Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-a...Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-aided diagnosis system is highly required.Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost.Recently,many learning-based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset(BUSI)datasets;however,the manual handling is not an easy process and time consuming.The authors propose an EfficientNet-integrated ResNet deep network and XAI-based framework for accurately classifying breast cancer(malignant and benign).In the initial step,data augmentation is performed to increase the number of training samples.For this purpose,three-pixel flip mathematical equations are introduced:horizontal,vertical,and 90°.Later,two pretrained deep learning models were employed,skipped some layers,and fine-tuned.Both fine-tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer.Explainable artificial intelligence-based analysed the performance of trained models.After that,a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean.This technique selects the best features and fuses using a new parallel zeropadding maximum correlated coefficient features.In the end,the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms.The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4%and 98%accuracy in two different experiments.Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy.In addition,the proposed framework was executed less than the original deep learning models.展开更多
Segmenting a breast ultrasound image is still challenging due to the presence of speckle noise,dependency on the operator,and the variation of image quality.This paper presents the UltraSegNet architecture that addres...Segmenting a breast ultrasound image is still challenging due to the presence of speckle noise,dependency on the operator,and the variation of image quality.This paper presents the UltraSegNet architecture that addresses these challenges through three key technical innovations:This work adds three things:(1)a changed ResNet-50 backbone with sequential 3×3 convolutions to keep fine anatomical details that are needed for finding lesion boundaries;(2)a computationally efficient regional attention mechanism that works on high-resolution features without using a transformer’s extra memory;and(3)an adaptive feature fusion strategy that changes local and global featuresbasedonhowthe image isbeing used.Extensive evaluation on two distinct datasets demonstrates UltraSegNet’s superior performance:On the BUSI dataset,it obtains a precision of 0.915,a recall of 0.908,and an F1 score of 0.911.In the UDAIT dataset,it achieves robust performance across the board,with a precision of 0.901 and recall of 0.894.Importantly,these improvements are achieved at clinically feasible computation times,taking 235 ms per image on standard GPU hardware.Notably,UltraSegNet does amazingly well on difficult small lesions(less than 10 mm),achieving a detection accuracy of 0.891.This is a huge improvement over traditional methods that have a hard time with small-scale features,as standard models can only achieve 0.63–0.71 accuracy.This improvement in small lesion detection is particularly crucial for early-stage breast cancer identification.Results from this work demonstrate that UltraSegNet can be practically deployable in clinical workflows to improve breast cancer screening accuracy.展开更多
BACKGROUND Ultrasound classification can be used to determine the severity of adhesive intestinal obstruction and to guide the formulation of treatment plans.AIM To explore the value of ultrasound classification in di...BACKGROUND Ultrasound classification can be used to determine the severity of adhesive intestinal obstruction and to guide the formulation of treatment plans.AIM To explore the value of ultrasound classification in disease judgment and treatment plan formulation for patients with adhesive intestinal obstruction.METHODS The medical records of 120 patients with adhesive intestinal obstruction presenting at Taihe Hospital Affiliated with Hubei Medical College were retrospectively analyzed from January 2022 to January 2024 according to the severity of ultrasound images,divided into simple(mild),complex(moderate),and critical(severe),analyzing the imaging characteristics of patients with different ultrasound classifications,and developing the corresponding treatment plan according to the ultrasound typing results,that is,conservative treatment and surgical treatment,contrast the ultrasound signs of patients in the conservative vs surgical treatment groups,and the value of ultrasound classification in the treatment of adhesive ileus.RESULTS Among the 120 patients,P>0.05,compared with the general data(sex,age,body quality index,time to onset,and history of onset),the proportion of bowel distension and abdominal effusion(P>0.05),and the proportion of adhesion mass and cross-cross in the conservative treatment group,P<0.05.CONCLUSION Ultrasound typing can aid in the clinical evaluation of the severity of adhesive intestinal obstruction and provide an imaging reference for clinicians to develop targeted treatment plans.展开更多
