Kenichi Yokoyama
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Kenichi Yokoyama has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Toshiaki Nitatori
Kyorin University School of Medicine 1 Department of Radiology, 6-20-2 Shinkawa, Mitaka-shi, Tokyo 181-8611, Japan
3 shared publications - Rieko Ishimura
Kyorin University School of Medicine 1 Department of Radiology, 6-20-2 Shinkawa, Mitaka-shi, Tokyo 181-8611, Japan
2 shared publications - Akihito Nakanishi
Department of Radiology, Kyorin University Hospital, Tokyo, Japan
1 shared publication - Akimichi Ichinose
Medical Systems Research & Development Center FUJIFILM Corporation Japan
1 shared publication Eisei Kachi
1 shared publication- Hideaki Yoshino
杏林大学医学部第二内
1 shared publication
Latest Publications
- Open Access
- 22 November 2022
- Published by Springer Nature in BMC Medical Imaging
- Vol. 22 (1) , 1-11
Development and performance evaluation of a deep learning lung nodule detection system
Background: Lung cancer is the leading cause of cancer-related deaths throughout the world. Chest computed tomography (CT) is now widely used in the screening and diagnosis of lung cancer due to its effectiveness. Radiologists must identify each small nodule shadow from 3D volume images, which is very burdensome and often results in missed nodules. To address these challenges, we developed a computer-aided detection (CAD) system that automatically detects lung nodules in CT images. Methods: A total of 1997 chest CT scans were collected for algorithm development. The algorithm was designed using deep learning technology. In addition to evaluating detection performance on various public datasets, its robustness to changes in radiation dose was assessed by a phantom study. To investigate the clinical usefulness of the CAD system, a reader study was conducted with 10 doctors, including inexperienced and expert readers. This study investigated whether the use of the CAD as a second reader could prevent nodular lesions in lungs that require follow-up examinations from being overlooked. Analysis was performed using the Jackknife Free-Response Receiver-Operating Characteristic (JAFROC). Results: The CAD system achieved sensitivity of 0.98/0.96 at 3.1/7.25 false positives per case on two public datasets. Sensitivity did not change within the range of practical doses for a study using a phantom. A second reader study showed that the use of this system significantly improved the detection ability of nodules that could be picked up clinically (p = 0.026). Conclusions: We developed a deep learning-based CAD system that is robust to imaging conditions. Using this system as a second reader increased detection performance.
- 22 November 2022
- Published by Springer Nature in BMC Medical Imaging
- Vol. 22 (1) , 1-11
Open AccessDevelopment and performance evaluation of a deep learning lung nodule detection system
Background: Lung cancer is the leading cause of cancer-related deaths throughout the world. Chest computed tomography (CT) is now widely used in the screening and diagnosis of lung cancer due to its effectiveness. Radiologists must identify each small nodule shadow from 3D volume images, which is very burdensome and often results in missed nodules. To address these challenges, we developed a computer-aided detection (CAD) system that automatically detects lung nodules in CT images. Methods: A total of 1997 chest CT scans were collected for algorithm development. The algorithm was designed using deep learning technology. In addition to evaluating detection performance on various public datasets, its robustness to changes in radiation dose was assessed by a phantom study. To investigate the clinical usefulness of the CAD system, a reader study was conducted with 10 doctors, including inexperienced and expert readers. This study investigated whether the use of the CAD as a second reader could prevent nodular lesions in lungs that require follow-up examinations from being overlooked. Analysis was performed using the Jackknife Free-Response Receiver-Operating Characteristic (JAFROC). Results: The CAD system achieved sensitivity of 0.98/0.96 at 3.1/7.25 false positives per case on two public datasets. Sensitivity did not change within the range of practical doses for a study using a phantom. A second reader study showed that the use of this system significantly improved the detection ability of nodules that could be picked up clinically (p = 0.026). Conclusions: We developed a deep learning-based CAD system that is robust to imaging conditions. Using this system as a second reader increased detection performance.
