Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

Whole-body bone scanning is a nuclear medicine technique with high sensitivity used for the diagnosis of bone-related diseases [., bone metastases] that can be obtained by positron emission tomography (PET) or single-photon emission computed tomography[SPECT] imaging, depending on the different radiopharmaceuticals used. In contrast to the high sensitivity of the bone scan, it has low specificity, which leads to misinterpretation, causing adverse effects of unwarranted intervention or interruption to timely treatment.

Objective

To address this problem, this paper proposes a joint model called mSegResRF-SPECT, which accomplishes for the first time the task of classifying whole-body bone scan images on a public SPECT dataset [BS-80K] for the diagnosis of bone metastases.

Methods

The mSegResRF-SPECT adopts a region algorithm to segment the whole body image into 13 regions, as an extractor to extract the regional features, and a algorithm as a classifier.

Results

The experimental results of the proposed model show that the average accuracy, sensitivity, and F1 score of the model on the BS-80K dataset reached SOTA.

Conclusion

The proposed method presents a promising solution for better bone scan classification methods.

© 2024 The Author(s). Published by Bentham Science Publisher.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056288472240129112028
2024-01-01
2025-07-03

  • From This Site

    /content/journals/cmir/10.2174/0115734056288472240129112028
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. HuttonB.F. The origins of SPECT and SPECT/CT.Eur. J. Nucl. Med. Mol. Imaging201441S1Suppl. 131610.1007/s00259‑013‑2606‑524218098
     [Google Scholar]
  2. DavisK.M. RyanJ.L. AaronV.D. SimsJ.B. PET and SPECT imaging of the brain: History, technical considerations, applications, and radiotracers.Seminars in Ultrasound, CT and MRI.Elsevier202052152910.1053/j.sult.2020.08.006
     [Google Scholar]
  3. Al BadarinF.J. MalhotraS. Diagnosis and prognosis of coronary artery disease with SPECT and PET.Curr. Cardiol. Rep.20192175710.1007/s11886‑019‑1146‑431104158
     [Google Scholar]
  4. Van den WyngaertT. Strobel K. Kampen WU. Kuwert T. van der BruggenW. Mohan HK. EANM bone & joint committee and the oncology committee. The EANM practice guidelines for bone scintigraphy.Eur J Nucl Med Mol Imaging.201643917231738
     [Google Scholar]
  5. AlbalooshiB. Al SharhanM. BagheriF. MiyanathS. RayB. MuhasinM. ZakaviS.R. Direct comparison of 99mTc-PSMA SPECT/CT and 68Ga-PSMA PET/CT in patients with prostate cancer.Asia Ocean. J. Nucl. Med. Biol.2020811732064277
     [Google Scholar]
  6. ZhangY. LinZ. LiT. WeiY. YuM. YeL. CaiY. YangS. ZhangY. ShiY. ChenW. Head-to-head comparison of 99mTc-PSMA and 99mTc-MDP SPECT/CT in diagnosing prostate cancer bone metastasis: A prospective, comparative imaging trial.Sci. Rep.20221211599310.1038/s41598‑022‑20280‑x36163353
     [Google Scholar]
  7. GandagliaG. KarakiewiczP.I. BrigantiA. PassoniN.M. SchiffmannJ. TrudeauV. GraefenM. MontorsiF. SunM. Impact of the site of metastases on survival in patients with metastatic prostate cancer.Eur. Urol.201568232533410.1016/j.eururo.2014.07.02025108577
     [Google Scholar]
  8. BafarajS.M. Assessment of sensitivity, specificity, and accuracy of nuclear medicines, CT scan, and ultrasound in diagnosing thyroid disorders.Curr. Med. Imaging Rev.202016319319810.2174/157340561466618090412291232133948
     [Google Scholar]
  9. D’AntoniF. RussoF. AmbrosioL. BaccoL. VolleroL. VadalàG. MeroneM. PapaliaR. DenaroV. Artificial intelligence and computer aided diagnosis in chronic low back pain: A systematic review.Int. J. Environ. Res. Public Health20221910597110.3390/ijerph1910597135627508
     [Google Scholar]
  10. YanaseJ. TriantaphyllouE. A systematic survey of computer-aided diagnosis in medicine: Past and present developments.Expert Syst. Appl.201913811282110.1016/j.eswa.2019.112821
     [Google Scholar]
  11. ChanH.P. HadjiiskiL.M. SamalaR.K. Computer‐aided diagnosis in the era of deep learning.Med. Phys.2020475e218e22710.1002/mp.1376432418340
     [Google Scholar]
