Deep Learning-Based Pulse Height Estimation for Separation of Pile-Up Pulses From NaI(Tl) Detector

Jeon, Byoungil; Lim, S. I.; Lee, Eunjoong; Hwang, Y.S.; Chung, Kwok Hung; Moon, Myungkook

doi:10.1109/tns.2021.3140050

Cited by 5 publications

(14 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At higher count rate, the pile-up issue becomes the dominant effect. This defect can be detected using deep learning technique at higher rates [21]. However, the recovery of pile-up pulses can be done using our previous proposed implemented algorithms in [22,23].…”

Section: Modeling Of Bgo and Lso Pulses Using Block Diagram Programmingmentioning

confidence: 99%

An efficient digital pulse processing approach for identification of BGO and LSO scintillator crystals

Tokhy

2023

J. Inst.

View full text Add to dashboard Cite

Identification and discrimination between BGO and LSO scintillators is a fundamental target for handling parallax error within positron emission tomography (PET) applications by depth of interaction. An approach is built for discrimination and identification of BGO and LSO scintillator crystals. This approach is tested using a simulated BGO and LSO pulses. A Matlab Simulink model is implemented for simulation and creation of BGO and LSO scintillation pulses. The simulated pulses depend on 22Na radiation source. The suggested approach has two different algorithms. The first algorithm uses both 1D-Walsh ordered fast Walsh-Hadamard transform (1WFWHT) and fast Chebyshev transform (FCHT) for extracting the features of crystal pulses. The optimum features are selected from 1WFWHT and FCHT using one of three optimization techniques that are binary dragonfly optimization (BDA), binary atom search optimization (BASO) and binary Harris Hawk optimization (BHHO). These optimized features are trained and tested using one of three based classifiers. These classifiers are Naive Bayes classifier (NBC), hierarchical prototype-based (HP) classifier and adaptive neuro-fuzzy inference system (ANFIS) classification. The ANFIS classifier achieves the best accuracy with all optimum (BASO, BDF and BHH) FCHT features. However, the NB classifier introduces the highest accuracy with all optimum (BASO, BDF and BHH) FWHT 1D features. The second algorithm uses the conventional neural network (CNN) for extracting the pulse features. Then, the deep neural network (DNN) is applied for training and testing of the captured pulses. The suggested algorithms are verified and compared in respect of statistical measures. The compared results confirm that the best accuracy and identification rate is accomplished using DNN algorithm. Besides, the DNN has better results compared to conventional classification techniques with optimum feature selection techniques in respect of time consumption. The proposed approach aids in the realisation of overcoming parallax inaccuracy in PET.

show abstract

Section: Modeling Of Bgo and Lso Pulses Using Block Diagram Programmingmentioning

confidence: 99%

An efficient digital pulse processing approach for identification of BGO and LSO scintillator crystals

Tokhy

2023

J. Inst.

View full text Add to dashboard Cite

show abstract

“…large amounts of data in high-radiation environments by directly estimating the pulse heights through the input of partial pulse data based on simple data processing into a deep learning model [17].…”

Section: Jinst 18 C12002mentioning

confidence: 99%

“…In this study, a deep learning-based PHE method was optimized for pile-up signal correction in high-radiation field. The overall PUC process adopted the previous PHE method [17] but with a modification of the peak-finding (PF) method to enhance the count restoration rate. Additionally, the performances of two deep learning models (convolutional neural networks (CNN) and deep neural networks (DNN)) were evaluated based on the input data length, which significantly affects efficient data processing.…”

Section: Jinst 18 C12002mentioning

confidence: 99%

“…First, a modified PF method for restoring the total counts was discussed. In a previous study [17], a simple PF method applied to piled-up signals to obtain sliced pulse data detected the peaks of a TPU pulse arising from overlap in the pulse tail. However, the peaks of the PPU pulse were not accurately detected because the PTP distance was short, resulting in spectral distortion and overall reduction in counts.…”

Section: Data Preprocessing For Establishing Training and Test Datasetmentioning

confidence: 99%

“…In recent years, deep learning technologies have been applied to various fields of radiation measurement, such as radiation imaging, dosimetry, spectral data analysis, and pulse signal analysis, owing to their recognized characteristics, including feature extraction of complex patterns, nonlinear responses, handling of large-scale data, high estimation accuracy, and the ability to solve various problems [13][14][15][16][17][18]. Among them, the deep learning-based PHE method presented by Jeon et al, (2022) has demonstrated high correction performance and can be universally applied without limitations to specific detectors [17,18]. Particularly, this method opens the possibility of real-time processing of…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimizing deep learning-based piled-up pulse height correction method for high radiation-field application

Kim,

Ko,

Lee

et al. 2023

J. Inst.

View full text Add to dashboard Cite

In high-radiation environments, measured pile-up pulses can lead to unavoidable issues such as total count loss and spectrum distortion. Additionally, the recording of large volumes of data within a short period makes real-time processing difficult. In this study, a deep learning-based pulse height estimation (PHE) method was optimized to perform pile-up signal correction in high-radiation fields. First, we adopted a previous deep-learning-based PHE method that allows for fast correction without being restricted to specific detectors. However, the peak-finding method was slightly modified to improve the count restoration rate. Moreover, the input data length of the deep learning model was optimized for convolutional neural networks (CNN) and deep neural networks (DNN) to achieve the maximum correction performance using minimal input data. A series of single pulses was experimentally obtained from a LaBr3 detector with a short decay time to prepare a dataset for training the deep learning models. The pile-up signals were generated by randomly synthesizing single pulses. Samples around their peaks were sliced using the peak-finding method and used as input data for the deep learning models. As a result of the optimization, the modified peak-finding method improved the count restoration rate compared to the previous method by effectively detecting the peaks of tail pile-up, and peak pile-up pulses. Furthermore, the input data length and region were optimized based on the performance evaluation of each deep learning model. Despite having a simpler architecture than the CNN model, the DNN model demonstrated excellent PHE performance. The results of this study showed the efficient and practical considerations necessary for applying pile-up signal correction in high-radiation fields.

show abstract

A method for correcting characteristic X-ray net peak count from drifted shadow peak

Tang,

Ma,

Shi

et al. 2023

NUCL SCI TECH

View full text Add to dashboard Cite

Deep Learning-Based Pulse Height Estimation for Separation of Pile-Up Pulses From NaI(Tl) Detector

Cited by 5 publications

References 37 publications

An efficient digital pulse processing approach for identification of BGO and LSO scintillator crystals

An efficient digital pulse processing approach for identification of BGO and LSO scintillator crystals

Optimizing deep learning-based piled-up pulse height correction method for high radiation-field application

A method for correcting characteristic X-ray net peak count from drifted shadow peak

Contact Info

Product

Resources

About