Knowledge-based isocenter selection in radiosurgery planning

Deep learning-based optimization of field geometry for total marrow irradiation delivered with volumetric modulated arc therapy

BACKGROUND

Total marrow (lymphoid) irradiation (TMI/TMLI) is a radiotherapy treatment used to selectively target the bone marrow and lymph nodes in conditioning regimens for allogeneic hematopoietic stem cell transplantation. A complex field geometry is needed to cover the large planning target volume (PTV) of TMI/TMLI with volumetric modulated arc therapy (VMAT). Five isocenters and ten overlapping fields are needed for the upper body, while, for patients with large anatomical conformation, two specific isocenters are placed on the arms. The creation of a field geometry is clinically challenging and is performed by a medical physicist (MP) specialized in TMI/TMLI.

PURPOSE

To develop convolutional neural networks (CNNs) for automatically generating the field geometry of TMI/TMLI.

METHODS

The dataset comprised 117 patients treated with TMI/TMLI between 2011 and 2023 at our Institute. The CNN input image consisted of three channels, obtained by projecting along the sagittal plane: (1) average CT pixel intensity within the PTV; (2) PTV mask; (3) brain, lungs, liver, bowel, and bladder masks. This "averaged" frontal view combined the information analyzed by the MP when setting the field geometry in the treatment planning system (TPS). Two CNNs were trained to predict the isocenters coordinates and jaws apertures for patients with (CNN-1) and without (CNN-2) isocenters on the arms. Local optimization methods were used to refine the models output based on the anatomy of the patient. Model evaluation was performed on a test set of 15 patients in two ways: (1) by computing the root mean squared error (RMSE) between the CNN output and ground truth; (2) with a qualitative assessment of manual and generated field geometries-scale: 1 = not adequate, 4 = adequate-carried out in blind mode by three MPs with different expertise in TMI/TMLI. The Wilcoxon signed-rank test was used to evaluate the independence of the given scores between manual and generated configurations (p < 0.05 significant).

RESULTS

The average and standard deviation values of RMSE for CNN-1 and CNN-2 before/after local optimization were 15 ± 2/13 ± 3 mm and 16 ± 2/18 ± 4 mm, respectively. The CNNs were integrated into a planning automation software for TMI/TMLI such that the MPs could analyze in detail the proposed field geometries directly in the TPS. The selection of the CNN model to create the field geometry was based on the PTV width to approximate the decision process of an experienced MP and provide a single option of field configuration. We found no significant differences between the manual and generated field geometries for any MP, with median values of 4 versus 4 (p = 0.92), 3 versus 3 (p = 0.78), 4 versus 3 (p = 0.48), respectively. Starting from October 2023, the generated field geometry has been introduced in our clinical practice for prospective patients.

CONCLUSIONS

The generated field geometries were clinically acceptable and adequate, even for an MP with high level of expertise in TMI/TMLI. Incorporating the knowledge of the MPs into the development cycle was crucial for optimizing the models, especially in this scenario with limited data.

Knowledge-based planning for Gamma Knife

BACKGROUND

Current methods for Gamma Knife (GK) treatment planning utilizes either manual forward planning, where planners manually place shots in a tumor to achieve a desired dose distribution, or inverse planning, whereby the dose delivered to a tumor is optimized for multiple objectives based on established metrics. For other treatment modalities like IMRT and VMAT, there has been a recent push to develop knowledge-based planning (KBP) pipelines to address the limitations presented by forward and inverse planning. However, no complete KBP pipeline has been created for GK.

PURPOSE

To develop a novel (KBP) pipeline, using inverse optimization (IO) with 3D dose predictions for GK.

METHODS

Data were obtained for 349 patients from Sunnybrook Health Sciences Centre. A 3D dose prediction model was trained using 322 patients, based on a previously published deep learning methodology, and dose predictions were generated for the remaining 27 out-of-sample patients. A generalized IO model was developed to learn objective function weights from dose predictions. These weights were then used in an inverse planning model to generate deliverable treatment plans. A dose mimicking (DM) model was also implemented for comparison. The quality of the resulting plans was compared to their clinical counterparts using standard GK quality metrics. The performance of the models was also characterized with respect to the dose predictions.

RESULTS

Across all quality metrics, plans generated using the IO pipeline performed at least as well as or better than the respective clinical plans. The average conformity and gradient indices of IO plans was 0.737 ± $\pm$ 0.158 and 3.356 ± $\pm$ 1.030 respectively, compared to 0.713 ± $\pm$ 0.124 and 3.452 ± $\pm$ 1.123 for the clinical plans. IO plans also performed better than DM plans for five of the six quality metrics. Plans generated using IO also have average treatment times comparable to that of clinical plans. With regards to the dose predictions, predictions with higher conformity tend to result in higher quality KBP plans.

CONCLUSIONS

Plans resulting from an IO KBP pipeline are, on average, of equal or superior quality compared to those obtained through manual planning. The results demonstrate the potential for the use of KBP to generate GK treatment with minimal human intervention.

Impact of ovary-sparing treatment planning on plan quality, treatment time and gamma passing rates in intensity-modulated radiotherapy for stage I/II cervical cancer

BACKGROUND

This study aimed to investigate the impact of ovary-sparing intensity-modulated radiotherapy (IMRT) on plan quality, treatment time, and gamma passing rates for stage I/II cervical cancer patients.

METHODS

Fifteen stage I/II cervical cancer patients were retrospectively enrolled, and a pair of clinically suitable IMRT plans were designed for each patient, with (Group A) and without (Group B) ovary-sparing. Plan factors affecting plan quality, treatment time, and gamma passing rates, including the number of segments, monitor units, percentage of small-area segments (field area < 20 cm2), and percentage of small-MU segments (MU < 10), were compared and statistically analyzed. Key plan quality indicators, including ovarian dose, target dose coverage (D98%, D95%, D50%, D2%), conformity index, and homogeneity index, were evaluated and statistically assessed. Treatment time and gamma passing rates collected by IBA MatriXX were also compared.

RESULTS

The median ovarian dose in Group A and Group B was 7.61 Gy (range 6.71-8.51 Gy) and 38.52 Gy (range 29.84-43.82 Gy), respectively. Except for monitor units, all other plan factors were significantly lower in Group A than in Group B (all P < .05). Correlation coefficients between plan factors, treatment time, and gamma passing rates that were statistically different were all negative. Both Groups of plans met the prescription requirement (D95% ≥ 45.00 Gy) for clinical treatment. D98% was smaller for Group A than for Group B (P < .05); D50% and D2% were larger for Group A than for Group B (P < .05, P < .05). Group A plans had worse conformity index and homogeneity index than Group B plans (P < .05, P < .05). Treatment time did not differ significantly (P > .05). Gamma passing rates in Group A were higher than in Group B with the criteria of 2%/3 mm (P < .05) and 3%/2 mm (P < .05).

CONCLUSION

Despite the slightly decreased quality of the treatment plans, the ovary-sparing IMRT plans exhibited several advantages including lower ovarian dose and plan complexity, improved gamma passing rates, and a negligible impact on treatment time.