Research article Special Issues

Transformation of PET raw data into images for event classification using convolutional neural networks

  • Received: 09 March 2023 Revised: 09 June 2023 Accepted: 25 June 2023 Published: 12 July 2023
  • In positron emission tomography (PET) studies, convolutional neural networks (CNNs) may be applied directly to the reconstructed distribution of radioactive tracers injected into the patient's body, as a pattern recognition tool. Nonetheless, unprocessed PET coincidence data exist in tabular format. This paper develops the transformation of tabular data into n-dimensional matrices, as a preparation stage for classification based on CNNs. This method explicitly introduces a nonlinear transformation at the feature engineering stage and then uses principal component analysis to create the images. We apply the proposed methodology to the classification of simulated PET coincidence events originating from NEMA IEC and anthropomorphic XCAT phantom. Comparative studies of neural network architectures, including multilayer perceptron and convolutional networks, were conducted. The developed method increased the initial number of features from 6 to 209 and gave the best precision results (79.8) for all tested neural network architectures; it also showed the smallest decrease when changing the test data to another phantom.

    Citation: Paweł Konieczka, Lech Raczyński, Wojciech Wiślicki, Oleksandr Fedoruk, Konrad Klimaszewski, Przemysław Kopka, Wojciech Krzemień, Roman Y. Shopa, Jakub Baran, Aurélien Coussat, Neha Chug, Catalina Curceanu, Eryk Czerwiński, Meysam Dadgar, Kamil Dulski, Aleksander Gajos, Beatrix C. Hiesmayr, Krzysztof Kacprzak, Łukasz Kapłon, Grzegorz Korcyl, Tomasz Kozik, Deepak Kumar, Szymon Niedźwiecki, Szymon Parzych, Elena Pérez del Río, Sushil Sharma, Shivani Shivani, Magdalena Skurzok, Ewa Łucja Stępień, Faranak Tayefi, Paweł Moskal. Transformation of PET raw data into images for event classification using convolutional neural networks[J]. Mathematical Biosciences and Engineering, 2023, 20(8): 14938-14958. doi: 10.3934/mbe.2023669

    Related Papers:

    [1] Belgüzar Kara, Elif Gökçe Tenekeci, Şeref Demirkaya . Factors Associated With Sleep Quality in Patients With Multiple Sclerosis. AIMS Medical Science, 2016, 3(2): 203-212. doi: 10.3934/medsci.2016.2.203
    [2] Melissa R. Bowman Foster, Ali Atef Hijazi, Raymond C. Sullivan Jr, Rebecca Opoku . Hydroxyurea and pyridostigmine repurposed for treating Covid-19 multi-systems dysfunctions. AIMS Medical Science, 2023, 10(2): 118-129. doi: 10.3934/medsci.2023010
    [3] Victor Okey Dinwoke, Michael Oluchukwu Amara, Linda Uzo Amara . Abdominal pregnancy—a diagnosis never to miss. AIMS Medical Science, 2022, 9(2): 342-347. doi: 10.3934/medsci.2022015
    [4] Ahlam Al-Zahrani, Shorooq Al-Marwani . The effectiveness of an educational session about folic acid on pregnant women's knowledge in Yanbu City, Kingdom of Saudi Arabia. AIMS Medical Science, 2022, 9(3): 394-413. doi: 10.3934/medsci.2022019
    [5] Juliet A Harvey, Sebastien FM Chastin, Dawn A Skelton . What happened to my legs when I broke my arm?. AIMS Medical Science, 2018, 5(3): 252-258. doi: 10.3934/medsci.2018.3.252
    [6] XinQi Dong, Manrui Zhang . The Prevalence of Neurological Symptoms among Chinese Older Adults in the Greater Chicago Area. AIMS Medical Science, 2015, 2(1): 35-50. doi: 10.3934/medsci.2015.1.35
    [7] Wenping Lin, Kai Dai, Luokun Xie . Recent Advances in αβ T Cell Biology: Wnt Signaling, Notch Signaling, Hedgehog Signaling and Their Translational Perspective. AIMS Medical Science, 2016, 3(4): 312-328. doi: 10.3934/medsci.2016.4.312
    [8] Pasha Grachev, Robert L. Goodman . The GnRH Pulse Generator. AIMS Medical Science, 2016, 3(4): 359-385. doi: 10.3934/medsci.2016.4.359
    [9] Nádia C. M. Okuyama, Fernando Cezar dos Santos, Kleber Paiva Trugilo, Karen Brajão de Oliveira . Involvement of CXCL12 Pathway in HPV-related Diseases. AIMS Medical Science, 2016, 3(4): 417-440. doi: 10.3934/medsci.2016.4.417
    [10] Ying Chen, Sok Kean Khoo, Richard Leach, Kai Wang . MTA3 Regulates Extravillous Trophoblast Invasion Through NuRD Complex. AIMS Medical Science, 2017, 4(1): 17-27. doi: 10.3934/medsci.2017.1.17
  • In positron emission tomography (PET) studies, convolutional neural networks (CNNs) may be applied directly to the reconstructed distribution of radioactive tracers injected into the patient's body, as a pattern recognition tool. Nonetheless, unprocessed PET coincidence data exist in tabular format. This paper develops the transformation of tabular data into n-dimensional matrices, as a preparation stage for classification based on CNNs. This method explicitly introduces a nonlinear transformation at the feature engineering stage and then uses principal component analysis to create the images. We apply the proposed methodology to the classification of simulated PET coincidence events originating from NEMA IEC and anthropomorphic XCAT phantom. Comparative studies of neural network architectures, including multilayer perceptron and convolutional networks, were conducted. The developed method increased the initial number of features from 6 to 209 and gave the best precision results (79.8) for all tested neural network architectures; it also showed the smallest decrease when changing the test data to another phantom.



