Mori Mio, Fujioka Tomoyuki, Hara Mayumi, Katsuta Leona, Yashima Yuka, Yamaga Emi, Yamagiwa Ken, Tsuchiya Junichi, Hayashi Kumiko, Kumaki Yuichi, Oda Goshi, Nakagawa Tsuyoshi, Onishi Iichiroh, Kubota Kazunori, Tateishi Ukihide
Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan.
Department of Surgery, Breast Surgery, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan.
Diagnostics (Basel). 2023 Feb 20;13(4):794. doi: 10.3390/diagnostics13040794.
We investigated whether F-fluorodeoxyglucose positron emission tomography (PET)/computed tomography images restored via deep learning (DL) improved image quality and affected axillary lymph node (ALN) metastasis diagnosis in patients with breast cancer. Using a five-point scale, two readers compared the image quality of DL-PET and conventional PET (cPET) in 53 consecutive patients from September 2020 to October 2021. Visually analyzed ipsilateral ALNs were rated on a three-point scale. The standard uptake values SUV and SUV were calculated for breast cancer regions of interest. For "depiction of primary lesion", reader 2 scored DL-PET significantly higher than cPET. For "noise", "clarity of mammary gland", and "overall image quality", both readers scored DL-PET significantly higher than cPET. The SUV and SUV for primary lesions and normal breasts were significantly higher in DL-PET than in cPET ( < 0.001). Considering the ALN metastasis scores 1 and 2 as negative and 3 as positive, the McNemar test revealed no significant difference between cPET and DL-PET scores for either reader ( 0.250, 0.625). DL-PET improved visual image quality for breast cancer compared with cPET. SUV and SUV were significantly higher in DL-PET than in cPET. DL-PET and cPET exhibited comparable diagnostic abilities for ALN metastasis.
我们研究了通过深度学习（DL）恢复的氟脱氧葡萄糖正电子发射断层扫描（PET）/计算机断层扫描图像是否能改善图像质量，并影响乳腺癌患者腋窝淋巴结（ALN）转移的诊断。两名阅片者使用五点量表，对2020年9月至2021年10月连续53例患者的DL-PET和传统PET（cPET）图像质量进行了比较。对同侧ALN进行视觉分析，并采用三点量表进行评分。计算乳腺癌感兴趣区域的标准摄取值SUV和SUV。对于“原发灶显示”，阅片者2对DL-PET的评分显著高于cPET。对于“噪声”、“乳腺清晰度”和“整体图像质量”，两名阅片者对DL-PET的评分均显著高于cPET。DL-PET中，原发灶和正常乳腺的SUV和SUV显著高于cPET（<0.001）。将ALN转移评分1和2视为阴性，3视为阳性，McNemar检验显示，两名阅片者的cPET和DL-PET评分之间均无显著差异（0.250，0.625）。与cPET相比，DL-PET改善了乳腺癌的视觉图像质量。DL-PET中的SUV和SUV显著高于cPET。DL-PET和cPET在ALN转移诊断方面具有相当的诊断能力。
