Background: Accurate diagnosis of breast cancer is of great importance to improve the prognosis of patients. Artificial intelligence (AI)-assisted diagnostic system for breast ultrasound is gradually being applied in the identification of benign and malignant breast lesions. This study aimed to evaluate the diagnostic performance and optimal application of AIassisted ultrasonography for breast lesions in clinical setting.
Methods: A total of 501 consecutive patients with 679 breast lesions were prospectively included in the study. Junior and senior radiologists were asked to interpret images of lesions with and without AI assistance, respectively. Three application modes of AI were employed: AI alone, adjusted Breast Imaging Reporting and Data System (BI-RADS; incorporating BI-RADS obtained by AI into BI-RADS obtained by radiologists), and second reading mode (combining characteristic information extracted by AI to conduct a second reading so as to obtain a new BI-RADS). The diagnostic performances of these application modes were analyzed and compared.
Results: The area under the curve (AUC) of junior radiologists increased from 0.879 to 0.921 in BI-RADS, which was higher than that in BI-RADS (0.901), similar to that in AI alone (0.924), and lower than that obtained by senior radiologists (0.950). Using BI-RADS category 4A as the threshold, the sensitivity of junior radiologists was found to increase from 0.83 to 0.92 (P<0.001). Furthermore, the specificity increased from 0.79 to 0.85, which was higher than those of AI alone and BI-RADS (P<0.001). The unnecessary biopsy rate decreased by 14.70% (P=0.01). For senior radiologists, the sensitivity increased from 0.91 to 0.96 (P=0.01). Similar results were observed in the subgroup analysis of lesions ≤2 cm. For lesions >2 cm, only the specificity of junior radiologists increased from 0.39 to 0.52 (P=0.03).
Conclusions: AI-assisted ultrasound is useful for the diagnosis of breast lesions, particularly for junior radiologists and lesions ≤2 cm. The use of the second reading mode can achieve excellent diagnostic performance.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11733640 | PMC |
| http://dx.doi.org/10.21037/gs-24-213 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Intraoperative ultrasound-guided breast-conserving surgery: A performance analysis on the basis of novel cancer lesion classification and patients' cosmetic satisfaction.
Surgery
January 2025
Breast Surgery Unit, Veneto Institute of Oncology IOV, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Padova, Italy.
Background: Intraoperative ultrasound-guided breast-conserving surgery guarantees real-time direct visualization of tumor and resection margins. We compared surgical, oncologic, and cosmetic outcomes between intraoperative ultrasound-guided breast-conserving surgery and traditional (palpation- or wire-guided) surgery across all breast cancer lesion types.
Methods: This prospective observational cohort study was conducted at the Veneto Institute of Oncology between January 2021 and October 2022.
Clinical utility of quantitative ultrasonography parameters combined with serum cancer antigen 15‑3, human epidermal growth factor receptor 2 and soluble E‑cadherin in diagnosing mass‑type breast cancer.
Oncol Lett
March 2025
Department of Imaging, The Affiliated Hospital of Beihua University, Jilin, Jilin 132011, P.R. China.
Contrast-enhanced ultrasonography (CEUS), a newly developed imaging technique, holds certain value in differentiating benign from malignant tumors. Additionally, serum tumor markers also exhibit significant clinical importance in the diagnosis and monitoring of malignant tumors. Reports have indicated abnormal expression of HER-2, CA153 and sE-cad in breast cancer.
View Article and Find Full Text PDFPigmented Superficial Basal Cell Carcinoma of the Nipple-Areola Complex: A Case Report.
Case Rep Dermatol
January 2025
Department of Dermatology, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Jinhua, PR China.
Introduction: Basal cell carcinoma (BCC) is the most common type of skin malignancy, accounting for approximately 80% of all non-melanoma skin cancers (NMSCs). Ultraviolet (UV) exposure is a significant risk factor for BCC development, which typically occurs in sun-exposed areas. BCC arising in non-sun-exposed regions, such as the nipple-areola complex (NAC), is exceedingly rare, with fewer than 100 cases reported globally.
View Article and Find Full Text PDFAcrometastasis of Lung Adenocarcinoma to the Fibula: A Report of a Rare Case.
Cureus
December 2024
Oncosurgery, State Cancer Institute, Gauhati Medical College and Hospital (GMCH), Guwahati, IND.
Acrometastasis is an extremely rare diagnosis, invariably associated with poor prognosis. A 60-year-old female with complaints of cough and breathing difficulty also presented with pain and swelling in her left leg. Radiological investigations suggested a double primary in the lung and leg; histopathology and immunohistochemistry (IHC) confirmed the lesion in the leg to be metastatic from the lung primary.
View Article and Find Full Text PDFApplication of an artificial intelligence-assisted diagnostic system for breast ultrasound: a prospective study.
Gland Surg
December 2024
Department of Ultrasound, The First Medical Center, Chinese PLA General Hospital, Beijing, China.
Background: Accurate diagnosis of breast cancer is of great importance to improve the prognosis of patients. Artificial intelligence (AI)-assisted diagnostic system for breast ultrasound is gradually being applied in the identification of benign and malignant breast lesions. This study aimed to evaluate the diagnostic performance and optimal application of AIassisted ultrasonography for breast lesions in clinical setting.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!