Background In clinical practice, reducing unnecessary biopsies for mammographic BI-RADS 4 lesions is crucial. The objective of this study was to explore the potential value of deep transfer learning (DTL) based on the different fine-tuning strategies for Inception V3 to reduce the number of unnecessary biopsies that residents need to perform for mammographic BI-RADS 4 lesions. Methods A total of 1980 patients with breast lesions were included, including 1473 benign lesions (185 women with bilateral breast lesions), and 692 malignant lesions collected and confirmed by clinical pathology or biopsy. The breast mammography images were randomly divided into three subsets, a training set, testing set, and validation set 1, at a ratio of 8:1:1. We constructed a DTL model for the classification of breast lesions based on Inception V3 and attempted to improve its performance with 11 fine-tuning strategies. The mammography images from 362 patients with pathologically confirmed BI-RADS 4 breast lesions were employed as validation set 2. Two images from each lesion were tested, and trials were categorized as correct if the judgement (≥ 1 image) was correct. We used precision (Pr), recall rate (Rc), F1 score (F1), and the area under the receiver operating characteristic curve (AUROC) as the performance metrics of the DTL model with validation set 2. Results The S5 model achieved the best fit for the data. The Pr, Rc, F1 and AUROC of S5 were 0.90, 0.90, 0.90, and 0.86, respectively, for Category 4. The proportions of lesions downgraded by S5 were 90.73%, 84.76%, and 80.19% for categories 4 A, 4B, and 4 C, respectively. The overall proportion of BI-RADS 4 lesions downgraded by S5 was 85.91%. There was no significant difference between the classification results of the S5 model and pathological diagnosis (P = 0.110). Conclusion The S5 model we proposed here can be used as an effective approach for reducing the number of unnecessary biopsies that residents need to conduct for mammographic BI-RADS 4 lesions and may have other important clinical uses.
Background In clinical practice, reducing unnecessary biopsies of BI-RADS 4 lesions of the mammogram is crucial. The objective of this study was to explore the potential value of deep transfer learning (DTL) based on the different fine-tuning strategies of Inception V3 to reduce the number of unnecessary biopsies of mammographic BI-RADS 4 lesions for residents. Methods A total of 1980 patients with breast lesions were included, including 1473 benign lesions (185 women with bilateral breast lesions), and 692 malignant lesions were collected and confirmed by clinical pathology or biopsy. The dataset of breast mammography images was randomly divided into three subsets: a training set, testing set, and validation set at a ratio of 8:1:1. We constructed a DTL model for the classification of breast lesions based on InceptionV3, and 11 fine-tuning strategies were attempted to improve the performance of the InceptionV3 model. Mammography images from 362 patients with BI-RADS 4 breast lesions were employed as validation set 2. All breast lesions in validation set 2 were pathologically confirmed. Two images from each lesion were tested and trials were categorized as correct if the judgement (≥ 1 image) was correct. We used precision (Pr), recall rate (Rc), f1 score (f1), and the area under the receiver operating characteristic curve (AUROC) as the performance metrics of the DTL model on validation set 2. Results The S5 model was the best fit for the data. The Pr, Rc, \(f1\) and AUROC of S5 were 0.90, 0.90, 0.90, and 0.86, respectively, for Category 4. The proportions of downgraded lesions by S5 were 90.73%, 84.76%, and 80.19% for category 4A,4B,4C, respectively. The overall proportion of lesions downgraded by S5 was 85.91% in Category 4. There was no statistical difference between the classification results of the S5 model and pathological diagnosis (P = 0.110). Conclusion The S5 model we propose here can be used as an effective approach to reduce the number of unnecessary biopsies of mammographic BI-RADS 4 lesions for residents and have important clinical uses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.