Breast cancer detection heavily relies on medical imaging, particularly ultrasound, for early diagnosis and effectivetreatment. This research addresses the challenges associated with computer-aided diagnosis (CAD) of ...Breast cancer detection heavily relies on medical imaging, particularly ultrasound, for early diagnosis and effectivetreatment. This research addresses the challenges associated with computer-aided diagnosis (CAD) of breastcancer fromultrasound images. The primary challenge is accurately distinguishing between malignant and benigntumors, complicated by factors such as speckle noise, variable image quality, and the need for precise segmentationand classification. The main objective of the research paper is to develop an advanced methodology for breastultrasound image classification, focusing on speckle noise reduction, precise segmentation, feature extraction, andmachine learning-based classification. A unique approach is introduced that combines Enhanced Speckle ReducedAnisotropic Diffusion (SRAD) filters for speckle noise reduction, U-NET-based segmentation, Genetic Algorithm(GA)-based feature selection, and Random Forest and Bagging Tree classifiers, resulting in a novel and efficientmodel. To test and validate the hybrid model, rigorous experimentations were performed and results state thatthe proposed hybrid model achieved accuracy rate of 99.9%, outperforming other existing techniques, and alsosignificantly reducing computational time. This enhanced accuracy, along with improved sensitivity and specificity,makes the proposed hybrid model a valuable addition to CAD systems in breast cancer diagnosis, ultimatelyenhancing diagnostic accuracy in clinical applications.展开更多
Objective:To explore the diagnostic value of ultrasound imaging for breast nodules of breast imaging-reporting and data system(BI-RADS)category 3 and above.Methods:From June 2021 to July 2022,163 patients with breast ...Objective:To explore the diagnostic value of ultrasound imaging for breast nodules of breast imaging-reporting and data system(BI-RADS)category 3 and above.Methods:From June 2021 to July 2022,163 patients with breast nodules of BI-RADS 3 or above were selected as the research subjects.After pathological diagnosis,24 cases were malignant breast nodules of BI-RADS 3 or above,while 139 cases were benign breast nodules of BI-RADS 3 or above.The diagnosis rate of malignant and benign breast nodules of BI-RADS 3 or above,including 95%CI,was observed and analyzed.Results:The malignant and benign detection rates of conventional ultrasound were 88.63%and 75.00%,respectively,and the malignant and benign detection rates of ultrasound imaging were 93.18%and 87.50%,respectively,with 95%CIs greater than 0.7.Conclusion:Ultrasound imaging can help improve the diagnostic accuracy of benign and malignant breast nodules of BI-RADS 3 and above and reduce the misdiagnosis rate.展开更多
Nowadays,inspired by the great success of Transformers in Natural Language Processing,many applications of Vision Transformers(ViTs)have been investigated in the field of medical image analysis including breast ultras...Nowadays,inspired by the great success of Transformers in Natural Language Processing,many applications of Vision Transformers(ViTs)have been investigated in the field of medical image analysis including breast ultrasound(BUS)image segmentation and classification.In this paper,we propose an efficient multi-task framework to segment and classify tumors in BUS images using hybrid convolutional neural networks(CNNs)-ViTs architecture and Multi-Perceptron(MLP)-Mixer.The proposed method uses a two-encoder architecture with EfficientNetV2 backbone and an adapted ViT encoder to extract tumor regions in BUS images.The self-attention(SA)mechanism in the Transformer encoder allows capturing a wide range of high-level and complex features while the EfficientNetV2 encoder preserves local information in image.To fusion the extracted features,a Channel Attention Fusion(CAF)module is introduced.The CAF module selectively emphasizes important features from both encoders,improving the integration of high-level and local information.The resulting feature maps are reconstructed to obtain the segmentation maps using a decoder.Then,our method classifies the segmented tumor regions into benign and malignant using a simple and efficient classifier based on MLP-Mixer,that is applied for the first time,to the best of our knowledge,for the task of lesion classification in BUS images.Experimental results illustrate the outperformance of our framework compared to recent works for the task of segmentation by producing 83.42%in terms of Dice coefficient as well as for the classification with 86%in terms of accuracy.展开更多
