Application of dual-modality ultrasound deep learning predictive model in diagnosing breast cancer
Journal Title: Chinese Journal of Clinical Research - Year 2024, Vol 37, Issue 3
Abstract
Objective To develop a predictive model using deep learning (DL) techniques based on breast ultrasound grayscale images and elastography, and to explore the diagnostic efficacy of this model in differentiating benign from malignant breast lesions. Methods Data of 1 000 breast lesions from patients who underwent surgical treatment at Linyi People's Hospital Breast Surgery Department from May 2020 to April 2021 were collected retrospectively. including ultrasound images and related clinical pathological information. The ultrasound grayscale image and elastography of the largest section of each lesion were selected and randomly divided into training, validation, and test sets at a ratio of 7∶2∶1. A predictive model was constructed based on neural networks using the training and validation sets, and the diagnostic efficacy of the model was tested with the test set images. Four sonographers were invited to read the test set ultrasound images independently, and their diagnostic efficacies were compared with the model's performance. Results The area under the curve (AUC) value (0.907) of the receiver operating characteristic curve (ROC) of DL model for breast lesion diagnosis was higher than all participating sonographers, with a statistically significant difference (P＜0.05). The average AUC value for the diagnosis by senior sonographers (0.835) was higher than that for junior sonographers (0.719), with a statistically significant difference (P＜0.05). When the model assisted junior sonographers and senior sonographers in diagnosing the test set breast lesions, the average AUC value was 0.806 and 0.864, respectively. After assistance from the model, the diagnostic efficacy of sonographers of different experience levels improved, with a more significant increase for junior sonographers (P＜0.05). Notably, there was no statistically significant difference in the AUC values between the junior sonographers assisted by the DL model and the senior sonographers reading alone (P＞0.05). Conclusion A predictive model based on dual-modality ultrasound DL can significantly improve the diagnostic efficacy of sonographers in differentiating benign from malignant breast lesions.
Authors and Affiliations
LI Xiaojie, ZHAO Guojia, REN Jinhe
Keywords
Related Articles
- EP ID EP734503
- DOI 10.13429/j.cnki.cjcr.2024.03.008
- Views 36
- Downloads 0
Factors associated with the severity of coronary artery disease in type 2 diabetes mellitus patients
Objective To analyze the factors related to the severity of coronary artery disease (CAD) in type 2 diabetes mellitus (T2DM) patients, with the aim of providing a reference for the risk assessment of them. Methods Clinic...
Efficacy and safety of oxaliplatin and capecitabine in combination with sintilimab as first-line treatment for HER2-negative advanced gastric cancer
"<b>Objective</b> To analyze the clinical efficacy and the occurrence of adverse events of the oxaliplatin and capecitabine (XELOX) combined with sintilimab as a first-line treatment in patients with human epidermal grow...
Clinical value of multiple hematological markers to predict infection after hepatic carcinectomy
"Objective To investigate the predictive value of multiple hematological markers in postoperative infection after hepatic carcinectomy, such as neutrophil to lymphocyte ratio (NLR) and monocyte to lymphocyte ratio (MLR)....
Effects of laparoscopic surgery combined with hyperthermic intraperitoneal chemotherapy on postoperative coagulation indicators in patients with colorectal cancer
Objective To observe the changes of coagulation function in patients with colorectal cancer (CRC) after laparoscopic surgery combined with hyperthermic intraperitoneal chemotherapy (HIPEC). Methods Sixty patients with CR...
Analysis of risk factors for delayed postoperative discharge of patients with pulmonary nodules
<b>Objective</b> To investigate the influencing factors of delayed postoperative discharge in patients with pulmonary nodules. <b>Methods</b> Electronic medical records of 223 patients, 91 males and 132 females, who...