Displaying publications 1 - 20 of 1492 in total

  1. Mohd Rohani MF, Zanial AZ, Suppiah S, Phay Phay K, Mohamed Aslum Khan F, Mohamad Najib FH, et al.
    Nucl Med Commun, 2021 Jan;42(1):9-20.
    PMID: 33165258 DOI: 10.1097/MNM.0000000000001306
    Skeletal whole-body scintigraphy (WBS), although widely used as a sensitive tool for detecting metastatic bone disease in oncology cases, has relatively low specificity. Indeterminate bone lesions (IBLs) detected by WBS cause a diagnostic dilemma, which hampers further management plans. In the advent of hybrid imaging, single-photon emission computed tomography/computed tomography (SPECT/CT) has been gaining popularity as a tool to improve the characterisation of IBLs detected by WBS. As yet, there has not been a systematic review to objectively evaluate the diagnostic capabilities of SPECT/CT in this area. We conducted a systematic review of relevant electronic databases up to 30 August 2020. The outcomes of interest were the reporting of SPECT/CT to identify benign and malignant IBLs and the calculation of the sensitivity and specificity of the index test, based on histopathological examination or clinical and imaging follow-up as the reference standard. After the risk of bias and eligibility assessment, 12 articles were identified and synthesised in the meta-analysis. The pooled sensitivity and specificity of SPECT/CT for diagnosing IBLs are 93.0% [95% confidence interval (CI) 0.91-0.95] and 96.0% (95% CI 0.94-0.97), respectively. There was heterogeneity of the articles due to variable imaging protocols, duration of follow-up and scoring methods for interpreting the SPECT/CT results. The heterogeneity poses a challenge for accurate interpretation of the true diagnostic capability of SPECT/CT. In conclusion, targeted SPECT/CT improves the specificity of diagnosing bone metastases, but efforts need to be made to standardise the thresholds for SPECT/CT, methodology, as well as harmonising the reporting and interpretation criteria. We also make some recommendations for future works.
    Matched MeSH terms: Single Photon Emission Computed Tomography Computed Tomography/methods*
  2. Halim F, Yahya H, Jaafar KN, Mansor S
    J Nucl Med Technol, 2021 Sep;49(3):250-255.
    PMID: 33722927 DOI: 10.2967/jnmt.120.259168
    Advances in iterative image reconstruction enable absolute quantification of SPECT/CT studies by incorporating compensations for collimator-detector response, attenuation, and scatter. This study aimed to assess the quantitative accuracy of SPECT/CT based on different levels of 99mTc activity (low/high) using different SUV metrics (SUVmean, SUVmax, SUV0.6 max, and SUV0.75 max [the average values that include pixels greater than 60% and 75% of the SUVmax in the volume of interest, respectively]). Methods: A Jaszczak phantom equipped with 6 fillable spheres was set up with low and high activity ratios of 1:4 and 1:10 (background-to-sphere) on background activities of 10 and 60 kBq/mL, respectively. The fixed-size volume of interest based on the diameter of each sphere was drawn on SPECT images using various metrics for SUV quantification purposes. Results: The convergence of activity concentration was dependent on the number of iterations and application of postfiltering. For the background-to-sphere ratio of 1:10 with a low background activity concentration, the SUVmean metric showed an underestimation of about 38% from the actual SUV, and SUVmax exhibited an overestimation of about 24% for the largest sphere diameter. Meanwhile, bias reductions of as much as -6% and -7% for SUV0.6 max and SUV0.75 max, respectively, were observed. SUVmax gave a more accurate reading than the others, although points that exceeded the actual value were detected. At 1:4 and 1:10 background activity of 10 kBq/mL, a low activity concentration attained a value close to the actual ratio. Use of 2 iterations and 10 subsets without postfiltering gave the most accurate values for reconstruction and the best image overall. Conclusion: SUVmax is the best metric in a high- or low-contrast-ratio phantom with at least 2 iterations, 10 subsets, and no postfiltering.
    Matched MeSH terms: Tomography, X-Ray Computed; Tomography, Emission-Computed, Single-Photon*; Single Photon Emission Computed Tomography Computed Tomography*
  3. Joshi SC, Pant I, Hamzah F, Kumar G, Shukla AN
    Indian J Cancer, 2008 12 30;45(4):137-41.
    PMID: 19112200
    Positron emission tomography (PET) has emerged as an important diagnostic tool in the management of lung cancers. Although PET is sensitive in detection of lung cancer, but FDG (2-deoxy-2- 18 fluro-D-glucose) is not tumor specific and may accumulate in a variety of nonmalignant conditions occasionally giving false positive result. Addition of CT to PET improves specificity foremost, but also sensitivity in tumor imaging. Thus, PET/CT fusion images are a more accurate test than either of its individual components and are probably also better than side-by-side viewing of images from both modalities. PET/CT fusion images are useful in differentiating between malignant and benign disease, fibrosis and recurrence, staging and in changing patient management to more appropriate therapy. With analysis and discussion it appears that PET/ CT fusion images have the potential to dramatically improve our ability to manage the patients with lung cancer and is contributing to our understanding of cancer cell biology and in development of new therapies.
    Matched MeSH terms: Tomography, X-Ray Computed/methods*; Tomography, X-Ray Computed/trends; Positron-Emission Tomography/methods*; Positron-Emission Tomography/trends
  4. May IJ, Nowak AK, Francis RJ, Ebert MA, Dhaliwal SS
    J Med Imaging Radiat Oncol, 2024 Feb;68(1):57-66.
    PMID: 37898984 DOI: 10.1111/1754-9485.13592
    INTRODUCTION: Malignant pleural mesothelioma is difficult to prognosticate. F18-Fluorodeoxyglucose positron emission tomography (FDG PET) shows promise for response assessment but is confounded by talc pleurodesis. F18-Fluorothymidine (FLT) PET is an alternative tracer specific for proliferation. We compared the prognostic value of FDG and FLT PET and determined the influence of talc pleurodesis on these parameters.

