Purpose: To evaluate the feasibility and utility of deep learning-based computer-aided diagnosis (DL-CAD) for the detection of pulmonary nodules on coronary artery calcium (CAC)-scoring computed tomography (CT). Materials and Methods: This retrospective study included 273 patients (aged 63.9±13.2 years; 129 men) who underwent CACscoring CT. A DL-CAD system based on thin-section images was used for pulmonary nodule detection, and two independent junior readers reviewed the standard CAC-scoring CT scans with and without referencing DL-CAD results. A reference standard was established through the consensus of two experienced radiologists. Sensitivity, positive predictive value, and F1-score were assessed on a per-nodule and per-patient basis. The patients’ medical records were monitored until November 2023. Results: A total of 269 nodules were identified in 129 patients. With DL-CAD assistance, the readers’ sensitivity significantly improved (65% vs. 80% for reader 1; 82% vs. 86% for reader 2; all p<0.001), without a notable increase in the number of false-positives per case (0.11 vs. 0.13, p=0.078 for reader 1; 0.11 vs. 0.11, p>0.999 for reader 2). Per-patient analysis also enhanced sensitivity with DL-CAD assistance (73% vs. 84%, p<0.001 for reader 1; 89% vs. 91%, p=0.250 for reader 2). During follow-up, lung cancer was diagnosed in four patients (1.5%). Among them, two had lesions detected on CAC-scoring CT, both of which were successfully identified by DL-CAD. Conclusion DL-CAD based on thin-section images can assist less experienced readers in detecting pulmonary nodules on CACscoring CT scans, improving detection sensitivity without significantly increasing false-positives.

Purpose: To evaluate the feasibility and utility of deep learning-based computer-aided diagnosis (DL-CAD) for the detection of pulmonary nodules on coronary artery calcium (CAC)-scoring computed tomography (CT). Materials and Methods: This retrospective study included 273 patients (aged 63.9±13.2 years; 129 men) who underwent CACscoring CT. A DL-CAD system based on thin-section images was used for pulmonary nodule detection, and two independent junior readers reviewed the standard CAC-scoring CT scans with and without referencing DL-CAD results. A reference standard was established through the consensus of two experienced radiologists. Sensitivity, positive predictive value, and F1-score were assessed on a per-nodule and per-patient basis. The patients’ medical records were monitored until November 2023. Results: A total of 269 nodules were identified in 129 patients. With DL-CAD assistance, the readers’ sensitivity significantly improved (65% vs. 80% for reader 1; 82% vs. 86% for reader 2; all p<0.001), without a notable increase in the number of false-positives per case (0.11 vs. 0.13, p=0.078 for reader 1; 0.11 vs. 0.11, p>0.999 for reader 2). Per-patient analysis also enhanced sensitivity with DL-CAD assistance (73% vs. 84%, p<0.001 for reader 1; 89% vs. 91%, p=0.250 for reader 2). During follow-up, lung cancer was diagnosed in four patients (1.5%). Among them, two had lesions detected on CAC-scoring CT, both of which were successfully identified by DL-CAD. Conclusion DL-CAD based on thin-section images can assist less experienced readers in detecting pulmonary nodules on CACscoring CT scans, improving detection sensitivity without significantly increasing false-positives.

Purpose: To evaluate the feasibility and utility of deep learning-based computer-aided diagnosis (DL-CAD) for the detection of pulmonary nodules on coronary artery calcium (CAC)-scoring computed tomography (CT). Materials and Methods: This retrospective study included 273 patients (aged 63.9±13.2 years; 129 men) who underwent CACscoring CT. A DL-CAD system based on thin-section images was used for pulmonary nodule detection, and two independent junior readers reviewed the standard CAC-scoring CT scans with and without referencing DL-CAD results. A reference standard was established through the consensus of two experienced radiologists. Sensitivity, positive predictive value, and F1-score were assessed on a per-nodule and per-patient basis. The patients’ medical records were monitored until November 2023. Results: A total of 269 nodules were identified in 129 patients. With DL-CAD assistance, the readers’ sensitivity significantly improved (65% vs. 80% for reader 1; 82% vs. 86% for reader 2; all p<0.001), without a notable increase in the number of false-positives per case (0.11 vs. 0.13, p=0.078 for reader 1; 0.11 vs. 0.11, p>0.999 for reader 2). Per-patient analysis also enhanced sensitivity with DL-CAD assistance (73% vs. 84%, p<0.001 for reader 1; 89% vs. 91%, p=0.250 for reader 2). During follow-up, lung cancer was diagnosed in four patients (1.5%). Among them, two had lesions detected on CAC-scoring CT, both of which were successfully identified by DL-CAD. Conclusion DL-CAD based on thin-section images can assist less experienced readers in detecting pulmonary nodules on CACscoring CT scans, improving detection sensitivity without significantly increasing false-positives.

