Implement a knowledge-based automated dose volume histogram prediction module in Pinnacle3 treatment planning system for plan quality assurance and guidance

Clinical implementation and evaluation of deep learning-assisted automatic radiotherapy treatment planning for lung cancer

PURPOSE

The purpose of the study is to investigate the clinical application of deep learning (DL)-assisted automatic radiotherapy planning for lung cancer.

METHODS

A DL model was developed for predicting patient-specific doses, trained and validated on a dataset of 235 patients with diverse target volumes and prescriptions. The model was integrated into clinical workflow with DL-predicted objective functions. The automatic plans were retrospectively designed for additional 50 treated manual volumetric modulated arc therapy (VMAT) plans. A comparison was made between automatic and manual plans in terms of dosimetric indexes, monitor units (MUs) and planning time. Plan quality metric (PQM) encompassing these indexes was evaluated, with higher PQM values indicating superior plan quality. Qualitative evaluations of two plans were conducted by four reviewers.

RESULTS

The PQM score was 40.7 ± 13.1 for manual plans and 40.8 ± 13.5 for automatic plans (P = 0.75). Compared to manual plans, the targets coverage and homogeneity of automatic plans demonstrated no significant difference. Manual plans exhibited better sparing for lung in V5 (difference: 1.8 ± 4.2 %, P = 0.02), whereas automatic plans showed enhanced sparing for heart in V30 (difference: 1.4 ± 4.7 %, P = 0.02) and for spinal cord in Dmax (difference: 0.7 ± 4.7 Gy, P = 0.04). The planning time and MUs of automatic plans were significantly reduced by 70.5 ± 20.0 min and 97.4 ± 82.1. Automatic plans were deemed acceptable in 88 % of the reviews (176/200).

CONCLUSIONS

The DL-assisted approach for lung cancer notably decreased planning time and MUs, while demonstrating comparable or superior quality relative to manual plans. It has the potential to provide benefit to lung cancer patients.

A modified U-net with graph representation for dose prediction in esophageal cancer radiotherapy plans

The manual design of esophageal cancer radiotherapy plan is time-consuming and labor-intensive. Automatic planning (AP) is prevalent nowadays to increase physicists' work efficiency. Because of the intuitiveness of dose distribution in AP evaluation, obtaining reasonable dose prediction provides effective guarantees to generate a satisfactory AP. Existing fully convolutional network-based methods for predicting dose distribution in esophageal cancer radiotherapy plans often capture features in a limited receptive field. Additionally, the correlations between voxel pairs are often ignored. This work modifies the U-net architecture and exploits graph convolution to capture long-range information for dose prediction in esophageal cancer plans. Meanwhile, attention mechanism gets correlations between planning target volume (PTV) and organs at risk, and adaptively learns their feature weights. Finally, a novel loss function that considers features between voxel pairs is used to highlight the predictions. 152 subjects with prescription doses of 50 Gy or 60 Gy are collected in this study. The mean absolute error and standard deviation of conformity index, homogeneity index, and max dose for PTV achieved by the proposed method are 0.036 ± 0.030, 0.036 ± 0.027, and 0.930 ± 1.162, respectively, which outperform other state-of-the-art models. The superior performance demonstrates that our proposed method has great potential for AP generation.

Africa's readiness for artificial intelligence in clinical radiotherapy delivery: Medical physicists to lead the way

BACKGROUND

There have been several proposals by researchers for the introduction of Artificial Intelligence (AI) technology due to its promising role in radiotherapy practice. However, prior to the introduction of the technology, there are certain general recommendations that must be achieved. Also, the current challenges of AI must be addressed. In this review, we assess how Africa is prepared for the integration of AI technology into radiotherapy service delivery.

METHODS

To assess the readiness of Africa for integration of AI in radiotherapy services delivery, a narrative review of the available literature from PubMed, Science Direct, Google Scholar, and Scopus was conducted in the English language using search terms such as Artificial Intelligence, Radiotherapy in Africa, Machine Learning, Deep Learning, and Quality Assurance.

RESULTS

We identified a number of issues that could limit the successful integration of AI technology into radiotherapy practice. The major issues include insufficient data for training and validation of AI models, lack of educational curriculum for AI radiotherapy-related courses, no/limited AI teaching professionals, funding, and lack of AI technology and resources. Solutions identified to facilitate smooth implementation of the technology into radiotherapy practices within the region include: creating an accessible national data bank, integrating AI radiotherapy training programs into Africa's educational curriculum, investing in AI technology and resources such as electronic health records and cloud storage, and creation of legal laws and policies to support the use of the technology. These identified solutions need to be implemented on the background of creating awareness among health workers within the radiotherapy space.