    METHODS: Overall, 29 prospectively recruited patients had FLT PET, FDG PET and CT-scans performed prior to and post one chemotherapy cycle; 10 had prior talc pleurodesis. Patients were followed for overall survival. CT response was assessed using mRECIST. Radiomic features were extracted using the MiM software platform. Changes in maximum SUV (SUVmax), mean SUV (SUVmean), FDG total lesion glycolysis (TLG), FLT total lesion proliferation (TLP) and metabolic tumour volume (MTV) after one chemotherapy cycle.

    RESULTS: Cox univariate analysis demonstrated FDG PET radiomics were confounded by talc pleurodesis, and that percentage change in FLT MTV was predictive of overall survival. Cox multivariate analysis showed a 10% increase in FLT tumour volume corresponded with 9.5% worsened odds for overall survival (P = 0.028, HR = 1.095, 95% CI [1.010, 1.187]). No other variables were significant on multivariate analysis.

    CONCLUSION: This is the first prospective study showing the statistical significance of FLT PET tumour volumes for measuring mesothelioma treatment response. FLT may be better than FDG for monitoring mesothelioma treatment response, which could help optimise mesothelioma treatment regimes.

    Matched MeSH terms: Positron-Emission Tomography/methods; Positron Emission Tomography Computed Tomography/methods
  5. Mahmud MH, Nordin AJ, Ahmad Saad FF, Azman AZ
    Quant Imaging Med Surg, 2015 Oct;5(5):700-7.
    PMID: 26682140 DOI: 10.3978/j.issn.2223-4292.2015.05.02
    Increased metabolic activity of fluorodeoxyglucose (FDG) in tissue is not only resulting of pathological uptake, but due to physiological uptake as well. This study aimed to determine the impacts of biological and procedural factors on FDG uptake of liver in whole body positron emission tomography/computed tomography (PET/CT) imaging.
    Matched MeSH terms: Positron-Emission Tomography; Positron Emission Tomography Computed Tomography
  6. Ahmad Sarji S
    Biomed Imaging Interv J, 2006 Oct;2(4):e59.
    PMID: 21614339 MyJurnal DOI: 10.2349/biij.2.4.e59
    Many potential pitfalls and artefacts have been described in PET imaging that uses F-18 fluorodeoxyglucose (FDG). Normal uptake of FDG occurs in many sites of the body and may cause confusion in interpretation particularly in oncology imaging. Clinical correlation, awareness of the areas of normal uptake of FDG in the body and knowledge of variation in uptake as well as benign processes that are FDG avid are necessary to avoid potential pitfalls in image interpretation. In this context, optimum preparation of patients for their scans can be instituted in an attempt to reduce the problem. Many of the problems and pitfalls associated with areas of normal uptake of FDG can be solved by using PET CT imaging. PET CT imaging has the ability to correctly attribute FDG activity to a structurally normal organ on CT. However, the development of combined PET CT scanners also comes with its own specific problems related to the combined PET CT technique. These include misregistration artefacts due to respiration and the presence of high density substances which may lead to artefactual overestimation of activity if CT data are used for attenuation correction.
