ESTRO 2023 - Abstract Book
S930
Digital Posters
ESTRO 2023
TMI plans, the coverage to lymph node might be lower than TMLI and its clinical significance is unknown. In the current study, we aimed to develop a deep learning model for automatic delineation of whole regional lymph nodes and assess the dose coverage of lymph nodes with TMI plans using the model. Materials and Methods Whole regional lymph nodes (cervical, axillary, mediastinal, para-aortic, common iliac, external iliac, internal iliac, obturator, presacral, inguinal lymph nodes) were manually contoured by 3 radiation oncologists in 26 patients having whole body computed tomography (CT) images. Twenty patients were designated as the training/validation set and 6 patients as the testing set, and model was developed using the 'nnUNET' framework. The trained model was evaluated with dice coefficient score (DCS), precision, and recall. In addition, dose coverage of the automatically or manually delineated lymph nodes in TMI plans was calculated. Results The mean value of DCS, precision, and recall of the trained model was 0.76 (range, 0.65-0.85), 0.81 (range, 0.75-0.90), and 0.74 (range, 0.59-0.85), respectively. DSC Precision Recall Inguinal 0.8479 0.8989 0.8062 Axillary 0.8246 0.8087 0.8502 Cervical 0.8152 0.7962 0.8388
External iliac 0.7882 0.8451 0.7455 Para-aortic 0.7808 0.8844 0.7173 Internal iliac 0.7376 0.7691 0.7227 Obturator 0.7365 0.7888 0.7068 Mediastinal 0.7122 0.7512 0.6892 Common iliac 0.6799 0.8018 0.6535 Presacral 0.6511 0.8019 0.5867 All 0.7620 0.8114 0.7405
Dose parameters for manually delineated lymph nodes in previously treated TMI plans showed the mean value of V100 % (the percentage of volume receiving 100% of the prescribed dose), V95%, and V90% to be 46.50%, 62.12%, and 73.68%, respectively. The highest V90% was observed in presacral (93.61%), axillary (90.40%), obturator (88.78%), and internal iliac lymph nodes (84.67%). In contrast, the lowest V90% was identified in inguinal (47.95%), cervical (61.69%), and para-aortic (65.75%) and external iliac lymph nodes (68.97%). For automatically delineated lymph nodes, the mean value of V100%, V95%, and V90% of TMI plan was 38.35%, 55.06%, and 67.84%, respectively. The difference with dose coverage of lymph node between delineated manually and automatically was not statistically significant.
Conclusion Automatic delineation of lymph node using deep learning showed the potential to reduce the labor-intensive process of TMLI. When treated with TMI, the coverage of inguinal, cervical, para-aortic and external iliac lymph nodes was lower than expected.
PO-1163 Orbital MALT Lymphoma Treated with Low Dose Radiotherapy Yields Excellent Outcomes
I. Sin 1 , W.S. Ong 2 , A. Hussein 1 , Z. Master 3 , S. Poh 1 , B. Ho 1 , W.S. Looi 1 , K.W. Yeoh 1
1 National Cancer Centre Singapore, Division of Radiation Oncology, Singapore, Singapore; 2 National Cancer Centre Singapore, Division of Clinical Trials and Epidemiology, Singapore, Singapore; 3 National Cancer Centre Singapore, Division of Radiation Oncology - Physics, Singapore, Singapore Purpose or Objective Orbital lymphoma is an uncommon disease, accounting for 10% of all orbital tumours and 1% of non-Hodgkin’s lymphoma. The use of 24Gy over 12 fractions has been proven to be the optimal dose for patients with indolent lymphomas in general, with 4Gy over 2 fractions being useful for palliation in the European population. There is, however, emerging evidence that the use of 4Gy over 2 fractions for indolent orbital lymphomas provides comparable local control and overall survival rates
Made with FlippingBook flipbook maker