  12. AljuaidH. AlturkiN. AlsubaieN. CavallaroL. LiottaA. Computer-aided diagnosis for breast cancer classification using deep neural networks and transfer learning.Comput. Methods Programs Biomed.202222310695110.1016/j.cmpb.2022.10695135767911
     [Google Scholar]
  13. SrideviS. MurugesanS. SakthivelV. KavithaD. Computer-aided decision support system for symmetry-based prenatal congenital heart defects.Advanced Machine Vision Paradigms for Medical Image Analysis.Elsevier2021115310.1016/B978‑0‑12‑819295‑5.00002‑0
     [Google Scholar]
  14. BiD. ZhuD. SheykhahmadF.R. QiaoM. Computer-aided skin cancer diagnosis based on a new meta-heuristic algorithm combined with support vector method.Biomed. Signal Process. Control20216810263110.1016/j.bspc.2021.102631
     [Google Scholar]
  15. ChangQ. WangQ. QiaoY. ZhuY. HuangG. YangJ. Adaptive detection of hotspots in thoracic spine from bone scintigraphy.Neural Information ProcessingLu BL, Zhang L, Kwok J, editors. Springer Berlin HeidelbergBerlin, Heidelberg2011257264Available from: http://link.springer.com/10.1007/978-3-642-24955-6_31
    [Google Scholar]
  16. MostafapourS. GholamiankhahF. MaroufpourS. MomennezhadM. AsadinezhadM. ZakaviS.R. Deep learning-guided attenuation correction in the image domain for myocardial perfusion SPECT imaging.J. Comput. Des. Eng.202292434447
     [Google Scholar]
  17. HuangZ. PuX. TangG. PingM. JiangG. WangM. WeiX. RenY. BS-80K: The first large open-access dataset of bone scan images.Comput. Biol. Med.2022151Pt A10622110.1016/j.compbiomed.2022.10622136334360
     [Google Scholar]
  18. Nhu HaiP. Chi ThanhN. Thanh TrungN. Trung KienT. Transfer learning for disease diagnosis from myocardial perfusion spect imaging.Comput. Mater. Continua20227335925594110.32604/cmc.2022.031027
     [Google Scholar]
  19. TeixeiraL.O. PereiraR.M. BertoliniD. OliveiraL.S. NanniL. CavalcantiG.D.C. CostaY.M.G. Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images.Sensors20212121711610.3390/s2121711634770423
     [Google Scholar]
  20. SungheethaD.A. Comparative study: Statistical approach and deep learning method for automatic segmentation methods for lung CT image segmentation.J Innovat. Image Processing20202418719310.36548/jiip.2020.4.003
     [Google Scholar]
  21. CaughlinK. ShahediM. ShoagJ.E. BarbieriC.E. MargolisD.J. FeiB. Three-dimensional prostate CT segmentation through fine-tuning of a pre-trained neural network using no reference labeling.Medical Imaging 2021: Image-Guided Procedures, Robotic Interventions, and Modeling. LinteC.A. SiewerdsenJ.H. Online Only, United StatesSPIE20211810.1117/12.2581963
     [Google Scholar]
  22. AltiniN. PrencipeB. CascaranoG.D. BrunettiA. BrunettiG. TriggianiV. CarnimeoL. MarinoF. GuerrieroA. VillaniL. ScardapaneA. BevilacquaV. Liver, kidney and spleen segmentation from CT scans and MRI with deep learning: A survey.Neurocomputing2022490305310.1016/j.neucom.2021.08.157
     [Google Scholar]
  23. LiL. JiangC. WangP.S.P. ZhengS. 3D PET/CT tumor co-segmentation based on background subtraction hybrid active contour model.Int. J. Pattern Recognit. Artif. Intell.2023378235700610.1142/S0218001423570069
     [Google Scholar]
  24. SaoodA. HatemI. COVID-19 lung CT image segmentation using deep learning methods: U-Net versus SegNet.BMC Med. Imaging20212111910.1186/s12880‑020‑00529‑533557772
     [Google Scholar]
  25. BhanA MangipudiPS GoyalA Cardiac MRI segmentation using efficient ResNeXT-50-based IEI level set and anisotropic sigmoid diffusion algorithms.Int J Image Grap. 2022234001410.1142/S0219467823400144
     [Google Scholar]
  26. GoceriN. GoceriE. A neural network based kidney segmentation from MR images.2015 IEEE 14th international conference on machine learning and applications (ICMLA)IEEE20151195810.1109/ICMLA.2015.229
     [Google Scholar]
  27. Göçeri̇E. ÜnlüM.Z. Di̇cleO. A comparative performance evaluation of various approaches for liver segmentation from SPIR images.Turk. J. Electr. Eng. Comput. Sci.201523374176810.3906/elk‑1304‑36
     [Google Scholar]
  28. GöçeriE. A comparative evaluation for liver segmentation from spir images and a novel level set method using signed pressure force function.TurkeyIzmir Institute of Technology2013
