Radiation shielding is one of the necessary procedures in radiation protection. The lead blocks are commonly used to shield against gamma- and X-rays. However, due to lead's biotoxicity, the development of alternative materials is required. We developed a novel ceramic product as a non-biotoxic shielding material composed mainly of iron (III) oxide. In this study, the radiation shielding performance against gamma-rays was evaluated and its potential as a radiation shielding material was investigated. We measured the gamma-ray amount transmitted through the ceramic specimens using a NaI scintillation counter with three different gamma sources (¹³³Ba, ¹³⁷Cs, and ⁶⁰Co). The order of shielding ability of the sample with the same volume was lead > iron > the ceramics. The effects of piling the blocks and the type of jointing agent used in the gaps on the shielding ability were also observed for considering actual use.

 In this study, we aimed to develop a deep convolutional neural network (DCNN)-based automatic time-activity curve (TAC) fitting method for input function determination. This will be achieved through a comparison between the DCNN method, manual method, and mathematical fitting methods using the expectation maximization algorithm (EM-method) to uncover the potential of the DCNN approach.

 A U-Net architecture based on convolutional neural networks was used to determine the TAC fittings. The area under the curve (AUC) values of the TAC by the EM and DCNN methods were compared to those obtained using the manual method.

 The AUC values for the EM-manual method exhibited similarity within an error range of approximately ±20%. Conversely, the error range for DCNN-manual method was approximately ±10%, signifying a reduction in the error range to approximately 1/2.

 Our findings indicate that the DCNN method provides accuracy equivalent to those of manual methods and even slightly superior to that of the EM method.