CONCLUSION

The challenges identified in this review are common among all the geographical regions in the African continent. Therefore, all institutions offering radiotherapy education and training programs, management of the medical centers for radiotherapy and oncology, national and regional professional bodies for medical physics, ministries of health, governments, and relevant stakeholders must take keen interest and work together to achieve this goal.

The effect of integrating knowledge-based planning with multicriteria optimization in treatment planning for prostate SBRT

Knowledge-based planning (KBP) and multicriteria optimization (MCO) are two powerful tools to assist treatment planners in achieving optimal target coverage and organ-at-risk (OAR) sparing. The purpose of this work is to investigate if integrating MCO with conventional KBP can further improve treatment plan quality for prostate cancer stereotactic body radiation therapy (SBRT). A two-phase study was designed to investigate the impact of MCO and KBP in prostate SBRT treatment planning. The first phase involved the creation of a KBP model based on thirty clinical SBRT plans, generated by manual optimization (KBP_M). A ten-patient validation cohort was used to compare manual, MCO, and KBP_M optimization techniques. The next phase involved replanning the original model cohort with additional tradeoff optimization via MCO to create a second model, KBP_MCO. Plans were then generated using linear integration (KBP_M+MCO), non-linear integration (KBP_MCO), and a combination of integration methods (KBP_MCO+MCO). All plans were analyzed for planning target volume (PTV) coverage, OAR constraints, and plan quality metrics. Comparisons were generated to evaluate plan and model quality. Phase 1 highlighted the necessity of KBP and MCO in treatment planning, as both optimization methods improved plan quality metrics (Conformity and Heterogeneity Indices) and reduced mean rectal dose by 2 Gy, as compared to manual planning. Integrating MCO with KBP did not further improve plan quality, as little significance was seen over KBP or MCO alone. Principal component score (PCS) fitting showed KBP_MCO improved bladder and rectum estimated and modeled dose correlation by 5% and 22%, respectively; however, model improvements did not significantly impact plan quality. KBP and MCO have shown to reduce OAR dose while maintaining desired PTV coverage in this study. Further integration of KBP and MCO did not show marked improvements in treatment plan quality while requiring increased time in model generation and optimization time.

A novel knowledge-based prediction model for estimating an initial equivalent uniform dose in semi-auto-planning for cervical cancer

Background

We developed a novel concept, equivalent uniform length (EUL), to describe the relationship between the generalized equivalent uniform dose (EUD) and the geometric anatomy around a tumor target. By correlating EUL with EUD, we established two EUD–EUL knowledge-based (EEKB) prediction models for the bladder and rectum that predict initial EUD values for generating quality treatment plans.

Methods

EUL metrics for the rectum and bladder were extracted and collected from the intensity-modulated radiotherapy therapy (IMRT) plans of 60 patients with cervical cancer. The two EEKB prediction models were built using linear regression to establish the relationships between EUL_r and EUD_r (EUL and EUD of rectum) and EUL_b, and EUD_b (EUL and EUD of bladder), respectively. The EE plans were optimized by incorporating the predicted initial EUD parameters for the rectum and bladder with the conventional pinnacle auto-planning (PAP) initial dose parameters for other organs. The efficiency of the predicted initial EUD values were then evaluated by comparing the consistency and quality of the EE plans, PAP plans (based on default PAP initial parameters), and manual plans (designed manually by different dosimetrists) for a sample of 20 patients.

Results

Linear regression analyses showed a significant correlation between EUL and EUD (R² = 0.79 and 0.69 for EUD_b and EUD_r, respectively). In a sample of 20 patients, the average bladder V40 and V50 derived from the EE plans were significantly lower (V40: 30.00 ± 5.76, V50: 14.36 ± 4.00) than the V40 and V50 values derived from manual plans (V40: 36.03 ± 8.02, V50: 19.02 ± 5.42). Compared with the PAP plans, the EE plans produced significantly lower average V30 and Dmean values for the bladder (V30: 50.55 ± 6.33, Dmean: 31.48 ± 1.97 Gy).

Conclusions

Our EEKB prediction models predicted reasonable initial EUD values for the rectum and bladder based on patient-specific geometric EUL values, thereby improving optimization and planning efficiency.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-022-02120-4.