- Open Access
- 1 September 2015
- Published by AIP Publishing in AIP Advances
- Vol. 5 (9) , 097182
Automatic slice-alignment method in cardiac magnetic resonance imaging for evaluation of the right ventricle in patients with pulmonary hypertension
We propose a new automatic slice-alignment method, which enables right ventricular scan planning in addition to the left ventricular scan planning developed in our previous work, to simplify right ventricular cardiac scan planning and assess its accuracy and the clinical acceptability of the acquired imaging planes in the evaluation of patients with pulmonary hypertension. Steady-state free precession (SSFP) sequences covering the whole heart in the end-diastolic phase with ECG gating were used to acquire 2D axial multislice images. To realize right ventricular scan planning, two morphological feature points are added to be detected and a total of eight morphological features of the heart were extracted from these series of images, and six left ventricular planes and four right ventricular planes were calculated simultaneously based on the extracted features. The subjects were 33 patients (25 with chronic thromboembolic pulmonary hypertension and 8 with idiopathic pulmonary arterial hypertension). The four right ventricular reference planes including right ventricular short-axis, 4-chamber, 2-chamber, and 3-chamber images were evaluated. The acceptability of the acquired imaging planes was visually evaluated using a 4-point scale, and the angular differences between the results obtained by this method and by conventional manual annotation were measured for each view. The average visual scores were 3.9±0.4 for short-axis images, 3.8±0.4 for 4-chamber images, 3.8±0.4 for 2-chamber images, and 3.5±0.6 for 3-chamber images. The average angular differences were 8.7±5.3, 8.3±4.9, 8.1±4.8, and 7.9±5.3 degrees, respectively. The processing time was less than 2.5 seconds in all subjects. The proposed method, which enables right ventricular scan planning in addition to the left ventricular scan planning developed in our previous work, can provide clinically acceptable planes in a short time and is useful because special proficiency in performing cardiac MR for patients with right ventricles of various sizes and shapes is not required.
- 1 September 2015
- Published by AIP Publishing in AIP Advances
- Vol. 5 (9) , 097182
Open AccessAutomatic slice-alignment method in cardiac magnetic resonance imaging for evaluation of the right ventricle in patients with pulmonary hypertension
We propose a new automatic slice-alignment method, which enables right ventricular scan planning in addition to the left ventricular scan planning developed in our previous work, to simplify right ventricular cardiac scan planning and assess its accuracy and the clinical acceptability of the acquired imaging planes in the evaluation of patients with pulmonary hypertension. Steady-state free precession (SSFP) sequences covering the whole heart in the end-diastolic phase with ECG gating were used to acquire 2D axial multislice images. To realize right ventricular scan planning, two morphological feature points are added to be detected and a total of eight morphological features of the heart were extracted from these series of images, and six left ventricular planes and four right ventricular planes were calculated simultaneously based on the extracted features. The subjects were 33 patients (25 with chronic thromboembolic pulmonary hypertension and 8 with idiopathic pulmonary arterial hypertension). The four right ventricular reference planes including right ventricular short-axis, 4-chamber, 2-chamber, and 3-chamber images were evaluated. The acceptability of the acquired imaging planes was visually evaluated using a 4-point scale, and the angular differences between the results obtained by this method and by conventional manual annotation were measured for each view. The average visual scores were 3.9±0.4 for short-axis images, 3.8±0.4 for 4-chamber images, 3.8±0.4 for 2-chamber images, and 3.5±0.6 for 3-chamber images. The average angular differences were 8.7±5.3, 8.3±4.9, 8.1±4.8, and 7.9±5.3 degrees, respectively. The processing time was less than 2.5 seconds in all subjects. The proposed method, which enables right ventricular scan planning in addition to the left ventricular scan planning developed in our previous work, can provide clinically acceptable planes in a short time and is useful because special proficiency in performing cardiac MR for patients with right ventricles of various sizes and shapes is not required.