Purpose: To evaluate the feasibility and utility of deep learning-based computer-aided diagnosis (DL-CAD) for the detection of pulmonary nodules on coronary artery calcium (CAC)-scoring computed tomography (CT). Materials and Methods: This retrospective study included 273 patients (aged 63.9±13.2 years; 129 men) who underwent CACscoring CT. A DL-CAD system based on thin-section images was used for pulmonary nodule detection, and two independent junior readers reviewed the standard CAC-scoring CT scans with and without referencing DL-CAD results. A reference standard was established through the consensus of two experienced radiologists. Sensitivity, positive predictive value, and F1-score were assessed on a per-nodule and per-patient basis. The patients’ medical records were monitored until November 2023. Results: A total of 269 nodules were identified in 129 patients. With DL-CAD assistance, the readers’ sensitivity significantly improved (65% vs. 80% for reader 1; 82% vs. 86% for reader 2; all p<0.001), without a notable increase in the number of false-positives per case (0.11 vs. 0.13, p=0.078 for reader 1; 0.11 vs. 0.11, p>0.999 for reader 2). Per-patient analysis also enhanced sensitivity with DL-CAD assistance (73% vs. 84%, p<0.001 for reader 1; 89% vs. 91%, p=0.250 for reader 2). During follow-up, lung cancer was diagnosed in four patients (1.5%). Among them, two had lesions detected on CAC-scoring CT, both of which were successfully identified by DL-CAD. Conclusion DL-CAD based on thin-section images can assist less experienced readers in detecting pulmonary nodules on CACscoring CT scans, improving detection sensitivity without significantly increasing false-positives.

Purpose: To evaluate the feasibility and utility of deep learning-based computer-aided diagnosis (DL-CAD) for the detection of pulmonary nodules on coronary artery calcium (CAC)-scoring computed tomography (CT). Materials and Methods: This retrospective study included 273 patients (aged 63.9±13.2 years; 129 men) who underwent CACscoring CT. A DL-CAD system based on thin-section images was used for pulmonary nodule detection, and two independent junior readers reviewed the standard CAC-scoring CT scans with and without referencing DL-CAD results. A reference standard was established through the consensus of two experienced radiologists. Sensitivity, positive predictive value, and F1-score were assessed on a per-nodule and per-patient basis. The patients’ medical records were monitored until November 2023. Results: A total of 269 nodules were identified in 129 patients. With DL-CAD assistance, the readers’ sensitivity significantly improved (65% vs. 80% for reader 1; 82% vs. 86% for reader 2; all p<0.001), without a notable increase in the number of false-positives per case (0.11 vs. 0.13, p=0.078 for reader 1; 0.11 vs. 0.11, p>0.999 for reader 2). Per-patient analysis also enhanced sensitivity with DL-CAD assistance (73% vs. 84%, p<0.001 for reader 1; 89% vs. 91%, p=0.250 for reader 2). During follow-up, lung cancer was diagnosed in four patients (1.5%). Among them, two had lesions detected on CAC-scoring CT, both of which were successfully identified by DL-CAD. Conclusion DL-CAD based on thin-section images can assist less experienced readers in detecting pulmonary nodules on CACscoring CT scans, improving detection sensitivity without significantly increasing false-positives.

