ورود
مقالات فارسیISIکنفرانسهاژورنالها

Feasibility of Dedicated Breast Positron Emission Tomography Image Denoising Using a Residual Neural Network

محل انتشار: مجله پزشکی هسته ای و زیست شناسی آسیا اقیانوسیه، دوره: 11، شماره: 2
سال انتشار: 1402
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 86

فایل این مقاله در 13 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:
https://civilica.com/doc/1677029

شناسه ملی سند علمی:

JR_JNMB-11-2_006

تاریخ نمایه سازی: 28 خرداد 1402

چکیده مقاله:

Objective(s): This study aimed to create a deep learning (DL)-based denoising model using a residual neural network (Res-Net) trained to reduce noise in ring-type dedicated breast positron emission tomography (dbPET) images acquired in about half the emission time, and to evaluate the feasibility and the effectiveness of the model in terms of its noise reduction performance and preservation of quantitative values compared to conventional post-image filtering techniques.Methods: Low-count (LC) and full-count (FC) PET images with acquisition durations of ۳ and ۷ minutes, respectively, were reconstructed. A Res-Net was trained to create a noise reduction model using fifteen patients’ data. The inputs to the network were LC images and its outputs were denoised PET (LC + DL) images, which should resemble FC images. To evaluate the LC + DL images, Gaussian and non-local mean (NLM) filters were applied to the LC images (LC + Gaussian and LC + NLM, respectively). To create reference images, a Gaussian filter was applied to the FC images (FC + Gaussian). The usefulness of our denoising model was objectively and visually evaluated using test data set of thirteen patients. The coefficient of variation (CV) of background fibroglandular tissue or fat tissue were measured to evaluate the performance of the noise reduction. The SUVmax and SUVpeak of lesions were also measured. The agreement of the SUV measurements was evaluated by Bland–Altman plots.Results: The CV of background fibroglandular tissue in the LC + DL images was significantly lower (۹.۱۰ ۲.۷۶) than the CVs in the LC (۱۳.۶۰  ۳.۶۶) and LC + Gaussian images (۱۱.۵۱  ۳.۵۶). No significant difference was observed in both SUVmax and SUVpeak of lesions between LC + DL and reference images. For the visual assessment, the smoothness rating for the LC + DL images was significantly better than that for the other images except for the reference images.Conclusion: Our model reduced the noise in dbPET images acquired in about half the emission time while preserving quantitative values of lesions. This study demonstrates that machine learning is feasible and potentially performs better than conventional post-image filtering in dbPET denoising.

کلیدواژه ها:

Deep neural networks ، db PET ، Noise Reduction ، Image Quality

نویسندگان

Koji Itagaki

Division of Clinical Radiology Service, Kyoto University Hospital, Kyoto, Japan

Kanae Miyake

Department of Advanced Medical Imaging Research, Graduate School of Medicine Kyoto University, Kyoto , Japan

Minori Tanoue

Division of Clinical Radiology Service, Kyoto University Hospital, Kyoto, Japan

Tae Oishi

Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine Kyoto University, Kyoto, Japan

Masako Kataoka

Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine Kyoto University, Kyoto, Japan

Masahiro Kawashima

Department of Breast Surgery, Graduate School of Medicine Kyoto University, Kyoto, Japan

Masakazu Toi

Department of Breast Surgery, Graduate School of Medicine Kyoto University, Kyoto, Japan

Yuji Nakamoto

Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine Kyoto University, Kyoto, Japan

مراجع و منابع این مقاله:

لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :
  • Fletcher JW, Djulbegovic B, Soares HP, Siegel BA, Lowe VJ, ...
  • Groheux D, Espié M, Giacchetti S, Hindié E. Performance of ...
  • Groheux D, Cochet A, Humbert O, Alberini JL, Hindié E, ...
  • Lee H, Lee DE, Park S, Kim TS, Jung SY, ...
  • Jo J, Chung HW, So Y, Yoo YB, Park KS, ...
  • Avril N, Rosé CA, Schelling M, Dose J, Kuhn W, ...
  • Kumar R, Chauhan A, Zhuang H, Chandra P, Schnall M, ...
  • Sueoka S, Sasada S, Masumoto N, Emi A, Kadoya T, ...
  • Nahmias C, Wahl LM. Reproducibility of standardized uptake value measurements ...
  • Pan T, Einstein SA, Kappadath SC, Grogg KS, Lois Gomez ...
  • Karlberg AM, Sæther O, Eikenes L, Goa PE. Quantitative comparison ...
  • Yano F, Itoh M, Hirakawa H, Yamamoto S, Yoshikawa A, ...
  • Satoh Y, Kawamoto M, Kubota K, Murakami K, Hosono M, ...
  • Thompson CJ, Murthy K, Picard Y, Weinberg IN, Mako R. ...
  • Miyake KK, Kataoka M, Ishimori T, Matsumoto Y, Torii M, ...
  • Miyake KK, Nakamoto Y, Togashi K. Current status of dedicated ...
  • Miyake KK, Matsumoto K, Inoue M, Nakamoto Y, Kanao S, ...
  • Satoh Y, Motosugi U, Imai M, Onishi H. Comparison of ...
  • Berg WA, Madsen KS, Schilling K, Tartar M, Pisano ED, ...
  • Sasada S, Masumoto N, Goda N, Kajitani K, Emi A, ...
  • Yuge S, Miyake KK, Ishimori T, Kataoka M, Matsumoto Y, ...
  • Buades A, Coll B, Morel JM. A non-local algorithm for ...
  • Teoh EJ, McGowan DR, Macpherson RE, Bradley KM, Gleeson F ...
  • Satoh Y, Imai M, Hirata K, Asakawa Y, Ikegawa C, ...
  • Schaefferkoetter J, Yan J, Ortega C, Sertic A, Lechtman E, ...
  • Weyts K, Lasnon C, Ciappuccini R, Lequesne J, Corroyer-Dulmont A, ...
  • Mehranian A, Wollenweber SD, Walker MD, Bradley KM, Fielding PA, ...
  • Spuhler K, Serrano-Sosa M, Cattell R, DeLorenzo C, Huang C. ...
  • Zhang K, Zuo W, Chen Y, Meng D, Zhang L. ...
  • Liu P, Fang R. Wide Inference Network for Image denoising ...
  • Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training ...
  • He K, Zhang X, Ren S, Sun J. Delving deep ...
  • Kingma DP, Ba JL. Adam: A method for stochastic optimization. ...
  • Watanabe M, Nakamoto Y, Nakamoto R, Ishimori T, Saga T, ...
  • Gong K, Guan J, Liu CC, Qi J. PET image ...
  • Teymurazyan A, Riauka T, Jans HS, Robinson D. Properties of ...
  • Kim JH, Ahn IJ, Nam WH, Chang Y, Ra JB. ...
  • Wang T, Sun M, Hu K. Dilated deep residual network ...
  • Tian C, Xu Y, Fei L, Wang J, Wen J, ...
  • Zhou L, Schaefferkoetter JD, Tham IWK, Huang G, Yan J. ...
  • Panda A, Naskar R, Rajbans S, Pal S. A ۳D ...
  • Gholizadeh-Ansari M, Alirezaie J, Babyn P. Deep learning for low-dose ...
  • Ataei S, Alirezaie J, Babyn P. Low dose ct denoising ...
  • Shreyamsha Kumar BK. Image denoising based on non-local means filter ...
  • Zhang X, Hou G, Jianhua M, Yang W, Lin B, ...
  • Barrett HH, Wilson DW, Tsui BMW. Noise properties of the ...
    • نمایش کامل مراجع