    Fanconi anemia (FA) is a pathologically diverse and recessive autosomal inherited rare genetic disorder that occurs in one in 130,000 births and is common among Ashkenazi Jews and South Africans [1]. It is caused by mutations in a cluster of proteins that perform DNA repair, especially those of covalent interstrand crosslinks (ICLs), via homologous recombination. FA culminates in bone marrow failure (BMF) in 90% of the affected individuals and leads to the development of various types of cancer, particularly myelogenous leukemia; gynecological squamous cell carcinoma; tumors in the liver, brain, skin, and kidney; esophageal carcinoma; and agammaessive head and neck squamous cell carcinoma [2][4]. Approximately, 60–75% of the affected people have congenital defects, short stature, skin hyperpigmentation, missing radii, and abnormal thumb, head, eyes, kidneys, and ears, and developmental disabilities, and 75% people exhibit endocrine disorders of varying severity. The first sign of a hematological problem is usually petechiae and bruises, with later onset of pale appearance, tiredness, and infections.

    Several patients develop BMF sometime during the course of the disease, but the onset of pancytopenia is correlated with the probability of FA. However, in some patients, the condition remains undiagnosed until the development of myelodysplastic syndromes/acute myeloid leukemia (MDS-AML). Patients with FA exhibit elevated levels of serum alpha-fetoproteins, fetal hemoglobin (HbF), and macrocytosis, although these cannot exclusively predict FA [5]. FA can be diagnosed in patients of age 0–48 years, and nearly 25–40% patients with FA appear healthy [6].

    The commonly available treatment strategies for BMF involve the use of androgens and hematopoietic growth factors; however, cases where patients have become refractory to these treatments have been reported. In such cases, hematopoietic stem cell transplantation is the treatment of choice depending on the availability of a donor. For solid tumors in patients with FA, surgery is the preferred mode of treatment than radiotherapy and chemotherapy due to the possibility of severe side effects [7].

    The list of mutations in genes associated with FA has increased ever since the discovery of the first FA gene, FANCC, over 25 years ago. There are over 22 known FA complementation groups, such as FANC-A, B, C, D1, D2, E, F, G, I, J, L, M, N, O, P, Q, R, S, T, U, V, and W [8]. All the proteins associated with FA pathway and their individual functions have been depicted in the Table 1 [9].