Background and Objectives: Angiographic assessment of coronary stenosis severity using quantitative coronary angiography (QCA) is often inconsistent with that based on fractional flow reserve (FFR) or intravascular ultrasound (IVUS). We investigated the incidence of discrepancies between QCA and FFR or IVUS, and the outcomes of FFR- and IVUS-guided strategies in discordant coronary lesions. Methods: This study was a post-hoc analysis of the FLAVOUR study. We used a QCA-derived diameter stenosis (DS) of 60% or greater, the highest tertile, to classify coronary lesions as concordant or discordant with FFR or IVUS criteria for percutaneous coronary intervention (PCI). The patient-oriented composite outcome (POCO) was defined as a composite of death, myocardial infarction, or revascularization at 24 months. Results: The discordance rate between QCA and FFR or IVUS was 30.2% (n=551). The QCAFFR discordance rate was numerically lower than the QCA-IVUS discordance rate (28.2% vs. 32.4%, p=0.050). In 200 patients with ≥60% DS, PCI was deferred according to negative FFR (n=141) and negative IVUS (n=59) (15.3% vs. 6.5%, p<0.001). The POCO incidence was comparable between the FFR- and IVUS-guided deferral strategies (5.9% vs. 3.4%, p=0.479).Conversely, 351 patients with DS <60% underwent PCI according to positive FFR (n=118) and positive IVUS (n=233) (12.8% vs. 25.9%, p<0.001). FFR- and IVUS-guided PCI did not differ in the incidence of POCO (9.5% vs. 6.5%, p=0.294). Conclusions The proportion of QCA-FFR or IVUS discordance was approximately one third for intermediate coronary lesions. FFR- or IVUS-guided strategies for these lesions were comparable with respect to POCO at 24 months.

Background and Objectives: Angiographic assessment of coronary stenosis severity using quantitative coronary angiography (QCA) is often inconsistent with that based on fractional flow reserve (FFR) or intravascular ultrasound (IVUS). We investigated the incidence of discrepancies between QCA and FFR or IVUS, and the outcomes of FFR- and IVUS-guided strategies in discordant coronary lesions. Methods: This study was a post-hoc analysis of the FLAVOUR study. We used a QCA-derived diameter stenosis (DS) of 60% or greater, the highest tertile, to classify coronary lesions as concordant or discordant with FFR or IVUS criteria for percutaneous coronary intervention (PCI). The patient-oriented composite outcome (POCO) was defined as a composite of death, myocardial infarction, or revascularization at 24 months. Results: The discordance rate between QCA and FFR or IVUS was 30.2% (n=551). The QCAFFR discordance rate was numerically lower than the QCA-IVUS discordance rate (28.2% vs. 32.4%, p=0.050). In 200 patients with ≥60% DS, PCI was deferred according to negative FFR (n=141) and negative IVUS (n=59) (15.3% vs. 6.5%, p<0.001). The POCO incidence was comparable between the FFR- and IVUS-guided deferral strategies (5.9% vs. 3.4%, p=0.479).Conversely, 351 patients with DS <60% underwent PCI according to positive FFR (n=118) and positive IVUS (n=233) (12.8% vs. 25.9%, p<0.001). FFR- and IVUS-guided PCI did not differ in the incidence of POCO (9.5% vs. 6.5%, p=0.294). Conclusions The proportion of QCA-FFR or IVUS discordance was approximately one third for intermediate coronary lesions. FFR- or IVUS-guided strategies for these lesions were comparable with respect to POCO at 24 months.

