Dose prediction for cervical cancer VMAT patients with a full-scale 3D-cGAN-based model and the comparison of different input data on the prediction results

Zhang, Gongsen; Jiang, Zejun; Zhu, Jian; Wang, Linlin

doi:10.1186/s13014-022-02155-7

Cited by 6 publications

(14 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to statistics, radiotherapists spend an average of 4 hours delineating the target volume plan and organs at risk, and it can also be delayed further by some complex illnesses. After this, the medical physicists formulate an RT plan which complies with treatment standards, which takes approximately 10 hours per patient [ 40 , 41 ]. A large amount of time required for planning inevitably leads to a delay in treatment, which then affects the quality of treatment and the prognosis of the patients [ 42 ].…”

Section: Discussionmentioning

confidence: 99%

“…A large amount of time required for planning inevitably leads to a delay in treatment, which then affects the quality of treatment and the prognosis of the patients [ 42 ]. In the future, based on steep learning networks and optimisation algorithms, like the voxel dose restriction optimisation model or setting up predicted Dose Volume Histograms-aided targets, it will allow the development of an automated planning system that will ultimately serve the doctors and physicists, balancing the cost of time and precision [ 41 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Cost analysis of three-dimensional radiation therapy versus intensitymodulated chemoradiotherapy for locally advanced cervical cancer in Peruvian citizens

Díaz¹

2023

ecancer

View full text Add to dashboard Cite

Background and objectives:The standard treatment for locally advanced cervical cancer (CC) is chemoradiotherapy (CTRT) followed by high-dose-rate brachytherapy (HDRBT). The ideal scenario would be under novel intensity-modulated radiation therapy (IMRT) volumetric-modulated arc therapy (VMAT) radiation techniques over three-dimensional (3D) radiation therapy. However, radiotherapy (RT) centres in low-and middle-income countries have limited equipment for teletherapy services like HDRBT. This is why the 3D modality is still in use. The objective of this study was to analyse costs in a comparison of 3D versus IMRT versus VMAT based on clinical staging. Materials and methods:From 02/01/2022 to 05/01/2023 a prospective registry of the costs for oncological management was carried out for patients with locally advanced CC who received CTRT ± HDRBT. This included the administration of radiation with chemotherapy. The cost associated with patient and family transfers and hours in the hospital was also identified. These expenses were used to project the direct and indirect costs of 3D versus IMRT versus VMAT. Results:The treatment regimens for stage IIIC2, including 3D and novel techniques, are those with the highest costs.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Cost analysis of three-dimensional radiation therapy versus intensitymodulated chemoradiotherapy for locally advanced cervical cancer in Peruvian citizens

Díaz¹

2023

ecancer

View full text Add to dashboard Cite

show abstract

“…Specifically, we have investigated the use of deep‐learning dose prediction to drive plan quality improvements for external beam radiotherapy for the treatment of gynecologic cancers. To date, 3D dose prediction for external‐beam radiotherapy of the female pelvis has not been widely studied 27,32,33 …”

Section: Introductionmentioning

confidence: 99%

“…To date, 3D dose pre-diction for external-beam radiotherapy of the female pelvis has not been widely studied. 27,32,33 The purpose of this study was to predict high-quality dose distributions for volumetric modulated arc therapy (VMAT) plans for patients with gynecologic cancers and to evaluate the usability of the predicted dose distributions in improving clinical plan quality. To the best of our knowledge, this is the first deep-learning dose prediction study to include a physician review of the dose predictions and to test the achievability of the predicted dose distributions in cases in which the predictions showed higher quality distributions (i.e., more sparing of normal tissue) than the original plans.…”

Section: Introductionmentioning

confidence: 99%

“…Geometric models that correlate patient geometry with achievable dose‐volume histograms (DVHs) 4–8 are advantageous for patient‐specific treatment plan quality assurance 9–11 . With the advent of deep learning, more advanced models that enable the prediction of entire 3D dose distributions have been developed in recent years 12–33 . The potential of deep learning–based dose prediction to develop patient‐specific plan quality assurance tools should be further investigated.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning–based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers

Gronberg,

Jhingran,

Netherton

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundIn recent years, deep‐learning models have been used to predict entire three‐dimensional dose distributions. However, the usability of dose predictions to improve plan quality should be further investigated.PurposeTo develop a deep‐learning model to predict high‐quality dose distributions for volumetric modulated arc therapy (VMAT) plans for patients with gynecologic cancer and to evaluate their usability in driving plan quality improvements.MethodsA total of 79 VMAT plans for the female pelvis were used to train (47 plans), validate (16 plans), and test (16 plans) 3D dense dilated U‐Net models to predict 3D dose distributions. The models received the normalized CT scan, dose prescription, and target and normal tissue contours as inputs. Three models were used to predict the dose distributions for plans in the test set. A radiation oncologist specializing in the treatment of gynecologic cancers scored the test set predictions using a 5‐point scale (5, acceptable as‐is; 4, prefer minor edits; 3, minor edits needed; 2, major edits needed; and 1, unacceptable). The clinical plans for which the dose predictions indicated that improvements could be made were reoptimized with constraints extracted from the predictions.ResultsThe predicted dose distributions in the test set were of comparable quality to the clinical plans. The mean voxel‐wise dose difference was −0.14 ± 0.46 Gy. The percentage dose differences in the predicted target metrics of and were −1.05% ± 0.59% and 0.21% ± 0.28%, respectively. The dose differences in the predicted organ at risk mean and maximum doses were −0.30 ± 1.66 Gy and −0.42 ± 2.07 Gy, respectively. A radiation oncologist deemed all of the predicted dose distributions clinically acceptable; 12 received a score of 5, and four received a score of 4. Replanning of flagged plans (five plans) showed that the original plans could be further optimized to give dose distributions close to the predicted dose distributions.ConclusionsDeep‐learning dose prediction can be used to predict high‐quality and clinically acceptable dose distributions for VMAT female pelvis plans, which can then be used to identify plans that can be improved with additional optimization.

show abstract

Selenium‐Doped Nanoheterojunctions for Highly Efficient Cancer Radiosensitization

Qiao,

Yuan,

Yang

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Exploring efficient and low‐toxicity radiosensitizers to break through the bottleneck of radiation tolerance, immunosuppression and poor prognosis remains one of the critical developmental challenges in radiotherapy. Nanoheterojunctions, due to their unique physicochemical properties, have demonstrated excellent radiosensitization effects in radiation energy deposition and in lifting tumor radiotherapy inhibition. Herein, they doped selenium (Se) into prussian blue (PB) to construct a nano‐heterojunction (Se@PB), which could promote the increase of Fe2+/Fe3+ ratio and conversion of Se to a high valence state with Se introduction. The Fe2+‐Se‐Fe3+ electron transfer chain accelerates the rate of electron transfer on the surface of the nanoparticles, which in turn endows it with efficient X‐ray energy transfer and electron transport capability, and enhances radiotherapy physical sensitivity. Furthermore, Se@PB induces glutathione (GSH) depletion and Fe2+ accumulation through pro‐Fenton reaction, thereby disturbs the redox balance in tumor cells and enhances biochemical sensitivity of radiotherapy. As an excellent radiosensitizer, Se@PB effectively enhances X‐ray induced mitochondrial dysfunction and DNA damage, thereby promotes cell apoptosis and synergistic cervical cancer radiotherapy. This study elucidates the radiosensitization mechanism of Se‐doped nanoheterojunction from the perspective of the electron transfer chain and biochemistry reaction, which provides an efficient and low‐toxic strategy in radiotherapy.

show abstract

Dose prediction for cervical cancer VMAT patients with a full-scale 3D-cGAN-based model and the comparison of different input data on the prediction results

Cited by 6 publications

References 54 publications

Cost analysis of three-dimensional radiation therapy versus intensitymodulated chemoradiotherapy for locally advanced cervical cancer in Peruvian citizens

Cost analysis of three-dimensional radiation therapy versus intensitymodulated chemoradiotherapy for locally advanced cervical cancer in Peruvian citizens

Deep learning–based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers

Selenium‐Doped Nanoheterojunctions for Highly Efficient Cancer Radiosensitization

Contact Info

Product

Resources

About