    Table 1.  Proteins in FA pathway and their individual roles [9].
    FA Proteins Involved in DNA damage Involved in other cellular processes
    FANCA CD40 signaling pathway; cell proliferation; inflammatory response; T cell differentiation; Sequence-specific DNA binding transcription factor activity
    FANCB DNA damage repair (not entirely dependent on the FA core complex)
    FANCC TP53 Regulation of DNA Repair Genes Generic transcription pathway; Gene expression; Diabetes
    FANCD1 DNA damage repair, (not entirely dependent on the monoubiquitinated D2/I) Cell cycle regulation; meiotic recombination; Presynaptic phase of homologous DNA pairing and strand exchange; Resolution of D-loop structures
    FANCD2 The HHR6 signaling pathway; The ATM signaling pathway; DNA damage repair; TP53 regulation of DNA Repair Genes; MiRNA regulation of DNA damage response Replication: Replication-origin firing, Stalled replication forks; Mitochondria function; gene expression;
    FANCE/F/G DNA damage repair (not entirely depending on the FA core complex)
    FANCI The ATR signaling pathway; TP53 regulation of DNA Repair Genes; DNA damage repair Gene expression
    FANCJ DNA damage repair (not entirely dependent on the monoubiquitinated D2/I); G2/M DNA damage checkpoint Cell cycle regulation; Cytosolic iron-sulfur cluster assembly; P53 activity; Presynaptic phase of homologous DNA pairing and strand exchange; Resolution of D-loop structures
    FANCL DNA damage repair (not entirely dependent on the FA core complex) Ubiquitin mediated proteolysis
    FANCM ATR regulator, or a major sensor of the DDR Stalled replication forks
    FANCN DNA damage repair (HR) (not entirely dependent on monoubiquitinated FANCD2) Resolution of D-loop structures; Homologous DNA Pairing and Strand Exchange
    FANCO DNA damage repair (not entirely dependent on monoubiquitinated FANCD2) Meiosis; Resolution of D-loop structures; Megakaryocyte development and platelet production; Cell cycle
    FANCP DNA damage repair (not entirely dependent on monoubiquitinated FANCD2/I) Resolution of D-loop structures
    FANCQ DNA damage repair (DSB, NER) (not entirely dependent on monoubiquitinated FANCD2) Transcription
    FANCR DNA damage repair (HR) (not entirely dependent on monoubiquitinated FANCD2/I); ATM signaling Cell cycle; Meiosis; Rac1/Pak1/p38/MMP-2 pathway
    FANCS DNA damage repair (HR) (not entirely dependent on monoubiquitinated FANCD2/I); ATM signaling Transcription (ATF-2, E2F, FOXA1 transcription factor networks); Androgen receptor signaling pathway; Aurora A signaling; Cell Cycle Checkpoints; Deubiquitinating;
    FANCT DNA damage repair (not entirely dependent on monoubiquitinated FANCD2/I); Post-translational protein modification
    FANCU DNA damage repair (not entirely dependent on monoubiquitinated FANCD2/I) Resolution of D-loop structures; Presynaptic phase of homologous DNA pairing and strand exchange
    FANCV TLS performed by POL1, POLK, REV1 or Zeta; post replication repair (not entirely dependent on monoubiquitinated FANCD2/I) Cell cycle regulation; Shigellosis; Oocyte meiosis; Endoderm Differentiation
    FANCW Ubiquitination of RPA (not entirely for the activation of the FA pathway) Ubiquitination; Mediation of p53 ubiquitination for its stability

     | Show Table
    DownLoad: CSV

    Moreover, mutations in FANCO, RAD51 (FANCR), and FANCS have been implicated in a FA-like syndrome in which patient cells are hypersensitive to ICL-inducing drugs, but the disease is not characterized with all the clinical features classically observed in FA. Among the bona fide FA genes, FANCA, FANCC, and FANCG are the most frequently inactivated by biallelic mutations linked to the hereditary disorder [10],[11]. Importantly, monoallelic mutations in certain FA genes, including FANCD1 (BRCA2), FANCS (BRCA1), FANCN (PALB2), FANCM, FANCJ (BRIP1), and FANCO (RAD51C), which are believed to operate downstream in the pathway and are implicated in homologous recombination, are associated with sporadic breast and ovarian cancer [11],[12]. With the identification of several FA genes, the pathway for repair of ICLs has become more complex and is now believed to involve nucleotide excision repair, base excision repair, double strand break repair, and mismatch repair. Although ICL repair occurs mostly in replicating cells, studies have also associated it with non-replicative repair, such as in cells treated with DNA crosslinking agents. ICL repair is critical as it affects DNA unwinding for basic life processes such as transcription and replication.

    FA pathway/signaling is crucial for DNA damage response (DDR), which further results in DNA ICL. However, it has been reported that genes and proteins, especially FANCC, of the FA pathway perform additional cytoprotective role. FANCC provides protection against proinflammatory cytokine-induced cell death. This role is associated with FANCC and its various biochemical interactions [13]. One study suggested that patients with FA carrying endogenously expressed FANCC mutant c.67delG exhibited a clinical course that was milder than patients with null mutations in FANCC [14]. FA cells are hypersensitive to oxidative stress, radio/chemotherapeutic agents, and DNA crosslinking agents, such as mitomycin, and exhibit cell cycle abnormalities [15]. Thus, FA phenotypes may require stressors to initiate the disease phenotype [16]. Thus, bone marrow transplant should be performed with extreme care so as not to induce any oxidative stress, especially via radio/chemotherapeutic agents, which may otherwise lead to BMF.

    FANCA, FANCB, FANCC, FANCE, FANCF, FANCG, FANCL, and FANCM form a core complex, which monoubiquitylates FANCD2 and FANCI [17][20]. The monoubiquitylated complex interacts with the endo/exonuclease FAN1 (FA associated nuclease 1) [20][24]. However, FA patients with mutations in FAN1 are not known till date. FANCD1/BRCA2 and BRCA2-interacting protein FANCN/PALB2, essential components of homologous recombination repair, act downstream in this pathway along with the helicase FANCJ /BRIP1/BACH1 [25][31]. The interaction of FANCJ with BRCA1 is dispensable for the FA pathway. Interestingly, although BRCA1 depletion sensitizes cells to crosslink damage, individuals with biallelic BRCA1 mutations have not been reported so far. Multiple proteins, including the nucleases XPF, MUS81, and SLX1, interact with FANCP/SLX4, the latest addition to the family of FA proteins, which acts as a protein scaffold [32][37]. XPF and MUS81 are involved in crosslink repair, and the SLX4-SLX1 interaction is responsible for Holliday junction resolution activity in vitro. However, which activity of SLX4 is essential for crosslink repair is currently unclear [38],[39]. Overall, it is clear that mutations in FA proteins, which perturb ICL resolution, are important for FA pathogenesis.

    BRCA2, a human tumor suppressor, is also known as FANCD1, indicating its associations with the FA complex (discussed above) [40],[41]. It is normally expressed in breast tissues and is involved in the repair of DNA damage as described in the previous section. BRCA2 also prevents nucleolytic degradation of stalled forks during DNA replication [42]. Thus, BRCA2 is critical for maintaining genome stability and preventing deleterious genomic rearrangements, which may lead to cancer. High penetrance mutations in BRCA2/FANCD1 lead to loss of its tumor suppressive character and increase the chances of developing breast cancer [43].

    Several mutations, usually small indels, have been identified in BRCA2, many of which increase the risk of cancer. These mutations lead to the synthesis of an abnormal product that does not function properly. In their analysis of the severity of BRCA2 mutations in 27 cases with breast cancer, Alter et al. (2007) showed that 20 mutations were frameshifts or truncations, three involved splice sites, five were missense variants of unknown severity, and two were benign polymorphisms [44]. Monoallelic germline mutations in BRCA2 increase the susceptibility for breast/ovarian cancer, whereas biallelic germ line mutations lead to the development of FA-D1 in patients. Indeed, among the known FA genes, only BRCA2/FANCD1 plays a major role in the development of high-risk breast cancer [45]. BRCA2-associated FA-D1 subtype accounts for nearly 3% of all FA cases, which, in comparison with other subtypes, results in more severe form of the phenotype, increases the frequency of leukemia and other tumors, as well as early onset of symptoms [44],[46]. Parents of patients with FA are heterozygous for the condition, and therefore are at a high risk of early-onset breast/ovarian cancer [47]. Furthermore, in heterozygous patients, loss of the second wild type BRCA2 allele leads to biallelic extinction of BRCA2, and subsequent exposure to DNA cross-linkers often result in chromosome breakage, resulting in tri-radial chromosomes, which are characteristic of FA cells [48]. Thus, FA and breast cancer are interlinked and share common functions in the DNA repair mechanism [49]. Children with biallelic mutation in BRCA2 show spontaneous chromosomal instability and develop solid tumors of childhood such as Wilm's tumor and medulloblastoma [50].

    Individuals with heterozygous mutations in BRCA2/FANCD1 are also at increased risk of developing pancreatic cancer. Hahn et al. (2003) showed that frameshift mutations in BRCA2/FANCD1were associated with 19% cases with history of hereditary pancreatic cancer [51]. Similarly, other cancers, such as prostate cancer, gastric cancer, and melanoma, have also been associated with heterozygous mutations in BRCA2/FANCD1 [52]. A recent study showed that colorectal cancer (CRC) can also be associated with biallelicBRCA2 mutations (a frameshift alteration (c. 1845_1846delCT, p. Asn615Lysfs*6) and a missense mutation (c. 7802A > G, p. Tyr2601Cys)) in families with cases of CRC, although CRC driver genes were not involved and the cardinal clinical symptoms of FA were not observed. This indicated that the presence of these mutations should be screened even in the absence of typical FA symptoms [53]. The biallelic p. Lys3326X mutation in BRCA2 was present in 27 of 746 ESCC cases and in 16 of 1,373 controls in a study on mutations in FA genes in Turkmen of Iran with esophageal cancer [54].

