Literature DB >> 35809210

Comparison of the performances of machine learning and deep learning in improving the quality of low dose lung cancer PET images.

Ying-Hwey Nai1, Hoi Yin Loi2, Sophie O'Doherty3, Teng Hwee Tan4, Anthonin Reilhac3.   

Abstract

PURPOSE: To compare the performances of machine learning (ML) and deep learning (DL) in improving the quality of low dose (LD) lung cancer PET images and the minimum counts required.
MATERIALS AND METHODS: 33 standard dose (SD) PET images, were used to simulate LD PET images at seven-count levels of 0.25, 0.5, 1, 2, 5, 7.5 and 10 million (M) counts. Image quality transfer (IQT), a ML algorithm that uses decision tree and patch-sampling was compared to two DL networks-HighResNet (HRN) and deep-boosted regression (DBR). Supervised training was performed by training the ML and DL algorithms with matched-pair SD and LD images. Image quality evaluation and clinical lesion detection tasks were performed by three readers. Bias in 53 radiomic features, including mean SUV, was evaluated for all lesions.
RESULTS: ML- and DL-estimated images showed higher signal and smaller error than LD images with optimal image quality recovery achieved using LD down to 5 M counts. True positive rate and false discovery rate were fairly stable beyond 5 M counts for the detection of small and large true lesions. Readers rated average or higher ratings to images estimated from LD images of count levels above 5 M only, with higher confidence in detecting true lesions.
CONCLUSION: LD images with a minimum of 5 M counts (8.72 MBq for 10 min scan or 25 MBq for 3 min scan) are required for optimal clinical use of ML and DL, with slightly better but more varied performance shown by DL.
© 2022. The Author(s) under exclusive licence to Japan Radiological Society.

Entities:  

Keywords:  Deep learning; Image quality; Lesion detection; Low-dose lung cancer PET; Machine learning

Year:  2022        PMID: 35809210     DOI: 10.1007/s11604-022-01311-z

Source DB:  PubMed          Journal:  Jpn J Radiol        ISSN: 1867-1071            Impact factor:   2.374


  2 in total

1.  Investigation of the quantitative accuracy of low-dose amyloid and tau PET imaging.

Authors:  Ying-Hwey Nai; Shoichi Watanuki; Manabu Tashiro; Nobuyuki Okamura; Hiroshi Watabe
Journal:  Radiol Phys Technol       Date:  2018-10-16

2.  NiftyNet: a deep-learning platform for medical imaging.

Authors:  Eli Gibson; Wenqi Li; Carole Sudre; Lucas Fidon; Dzhoshkun I Shakir; Guotai Wang; Zach Eaton-Rosen; Robert Gray; Tom Doel; Yipeng Hu; Tom Whyntie; Parashkev Nachev; Marc Modat; Dean C Barratt; Sébastien Ourselin; M Jorge Cardoso; Tom Vercauteren
Journal:  Comput Methods Programs Biomed       Date:  2018-01-31       Impact factor: 5.428

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.