File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Real-time AI-based computer-aided detection/diagnosis (AI-CAD) for breast ultrasound: A prospective, multicenter, multinational study (Poster presentation)
| Title | Real-time AI-based computer-aided detection/diagnosis (AI-CAD) for breast ultrasound: A prospective, multicenter, multinational study (Poster presentation) |
|---|---|
| Authors | |
| Issue Date | 17-Apr-2025 |
| Abstract | Background: To evaluate the effectiveness of a real-time artificial intelligence (AI)-based computer-aided detection/diagnosis (AI-CAD) system as a diagnostic decision support tool for breast ultrasound in a real-world clinical setting, conducted as a prospective, multicenter, and multinational study. Methods: From May to December 2024, total of 75 patients undergoing breast ultrasound were enrolled in prospective study conducted in Korea (n = 38) and Hong Kong (n = 37). In this study, six experts operated realtime AI-CAD system (CadAI-B, BeamWorks Inc., Korea) on tablet PC connected to handheld ultrasound device during breast ultrasound examinations. Image and clinical data were collected from patients with established ground truth through follow up, biopsy, or surgery. AI-CAD system highlights suspicious areas during scanning to assist physicians in breast cancer detection and supports data-driven diagnosis by providing BI-RADS categories and malignancy scores (0-100%) when the user freezes the image.AI-CAD. Diagnostic performance of experts and real-time AI-CAD system were evaluated using area under receiver operating characteristic curve (AUC), sensitivity and specificity. Result: The analysis included 75 patients (mean age 55 years, IQR 46-66) with 24 malignancies (32.0%), 45 benign lesions (60.0%), and 6 normal cases (8.0%). Mean breast mass size was 1.2 cm ( ± 1.0 cm): benign 0.8 cm ( ± 0.7 cm), malignant 1.8 cm ( ± 1.3 cm). BI-RADS category distribution was: for experts category 1 (4.0%), 2 (21.3%), 3 (24.0%), 4a (16.0%), 4b (18.7%), 4c (4.0%), 5 (12.0%); and for AI-CAD category 1 (32.0%), 2 (5.3%), 3 (9.3%), 4a (17.3%), 4b (21.3%), 4c (13.3%), 5 (1.3%). Overall diagnostic performance of experts and AI-CAD, as AUCs calculated by BI-RADS, were 0.801 and 0.751, respectively (P= .679). Sensitivity and specificity were 91.7% (22/24) and 68.6% (35/51) in experts and 87.5% (21/24) and 57.8% (32/51) in AI-CAD, respectively (P= .481). Conclusions: In this real-world clinical setting, AI-CAD demonstrated promising performance comparable to that of experts. |
| Persistent Identifier | http://hdl.handle.net/10722/355670 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Baek, John | - |
| dc.contributor.author | Kim, Won Hwa | - |
| dc.contributor.author | Kwong, Ava | - |
| dc.contributor.author | Kim, Jaeil | - |
| dc.contributor.author | Kim, Hye Jung | - |
| dc.contributor.author | Park, Ho Yong | - |
| dc.contributor.author | Lee, Jeeyeon | - |
| dc.date.accessioned | 2025-04-30T00:35:03Z | - |
| dc.date.available | 2025-04-30T00:35:03Z | - |
| dc.date.issued | 2025-04-17 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/355670 | - |
| dc.description.abstract | <p>Background: To evaluate the effectiveness of a real-time artificial intelligence (AI)-based computer-aided detection/diagnosis (AI-CAD) system as a diagnostic decision support tool for breast ultrasound in a real-world clinical setting, conducted as a prospective, multicenter, and multinational study.<br></p><p>Methods: From May to December 2024, total of 75 patients undergoing breast ultrasound were enrolled in prospective study conducted in Korea (n = 38) and Hong Kong (n = 37). In this study, six experts operated realtime AI-CAD system (CadAI-B, BeamWorks Inc., Korea) on tablet PC connected to handheld ultrasound device during breast ultrasound examinations. Image and clinical data were collected from patients with established ground truth through follow up, biopsy, or surgery. AI-CAD system highlights suspicious areas during scanning to assist physicians in breast cancer detection and supports data-driven diagnosis by providing BI-RADS categories and malignancy scores (0-100%) when the user freezes the image.AI-CAD. Diagnostic performance of experts and real-time AI-CAD system were evaluated using area under receiver operating characteristic curve (AUC), sensitivity and specificity.<br></p><p>Result: The analysis included 75 patients (mean age 55 years, IQR 46-66) with 24 malignancies (32.0%), 45 benign lesions (60.0%), and 6 normal cases (8.0%). Mean breast mass size was 1.2 cm ( ± 1.0 cm): benign 0.8 cm ( ± 0.7 cm), malignant 1.8 cm ( ± 1.3 cm). BI-RADS category distribution was: for experts category 1 (4.0%), 2 (21.3%), 3 (24.0%), 4a (16.0%), 4b (18.7%), 4c (4.0%), 5 (12.0%); and for AI-CAD category 1 (32.0%), 2 (5.3%), 3 (9.3%), 4a (17.3%), 4b (21.3%), 4c (13.3%), 5 (1.3%). Overall diagnostic performance of experts and AI-CAD, as AUCs calculated by BI-RADS, were 0.801 and 0.751, respectively (P= .679). Sensitivity and specificity were 91.7% (22/24) and 68.6% (35/51) in experts and 87.5% (21/24) and 57.8% (32/51) in AI-CAD, respectively (P= .481).<br></p><p>Conclusions: In this real-world clinical setting, AI-CAD demonstrated promising performance comparable to that of experts.<br></p> | - |
| dc.language | eng | - |
| dc.relation.ispartof | Global Breast Cancer Conference 2025 (17/04/2025-19/04/2025, Seoul) | - |
| dc.title | Real-time AI-based computer-aided detection/diagnosis (AI-CAD) for breast ultrasound: A prospective, multicenter, multinational study (Poster presentation) | - |
| dc.type | Conference_Paper | - |