ESTRO 2023 - Abstract Book

S1309

Digital Posters

ESTRO 2023

The mean age at treatment was 51.3 years, 43% of these patients were female, median follow-up time was 87 months. Out of the 150 patients: 34,2% had cervical cancer, 43,3% had prostate cancer, intensity-modulated radiation therapy was used in 31,7% of the cases. 3,5% had stereotactic pelvic radiotherapy. The mean prescribed radiation dose was 64.3 +5.8Gy (EQ2D), conventional fractionation was used for 95,4% of the patients. The average maximum dose to the lumbosacral plexus (average Dmax) was 49Gy+ 13,5, the average volume receiving 50 Gy (V50Gy) was 15.6%. only 8% of the patients had clinical symptoms of lumbo-sacral plexopathy (all Grade 3). LS doses exceeded 70Gy in 41.7% of patients with neurologic toxicity. All symptomatic patients were associated with LS doses above 70Gy. The median and mean LS doses in patients with neurological toxicity (73.9 Gy and 72.5 Gy respectively) were significantly higher than the median and mean LS doses in patients without neurological toxicity (63.9 Gy and 59.1 Gy respectively ( p=O.0015). Gender and diabetes were significant predictors of radiation induced plexopathy. Conclusion Given this high correlation between dosimetric data and radiation-induced lumbo sacral plexopathy in symptomatic patients, we encourage the documentation of lumbo sacral plexus doses by systematically delineating it during pelvic irradiations.

Poster (Digital): Automation

PO-1614 Head and Neck high-risk lymph nodes detection – a three-dimensional deep learning proposal

T. Yu 1 , Y. Lin 2,3,4 , Y. Lu 2 , C. Huang 5 , W. Yan 6

1 Taichung Veterans Genearl Hospital, Department of Psychiatry, Taichung, Taiwan; 2 Taichung Veterans General Hospital, Department of Radiation Oncology, Taichung, Taiwan; 3 National Yang Ming Chiao Tung University, Institute of Computer Science and Engineering, Taichung, Taiwan; 4 National Yang Ming Chiao Tung University, Department of Computer Science, Hsinchu, Taiwan; 5 National Chung Hsing University, Department of Computer Science and Engineering, Taichung, Taiwan; 6 University Of Kentucky, Department of Radiation ONcology, Lexington, USA Purpose or Objective Nowadays, automated normal organ segmentation by deep learning model is mature, economic efficient and clinically adapted world-wide. When talking about contouring cancerous lesion, it remains state of the art. In our previous works, we successfully recognized metastatic lymph nodes from reactive ones from Head and Neck tomography. To make the workflow more automatically, we experimental several deep learning model to find out best one for high-risk lymph nodes instance detection from pre-treatment tomography. Materials and Methods We retrospectively collected newly diagnosed head and neck cancer patient. Collect pre-treatment contrast-enhanced tomography. Correlate with pathology report. Label lymph nodes status as (1) metastasis-positive, extranodal-extention positive (LNM+, ENE+) (2) metastasis-positive, extranodal-extention-negative (LNM+, ENE-) or (3) metastasis-negative (LNM- ). If the lymph node did note been dissected, then this node is excluded from our research. If the lymph node cannot be recognized by or neck level, it will be excluded. The recognized lymph nodes then contoured and labels by two Radiation Oncologists. The model performance is evaluated by mean average precision (mAP) under intersection over union (IoU) threshold 0.6. Results From 2019-2021, 158 patients with 158 CT scans meet our criteria. The median duration from CT scan to surgery was 10 days (range: 1–28 days). Following pathologic correlation with CT scans, 350 lymph nodes were segmented in total (range: 1–8 per patient): 241 negative nodes, 111 nodes contained tumor cells. In the metastasis-positive nodes, 56 were ENE positive and 55 were ENE-negative. Diameters of LNM- nodes were 22mm-62mm and LNM+ ones were 28mm-131mm, separately. We set the high-risk threshold as beyond 28mm diameters in any axis. In our dataset, 234 nodes assigned as high-risk and 116 were low-risk. After data augmentation, the dataset were divided into train, validation and test set as 7:1:2 ratio. The mAP of hierarchical LSTM was 0.89. Conclusion Hierarchical LSTM based deep learning model served as a useful tool for head and neck lymph node detection. Further external validation is needed before deployed into clinical use. This work was supported in part by the National Science and Technology Council, Taiwan under Grant of NSTC 111-2634-F 006-012

PO-1615 Automated treatment planning – Three-year clinical summary of dosimetry and user experience

J. wu 1 , Y. sheng 2 , S. yoo 2 , X. li 2 , F. yin 2 , Q. wu 2

1 Duke University, radiation oncology, durham, USA; 2 duke university, radiation oncology, durham, USA

Purpose or Objective In the past five years, we have commissioned and clinically implemented artificial intelligence (AI) tools for automatic radiation treatment planning. We report our prospective data analysis and user experience from 2019-2021.

Materials and Methods