An Artificial Intelligence-Based Full-Process Solution for Radiotherapy: A Proof of Concept Study on Rectal Cancer

BACKGROUND AND PURPOSE

To develop an artificial intelligence-based full-process solution for rectal cancer radiotherapy.

MATERIALS AND METHODS

A full-process solution that integrates autosegmentation and automatic treatment planning was developed under a single deep-learning framework. A convolutional neural network (CNN) was used to generate segmentations of the target and the organs at risk (OAR) as well as dose distribution. A script in Pinnacle that simulates the treatment planning process was used to execute plan optimization. A total of 172 rectal cancer patients were used for model training, and 18 patients were used for model validation. Another 40 rectal cancer patients were used for an end-to-end evaluation for both autosegmentation and treatment planning. The PTV and OAR segmentation was compared with manual segmentation. The planning results was evaluated by both objective and subjective assessment.

RESULTS

The total time for full-process planning without contour modification was 7 min, and an additional 15 min may require for contour modification and re-optimization. The PTV DICE similarity coefficient was greater than 0.85 for all 40 patients in the evaluation dataset while the DICE indices of the OARs also indicated good performance. There were no significant differences between the auto plans and manual plans. The physician accepted 80% of the auto plans without any further operation.

CONCLUSION

We developed a deep learning-based automatic solution for rectal cancer treatment that can improve the efficiency of treatment planning.

Volumetric modulated arc therapy versus intensity-modulated proton therapy in neoadjuvant irradiation of locally advanced oesophageal cancer

Background

To investigate the role of intensity-modulated proton therapy (IMPT) compared to volumetric modulated arc therapy (VMAT), realised with RapidArc and RapidPlan methods (RA_RP) for neoadjuvant radiotherapy in locally advanced oesophagal cancer.

Methods

Twenty patients were retrospectively planned for IMPT (with two fields, (IMPT_2F) or with three fields (IMPT_3F)) and RA_RP and the results were compared according to dose-volume metrics. Estimates of the excess absolute risk (EAR) of secondary cancer induction were determined for the lungs. For the cardiac structures, the relative risk (RR) of coronary artery disease (CAD) and chronic heart failure (CHF) were estimated.

Results

Both the RA_RP and IMPT approached allowed to achieve the required coverage for the gross tumour volume, (GTV) and the clinical and the planning target volumes, CTV and PTV (V_98% > 98 for CTV and GTV and V_95% > 95 for the PTV)). The conformity index resulted in 0.88 ± 0.01, 0.89 ± 0.02 and 0.89 ± 0.02 for RA_RP, IMPT_2F and IMPT_3F respectively. With the same order, the homogeneity index for the PTV resulted in 5.6 ± 0.6%, 4.4 ± 0.9% and 4.5 ± 0.8%. Concerning the organs at risk, the IMPT plans showed a systematic and statistically significant incremental sparing when compared to RA_RP, especially for the heart. The mean dose to the combined lungs was 8.6 ± 2.9 Gy for RA_RP, 3.2 ± 1.5 Gy and 2.9 ± 1.2 Gy for IMPT_2F and IMPT_3F. The mean dose to the whole heart resulted to 9.9 ± 1.9 Gy for RA_RP compared to 3.7 ± 1.3 Gy or 4.0 ± 1.4 Gy for IMPT_2F or IMPT_3F; the mean dose to the left ventricle resulted to 6.5 ± 1.6 Gy, 1.9 ± 1.5 Gy, 1.9 ± 1.6 Gy respectively. Similar sparing effects were observed for the liver, the kidneys, the stomach, the spleen and the bowels.

The EAR per 10,000 patients-years of secondary cancer induction resulted in 19.2 ± 5.7 for RA_RP and 6.1 ± 2.7 for IMPT_2F or 5.7 ± 2.4 for IMPT_3F. The RR for the left ventricle resulted in 1.5 ± 0.1 for RA_RP and 1.1 ± 0.1 for both IMPT sets. For the coronaries, the RR resulted in 1.6 ± 0.4 for RA_RP and 1.2 ± 0.3 for protons.

Conclusion

With regard to cancer of the oesophagogastric junction type I and II, the use of intensity-modulated proton therapy seems to have a clear advantage over VMAT. In particular, the reduction of the heart and abdominal structures dose could result in an optimised side effect profile. Furthermore, reduced risk of secondary neoplasia in the lung can be expected in long-term survivors and would be a great gain for cured patients.