    Recently, biallelic BRCA2 mutation was found to predispose toward glioblastoma multiforme (GBM), with multiple genetic rearrangements [55]. In that study, methylation analysis of GBM from a 3-year-old patient with FA, who harbored biallelic mutation in BRCA2, revealed strong clustering with the K27 mutation subetaoup, copy number analysis showed gains of chromosomes 1q, 4q, part of 7q, part of 8q and 17q, with resultant amplifications of MDM4, CDK6, MET, MYC, and PPM1D (WIP1). This study also reported the first germline mutation in BRCA2, c. 8057T > C, resulting in p. Leu2686Pro substitution in the patient. Biallelic BRCA2 mutation has also been reported in two siblings with early age central nervous system embryonal tumor, which is the first reported case of a spinal cord primitive neuroectodermal tumor in BRCA2/FANCD1 kindred [56].

    Currently, the precise effect of mutations in some FA gene leading to breast and ovarian cancer remains unclear. While somatic cells with mutations in the DNA repair pathway undergo apoptosis, estrogen might promote the survival of breast and ovarian cells. Estrogen possibly promotes the survival of breast and ovarian cells harboring significant DNA damage, whereas apoptosis may occur in somatic cells with mutations in the DNA repair pathway [57]. In contrast, breast/ovarian cancer infrequently develop in patients with FA. Hypogonadism with decreased levels of estrogen in females with FA might account for this observation. In families carrying BRCA2/FANCD1 mutations, > 40 years marks the peak age for the onset of breast/ovarian cancer among heterozygote carriers, whereas patients with biallelic mutations frequently die from complications of aplastic anemia before 40 years [58]. Altogether, these observations show that the timing of biallelic loss of BRCA2 can establish the specific cancer spectrum [59][65]. Figure 1 provides a schematic representation of FA pathway [66].

    Figure 1.  FA pathway at a glance [66].

    FA is a genetic disorder that predisposes patients to pancytopenia, MDS, and AML. Better understanding of the FA pathway might lead to the development of methods for correcting the perturbed pathway, thereby preventing carcinogenesis in FA patients or those carrying mutations in FA genes. Indeed, the CRISPR/Cas9 technology has already been used to rectify a FANCD1 deletion in a patient-derived fibroblast with the above mutation, providing proof-of-principle that gene editing may be used to rectify FA. As the sensitivity of cancer cells to chemotherapy drugs is affected by defective DNA repair mechanism, mutations in FA genes could help in predicting the success of chemotherapy drugs such as DNA inhibitors, or DNA crosslinking agents (melphalan, mitomycin C, and cisplatin). In this review, we have specifically discussed the effects of the FANCD1/BRCA2 mutation on FA and cancer pathogenesis. The collective knowledge can be used for further understanding the FA-D1 subtype of the disease.



