segmentation for the tumour site and organ-at-risks (OARs) could assist in the reduction of treatment side effects and improve treatment planning efficiency. Cervical cancer Magnetic Resonance Imaging (MRI) segmentation is challenging due to a limited amount of training data available and large inter- and intra- patient shape variation for OARs. The proposed Masked-Net consists of a masked encoder within the 3D U-Net to account for the large shape variation within the dataset, with additional dilated layers added to improve segmentation performance. A new loss function was introduced to consider the bounding box loss during training with the proposed Masked-Net. Transfer learning from a male pelvis MRI data with a similar field of view was included. The approaches were compared to the 3D U-Net which was widely used in MRI image segmentation. The data used consisted of 52 volumes obtained from 23 patients with stage IB to IVB cervical cancer across a maximum of 7 weeks of RT with manually contoured labels including the bladder, cervix, gross tumour volume, uterus and rectum. The model was trained and tested with a 5-fold cross validation. Outcomes were evaluated based on the Dice Similarity Coefficients (DSC), the Hausdorff Distance (HD) and the Mean Surface Distance (MSD). The proposed method accounted for the small dataset, large variations in OAR shape and tumour sizes with an average DSC, HD and MSD for all anatomical structures of 0.790, 30.19mm and 3.15mm respectively.

show abstract

Dedicated MRI simulation for cervical cancer radiation treatment planning: Assessing the impact on clinical target volume delineation

Cited by 9 publications

References 25 publications

Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges

Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges

Impact of dosimetric differences between CT and MRI derived target volumes for external beam cervical cancer radiotherapy

Automatic segmentation of tumour and organs at risk in 3D MRI for cervical cancer radiation therapy with anatomical variations

Contact Info

Product

Resources

About