AIM To establish a classification method for differential diagnosis of colorectal ulcerative diseases, especially Crohn's disease(CD), primary intestinal lymphoma(PIL) and intestinal tuberculosis(ITB).METHODS We s...AIM To establish a classification method for differential diagnosis of colorectal ulcerative diseases, especially Crohn's disease(CD), primary intestinal lymphoma(PIL) and intestinal tuberculosis(ITB).METHODS We searched the in-patient medical record database for confirmed cases of CD, PIL and ITB from 2008 to 2015 at our center, collected data on endoscopic ultrasound(EUS) from randomly-chosen patients who formed the training set, conducted univariate logistic regression analysis to summarize EUS features of CD, PIL and ITB, and created a diagnostic classification method. All cases found to have colorectal ulcers using EUS were obtained from the endoscopy database and formed the test set. We then removed the cases which were easily diagnosed, and the remaining cases formed the perplexing test set. We re-diagnosed the cases in the three sets using the classification method, determined EUS diagnostic accuracies, and adjusted the classification accordingly. Finally, the re-diagnosing and accuracy-calculating steps were repeated.RESULTS In total, 272 CD, 60 PIL and 39 ITB cases were diagnosed from 2008 to 2015 based on the in-patient database, and 200 CD, 30 PIL and 20 ITB cases were randomly chosen to form the training set. The EUS features were summarized as follows: CD: Thickened submucosa with a slightly high echo level and visible layer; PIL: Absent layer and diffuse hypoechoic mass; and ITB: Thickened mucosa with a high or slightly high echo level and visible layer. The test set consisted of 77 CD, 30 PIL, 23 ITB and 140 cases of other diseases obtained from the endoscopy database. Seventy-four cases were excluded to form the perplexing test set. After adjustment of the classification, EUS diagnostic accuracies for CD, PIL and ITB were 83.6%(209/250), 97.2%(243/250) and 85.6%(214/250) in the training set, were 89.3%(241/270), 97.8%(264/270) and 84.1%(227/270) in the test set, and were 86.7%(170/196), 98.0%(192/196) and 85.2%(167/196) in the perplexing set, respectively.CONCLUSION The EUS features of CD, PIL and ITB are different. The diagnostic classification method is reliable in the differential diagnosis of colorectal ulcerative diseases.展开更多
BACKGROUND The incidence rate of breast cancer has exceeded that of lung cancer,and it has become the most malignant type of cancer in the world.BI-RADS 4 breast nodules have a wide range of malignant risks and are as...BACKGROUND The incidence rate of breast cancer has exceeded that of lung cancer,and it has become the most malignant type of cancer in the world.BI-RADS 4 breast nodules have a wide range of malignant risks and are associated with challenging clinical decision-making.AIM To explore the diagnostic value of artificial intelligence(AI)automatic detection systems for BI-RADS 4 breast nodules and to assess whether conventional ultrasound BI-RADS classification with AI automatic detection systems can reduce the probability of BI-RADS 4 biopsy.METHODS A total of 107 BI-RADS breast nodules confirmed by pathology were selected between June 2019 and July 2020 at Hwa Mei Hospital,University of Chinese Academy of Sciences.These nodules were classified by ultrasound doctors and the AI-SONIC breast system.The diagnostic values of conventional ultrasound,the AI automatic detection system,conventional ultrasound combined with the AI automatic detection system and adjusted BI-RADS classification diagnosis were statistically analyzed.RESULTS Among the 107 breast nodules,61 were benign(57.01%),and 46 were malignant(42.99%).The pathology results were considered the gold standard;furthermore,the sensitivity,specificity,accuracy,Youden index,and positive and negative predictive values were 84.78%,67.21%,74.77%,0.5199,66.10%and 85.42%for conventional ultrasound BI-RADS classification diagnosis,86.96%,75.41%,80.37%,0.6237,72.73%,and 88.46%for automatic AI detection,80.43%,90.16%,85.98%,0.7059,86.05%,and 85.94%for conventional ultrasound BI-RADS classification with automatic AI detection and 93.48%,67.21%,78.50%,0.6069,68.25%,and 93.18%for adjusted BI-RADS classification,respectively.The biopsy rate,cancer detection rate and malignancy risk were 100%,42.99%and 0%and 67.29%,61.11%,and 1.87%before and after BI-RADS adjustment,respectively.CONCLUSION Automatic AI detection has high accuracy in determining benign and malignant BI-RADS 4 breast nodules.Conventional ultrasound BI-RADS classification combined with AI automatic detection can reduce the biopsy rate of BI-RADS 4 breast nodules.展开更多