    Matched MeSH terms: Tomography Scanners, X-Ray Computed; Positron-Emission Tomography; Positron Emission Tomography Computed Tomography
  7. Hayati F, Wong MJJ, Jailani RF, Ng CY
    ANZ J Surg, 2021 10;91(10):2226.
    PMID: 34665495 DOI: 10.1111/ans.17088
    Matched MeSH terms: Tomography, X-Ray Computed
  8. Abuzaid MM, Elshami W, Tekin HO, Sulieman A, Bradley DA
    Radiat Prot Dosimetry, 2021 Nov 03;196(1-2):10-16.
    PMID: 34423365 DOI: 10.1093/rpd/ncab125
    The present study compares three different multidetector CT (MDCT) scanners for routine brain imaging in terms of image quality and radiation doses. The volume CT dose index (CTDIvol), dose-length product (DLP), and effective dose (E) were calculated. Subjective image assessment was obtained based on a scale ranging from 1 (unacceptable) to 5 (optimum). All images scored 3.5 or over, with the 160-slice MDCT images being favoured. For the 4-, 16- and 160-slice MDCT scanners, the respective median values for CTDIvol were 57 mGy, 41 mGy, and 28 mGy; DLP values were 901 mGy.cm, 680 mGy.cm, and 551 mGy.cm; and effective doses were 2 mSv, 1.5 mSv, and 1 mSv, respectively. Compared to the 160-slice MDCT, the dose values for the 4- and 16-slice units were significantly greater. In practice, the CT modality used must be carefully selected to avoid elevated radiation doses and maintain image quality.
    Matched MeSH terms: Tomography Scanners, X-Ray Computed; Cone-Beam Computed Tomography; Multidetector Computed Tomography*
  9. Ren X, Nur Salihin Yusoff M, Hartini Mohd Taib N, Zhang L, Wang K
    Eur J Radiol, 2024 Jan;170:111274.
    PMID: 38147764 DOI: 10.1016/j.ejrad.2023.111274
    PURPOSE: The goal of this study was to evaluate the effectiveness of two diagnostic methods, 68Ga-PSMA-11 PET/CT and mpMRI, in detecting primary prostate cancer without limitations on the Gleason score.

    METHODS: We conducted a comprehensive literature review, searching databases such as PubMed, Embase, and Web of Science until June 2023. Our objective was to identify studies that compared the efficacy of 68Ga-PSMA-11 PET/CT and mpMRI in detecting primary prostate cancer. To determine heterogeneity, the I2 statistic was used. Meta-regression analysis and leave-one-out sensitivity analysis were conducted to identify potential sources of heterogeneity.

    RESULTS: Initially, 1286 publications were found, but after careful evaluation, only 16 studies involving 1227 patients were analyzed thoroughly. The results showed that the 68Ga-PSMA-11 PET/CT method had a pooled sensitivity and specificity of 0.87 (95 % CI: 0.80-0.92) and 0.80 (95 % CI: 0.69-0.89), respectively, for diagnosing prostatic cancer. Similarly, the values for mpMRI were determined as 0.84 (95 % CI: 0.75-0.92) and 0.74 (95 % CI: 0.61-0.86), respectively. There were no significant differences in diagnostic effectiveness observed when comparing two primary prostate cancer methodologies (pooled sensitivity P = 0.62, pooled specificity P = 0.50). Despite this, the funnel plots showed symmetry and the Egger test results (P values > 0.05) suggested there was no publication bias.