    [1] Y. Lecun, Y. Bengio, G. Hinton, Deep Learning, Nature, 521 (2015), 436—444. https://doi.org/10.1038/nature14539 doi: 10.1038/nature14539
    [2] M. Z. Alom, T. M. Taha, C. Yakopcic, S. Westberg, P. Sidike, M. S. Nasrin, et al., A state-of-the-art survey on deep learning theory and architectures, Electronics, 8 (2019), 292. https://doi.org/10.3390/electronics8030292 doi: 10.3390/electronics8030292
    [3] A. H. Habibi, H. E. Jahani, Guide to Convolutional Neural Networks: A Practical Application to Traffic-Sign Detection and Classification, Springer International Publishing, 2017. https://doi.org/10.1007/978-3-319-57550-6
    [4] K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2016), 770–778. https://doi.org/10.1109/CVPR.2016.90
    [5] J. Redmon, S. Divvala, R. Girshick, A. Farhadi, You only look once: Unfied, real-time object detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2016), 779–788. https://doi.org/10.1109/CVPR.2015.7298594
    [6] C. Szegedy, W. Liu, Y. Q. Jia, P. Sermanet, S. Reed, D. Anguelov, et al., Going deeper with convolutions, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2015), 1–9. https://doi.org/10.48550/arXiv.1409.4842
    [7] C. Szegedy, S. Ioffe, V. Vanhoucke, A. A. Alemi, Inception-v4, inception-ResNet and the impact of residual connections on learning, in Proceedings of the AAAI Conference on Artficial Intelligence, (2017), 4278–4284. https://doi.org/10.48550/arXiv.1602.07261
    [8] D. S. Kermany, M. Goldbaum, W. J. Cai, C. C. S. Valentim, H. Y. Liang, S. L. Baxter, et al., Identifying medical diagnoses and treatable diseases by image-based deep learning, Cell, 172 (2018), 1122–1131. https://doi.org/10.1016/j.cell.2018.02.010 doi: 10.1016/j.cell.2018.02.010
    [9] S. Cheng, Y. F. Jin, S. P. Harrison, C. Quilodrán-Casas, L. C. Prentice, Y. K. Guo, et al., Parameter flexible wildfire prediction using machine learning techniques: Forward and inverse modelling, Remote Sens., 14 (2022), 3228. https://doi.org/10.3390/rs14133228 doi: 10.3390/rs14133228
    [10] Y. Zhuang, S. Cheng, N. Kovalchuk, M. Simmons, O. K. Matar, Y.-K. Guo, et al., Ensemble latent assimilation with deep learning surrogate model: application to drop interaction in a microfluidics device, Lab Chip, 22 (2022), 3187–3202. https://doi.org/10.1039/D2LC00303A doi: 10.1039/D2LC00303A
    [11] J. L. Humm, A. Rosenfeld, A. Del Guerra, From PET detectors to PET scanners, European J. Nucl. Med. Mol. Imag., 30 (2003), 1574–1597. 10.1007/s00259-003-1266-2 doi: 10.1007/s00259-003-1266-2
    [12] D. L. Bailey, Positron Emission Tomography: Basic Sciences, Springer-Verlag, 2005. https://doi.org/10.1007/b136169
    [13] A. Alavi, T. J. Werner, E. L. Stępień, P. Moskal, Unparalleled and revolutionary impact of PET imaging on research and day to day practice of medicine, Bio-Algor. Med-Syst., 17 (2021), 203–212. https://doi.org/10.1515/bams-2021-0186 doi: 10.1515/bams-2021-0186
    [14] E. Berg, S. Cherry, Using convolutional neural networks to estimate time-of-flight from PET detector waveforms, Phys. Med. Biol., 63 (2018), 02LT01. https://doi.org/10.1088/1361-6560/aa9dc5 doi: 10.1088/1361-6560/aa9dc5
    [15] J. Bielecki, Application of the machine learning methods to the multi-photon event classification in the J-PET scanner, M.Sc thesis, Warsaw University of Technology, 2019. Available from: https://pet.ncbj.gov.pl/wp-content/uploads/2019/10/JanBieleckiMasterThesis.pdf
    [16] A. Sharma, E. Vans, D. Shigemizu, K. A. Boroevich, T. Tsunoda, Deepinsight: A methodology to transform a non-image data to an image for convolution neural network architecture, Sci. Rep., 9 (2019), 11399. https://doi.org/10.1038/s41598-019-47765-6 doi: 10.1038/s41598-019-47765-6
