Automatização da Determinação dos Campos na Radioterapia de Mama: Desenvolvimento e Comparação entre Dois Algoritmos

Rivelli Rodrigues Zaratim, Giulianne; Bicudo dos Santos, Leonardo; Gomes dos Reis, Ricardo; Oliveira e Silva, Luis Felipe

doi:10.29384/rbfm.2023.v17.19849001720

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This involved calculating the intersection area between the planning target volume (PTV) and the ipsilateral lung for various angles in the Beam's Eye View projection. 21 For medial tangents, angles were explored between 295−330° for the left breast and 25−70° for the right breast. Lateral tangents were considered between 110−150° for the left breast and 200−245° for the right breast.…”

Section: Methodsmentioning

confidence: 99%

Automated treatment planning for whole breast irradiation with individualized tangential IMRT fields

Zaratim,

dos Reis,

dos Santos

et al. 2024

J Applied Clin Med Phys

Self Cite

View full text Add to dashboard Cite

PurposesThis study aimed to develop and validate algorithms for automating intensity modulated radiation therapy (IMRT) planning in breast cancer patients, with a focus on patient anatomical characteristics.Material and MethodsWe retrospectively selected 400 breast cancer patients without lymph node involvement for automated treatment planning. Automation was achieved using the Eclipse Scripting Application Programming Interface (ESAPI) integrated into the Eclipse Treatment Planning System. We employed three beam insertion geometries and three optimization strategies, resulting in 3600 plans, each delivering a 40.05 Gy dose in 15 fractions. Gantry angles in the tangent fields were selected based on a criterion involving the minimum intersection area between the Planning Target Volume (PTV) and the ipsilateral lung in the Beam's Eye View projection. ESAPI was also used to gather patient anatomical data, serving as input for Random Forest models to select the optimal plan. The Random Forest classification considered both beam insertion geometry and optimization strategy. Dosimetric data were evaluated in accordance with the Radiation Therapy Oncology Group (RTOG) 1005 protocol.ResultsOverall, all approaches generated high‐quality plans, with approximately 94% meeting the acceptable dose criteria for organs at risk and/or target coverage as defined by RTOG guidelines. Average automated plan generation time ranged from 6 min and 37 s to 9 min and 22 s, with the mean time increasing with additional fields. The Random Forest approach did not successfully enable automatic planning strategy selection. Instead, our automated planning system allows users to choose from the tested geometry and strategy options.ConclusionsAlthough our attempt to correlate patient anatomical features with planning strategy using machine learning tools was unsuccessful, the resulting dosimetric outcomes proved satisfactory. Our algorithm consistently produced high‐quality plans, offering significant time and efficiency advantages.

show abstract

Section: Methodsmentioning

confidence: 99%

Automated treatment planning for whole breast irradiation with individualized tangential IMRT fields

Zaratim,

dos Reis,

dos Santos

et al. 2024

J Applied Clin Med Phys

Self Cite

View full text Add to dashboard Cite

show abstract

Fluence smoothing evaluation for whole‐breast automatically generated treatment plans

Zaratim,

Oliveira e Silva,

dos Reis

et al. 2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

PurposeThis study aimed to identify the fluence smoothing threshold that preserves the dosimetric quality of planning for breast cancer intensity‐modulated radiation therapy (IMRT).Material and methodsWe conducted automated treatment planning for 60 breast cancer patients using the Eclipse Scripting Application Programming Interface. The plans included four‐field IMRT, emphasizing smoothing weight combinations while maintaining a 4:3 aspect ratio between the X and Y directions. Four weight sets (40 × 30, 100 × 75, 150 × 115.2, and 200 × 150) were tested, resulting in four plans per patient. A total dose of 40.05 Gy over 15 fractions was prescribed. Optimization weigths were dynamically adjusted based on dosimetric evaluations, with the maximum coverage priority set at 200. Statistical analyses were used to assess the dosimetric data.ResultsThe median planning target volume (PTV) coverage varied across smoothing levels, with default smoothing (40 × 30) providing superior median PTV coverage. Lung constraints showed significant differences mainly at higher smoothing levels. Heart constraints exhibited less variation between smoothing levels, with significant differences primarily in the maximum and mean doses for right‐sided patients and between default and higher smoothing levels for left‐sided patients. No significant differences were observed in contralateral breast constraints among all smoothing levels, except at the maximum level for right‐sided patients. Monitor units decreased with increasing smoothing weight, showing significant differences between default and other settings. For right‐sided patients, the median number of monitor units varied from 1346 (40 × 30) to 754 (200 × 150), and for left‐sided patients, from 1333 (40 × 30) to 804 (200 × 150). Chi‐square tests revealed differences in dose constraint adherence between default and maximum smoothing levels, particularly in target coverage.ConclusionOur findings suggest that using a ratio of smoothing weights to target priorities between 1:1.5 and 1:1.6 leads to a favorable balance between complexity and dosimetric plan quality, with no significant impacts on dose constraint adherence.

show abstract

Automatização da Determinação dos Campos na Radioterapia de Mama: Desenvolvimento e Comparação entre Dois Algoritmos

Cited by 2 publications

References 13 publications

Automated treatment planning for whole breast irradiation with individualized tangential IMRT fields

Automated treatment planning for whole breast irradiation with individualized tangential IMRT fields

Fluence smoothing evaluation for whole‐breast automatically generated treatment plans

Contact Info

Product

Resources

About