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.

Phyllodes tumors of the breast are rare biphasic fibroepithelial neoplasms that may coexist with breast carcinomas. Herein, we report a case of invasive ductal carcinoma (IDC) within a borderline phyllodes tumor accompanied by extensive ductal carcinoma in situ (DCIS) in the same breast. A 72-year-old woman presented with a palpable lump in the right breast.Mammography showed an oval mass associated with segmental microcalcifications, and breast ultrasound (US) revealed a 2.3 cm oval mass and an associated non-mass lesion. Based on US-guided core needle biopsy, the initial biopsy result of the non-mass lesion suggested DCIS; however, the mass was diagnosed as a fibroepithelial lesion. Preoperative dynamic contrast-enhanced magnetic resonance imaging showed a rim-enhancing oval mass with areas of T2 hyperintensity, accompanied by segmental non-mass enhancement. The mass was highly suspicious for malignancy and was considered imaging-pathology discordant.Subsequently, the patient underwent mastectomy. Histopathological examination of the surgical specimens confirmed a borderline phyllodes tumor with an IDC within the tumor and an extensive intraductal component. The invasive carcinoma component was triplenegative breast cancer. This case highlights the diagnostic challenges of identifying coexisting carcinomas within phyllodes tumors and emphasizes the necessity for increased awareness among radiologists regarding this possibility.

Phyllodes tumors of the breast are rare biphasic fibroepithelial neoplasms that may coexist with breast carcinomas. Herein, we report a case of invasive ductal carcinoma (IDC) within a borderline phyllodes tumor accompanied by extensive ductal carcinoma in situ (DCIS) in the same breast. A 72-year-old woman presented with a palpable lump in the right breast.Mammography showed an oval mass associated with segmental microcalcifications, and breast ultrasound (US) revealed a 2.3 cm oval mass and an associated non-mass lesion. Based on US-guided core needle biopsy, the initial biopsy result of the non-mass lesion suggested DCIS; however, the mass was diagnosed as a fibroepithelial lesion. Preoperative dynamic contrast-enhanced magnetic resonance imaging showed a rim-enhancing oval mass with areas of T2 hyperintensity, accompanied by segmental non-mass enhancement. The mass was highly suspicious for malignancy and was considered imaging-pathology discordant.Subsequently, the patient underwent mastectomy. Histopathological examination of the surgical specimens confirmed a borderline phyllodes tumor with an IDC within the tumor and an extensive intraductal component. The invasive carcinoma component was triplenegative breast cancer. This case highlights the diagnostic challenges of identifying coexisting carcinomas within phyllodes tumors and emphasizes the necessity for increased awareness among radiologists regarding this possibility.

Phyllodes tumors of the breast are rare biphasic fibroepithelial neoplasms that may coexist with breast carcinomas. Herein, we report a case of invasive ductal carcinoma (IDC) within a borderline phyllodes tumor accompanied by extensive ductal carcinoma in situ (DCIS) in the same breast. A 72-year-old woman presented with a palpable lump in the right breast.Mammography showed an oval mass associated with segmental microcalcifications, and breast ultrasound (US) revealed a 2.3 cm oval mass and an associated non-mass lesion. Based on US-guided core needle biopsy, the initial biopsy result of the non-mass lesion suggested DCIS; however, the mass was diagnosed as a fibroepithelial lesion. Preoperative dynamic contrast-enhanced magnetic resonance imaging showed a rim-enhancing oval mass with areas of T2 hyperintensity, accompanied by segmental non-mass enhancement. The mass was highly suspicious for malignancy and was considered imaging-pathology discordant.Subsequently, the patient underwent mastectomy. Histopathological examination of the surgical specimens confirmed a borderline phyllodes tumor with an IDC within the tumor and an extensive intraductal component. The invasive carcinoma component was triplenegative breast cancer. This case highlights the diagnostic challenges of identifying coexisting carcinomas within phyllodes tumors and emphasizes the necessity for increased awareness among radiologists regarding this possibility.

The prevalence of thyroid cancer in pregnant women is unknown; however, given that thyroid cancer commonly develops in women, especially young women of childbearing age, new cases are often diagnosed during pregnancy. This recommendation summarizes the follow-up and treatment when thyroid cancer is diagnosed during pregnancy and when a woman with thyroid cancer becomes pregnant. If diagnosed in the first trimester, surgery should be postponed until after delivery, and the patient should be monitored with ultrasound. If follow-up before 24–26 weeks of gestation shows that thyroid cancer has progressed, surgery should be considered. If it has not progressed at 24–26 weeks of gestation or if papillary thyroid cancer is diagnosed after 20 weeks of pregnancy, surgery should be considered after delivery.

Based on the clinical, histopathological, and perioperative data of a patient with differentiated thyroid cancer (DTC), risk stratification based on their initial recurrence risk is a crucial follow-up (FU) strategy during the first 1–2 years after initial therapy. However, restratifiying the recurrence risk on the basis of current clinical data that becomes available after considering the response to treatment (ongoing risk stratification, ORS) provides a more accurate prediction of the status at the final FU and a more tailored management approach. Since the 2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and DTC, the latest guidelines that include the National Comprehensive Cancer Network clinical practice and European Association for Medical Oncology guidelines have been updated to reflect several recent evidence in ORS and thyroid-stimulating hormone (TSH) suppression of DTC. The current clinical practice guideline was developed by extracting FU surveillance after the initial treatment section from the previous version of guidelines and updating it to reflect recent evidence. The current revised guideline includes recommendations for recent ORS, TSH target level based on risk stratification, FU tools for detection of recurrence and assessment of disease status, and long-term FU strategy for consideration of the disease status. These evidence-based recommendations are expected to avoid overtreatment and intensive FU of the majority of patients who will have a very good prognosis after the initial treatment of DTC patients, thereby ensuring that patients receive the most appropriate and effective treatment and FU options.