文摘Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-aided diagnosis system is highly required.Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost.Recently,many learning-based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset(BUSI)datasets;however,the manual handling is not an easy process and time consuming.The authors propose an EfficientNet-integrated ResNet deep network and XAI-based framework for accurately classifying breast cancer(malignant and benign).In the initial step,data augmentation is performed to increase the number of training samples.For this purpose,three-pixel flip mathematical equations are introduced:horizontal,vertical,and 90°.Later,two pretrained deep learning models were employed,skipped some layers,and fine-tuned.Both fine-tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer.Explainable artificial intelligence-based analysed the performance of trained models.After that,a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean.This technique selects the best features and fuses using a new parallel zeropadding maximum correlated coefficient features.In the end,the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms.The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4%and 98%accuracy in two different experiments.Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy.In addition,the proposed framework was executed less than the original deep learning models.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R435),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Segmenting a breast ultrasound image is still challenging due to the presence of speckle noise,dependency on the operator,and the variation of image quality.This paper presents the UltraSegNet architecture that addresses these challenges through three key technical innovations:This work adds three things:(1)a changed ResNet-50 backbone with sequential 3×3 convolutions to keep fine anatomical details that are needed for finding lesion boundaries;(2)a computationally efficient regional attention mechanism that works on high-resolution features without using a transformer’s extra memory;and(3)an adaptive feature fusion strategy that changes local and global featuresbasedonhowthe image isbeing used.Extensive evaluation on two distinct datasets demonstrates UltraSegNet’s superior performance:On the BUSI dataset,it obtains a precision of 0.915,a recall of 0.908,and an F1 score of 0.911.In the UDAIT dataset,it achieves robust performance across the board,with a precision of 0.901 and recall of 0.894.Importantly,these improvements are achieved at clinically feasible computation times,taking 235 ms per image on standard GPU hardware.Notably,UltraSegNet does amazingly well on difficult small lesions(less than 10 mm),achieving a detection accuracy of 0.891.This is a huge improvement over traditional methods that have a hard time with small-scale features,as standard models can only achieve 0.63–0.71 accuracy.This improvement in small lesion detection is particularly crucial for early-stage breast cancer identification.Results from this work demonstrate that UltraSegNet can be practically deployable in clinical workflows to improve breast cancer screening accuracy.
文摘BACKGROUND Ultrasound classification can be used to determine the severity of adhesive intestinal obstruction and to guide the formulation of treatment plans.AIM To explore the value of ultrasound classification in disease judgment and treatment plan formulation for patients with adhesive intestinal obstruction.METHODS The medical records of 120 patients with adhesive intestinal obstruction presenting at Taihe Hospital Affiliated with Hubei Medical College were retrospectively analyzed from January 2022 to January 2024 according to the severity of ultrasound images,divided into simple(mild),complex(moderate),and critical(severe),analyzing the imaging characteristics of patients with different ultrasound classifications,and developing the corresponding treatment plan according to the ultrasound typing results,that is,conservative treatment and surgical treatment,contrast the ultrasound signs of patients in the conservative vs surgical treatment groups,and the value of ultrasound classification in the treatment of adhesive ileus.RESULTS Among the 120 patients,P>0.05,compared with the general data(sex,age,body quality index,time to onset,and history of onset),the proportion of bowel distension and abdominal effusion(P>0.05),and the proportion of adhesion mass and cross-cross in the conservative treatment group,P<0.05.CONCLUSION Ultrasound typing can aid in the clinical evaluation of the severity of adhesive intestinal obstruction and provide an imaging reference for clinicians to develop targeted treatment plans.