     [Google Scholar]
  29. WadhwaA. BhardwajA. Singh VermaV. A review on brain tumor segmentation of MRI images.Magn. Reson. Imaging20196124725910.1016/j.mri.2019.05.04331200024
     [Google Scholar]
  30. ChengD. LamE.Y. Transfer learning u-net deep learning for lung ultrasound segmentation.arXiv2021Available from: http://arxiv.org/abs/2110.02196
    [Google Scholar]
  31. WangR. ZhouH. FuP. ShenH. BaiY. A multiscale attentional unet model for automatic segmentation in medical ultrasound images.Ultrason. Imaging202345415917410.1177/0161734623116978937114669
     [Google Scholar]
  32. M. Abdalla A. Abu Awad M. AlZoubi O. A. Al-SamrraieL. Automatic segmentation and detection system for varicocele using ultrasound images.Comput. Mater. Continua202272179781410.32604/cmc.2022.024913
     [Google Scholar]
  33. ZhouX. ChenY. LiuS. Deep learning for image segmentation: Ultrasound image segmentation of thyroid nodules based on U_Net. In: 2022 6th international conference on advances in image processing.InternetZhanjiang, ChinaACM20228790https://dl.acm.org/doi/10.1145/3577117.3577144
     [Google Scholar]
  34. XuY. WangY. YuanJ. ChengQ. WangX. CarsonP.L. Medical breast ultrasound image segmentation by machine learning.Ultrasonics2019911910.1016/j.ultras.2018.07.00630029074
     [Google Scholar]
  35. GoceriE. Automated skin cancer detection: Where we are and the way to the future.2021 44th international conference on telecommunications and signal processing (TSP).IEEE2021485110.1109/TSP52935.2021.9522605
     [Google Scholar]
  36. BuettnerR. BiloM. BayN. ZubacT. A systematic literature review of medical image analysis using deep learning.2020 IEEE Symposium on Industrial Electronics & Applications (ISIEA)Malaysia20201410.1109/ISIEA49364.2020.9188131
     [Google Scholar]
  37. ZhongY. XuM. WuM. Dive into Plane: Lightweight & Modular Linear Projection Cross-dimensional Network for Retinal Vessel Segmentation in OCTA Images. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).Las Vegas, NV, USAIEEE2022897901https://ieeexplore.ieee.org/document/9995294/
     [Google Scholar]
  38. WangM. QiS. WuY. SunY. ChangR. PangH. QianW. CE-NC-VesselSegNet: Supervised by contrast-enhanced CT images but utilized to segment pulmonary vessels from non-contrast-enhanced CT images.Biomed. Signal Process. Control20238210456510.1016/j.bspc.2022.104565
     [Google Scholar]
  39. Kumar KannathS. AnzarA. Sivan SulajaJ. Enakshy RajanJ. PnS. Semi-automated mapping of occluded arterial segments in acute large vessel stroke from computed tomography angiography.J. Stroke Cerebrovasc. Dis.2022311110676310.1016/j.jstrokecerebrovasdis.2022.10676336191567
     [Google Scholar]
  40. GaddamD.S. CrewsG. ChryssikosT. GandhiD. MoralesR. ZhuoJ. AlmardawiR. RaghavanP. Circumferential segmental vessel-wall enhancement on black blood MRI in patients referred for the evaluation of vasculopathy.Clin. Imaging202180677110.1016/j.clinimag.2021.05.02434246832
     [Google Scholar]
  41. MB. Automatic segmenting technique of brain tumors with convolutional neural networks in MRI images.2021 6th International Conference on Inventive Computation Technologies (ICICT) Coimbatore, India2021759764Available from: https://ieeexplore.ieee.org/document/9358737/ [cited 2023 Oct 23].
    [Google Scholar]
  42. ZhangB. QiS. WuY. PanX. YaoY. QianW. GuanY. Multi-scale segmentation squeeze-and-excitation UNet with conditional random field for segmenting lung tumor from CT images.Comput. Methods Programs Biomed.202222210694610.1016/j.cmpb.2022.10694635716533
     [Google Scholar]
  43. LiuJ. ZhengJ. JiaoG. Transition net: 2D backbone to segment 3D brain tumor.Biomed. Signal Process. Control20227510362210.1016/j.bspc.2022.103622
     [Google Scholar]
  44. KarmarkarR. BenjafieldA. JayarajP. ArooriS. Fluorescence guided resection of liver tumours: Same day administration of indocyanine green with the use of spy- colour segmented fluorescence imaging.HPB202325S55010.1016/j.hpb.2023.07.735
     [Google Scholar]