    [17] P. Moskal, Sz. Niedźwiecki, T. Bednarski, E. Czerwiński, Ł. Kapłon, E. Kubicz, et al., Test of a single module of the J-PET scanner based on plastic scintillators, Nucl. Instrum. Meth. Phys. Res. A, 764 (2014), 317–321. https://doi.org/10.1016/j.nima.2014.07.052 doi: 10.1016/j.nima.2014.07.052
    [18] L. Raczyński, P. Moskal, P. Kowalski, W. Wiślicki, T. Bednarski, P. Białas, et al., Compressive sensing of signals generated in plastic scintillators in a novel J-PET instrument, Nucl. Instrum. Meth. Phys. Res. A, 786 (2015), 105–112. https://doi.org/10.1016/j.nima.2015.03.032 doi: 10.1016/j.nima.2015.03.032
    [19] P. Moskal, O. Rundel, D. Alfs, T. Bednarski, P. Białas, E. Czerwiński, et al., Time resolution of the plastic scintillator strips with matrix photomultiplier readout for J-PET tomograph, Phys. Med. Biol., 61 (2016), 2025–2047. https://doi.org/10.1088/0031-9155/61/5/2025 doi: 10.1088/0031-9155/61/5/2025
    [20] S. Niedźwiecki, P. Białas, C. Curceanu, E. Czerwiński, K. Dulski, A. Gajos, et al., J-PET: A new technology for the whole-body PET imaging, Acta Phys. Polon. B, 48 (2017), 1567–1576. https://doi.org/10.5506/APhysPolB.48.1567 doi: 10.5506/APhysPolB.48.1567
    [21] G. Korcyl, P. Białas, C. Curceanu, E. Czerwiński, K. Dulski, B. Flak, et al., Evaluation of single-chip, real-time tomographic data processing on FPGA—SoC devices, IEEE Trans. Med. Imag., 37 (2018), 2526–2535. https://doi.org/10.1109/TMI.2018.2837741 doi: 10.1109/TMI.2018.2837741
    [22] P. Moskal, K. Dulski, N. Chug, C. Curceanu, E. Czerwiński, M. Dadgar, et al., Positronium imaging with the novel multiphoton PET scanner, Sci. Adv., 7 (2021), eabh4394. https://doi.org/10.1126/sciadv.abh4394 doi: 10.1126/sciadv.abh4394
    [23] P. Moskal, A. Gajos, M. Mohammed, J. Chhokar, N. Chug, C. Curceanu, et al., Testing CPT symmetry in ortho-positronium decays with positronium annihilation tomography, Nat. Commun., 12 (2021), 5658. https://doi.org/10.1038/s41467-021-25905-9 doi: 10.1038/s41467-021-25905-9
    [24] R. D. Badawi, H. C. Shi, P. C. Hu, S. G. Chen, T. Y. Xu, P. M. Price, et al., First human imaging studies with the EXPLORER total-body PET scanner, J. Nuclear Med., 60 (2019), 299–303. https://doi.org/10.2967/jnumed.119.226498 doi: 10.2967/jnumed.119.226498
    [25] E. N. Holy, A. P. Fan, E. R. Alfaro, E. Fletcher, B. A. Spencer, S. R. Cherry, et al., Non-invasive quantification and SUVR validation of [18F]-florbetaben with total-body EXPLORER PET, Alzheimer's Dement., 18 (2022), e066123. https://doi.org/10.1002/alz.066123 doi: 10.1002/alz.066123
    [26] S. Vandenberghe, P. Moskal, J. S. Karp, State of the art in total body PET, EJNMMI Phys., 7 (2020), 1–33. https://doi.org/10.1186/s40658-020-00290-2 doi: 10.1186/s40658-020-00290-2
    [27] A. Rahmim, M. Lenox, A. J. Reader, C. Michel, Z. Burbar, T. J. Ruth, et al., Statistical list-mode image reconstruction for the high resolution research tomograph, Phys. Med. Biol., 49 (2004), 4239–4258. https://doi.org/10.1088/0031-9155/49/18/004 doi: 10.1088/0031-9155/49/18/004
    [28] R. Accorsi, L.-E. Adam, M. E. Werner, J. S Karp, Optimization of a fully 3D single scatter simulation algorithm for 3D PET, Phys. Med. Biol., 49 (2004), 2577–2598. https://doi.org/10.1088/0031-9155/49/12/008 doi: 10.1088/0031-9155/49/12/008
    [29] C. C. Watson, Extension of Single Scatter Simulation to Scatter Correction of Time-of-Flight PET, IEEE Trans. Nucl. Sci., 54 (2007), 1679–1686. https://doi.org/10.1109/TNS.2007.901227 doi: 10.1109/TNS.2007.901227
    [30] L. J. Maaten, G. Hinton, Visualizing High-Dimesional Data using t-SNE, J. Mach. Learn. Research, 9 (2008), 2579–2605. Available from: https://www.jmlr.org/papers/volume9/vandermaaten08a/vandermaaten08a.pdf.
    [31] B. Scholkopf, S. A. Bernhard, K. R. Muller, Nonlinear component analysis as a kernel eigenvalue problem, Neural Comput., 10 (1998), 1299–1319. https://doi.org/10.1162/089976698300017467 doi: 10.1162/089976698300017467