基金funded through Researchers Supporting Project Number(RSPD2024R996)King Saud University,Riyadh,Saudi Arabia。
文摘Breast cancer detection heavily relies on medical imaging, particularly ultrasound, for early diagnosis and effectivetreatment. This research addresses the challenges associated with computer-aided diagnosis (CAD) of breastcancer fromultrasound images. The primary challenge is accurately distinguishing between malignant and benigntumors, complicated by factors such as speckle noise, variable image quality, and the need for precise segmentationand classification. The main objective of the research paper is to develop an advanced methodology for breastultrasound image classification, focusing on speckle noise reduction, precise segmentation, feature extraction, andmachine learning-based classification. A unique approach is introduced that combines Enhanced Speckle ReducedAnisotropic Diffusion (SRAD) filters for speckle noise reduction, U-NET-based segmentation, Genetic Algorithm(GA)-based feature selection, and Random Forest and Bagging Tree classifiers, resulting in a novel and efficientmodel. To test and validate the hybrid model, rigorous experimentations were performed and results state thatthe proposed hybrid model achieved accuracy rate of 99.9%, outperforming other existing techniques, and alsosignificantly reducing computational time. This enhanced accuracy, along with improved sensitivity and specificity,makes the proposed hybrid model a valuable addition to CAD systems in breast cancer diagnosis, ultimatelyenhancing diagnostic accuracy in clinical applications.
文摘Objective:To explore the diagnostic value of ultrasound imaging for breast nodules of breast imaging-reporting and data system(BI-RADS)category 3 and above.Methods:From June 2021 to July 2022,163 patients with breast nodules of BI-RADS 3 or above were selected as the research subjects.After pathological diagnosis,24 cases were malignant breast nodules of BI-RADS 3 or above,while 139 cases were benign breast nodules of BI-RADS 3 or above.The diagnosis rate of malignant and benign breast nodules of BI-RADS 3 or above,including 95%CI,was observed and analyzed.Results:The malignant and benign detection rates of conventional ultrasound were 88.63%and 75.00%,respectively,and the malignant and benign detection rates of ultrasound imaging were 93.18%and 87.50%,respectively,with 95%CIs greater than 0.7.Conclusion:Ultrasound imaging can help improve the diagnostic accuracy of benign and malignant breast nodules of BI-RADS 3 and above and reduce the misdiagnosis rate.
文摘Nowadays,inspired by the great success of Transformers in Natural Language Processing,many applications of Vision Transformers(ViTs)have been investigated in the field of medical image analysis including breast ultrasound(BUS)image segmentation and classification.In this paper,we propose an efficient multi-task framework to segment and classify tumors in BUS images using hybrid convolutional neural networks(CNNs)-ViTs architecture and Multi-Perceptron(MLP)-Mixer.The proposed method uses a two-encoder architecture with EfficientNetV2 backbone and an adapted ViT encoder to extract tumor regions in BUS images.The self-attention(SA)mechanism in the Transformer encoder allows capturing a wide range of high-level and complex features while the EfficientNetV2 encoder preserves local information in image.To fusion the extracted features,a Channel Attention Fusion(CAF)module is introduced.The CAF module selectively emphasizes important features from both encoders,improving the integration of high-level and local information.The resulting feature maps are reconstructed to obtain the segmentation maps using a decoder.Then,our method classifies the segmented tumor regions into benign and malignant using a simple and efficient classifier based on MLP-Mixer,that is applied for the first time,to the best of our knowledge,for the task of lesion classification in BUS images.Experimental results illustrate the outperformance of our framework compared to recent works for the task of segmentation by producing 83.42%in terms of Dice coefficient as well as for the classification with 86%in terms of accuracy.