  45. SunY. KangH. ZhangH. WangY. ShenH. YuP. A global-local cascade network for multi-bone segmentation in chest CT. In: 2022 IEEE international conference on bioinformatics and biomedicine (BIBM).Las Vegas, NV, USAIEEE202280981210.1109/BIBM55620.2022.9995558
     [Google Scholar]
  46. RonnebergerO. FischerP. BroxT. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAINavab N, Hornegger J, Wells WM, Frangi AF, editors. Cham: Springer International Publishing.20159351234241Available from: http://link.springer.com/10.1007/978-3-319-24574-4_28
    [Google Scholar]
  47. ChenJ. LuY. YuQ. LuoX. AdeliE. WangY. TransUNet: Transformers make strong encoders for medical image segmentation.arXiv2021Available from: http://arxiv.org/abs/2102.04306 [cited 2023 Aug 6].
    [Google Scholar]
  48. IsenseeF. PetersenJ. KleinA. ZimmererD. JaegerP.F. KohlS. nnU-Net: Self-adapting framework for u-net-based medical image segmentation.arXiv2018Available from: http://arxiv.org/abs/1809.10486 [cited 2023 Oct 23].
    [Google Scholar]
  49. GuanS. KhanA.A. SikdarS. ChitnisP.V. Fully dense UNet for 2-D sparse photoacoustic tomography artifact removal.IEEE J. Biomed. Health Inform.202024256857610.1109/JBHI.2019.291293531021809
     [Google Scholar]
  50. XiaoX. LianS. LuoZ. LiS. Weighted res-unet for high-quality retina vessel segmentation.2018 9th International Conference on Information Technology in Medicine and Education (ITME).HangzhouIEEE2018327331https://ieeexplore.ieee.org/document/8589312/10.1109/ITME.2018.00080
     [Google Scholar]
  51. ZhuW. Deep learning for automated medical image analysis.arXiv2019Available from: http://arxiv.org/abs/1903.04711 [cited 2023 Oct 23].
    [Google Scholar]
  52. AydınN. ÇelikÖ. AslanA.F. OdabaşA. DündarE. ŞahinM.C. Detection of lung cancer on computed tomography using artificial intelligence applications developed by deep learning methods and the contribution of deep learning to the classification of lung carcinoma.Curr. Med. Imaging Rev.20211791137114110.2174/157340561766621020421050033563200
     [Google Scholar]
  53. LiuJ. DuH. BiQ. LiaoH. PanY. MEST: Multi-plane embedding and spatial-temporal transformer for parkinson’s disease diagnosis.2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).Las Vegas, NV, USAIEEE202210721077https://ieeexplore.ieee.org/document/9995498/
     [Google Scholar]
  54. GunduzH. Deep learning-based Parkinson’s disease classification using vocal feature sets.IEEE Access2019711554011555110.1109/ACCESS.2019.2936564
     [Google Scholar]
  55. WodzinskiM. SkalskiA. HemmerlingD. Orozco-ArroyaveJ.R. NothE. Deep learning approach to parkinson’s disease detection using voice recordings and convolutional neural network dedicated to image classification.2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).InternetBerlin, GermanyIEEE2019717720https://ieeexplore.ieee.org/document/8856972/
     [Google Scholar]
  56. ZhangM. ZhaoN. YuY. ZhuangY. ZhuQ. HuangT. A simple yet effective hand pose tremor classification algorithm to diagnosis parkinsons disease.2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).Las Vegas, NV, USAIEEE202288789010.1109/BIBM55620.2022.9995709
     [Google Scholar]
  57. XiaoM. KuangH. LiuJ. ZhangY. XiangY. WangJ. Integrating multi-scale feature representation and ensemble learning for schizophrenia diagnosis.2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).Las Vegas, NV, USAIEEE20221305131010.1109/BIBM55620.2022.9994950
     [Google Scholar]
  58. SaikumarK RajeshV. A novel implementation heart diagnosis system based on random forest machine learning technique. Int. J. Pharm. Res.202009752366
     [Google Scholar]
  59. CalinM.A. ElfarraF.G. ParascaS.V. Object-oriented classification approach for bone metastasis mapping from whole-body bone scintigraphy.Phys. Med.20218414114810.1016/j.ejmp.2021.03.04033894584
     [Google Scholar]
  60. WuestemannJ. HupfeldS. KupitzD. GensekeP. SchenkeS. PechM. KreisslM.C. GrosserO.S. Analysis of bone scans in various tumor entities using a deep-learning-based artificial neural network algorithm—evaluation of diagnostic performance.Cancers2020129265410.3390/cancers1209265432957650
     [Google Scholar]