    CONCLUSIONS: After an extensive meta-analysis, it was found that both 68Ga-PSMA-11 PET/CT and mpMRI demonstrate similar diagnostic effectiveness in detecting primary prostate cancer. Future larger prospective studies are warranted to investigate this issue further.

    Matched MeSH terms: Positron Emission Tomography Computed Tomography/methods
  10. Rahim RA, Chen LL, San CK, Rahiman MH, Fea PJ
    Sensors (Basel), 2009;9(11):8562-78.
    PMID: 22291523 DOI: 10.3390/s91108562
    This paper explains in detail the solution to the forward and inverse problem faced in this research. In the forward problem section, the projection geometry and the sensor modelling are discussed. The dimensions, distributions and arrangements of the optical fibre sensors are determined based on the real hardware constructed and these are explained in the projection geometry section. The general idea in sensor modelling is to simulate an artificial environment, but with similar system properties, to predict the actual sensor values for various flow models in the hardware system. The sensitivity maps produced from the solution of the forward problems are important in reconstructing the tomographic image.
    Matched MeSH terms: Tomography; Tomography, X-Ray Computed
  11. Ariffin AC, Ngadiron H
    World J Surg, 2018 04;42(4):1212.
    PMID: 28879497 DOI: 10.1007/s00268-017-4222-1
    Matched MeSH terms: Tomography, X-Ray Computed*
  12. Rukiah A. Latiff, Akmal Sabaruddin, Norfadilah Mat Nor
    Thyroid and gonads are radiosensitive organs which requires radiation shield to reduce the dose received. However,
    radiation shielding is not widely used in radionuclide imaging because it is heavy, uncomfortable and can cause pain
    in the spine. Therefore, a research was carried out to determine the ability of thyroid and gonad radiation shield
    which is thinner and lighter in reducing radiation dose. A study was conducted in Hospital Putrajaya to determine
    the radiation dose received by the thyroid and gonads during a complete Positron Emission Tomography-Computed
    Tomography (PET-CT) procedure with and without radiation shield. A total of six male staffs have been chosen as subject
    and data from 33 complete PET-CT procedures have been collected. For every PET-CT procedure, the subject’s thyroid
    and gonad were shielded using 0.5-mm thick radiation shielded, model Mavig 615 (USA) and Shielding International
    (USA) respectively. Thermal luminescent dosimeter (TLD) chips were used as radiation dose detector. The average 18FFDG radioactivity administered to the patient was 387 MBq and the average scan time is 9.224 ± 1.797 minutes. The
    results showed that the mean equivalent dose received by the thyroid with and without shielding were 0.080 ± 0.033
    mSv and 0.078 ± 0.039 mSv respectively. The mean equivalent dose received by gonad with and without shielding
    were 0.059 ± 0.040 mSv and 0.061 ± 0.030 mSv respectively. Radiation shield with 0.5 mm thickness is unable to
    reduce radiation dose received by the thyroid (p = 0.76) and gonads (p = 0.79) because it is too thin to resist the
    high-energy radiation during PET-CT procedures. Thyroid receive higher radiation dose of 0.016 m Sv compared to
    the gonads (p < 0.05) because the thyroid’s position is more exposed to radiation sources which are 18F-FDG during
    radiopharmaceutical preparation and patients after administered with 18F-FDG during PET-CT procedure.
    Keywords: equivalent dose, radiation shield, TLD
    Matched MeSH terms: Tomography, X-Ray Computed; Positron-Emission Tomography
  13. Pszczolkowski S, Manzano-Patrón JP, Law ZK, Krishnan K, Ali A, Bath PM, et al.
    Eur Radiol, 2021 Oct;31(10):7945-7959.
    PMID: 33860831 DOI: 10.1007/s00330-021-07826-9
    OBJECTIVES: To test radiomics-based features extracted from noncontrast CT of patients with spontaneous intracerebral haemorrhage for prediction of haematoma expansion and poor functional outcome and compare them with radiological signs and clinical factors.

