Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence Detection
We compared diagnostic performances between radiologists with reference to clinical information and standalone artificial intelligence (AI) detection of breast cancer on digital mammography. This study included 392 women (average age: 57.3 ± 12.1 years, range: 30–94 years) diagnosed with malignancy...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/1/117 |
| _version_ | 1797626052887969792 |
|---|---|
| author | Won Jae Choi Jin Kyung An Jeong Joo Woo Hee Yong Kwak |
| author_facet | Won Jae Choi Jin Kyung An Jeong Joo Woo Hee Yong Kwak |
| author_sort | Won Jae Choi |
| collection | DOAJ |
| description | We compared diagnostic performances between radiologists with reference to clinical information and standalone artificial intelligence (AI) detection of breast cancer on digital mammography. This study included 392 women (average age: 57.3 ± 12.1 years, range: 30–94 years) diagnosed with malignancy between January 2010 and June 2021 who underwent digital mammography prior to biopsy. Two radiologists assessed mammographic findings based on clinical symptoms and prior mammography. All mammographies were analyzed via AI. Breast cancer detection performance was compared between radiologists and AI based on how the lesion location was concordant between each analysis method (radiologists or AI) and pathological results. Kappa coefficient was used to measure the concordance between radiologists or AI analysis and pathology results. Binominal logistic regression analysis was performed to identify factors influencing the concordance between radiologists’ analysis and pathology results. Overall, the concordance was higher in radiologists’ diagnosis than on AI analysis (kappa coefficient: 0.819 vs. 0.698). Impact of prior mammography (odds ratio (OR): 8.55, <i>p</i> < 0.001), clinical symptom (OR: 5.49, <i>p</i> < 0.001), and fatty breast density (OR: 5.18, <i>p</i> = 0.008) were important factors contributing to the concordance of lesion location between radiologists’ diagnosis and pathology results. |
| first_indexed | 2024-03-11T10:05:09Z |
| format | Article |
| id | doaj.art-a2593c4394eb4cbea08235e2a59a4594 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T10:05:09Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-a2593c4394eb4cbea08235e2a59a45942023-11-16T15:09:05ZengMDPI AGDiagnostics2075-44182022-12-0113111710.3390/diagnostics13010117Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence DetectionWon Jae Choi0Jin Kyung An1Jeong Joo Woo2Hee Yong Kwak3Department of Radiology, Nowon Eulji University Hospital, Eulji University School of Medicine, Seoul 01830, Republic of KoreaDepartment of Radiology, Nowon Eulji University Hospital, Eulji University School of Medicine, Seoul 01830, Republic of KoreaDepartment of Radiology, Nowon Eulji University Hospital, Eulji University School of Medicine, Seoul 01830, Republic of KoreaDepartment of Surgery, Nowon Eulji University Hospital, Eulji University School of Medicine, Seoul 01830, Republic of KoreaWe compared diagnostic performances between radiologists with reference to clinical information and standalone artificial intelligence (AI) detection of breast cancer on digital mammography. This study included 392 women (average age: 57.3 ± 12.1 years, range: 30–94 years) diagnosed with malignancy between January 2010 and June 2021 who underwent digital mammography prior to biopsy. Two radiologists assessed mammographic findings based on clinical symptoms and prior mammography. All mammographies were analyzed via AI. Breast cancer detection performance was compared between radiologists and AI based on how the lesion location was concordant between each analysis method (radiologists or AI) and pathological results. Kappa coefficient was used to measure the concordance between radiologists or AI analysis and pathology results. Binominal logistic regression analysis was performed to identify factors influencing the concordance between radiologists’ analysis and pathology results. Overall, the concordance was higher in radiologists’ diagnosis than on AI analysis (kappa coefficient: 0.819 vs. 0.698). Impact of prior mammography (odds ratio (OR): 8.55, <i>p</i> < 0.001), clinical symptom (OR: 5.49, <i>p</i> < 0.001), and fatty breast density (OR: 5.18, <i>p</i> = 0.008) were important factors contributing to the concordance of lesion location between radiologists’ diagnosis and pathology results.https://www.mdpi.com/2075-4418/13/1/117artificial intelligencebreast neoplasmmammographyradiologists |
| spellingShingle | Won Jae Choi Jin Kyung An Jeong Joo Woo Hee Yong Kwak Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence Detection Diagnostics artificial intelligence breast neoplasm mammography radiologists |
| title | Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence Detection |
| title_full | Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence Detection |
| title_fullStr | Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence Detection |
| title_full_unstemmed | Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence Detection |
| title_short | Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence Detection |
| title_sort | comparison of diagnostic performance in mammography assessment radiologist with reference to clinical information versus standalone artificial intelligence detection |
| topic | artificial intelligence breast neoplasm mammography radiologists |
| url | https://www.mdpi.com/2075-4418/13/1/117 |
| work_keys_str_mv | AT wonjaechoi comparisonofdiagnosticperformanceinmammographyassessmentradiologistwithreferencetoclinicalinformationversusstandaloneartificialintelligencedetection AT jinkyungan comparisonofdiagnosticperformanceinmammographyassessmentradiologistwithreferencetoclinicalinformationversusstandaloneartificialintelligencedetection AT jeongjoowoo comparisonofdiagnosticperformanceinmammographyassessmentradiologistwithreferencetoclinicalinformationversusstandaloneartificialintelligencedetection AT heeyongkwak comparisonofdiagnosticperformanceinmammographyassessmentradiologistwithreferencetoclinicalinformationversusstandaloneartificialintelligencedetection |