  61. AlongiP. StefanoA. ComelliA. LaudicellaR. ScalisiS. ArnoneG. BaroneS. SpadaM. PurpuraP. BartolottaT.V. MidiriM. LagallaR. RussoG. Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients.Eur. Radiol.20213174595460510.1007/s00330‑020‑07617‑833443602
     [Google Scholar]
  62. HigashiyamaS. YoshidaA. KawabeJ. Study of the usefulness of bone scan index calculated from 99m-technetium-hydroxymethylene diphosphonate (99mTc-HMDP) bone scintigraphy for bone metastases from prostate cancer using deep learning algorithms.Curr. Med. Imaging Rev.2021171899610.2174/157340561666620052815345332484112
     [Google Scholar]
  63. HeK. ZhangX. RenS. SunJ. Deep residual learning for image recognition.arXiv2015Available from: http://arxiv.org/abs/1512.03385 [cited 2023 Aug 11].
    [Google Scholar]
  64. SzegedyC. LiuW. JiaY. SermanetP. ReedS. AnguelovD. Going deeper with convolutions.2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston, MA, USAIEEE20151910.1109/CVPR.2015.7298594
     [Google Scholar]
  65. HuangG. LiuZ. Van Der MaatenL. WeinbergerK.Q. Densely connected convolutional networks.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu, HIIEEE20172261226910.1109/CVPR.2017.243
     [Google Scholar]
  66. IoffeS. SzegedyC. Batch normalization: Accelerating deep network training by reducing internal covariate shift.arXiv2015Available from: http://arxiv.org/abs/1502.03167 [cited 2023 Oct 23].
    [Google Scholar]
  67. SnellJ. SwerskyK. ZemelR.S. Prototypical networks for few-shot learning.arXiv2017Available from: http://arxiv.org/abs/1703.05175 [cited 2023 Jul 31].
    [Google Scholar]
  68. FinnC. AbbeelP. LevineS. Model-agnostic meta-learning for fast adaptation of deep networks.arXiv2017
     [Google Scholar]
  69. DineshP. PK. Medical image prediction for diagnosis of breast cancer disease comparing the machine learning algorithms: SVM, KNN, logistic regression, random forest, and decision tree to measure accuracy.ECS Trans.20221071126811269110.1149/10701.12681ecst
     [Google Scholar]
  70. GoceriE. Intensity normalization in brain MR images using spatially varying distribution matching.11th Int Conf on computer graphics, visualization, computer vision and image processing (CGVCVIP 2017). 2017300304
     [Google Scholar]
  71. GoceriE. Fully automated and adaptive intensity normalization using statistical features for brain MR images.Celal Bayar University J. Sci. Technol.201814112513410.18466/cbayarfbe.384729
     [Google Scholar]
  72. SarvamangalaD.R. KulkarniR.V. Convolutional neural networks in medical image understanding: A survey.Evol. Intell.202215112210.1007/s12065‑020‑00540‑333425040
     [Google Scholar]
  73. GoceriE. Medical image data augmentation: Techniques, comparisons and interpretations.Artif. Intell. Rev.20235611125611260510.1007/s10462‑023‑10453‑z37362888
     [Google Scholar]
  74. GoceriE. Image augmentation for deep learning based lesion classification from skin images.2020 IEEE 4th International conference on image processing, applications and systems (IPAS). 202014414810.1109/IPAS50080.2020.9334937
     [Google Scholar]
  75. LoshchilovI. HutterF. Decoupled weight decay regularization.arXiv2019
     [Google Scholar]
  76. GoceriE. Analysis of capsule networks for image classification.International conference on computer graphics, visualization, computer vision and image processing2021
     [Google Scholar]
  77. GoceriE. Capsule neural networks in classification of skin lesions.International conference on computer graphics, visualization, computer vision and image processing20212936
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056288472240129112028
Loading
mSegResRF-SPECT: A Novel Joint Classification Model of Whole Body Bone Scan Images for Bone Metastasis Diagnosis
Curr. Med. Imaging 20, e15734056288472 (2024); https://doi.org/10.2174/0115734056288472240129112028
/content/journals/cmir/10.2174/0115734056288472240129112028
/content/journals/cmir/10.2174/0115734056288472240129112028
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Bone metastasis; Deep learning; Joint model; Random forest; Single-photon emission computed tomography; Whole body bone scan

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test