    MATERIALS AND METHODS: Seven hundred fifty-four radiomics-based features were extracted from 1732 scans derived from the TICH-2 multicentre clinical trial. Features were harmonised and a correlation-based feature selection was applied. Different elastic-net parameterisations were tested to assess the predictive performance of the selected radiomics-based features using grid optimisation. For comparison, the same procedure was run using radiological signs and clinical factors separately. Models trained with radiomics-based features combined with radiological signs or clinical factors were tested. Predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) score.

    RESULTS: The optimal radiomics-based model showed an AUC of 0.693 for haematoma expansion and an AUC of 0.783 for poor functional outcome. Models with radiological signs alone yielded substantial reductions in sensitivity. Combining radiomics-based features and radiological signs did not provide any improvement over radiomics-based features alone. Models with clinical factors had similar performance compared to using radiomics-based features, albeit with low sensitivity for haematoma expansion. Performance of radiomics-based features was boosted by incorporating clinical factors, with time from onset to scan and age being the most important contributors for haematoma expansion and poor functional outcome prediction, respectively.

    CONCLUSION: Radiomics-based features perform better than radiological signs and similarly to clinical factors on the prediction of haematoma expansion and poor functional outcome. Moreover, combining radiomics-based features with clinical factors improves their performance.

    KEY POINTS: • Linear models based on CT radiomics-based features perform better than radiological signs on the prediction of haematoma expansion and poor functional outcome in the context of intracerebral haemorrhage. • Linear models based on CT radiomics-based features perform similarly to clinical factors known to be good predictors. However, combining these clinical factors with radiomics-based features increases their predictive performance.

    Matched MeSH terms: Tomography, X-Ray Computed*
  14. Tan HY, Wong YH, Kasbollah A, Md Shah MN, Perkins AC, Yeong CH
    Nucl Med Commun, 2023 Apr 01;44(4):227-243.
    PMID: 36808108 DOI: 10.1097/MNM.0000000000001665
    Personalised cancer treatment is of growing importance and can be achieved via targeted radionuclide therapy. Radionuclides with theranostic properties are proving to be clinically effective and are widely used because diagnostic imaging and therapy can be accomplished using a single formulation that avoids additional procedures and unnecessary radiation burden to the patient. For diagnostic imaging, single photon emission computed tomography (SPECT) or positron emission tomography (PET) is used to obtain functional information noninvasively by detecting the gamma (γ) rays emitted from the radionuclide. For therapeutics, high linear energy transfer (LET) radiations such as alpha (α), beta (β - ) or Auger electrons are used to kill cancerous cells in close proximity, whereas sparing the normal tissues surrounding the malignant tumour cells. One of the most important factors that lead to the sustainable development of nuclear medicine is the availability of functional radiopharmaceuticals. Nuclear research reactors play a vital role in the production of medical radionuclides for incorporation into clinical radiopharmaceuticals. The disruption of medical radionuclide supplies in recent years has highlighted the importance of ongoing research reactor operation. This article reviews the current status of operational nuclear research reactors in the Asia-Pacific region that have the potential for medical radionuclide production. It also discusses the different types of nuclear research reactors, their operating power, and the effects of thermal neutron flux in producing desirable radionuclides with high specific activity for clinical applications.
    Matched MeSH terms: Tomography, Emission-Computed, Single-Photon; Positron-Emission Tomography
  15. Dureja S, McDonnell M, Van Genechten D, Bouvier C, Kolarova T, O'Toole D, et al.
    J Neuroendocrinol, 2023 Jun;35(6):e13310.
    PMID: 37351944 DOI: 10.1111/jne.13310
    SCAN, an online survey, measured access to diagnosis, treatments and monitoring of neuroendocrine tumor (NET) patients globally. Between September and November 2019, NET patients and healthcare professionals (HCPs) completed an online, semi-standardized survey with 54 patient questions and 33 HCP questions. A total of 2359 patients with NETs and 436 HCPs responded. Misdiagnosis was common (44% [1043/2359]). Mean time to diagnosis was 4.8 years (standard deviation [SD], 6.2). Compared with global figures (60% [1407/2359]), the availability of 68 Ga-DOTA positron emission tomography (PET)/computed tomography (CT) was significantly lower in Asia (45% [126/280]) and higher in Oceania (86% [171/200]). HCPs reported that 68 Ga-DOTA PET/CT was free/affordable to fewer patients in Emerging and Developing Economies (EDE) than Advanced Economies (AE; 17% [26/150] and 59% [84/142], respectively). Compared with global data (52% [1234/2359]), patient-reported availability of peptide receptor radionuclide therapy (PRRT) was significantly lower in Asia (31% [88/280]) and higher in Oceania (61% [122/200]). Significant differences were observed in average annual NET specialist costs between AE and EDE ($1081 and $2915, respectively). Compared with AE, patients in EDE traveled further for NET specialists (1032 [SD, 1578] and 181 [SD, 496] km, respectively). Patients and HCPs both recommended referral to HCPs that were more knowledgeable in the field of NETs and had better access to NET experts/specialist centers. National care pathways, enhancing HCP NET knowledge and ensuring effective diagnostics and access to appropriate treatments are crucial to improving patient survival and NET care worldwide.
    Matched MeSH terms: Positron Emission Tomography Computed Tomography
  16. Potapov AL, Loginova MM, Moiseev AA, Radenska-Lopovok SG, Kuznetsov SS, Kuznetsova IA, et al.
    Sovrem Tekhnologii Med, 2023;15(1):53-60.
    PMID: 37388751 DOI: 10.17691/stm2023.15.1.06
    The aim of the study was to identify different degrees of dermal lesions in vulvar lichen sclerosus (VLS) using cross-polarization optical coherence tomography (CP OCT) based on attenuation coefficient to detect disease early manifestations and to monitor the effectiveness of treatment.