- Open Access
- 30 April 2015
- Published by ClinMed International Library in International Journal of Clinical Cardiology
- Vol. 2 (2)
Influence of MRI-Conditional Cardiac Pacemakers on Quality and Interpretability of Images Acquiredin 1.5-T Cardiac MRI
- 30 April 2015
- Published by ClinMed International Library in International Journal of Clinical Cardiology
- Vol. 2 (2)
Open AccessInfluence of MRI-Conditional Cardiac Pacemakers on Quality and Interpretability of Images Acquiredin 1.5-T Cardiac MRI
- 1 March 2015
- Published by Elsevier in Microvascular Research
- Vol. 98, 94-101
Non-contrast myocardial perfusion using a novel 4D magnetic resonance arterial spin labeling technique: Initial experience
- 1 March 2015
- Published by Elsevier in Microvascular Research
- Vol. 98, 94-101
Non-contrast myocardial perfusion using a novel 4D magnetic resonance arterial spin labeling technique: Initial experience
- 1 December 2002
- Vol. 62 (14) , 808-15
[Detection and diagnosis of coronary arteries using multi-detector CT].
In this study coronary arteries were compared and evaluated in 41 cases using multidetector CT with slice thicknesses of 2 mm and 1 mm. All 323 segments including #1-3, 5-8, and 11 [based on the American Heart Association (AHA) classification system] were used: 163 segments of 2 mm and 160 segments of 1 mm. The images obtained were separated into fivelevels (0-4 points) of cardiac motion artifacts and evaluated based on volume rendering (VR) and partial maximum intensity projection (partial MIP). Of the results obtained, slice images of 1 mm in thickness were superior to those of 2 mm by 15.4% for sensitivity, 7.5% for specificity, and 8.2% for accuracy. On evaluation by segment, diagnostic accuracy was 2.88 +/- 0.57 for 2-mm slices and 3.28 +/- 0.59 for 1-mm slices of the left coronary artery, and 2.11 +/- 0.82 for 2-mm slices and 2.33 +/- 0.67 for 1-mm slices of the right coronary artery. Particularly for #6, a significantly high value was found for 1-mm slices (p < 0.05). Diagnostic accuracy was low in groups #2 and #3. On the basis of these findings, we were persuaded of the usefulness of MDCT for the evaluation of coronary arterial stenosed lesions, and we consider that diagnostic capability is improved by using thinner slices. We concluded that further studies would be necessary for visualization of the right coronary artery, which was seriously affected by cardiac motion artifacts.
- 1 December 2002
- Vol. 62 (14) , 808-15
[Detection and diagnosis of coronary arteries using multi-detector CT].
In this study coronary arteries were compared and evaluated in 41 cases using multidetector CT with slice thicknesses of 2 mm and 1 mm. All 323 segments including #1-3, 5-8, and 11 [based on the American Heart Association (AHA) classification system] were used: 163 segments of 2 mm and 160 segments of 1 mm. The images obtained were separated into fivelevels (0-4 points) of cardiac motion artifacts and evaluated based on volume rendering (VR) and partial maximum intensity projection (partial MIP). Of the results obtained, slice images of 1 mm in thickness were superior to those of 2 mm by 15.4% for sensitivity, 7.5% for specificity, and 8.2% for accuracy. On evaluation by segment, diagnostic accuracy was 2.88 +/- 0.57 for 2-mm slices and 3.28 +/- 0.59 for 1-mm slices of the left coronary artery, and 2.11 +/- 0.82 for 2-mm slices and 2.33 +/- 0.67 for 1-mm slices of the right coronary artery. Particularly for #6, a significantly high value was found for 1-mm slices (p < 0.05). Diagnostic accuracy was low in groups #2 and #3. On the basis of these findings, we were persuaded of the usefulness of MDCT for the evaluation of coronary arterial stenosed lesions, and we consider that diagnostic capability is improved by using thinner slices. We concluded that further studies would be necessary for visualization of the right coronary artery, which was seriously affected by cardiac motion artifacts.