著者
Yuki Kataoka Tomohisa Baba Tatsuyoshi Ikenoue Yoshinori Matsuoka Junichi Matsumoto Junji Kumasawa Kentaro Tochitani Hiraku Funakoshi Tomohiro Hosoda Aiko Kugimiya Michinori Shirano Fumiko Hamabe Sachiyo Iwata Yoshiro Kitamura Tsubasa Goto Tomohiro Handa Shoji Kido Shingo Fukuma Noriyuki Tomiyama Toyohiro Hirai Takashi Ogura Japan COVID-19 AI team
出版者
Society for Clinical Epidemiology
雑誌
Annals of Clinical Epidemiology (ISSN:24344338)
巻号頁・発行日
pp.22014, (Released:2022-07-08)
被引用文献数
2

Background: We aimed to develop and externally validate a novel machine learning model that can classify CT image findings as positive or negative for SARS-CoV-2 reverse transcription polymerase chain reaction (RT-PCR).Methods: We used 2,928 images from a wide variety of case-control type data sources for the development and internal validation of the machine learning model. A total of 633 COVID-19 cases and 2,295 non-COVID-19 cases were included in the study. We randomly divided cases into training and tuning sets at a ratio of 8:2. For external validation, we used 893 images from 740 consecutive patients at 11 acute care hospitals suspected of having COVID-19 at the time of diagnosis. The dataset included 343 COVID-19 patients. The reference standard was RT-PCR.Results: In external validation, the sensitivity and specificity of the model were 0.869 and 0.432, at the low-level cutoff, 0.724 and 0.721, at the high-level cutoff. Area under the receiver operating characteristic was 0.76.Conclusions: Our machine learning model exhibited a high sensitivity in external validation datasets and may assist physicians to rule out COVID-19 diagnosis in a timely manner at emergency departments. Further studies are warranted to improve model specificity.
著者
Atsushi Nakamoto Hiromitsu Onishi Takahiro Tsuboyama Hideyuki Fukui Takashi Ota Keigo Yano Kengo Kiso Toru Honda Hiroyuki Tarewaki Yoshihiro Koyama Mitsuaki Tatsumi Noriyuki Tomiyama
出版者
Japanese Society for Magnetic Resonance in Medicine
雑誌
Magnetic Resonance in Medical Sciences (ISSN:13473182)
巻号頁・発行日
pp.mp.2023-0039, (Released:2023-10-28)
参考文献数
25

Purpose: To compare objective and subjective image quality, lesion conspicuity, and apparent diffusion coefficient (ADC) of high-resolution multiplexed sensitivity-encoding diffusion-weighted imaging (MUSE-DWI) with conventional DWI (c-DWI) and reduced FOV DWI (rFOV-DWI) in prostate MRI.Methods: Forty-seven patients who underwent prostate MRI, including c-DWI, rFOV-DWI, and MUSE-DWI, were retrospectively evaluated. SNR and ADC of normal prostate tissue and contrast-to-noise ratio (CNR) and ADC of prostate cancer (PCa) were measured and compared between the three sequences. Image quality and lesion conspicuity were independently graded by two radiologists using a 5-point scale and compared between the three sequences.Results: The SNR of normal prostate tissue was significantly higher with rFOV-DWI than with the other two DWI techniques (P ≤ 0.01). The CNR of the PCa was significantly higher with rFOV-DWI than with MUSE-DWI (P < 0.05). The ADC of normal prostate tissue measured by rFOV-DWI was lower than that measured by MUSE-DWI and c-DWI (P < 0.01), while there was no difference in the ADC of cancers. In the qualitative analysis, MUSE-DWI showed significantly higher scores than rFOV-DWI and c-DWI for visibility of anatomy and overall image quality in both readers, and significantly higher scores for distortion in one of the two readers (P < 0.001). There was no difference in lesion conspicuity between the three sequences.Conclusion: High-resolution MUSE-DWI showed higher image quality and reduced distortion compared to c-DWI, while maintaining a wide FOV and similar ADC quantification, although no difference in lesion conspicuity was observed.
著者
Kengo Kiso Takahiro Tsuboyama Hiromitsu Onishi Kazuya Ogawa Atsushi Nakamoto Mitsuaki Tatsumi Takashi Ota Hideyuki Fukui Keigo Yano Toru Honda Shinji Kakemoto Yoshihiro Koyama Hiroyuki Tarewaki Noriyuki Tomiyama
出版者
Japanese Society for Magnetic Resonance in Medicine
雑誌
Magnetic Resonance in Medical Sciences (ISSN:13473182)
巻号頁・発行日
pp.mp.2022-0111, (Released:2023-03-29)
参考文献数
25

Purpose: To compare the effects of deep learning reconstruction (DLR) on respiratory-triggered T2-weighted MRI of the liver between single-shot fast spin-echo (SSFSE) and fast spin-echo (FSE) sequences.Methods: Respiratory-triggered fat-suppressed liver T2-weighted MRI was obtained with the FSE and SSFSE sequences at the same spatial resolution in 55 patients. Conventional reconstruction (CR) and DLR were applied to each sequence, and the SNR and liver-to-lesion contrast were measured on FSE-CR, FSE-DLR, SSFSE-CR, and SSFSE-DLR images. Image quality was independently assessed by three radiologists. The results of the qualitative and quantitative analyses were compared among the four types of images using repeated-measures analysis of variance or Friedman’s test for normally and non-normally distributed data, respectively, and a visual grading characteristics (VGC) analysis was performed to evaluate the image quality improvement by DLR on the FSE and SSFSE sequences.Results: The liver SNR was lowest on SSFSE-CR and highest on FSE-DLR and SSFSE-DLR (P < 0.01). The liver-to-lesion contrast did not differ significantly among the four types of images. Qualitatively, noise scores were worst on SSFSE-CR but best on SSFSE-DLR because DLR significantly reduced noise (P < 0.01). In contrast, artifact scores were worst both on FSE-CR and FSE-DLR (P < 0.01) because DLR did not reduce the artifacts. Lesion conspicuity was significantly improved by DLR compared with CR in the SSFSE (P < 0.01) but not in FSE sequences for all readers. Overall image quality was significantly improved by DLR compared with CR for all readers in the SSFSE (P < 0.01) but only one reader in the FSE (P < 0.01). The mean area under the VGC curve values for the FSE-DLR and SSFSE-DLR sequences were 0.65 and 0.94, respectively.Conclusion: In liver T2-weighted MRI, DLR produced more marked improvements in image quality in SSFSE than in FSE.