    [32] M. A. Aizerman, E. M. Braverman, L. I. Rozonoer, Theoretical foundations of the potential function method in pattern recognition learning, Autom. Remote Control, 25 (1964), 821–837. Available from: https://cs.uwaterloo.ca/y328yu/classics/kernel.pdf
    [33] V. Vapnik, The Nature of Statistical Learning Theory, Springer-Verlag, 1995. https://doi.org/10.1007/978-1-4757-2440-0
    [34] V. Vapnik, Statistical Learning Theory, Wiley, 1998. Available from: https://www.wiley.com/en-ie/Statistical+Learning+Theory-p-9780471030034
    [35] J. Mockus, Application of Bayesian approach to numerical methods of global and stochastic optimization, J. Global Optim., 4 (1994), 347–365. https://doi.org/10.1007/BF01099263 doi: 10.1007/BF01099263
    [36] S. Jan, G. Santin, D. Strul, S. Staelens, K. Assié, D. Autret, et al., GATE: A simulation toolkit for PET and SPECT, Phys. Med. Biol., 49 (2004), 454-4562. https://doi.org/10.1088/0031-9155/49/19/007 doi: 10.1088/0031-9155/49/19/007
    [37] D. Sarrut, M. Bała, M. Bardiès, J. Bert, M. Chauvin, K. Chatzipapas, et al., Advanced Monte Carlo simulations of emission tomography imaging systems with GATE, Phys. Med. Biol., 66 (2021), 10TR03. https://doi.org/10.1088/1361-6560/abf276 doi: 10.1088/1361-6560/abf276
    [38] J. Baran, W. Krzemien, L. Raczyński, M. Bała, A. Coussat, S. Parzych, et al., Realistic Total-Body J-PET Geometry Optimization–Monte Carlo Study, preprint arXiv e-prints, (2022), arXiv: 2212.02285. https://doi.org/10.48550/arXiv.2212.02285
    [39] NEMA Standards Publication NU 2-2007: Performance measurements of Positron Emission Tomographs, Nat. Elect. Manuf. Assoc., (2007). Available from: https://psec.uchicago.edu/library/applications/PET/chien_min_NEMA_NU2_2007.pdf
    [40] W. P. Segars, G. Sturgeon, S. Mendonca, J. Grimes, B. M. W. Tsui, 4D XCAT phantom for multimodality imaging research, Med. Phys., 37 (2010), 4902–4915. https://doi.org/10.1118/1.3480985 doi: 10.1118/1.3480985
    [41] P. Kowalski, W. Wi'slicki, L. Raczy'nski, D. Alfs, T. Bednarski, P. Bialas, et al., Scatter fraction of the J-PET tomography scanner, Acta Phys. Pol. B, 47 (2016), 549–560. https://doi.org/10.5506/APhysPolB.47.549 doi: 10.5506/APhysPolB.47.549
    [42] M. Pawlik-Niedźwiecka, S. Niedźwiecki, D. Alfs, P. Bialas, C. Curceanu, E. Czerwiński, et al., Preliminary studies of J-PET detector spatial resolution, Acta Phys. Polon. A, 132 (2017), 1645–1648. https://doi.org/10.12693/APhysPolA.132.1645 doi: 10.12693/APhysPolA.132.1645
    [43] P. Moskal, P. Kowalski, R. Y. Shopa, L. Raczyński, J. Baran, N. Chug, et al., Simulating NEMA characteristics of the modular total-body J-PET scanner - an economic total-body PET from plastic scintillators, Phys. Med. Biol., 66 (2021), 175015. https://doi.org/10.1088/1361-6560/ac16bd doi: 10.1088/1361-6560/ac16bd
    [44] F. Murtagh, Multilayer perceptrons for classification and regression, Neurocomputing, 2 (1991), 183–197. https://doi.org/10.1016/0925-2312(91)90023-5 doi: 10.1016/0925-2312(91)90023-5
    [45] H. Ramchoun, M. A. Janati Idrissi, Y. Ghanou, M. Ettaouil, Multilayer perceptron: Architecture optimization and training, Int. J. Interact. Multim. Artif. Intell., 4 (2016), 26–30. https://doi.org/10.9781/ijimai.2016.415 doi: 10.9781/ijimai.2016.415
    [46] A. Landi, P. Piaggi, M. Laurino, D. Menicucci, Artificial neural networks for nonlinear regression and classification, in 2010 10th International Conference on Intelligent Systems Design and Applications, (2010), 115–120. https://doi.org/10.1109/ISDA.2010.5687280
  • Reader Comments
  • © 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(2441) PDF downloads(109) Cited by(2)

Figures and Tables

Figures(11)  /  Tables(4)

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog