Dataset Information

Artificial intelligence based treatment planning of radiotherapy for locally advanced breast cancer.

ABSTRACT: Background and purpose:Treatment planning of radiotherapy for locally advanced breast cancer patients can be a time consuming process. Artificial intelligence based treatment planning could be used as a tool to speed up this process and maintain plan quality consistency. The purpose of this study was to create treatment plans for locally advanced breast cancer patients using a Convolutional Neural Network (CNN). Materials and methods:Data of 60 patients treated for left-sided breast cancer was used with a training, validation and test split of 36/12/12, respectively. The in-house built CNN model was a hierarchically densely connected U-net (HD U-net). The inputs for the HD U-net were 2D distance maps of the relevant regions of interest. Dose predictions, generated by the HD U-net, were used for a mimicking algorithm in order to create clinically deliverable plans. Results:Dose predictions were generated by the HD U-net and mimicked using a commercial treatment planning system. The predicted plans fulfilling all clinical goals while showing small (≤0.5 Gy) statistically significant differences (p < 0.05) in the doses compared to the manual plans. The mimicked plans show statistically significant differences in the average doses for the heart and lung of ≤0.5 Gy and a reduced D2% of all PTVs. In total, ten of the twelve mimicked plans were clinically acceptable. Conclusions:We created a CNN model which can generate clinically acceptable plans for left-sided locally advanced breast cancer patients. This model shows great potential to speed up the treatment planning process while maintaining consistent plan quality.

SUBMITTER: van de Sande D

PROVIDER: S-EPMC8645926 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundTo investigate the feasibility of a knowledge-based automated intensity-modulated radiation therapy (IMRT) planning technique for locally advanced nasopharyngeal carcinoma (NPC) radiotherapy.MethodsOne hundred forty NPC patients treated with definitive radiation therapy with the step-and-shoot IMRT techniques were retrospectively selected and separated into a knowledge library (n = 115) and a test library (n = 25). For each patient in the knowledge library, the overlap volume histogram (OVH), target volume histogram (TVH) and dose objectives were extracted from the manually generated plan. 5-fold cross validation was performed to divide the patients in the knowledge library into 5 groups before validating one group by using the other 4 groups to train each neural network (NN) machine learning models. For patients in the test library, their OVH and TVH were then used by the trained models to predict a corresponding set of mean dose objectives, which were subsequently used to generate automated plans (APs) in Pinnacle planning system via an in-house developed automated scripting system. All APs were obtained after a single step of optimization. Manual plans (MPs) for the test patients were generated by an experienced medical physicist strictly following the established clinical protocols. The qualities of the APs and MPs were evaluated by an attending radiation oncologist. The dosimetric parameters for planning target volume (PTV) coverage and the organs-at-risk (OAR) sparing were also quantitatively measured and compared using Mann-Whitney U test and Bonferroni correction.ResultsAPs and MPs had the same rating for more than 80% of the patients (19 out of 25) in the test group. Both AP and MP achieved PTV coverage criteria for no less than 80% of the patients. For each OAR, the number of APs achieving its criterion was similar to that in the MPs. The AP approach improved planning efficiency by greatly reducing the planning duration to about 17% of the MP (9.85 ± 1.13 min vs. 57.10 ± 6.35 min).ConclusionA robust and effective knowledge-based IMRT treatment planning technique for locally advanced NPC is developed. Patient specific dose objectives can be predicted by trained NN models based on the individual's OVH and clinical TVH goals. The automated planning scripts can use these dose objectives to efficiently generate APs with largely shortened planning time. These APs had comparable dosimetric qualities when compared to our clinic's manual plans.

Project description:BACKGROUND:Radiation therapy is an indispensable part of various treatment modalities for breast cancer. Specifically, for non-inflammatory locally advanced breast cancer (LABC) patients, preoperative radiotherapy (pRT) is currently indicated as a second line therapy in the event of lack of response to neoadjuvant chemotherapy. Still approximately one third of patients fails to respond favourably to pRT. The aim of this study was to explore molecular mechanisms underlying differential response to radiotherapy (RT) to identify predictive biomarkers and potential targets for increasing radiosensitivity. METHODS:The study was based on a cohort of 134 LABC patients, treated at the Institute of Oncology and Radiology of Serbia (IORS) with pRT, without previous or concomitant systemic therapy. Baseline transcriptional profiles were established using Agilent 60 K microarray platform in a subset of 23 formalin-fixed paraffin-embedded (FFPE) LABC tumour samples of which 11 radiotherapy naïve and 3 post-radiotherapy samples passed quality control and were used for downstream analysis. Biological networks and signalling pathways underlying differential response to RT were identified using Ingenuity Pathways Analysis software. Predictive value of candidate genes in the preoperative setting was further validated by qRT-PCR in an independent subset of 60 LABC samples of which 42 had sufficient quality for data analysis, and in postoperative setting using microarray data from 344 node-negative breast cancer patients (Erasmus cohort, GSE2034 and GSE5327) treated either with surgery only (20%) or surgery with RT (80%). RESULTS:We identified 192 significantly differentially expressed genes (FDR < 0.10) between pRT-responsive and non-responsive tumours, related to regulation of cellular development, growth and proliferation, cell cycle control of chromosomal replication, glucose metabolism and NAD biosynthesis II route. APOA1, MAP3K4, and MMP14 genes were differentially expressed (FDR < 0.20) between pRT responders and non-responders in preoperative setting, while MAP3K4 was further validated as RT-specific predictive biomarker of distant metastasis free survival (HR = 2.54, [95%CI:1.42-4.55], p = 0.002) in the postoperative setting. CONCLUSIONS:This study pinpoints MAP3K4 as a putative biomarker of response to RT in both preoperative and postoperative settings and a potential target for radiosensitising combination therapy, warranting further pre-clinical studies and prospective clinical validation.

Dataset Information

Artificial intelligence based treatment planning of radiotherapy for locally advanced breast cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets