Purpose: to predict eligibility for deep inspiration breath-hold (DIBH) radiotherapy (RT) treatment of patients with left breast cancer from analysis of respiratory signal, using Deep Bidirectional Long Short-Term Memory (BLSTM) recurrent neural networks. Methods: The respiratory traces from 36 patients who underwent DIBH RT were collected. The patients’ RT treatment plans were generated for both DIBH and free-breathing (FB) modalities. The patients were divided into two classes (patient eligible or not), based on the decrease of maximum dose to the left anterior descending (LAD) artery achieved with DIBH, compared to that achieved with FB and ΔD_L. Patients with ΔD_L > median value of ΔD_L within the patient cohort were assumed to be those selected for DIBH. A BLSTM-RNN was trained for classification of patients eligible for DIBH by analysis of their respiratory signals, as acquired during acquisition of the pre-treatment computed tomography (CT), for selecting the window for DIBH. The dataset was split into training (60%) and test groups (40%), and the hyper-parameters, including the number of hidden layers, the optimizer, the learning rate, and the number of epochs, were selected for optimising model performance. The BLSTM included 2 layers of 100 neural units, each followed by a dropout layer with 20% dropout, and was trained in 35 epochs using the Adam optimizer, with an initial learning rate of 0.0003. Results: The system achieved accuracy, specificity, and sensitivity of, F1 score and area under the receiving operating characteristic curve (AUC) of 71.4%, 66.7%, 80.1%, 72.4%, and 69.4% in the test dataset, respectively. Conclusions: The proposed BLSTM-RNN classified patients in the test set eligible for DIBH with good accuracy. These results look promising for building an accurate and robust decision system to provide automated assistance to the radiotherapy team in assigning patients to DIBH.

Parvej.baec@gmail.com Introduction: Radiation shielding is crucial in the design of a linear accelerator (LINAC) bunker. The thickness of the concrete slab used for shielding purposes is an essential factor in reducing the radiation dose to acceptable levels. In the Institute of Nuclear Medical Physics (INMP), Savar, Dhaka, there is a plan to install second clinical LINAC whose bunker is now under construction under the ground. In this study, we evaluate the slab thickness of the new LINAC bunker to determine if it provides adequate radiation shielding. Methods: The LINAC will use a maximum energy photon beam of 18 MV. The internal height of the bunker is 610 cm and the distance from the iso-center to the slab is 480 cm. The slab is constructed with concrete (2.35 g/cm³) as the shielding material. To calculate the required shielding thickness, we used a theoretical shielding calculation model, we assumed that the LINAC will treat a maximum of 50 patients per week, with an equal distribution of 6 MV and 18 MV photon energies and 3DCRT and IMRT treatment techniques. Based on NCRP-151 and Safety Series 47, we set the occupancy factor (T) to 1, the use factor (U) to 0.263 for the gantry angles of 0°/180°, and the dose limit factor (P) to 5 mSv/y. Finally, we calculated the shielding thickness of the slab according to all factors. Results: According to our theoretical model, the required shielding thickness for the LINAC bunker is 231.59 cm. However, the slab thickness currently under construction is 304 cm, which is more than sufficient to provide the necessary shielding. Conclusion: Our study confirms that the thickness of the slab for the new LINAC bunker at the INMP provides adequate radiation shielding for the proposed treatment workload. These findings can contribute to the safer delivery of radiation therapy for patients and personnel. There are further options to study to evaluate all surrounding walls of the new bunker. Article published online: 25 May 2023 © 2023. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/) Thieme Medical and Scientific Publishers Pvt. Ltd. A-12, 2nd Floor, Sector 2, Noida-201301 UP, India