Objective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version 1.1.7.2) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics.The results of SM and FFDM were compared. Results: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P < 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P < 0.001), higher specificity (95.5% vs.91.8%, P < 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM in asymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts. Conclusion AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM.Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.

Objective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version 1.1.7.2) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics.The results of SM and FFDM were compared. Results: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P < 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P < 0.001), higher specificity (95.5% vs.91.8%, P < 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM in asymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts. Conclusion AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM.Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.

Objective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version 1.1.7.2) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics.The results of SM and FFDM were compared. Results: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P < 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P < 0.001), higher specificity (95.5% vs.91.8%, P < 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM in asymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts. Conclusion AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM.Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.

Objective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version 1.1.7.2) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics.The results of SM and FFDM were compared. Results: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P < 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P < 0.001), higher specificity (95.5% vs.91.8%, P < 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM in asymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts. Conclusion AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM.Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.

Objective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version 1.1.7.2) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics.The results of SM and FFDM were compared. Results: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P < 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P < 0.001), higher specificity (95.5% vs.91.8%, P < 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM in asymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts. Conclusion AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM.Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.

Purpose: Li-Fraumeni syndrome (LFS) is a hereditary disorder caused by germline mutation in TP53. Owing to the rarity of LFS, data on its clinical features are limited. This study aimed to evaluate the clinical characteristics and prognosis of Korean patients with LFS. Materials and Methods: Patients who underwent genetic counseling and confirmed with germline TP53 mutation in the National Cancer Center in Korea between 2011 and 2022 were retrospectively reviewed. Data on family history with pedigree, types of mutation, clinical features, and prognosis were collected. Results: Fourteen patients with LFS were included in this study. The median age at diagnosis of the first tumor was 32 years. Missense and nonsense mutations were observed in 13 and one patients, respectively. The repeated mutations were p.Arg273His, p.Ala138Val, and pPro190Leu. The sister with breast cancer harbored the same mutation of p.Ala138Val. Seven patients had multiple primary cancers. Breast cancer was most frequently observed, and other types of tumor included sarcoma, thyroid cancer, pancreatic cancer, brain tumor, adrenocortical carcinoma, ovarian cancer, endometrial cancer, colon cancer, vaginal cancer, skin cancer, and leukemia. The median follow-up period was 51.5 months. Two and four patients showed local recurrence and distant metastasis, respectively. Two patients died of leukemia and pancreatic cancer 3 and 23 months after diagnosis, respectively. Conclusion This study provides information on different characteristics of patients with LFS, including types of mutation, types of cancer, and prognostic outcomes. For more appropriate management of these patients, proper genetic screening and multidisciplinary discussion are required.

This manuscript represents the official position of the Korean Society of Echocardiography on valvular heart diseases.This position paper focuses on the clinical management of valvular heart diseases with reference to the guidelines recently published by the American College of Cardiology/American Heart Association and the European Society of Cardiology. The committee tried to reflect the recently published results on the topic of valvular heart diseases and Korean data by a systematic literature search based on validity and relevance. In part I of this article, we will review and discuss the current position of aortic valve disease in Korea.

This manuscript represents the official position of the Korean Society of Echocardiography on valvular heart diseases.This position paper focuses on the diagnosis and management of valvular heart diseases with referring to the guide‑ lines recently published by the American College of Cardiology/American Heart Association and the European Society of Cardiology. The committee sought to reflect national data on the topic of valvular heart diseases published to date through a systematic literature search based on validity and relevance. In the part II of this article, we intend to pre‑ sent recommendations for diagnosis and treatment of mitral valve disease and tricuspid valve disease.

Background: We aimed to evaluate long-term outcomes of gamma knife radiosurgery (GKS) for cerebral cavernous malformations (CCMs). Methods: Among the 233 CCM patients who underwent GKS, 79 adult patients (96 lesions) followed for over 10 years were included and analyzed retrospectively. Annual hemorrhage rate (AHR) was analyzed the entire cohort of 233 patients and the subset of 79 enrolled patients by dividing lesions into overall CCM lesions and brainstem lesions. AHR, neurologic outcome, adverse radiation effect (ARE), and changes of lesions in magnetic resonance imaging (MRI) were compared before and after GKS. Cox-regression analysis was performed to identify risk factors for hemorrhage following GKS. Results: Mean follow-up duration of 79 enrolled patients was 14 years (range, 10–23 years).The AHR of all CCMs for entire cohort at each time point was 17.8% (pre-GKS), 5.9% (≤ 2 years post-GKS), 1.8% (≤ 10 years post-GKS). The AHR of all CCM for 79 enrolled patients was 21.4% (pre-GKS), 3.8% (2 years post-GKS), 1.4% (10 years post-GKS), and 2.3% (> 10 years post-GKS). The AHR of brainstem cavernous malformation (CM) for entire cohort at each time point was 22.4% (pre-GKS), 10.1% (≤ 2 years post-GKS), 3.2% (≤ 10 years post-GKS). The AHR of brainstem CM for 79 enrolled patients was 27.2% (pre-GKS), 5.8% (2 years post-GKS), 3.4% (10 years post-GKS), and 3.5% (> 10 years post-GKS). Out of the 79 enrolled patients, 35 presented with focal neurologic deficits at the initial clinical visit. Among these patients, 74.3% showed recovery at the last follow-up. Symptomatic ARE occurred in five (6.4%) patients. No mortality occurred. Most lesions were decreased in size at the last follow-up MRI. Previous hemorrhage history (hazard ratio [HR], 8.38; 95% confidence interval [CI], 1.07–65.88; P = 0.043), and brainstem location (HR, 3.10; 95% CI, 1.26–7.64; P = 0.014) were significant risk factors for hemorrhage event. Conclusion GKS for CCM showed favorable long-term outcomes. GKS should be considered for CCM, especially when it has a previous hemorrhage history and brainstem location.

Background: Treatment for large (> 10 mL) arteriovenous malformations (AVMs) remains highly challenging. This study evaluated long-term effect of time-staged gamma knife radiosurgery (GKS) for large AVMs. Methods: For patients with large AVMs treated by time-staged GKS over 10 years, timestaged GKS was repeated every three years targeting the entire nidus if total obliteration was not achieved. Obliteration rate and post-GKS complications were assessed based on 10 mL volume interval of AVMs. Prognostic factors for these outcomes were evaluated using Cox regression analysis. Results: Ninety-six patients were analyzed. For AVMs in the 10–20 mL subgroup, a dose ≥ 13.5Gy yielded higher obliteration rate in the first GKS. In the 20–30 mL subgroup, a second GKS significantly boosted obliteration. AVMs > 30 mL did not achieve any obliteration with the first GKS. Among 35 (36.4%) cases lost to follow-up, 7 (7.2%) were lost due to GKS complications. Kaplan-Meier analysis showed that each subgroup needed different time for achieving 50% favorable obliteration outcome rate: 3.5, 6.5, and 8.2 years for 10–20 mL, 20–30 mL, and > 30 mL subgroup, respectively. Total obliteration rate calculated by intention-to-treat method: 73%, 51.7%, 35.7%, respectively, 61.5% overall. Post-GKS hemorrhage and chronic encapsulated expanding hematoma (CEEH) occurred in 13.5% and 8.3% of cases, respectively.Two patients died. Dose and volume were significant prognostic factors for obliteration. Initial AVM volume was a significant prognostic factor of post-GKS hemorrhage and CEEH. Conclusion Time-staged GKS for large AVMs less than 30 mL has highly favorable long-term outcome and a tolerable complication rate.