    MATERIALS AND METHODS: The study included 10 patients without pathology and 39 patients with VLS diagnosed histologically. CP OCT was performed in vivo on the inner surface of the labia minora, in the main lesion area. From each scanning point, a 3.4×3.4×1.25-mm3 3D data array was obtained in 26 s. CP OCT examination results were compared with histological examination of specimens stained with Van Gieson's picrofuchsin.Quantitative analysis of OCT images was performed by measuring the attenuation coefficient in co-polarization and cross-polarization. For visual analysis, color-coded charts were developed based on OCT attenuation coefficients.

    RESULTS: According to histological examination, all patients with VLS were divided into 4 groups as per dermal lesion degree: initial (8 patients); mild (7 patients); moderate (9 patients); severe (15 patients). Typical features of different degrees were interfibrillary edema up to 250 μm deep for initial degree, thickened collagen bundles without edema up to 350 μm deep for mild degree, dermis homogenization up to 700 μm deep for moderate degree, dermis homogenization and total edema up to 1200 μm deep for severe degree.Pathological processes in dermis during VLS like interfibrillary edema and collagen bundles homogenization were visualized using CP OCT method based on values of attenuation coefficient in co- and cross-polarization channels. However, CP OCT method appeared to be less sensitive to changes of collagen bundles thickness not allowing to distinguish thickened collagen bundles from normal ones with enough statistical significance. The CP OCT method was able to differentiate all degrees of dermal lesions among themselves. OCT attenuation coefficients differed from normal condition with statistical significance for all degrees of lesions, except for mild.

    CONCLUSION: For the first time, quantitative parameters for each degrees of dermis lesion in VLS, including initial degree, were determined by CP OCT method allowing to detect the disease at an early stage and to monitor the applied clinical treatment effectiveness.