Background: Bulky or multiple lymph node (LN) metastases are associated with poor prognosis in cervical cancer, and the size or number of LN metastases is not yet reflected in the staging system and therapeutic strategy. Although the therapeutic effects of surgical resection of bulky LNs before standard treatment have been reported in several retrospective studies, wellplanned randomized clinical studies are lacking. Therefore, the aim of the Korean Gynecologic Oncology Group (KGOG) 1047/DEBULK trial is to investigate whether the debulking surgery of bulky or multiple LNs prior to concurrent chemoradiation therapy (CCRT) improves the survival rate of patients with cervical cancer IIICr diagnosed by imaging tests. Methods The KGOG 1047/DEBULK trial is a phase III, multicenter, randomized clinical trial involving patients with bulky or multiple LN metastases in cervical cancer IIICr. This study will include patients with a short-axis diameter of a pelvic or para-aortic LN ≥2 cm or ≥3 LNs with a short-axis diameter ≥1 cm and for whom CCRT is planned. The treatment arms will be randomly allocated in a 1:1 ratio to either receive CCRT (control arm) or undergo surgical debulking of bulky or multiple LNs before CCRT (experimental arm). CCRT consists of extended-field external beam radiotherapy/pelvic radiotherapy, brachytherapy and LN boost, and weekly chemotherapy with cisplatin (40 mg/m 2 ), 4–6 times administered intravenously.The primary endpoint will be 3-year progression-free survival rate. The secondary endpoints will be 3-year overall survival rate, treatment-related complications, and accuracy of radiological diagnosis of bulky or multiple LNs.

Background: Bulky or multiple lymph node (LN) metastases are associated with poor prognosis in cervical cancer, and the size or number of LN metastases is not yet reflected in the staging system and therapeutic strategy. Although the therapeutic effects of surgical resection of bulky LNs before standard treatment have been reported in several retrospective studies, wellplanned randomized clinical studies are lacking. Therefore, the aim of the Korean Gynecologic Oncology Group (KGOG) 1047/DEBULK trial is to investigate whether the debulking surgery of bulky or multiple LNs prior to concurrent chemoradiation therapy (CCRT) improves the survival rate of patients with cervical cancer IIICr diagnosed by imaging tests. Methods The KGOG 1047/DEBULK trial is a phase III, multicenter, randomized clinical trial involving patients with bulky or multiple LN metastases in cervical cancer IIICr. This study will include patients with a short-axis diameter of a pelvic or para-aortic LN ≥2 cm or ≥3 LNs with a short-axis diameter ≥1 cm and for whom CCRT is planned. The treatment arms will be randomly allocated in a 1:1 ratio to either receive CCRT (control arm) or undergo surgical debulking of bulky or multiple LNs before CCRT (experimental arm). CCRT consists of extended-field external beam radiotherapy/pelvic radiotherapy, brachytherapy and LN boost, and weekly chemotherapy with cisplatin (40 mg/m 2 ), 4–6 times administered intravenously.The primary endpoint will be 3-year progression-free survival rate. The secondary endpoints will be 3-year overall survival rate, treatment-related complications, and accuracy of radiological diagnosis of bulky or multiple LNs.

Background and Objectives: Angiographic assessment of coronary stenosis severity using quantitative coronary angiography (QCA) is often inconsistent with that based on fractional flow reserve (FFR) or intravascular ultrasound (IVUS). We investigated the incidence of discrepancies between QCA and FFR or IVUS, and the outcomes of FFR- and IVUS-guided strategies in discordant coronary lesions. Methods: This study was a post-hoc analysis of the FLAVOUR study. We used a QCA-derived diameter stenosis (DS) of 60% or greater, the highest tertile, to classify coronary lesions as concordant or discordant with FFR or IVUS criteria for percutaneous coronary intervention (PCI). The patient-oriented composite outcome (POCO) was defined as a composite of death, myocardial infarction, or revascularization at 24 months. Results: The discordance rate between QCA and FFR or IVUS was 30.2% (n=551). The QCAFFR discordance rate was numerically lower than the QCA-IVUS discordance rate (28.2% vs. 32.4%, p=0.050). In 200 patients with ≥60% DS, PCI was deferred according to negative FFR (n=141) and negative IVUS (n=59) (15.3% vs. 6.5%, p<0.001). The POCO incidence was comparable between the FFR- and IVUS-guided deferral strategies (5.9% vs. 3.4%, p=0.479).Conversely, 351 patients with DS <60% underwent PCI according to positive FFR (n=118) and positive IVUS (n=233) (12.8% vs. 25.9%, p<0.001). FFR- and IVUS-guided PCI did not differ in the incidence of POCO (9.5% vs. 6.5%, p=0.294). Conclusions The proportion of QCA-FFR or IVUS discordance was approximately one third for intermediate coronary lesions. FFR- or IVUS-guided strategies for these lesions were comparable with respect to POCO at 24 months.