    Matched MeSH terms: Tomography, Optical Coherence*
  17. Ng AH, Ng KH, Dharmendra H, Perkins AC
    Appl Radiat Isot, 2009 Oct;67(10):1864-8.
    PMID: 19049851 DOI: 10.1016/j.apradiso.2008.10.010
    A simple sphere test phantom has been developed for routine performance testing of SPECT systems in situations where expensive commercial phantoms may not be available. The phantom was based on a design with six universal syringe hubs set in the frame to support a circular array of six glass blown spheres of different sizes. The frame was then placed into a water-filled CT abdomen phantom and scanned with a triple head camera system (Philips IRIX, USA). Comparison was made with a commercially available phantom (Deluxe Jaszczak phantom). Whereas the commercial phantom demonstrates cold spot resolution, an important advantage of the sphere test phantom was that hot spot resolution could be easily measured using almost half (370MBq) of the activity recommended for use in the commercial phantom. Results showed that the contrast increased non-linearly with sphere volume and radionuclide concentration. The phantom was found to be suitable as an inexpensive option for daily performance tests.
    Matched MeSH terms: Tomography, Emission-Computed, Single-Photon/instrumentation*; Tomography, Emission-Computed, Single-Photon/methods
  18. Karobari MI, Noorani TY, Halim MS, Ahmed HMA
    Aust Endod J, 2021 Aug;47(2):202-216.
    PMID: 33159714 DOI: 10.1111/aej.12454
    This cone beam computed tomography (CBCT) study aimed to evaluate the root canal morphology of permanent anteriors in Malaysian population using two classification systems (Vertucci 1984 and Ahmed et al 2017). CBCT images of 856 patients with 10,080 anterior teeth were analysed. Results showed that, except for six mandibular canines, all anterior teeth were single-rooted. According to Ahmed et al's system and Vertucci's classification, code 1 MaxA1 and type I were the most common types except in mandibular laterals where 1 ManA1-2-1 and type III were the most common, respectively. The prevalence of canal variations in mandibular incisors was higher in males and the 20-30 age group than in females and other age groups (P 
    Matched MeSH terms: Cone-Beam Computed Tomography; Spiral Cone-Beam Computed Tomography*
  19. Reduwan NH, Abdul Aziz AA, Mohd Razi R, Abdullah ERMF, Mazloom Nezhad SM, Gohain M, et al.
    BMC Oral Health, 2024 Feb 19;24(1):252.
    PMID: 38373931 DOI: 10.1186/s12903-024-03910-w
    BACKGROUND: Artificial intelligence has been proven to improve the identification of various maxillofacial lesions. The aim of the current study is two-fold: to assess the performance of four deep learning models (DLM) in external root resorption (ERR) identification and to assess the effect of combining feature selection technique (FST) with DLM on their ability in ERR identification.

    METHODS: External root resorption was simulated on 88 extracted premolar teeth using tungsten bur in different depths (0.5 mm, 1 mm, and 2 mm). All teeth were scanned using a Cone beam CT (Carestream Dental, Atlanta, GA). Afterward, a training (70%), validation (10%), and test (20%) dataset were established. The performance of four DLMs including Random Forest (RF) + Visual Geometry Group 16 (VGG), RF + EfficienNetB4 (EFNET), Support Vector Machine (SVM) + VGG, and SVM + EFNET) and four hybrid models (DLM + FST: (i) FS + RF + VGG, (ii) FS + RF + EFNET, (iii) FS + SVM + VGG and (iv) FS + SVM + EFNET) was compared. Five performance parameters were assessed: classification accuracy, F1-score, precision, specificity, and error rate. FST algorithms (Boruta and Recursive Feature Selection) were combined with the DLMs to assess their performance.

    RESULTS: RF + VGG exhibited the highest performance in identifying ERR, followed by the other tested models. Similarly, FST combined with RF + VGG outperformed other models with classification accuracy, F1-score, precision, and specificity of 81.9%, weighted accuracy of 83%, and area under the curve (AUC) of 96%. Kruskal Wallis test revealed a significant difference (p = 0.008) in the prediction accuracy among the eight DLMs.

    CONCLUSION: In general, all DLMs have similar performance on ERR identification. However, the performance can be improved by combining FST with DLMs.

    Matched MeSH terms: Cone-Beam Computed Tomography; Spiral Cone-Beam Computed Tomography*
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links