文摘AIM To establish a classification method for differential diagnosis of colorectal ulcerative diseases, especially Crohn's disease(CD), primary intestinal lymphoma(PIL) and intestinal tuberculosis(ITB).METHODS We searched the in-patient medical record database for confirmed cases of CD, PIL and ITB from 2008 to 2015 at our center, collected data on endoscopic ultrasound(EUS) from randomly-chosen patients who formed the training set, conducted univariate logistic regression analysis to summarize EUS features of CD, PIL and ITB, and created a diagnostic classification method. All cases found to have colorectal ulcers using EUS were obtained from the endoscopy database and formed the test set. We then removed the cases which were easily diagnosed, and the remaining cases formed the perplexing test set. We re-diagnosed the cases in the three sets using the classification method, determined EUS diagnostic accuracies, and adjusted the classification accordingly. Finally, the re-diagnosing and accuracy-calculating steps were repeated.RESULTS In total, 272 CD, 60 PIL and 39 ITB cases were diagnosed from 2008 to 2015 based on the in-patient database, and 200 CD, 30 PIL and 20 ITB cases were randomly chosen to form the training set. The EUS features were summarized as follows: CD: Thickened submucosa with a slightly high echo level and visible layer; PIL: Absent layer and diffuse hypoechoic mass; and ITB: Thickened mucosa with a high or slightly high echo level and visible layer. The test set consisted of 77 CD, 30 PIL, 23 ITB and 140 cases of other diseases obtained from the endoscopy database. Seventy-four cases were excluded to form the perplexing test set. After adjustment of the classification, EUS diagnostic accuracies for CD, PIL and ITB were 83.6%(209/250), 97.2%(243/250) and 85.6%(214/250) in the training set, were 89.3%(241/270), 97.8%(264/270) and 84.1%(227/270) in the test set, and were 86.7%(170/196), 98.0%(192/196) and 85.2%(167/196) in the perplexing set, respectively.CONCLUSION The EUS features of CD, PIL and ITB are different. The diagnostic classification method is reliable in the differential diagnosis of colorectal ulcerative diseases.
文摘BACKGROUND The incidence rate of breast cancer has exceeded that of lung cancer,and it has become the most malignant type of cancer in the world.BI-RADS 4 breast nodules have a wide range of malignant risks and are associated with challenging clinical decision-making.AIM To explore the diagnostic value of artificial intelligence(AI)automatic detection systems for BI-RADS 4 breast nodules and to assess whether conventional ultrasound BI-RADS classification with AI automatic detection systems can reduce the probability of BI-RADS 4 biopsy.METHODS A total of 107 BI-RADS breast nodules confirmed by pathology were selected between June 2019 and July 2020 at Hwa Mei Hospital,University of Chinese Academy of Sciences.These nodules were classified by ultrasound doctors and the AI-SONIC breast system.The diagnostic values of conventional ultrasound,the AI automatic detection system,conventional ultrasound combined with the AI automatic detection system and adjusted BI-RADS classification diagnosis were statistically analyzed.RESULTS Among the 107 breast nodules,61 were benign(57.01%),and 46 were malignant(42.99%).The pathology results were considered the gold standard;furthermore,the sensitivity,specificity,accuracy,Youden index,and positive and negative predictive values were 84.78%,67.21%,74.77%,0.5199,66.10%and 85.42%for conventional ultrasound BI-RADS classification diagnosis,86.96%,75.41%,80.37%,0.6237,72.73%,and 88.46%for automatic AI detection,80.43%,90.16%,85.98%,0.7059,86.05%,and 85.94%for conventional ultrasound BI-RADS classification with automatic AI detection and 93.48%,67.21%,78.50%,0.6069,68.25%,and 93.18%for adjusted BI-RADS classification,respectively.The biopsy rate,cancer detection rate and malignancy risk were 100%,42.99%and 0%and 67.29%,61.11%,and 1.87%before and after BI-RADS adjustment,respectively.CONCLUSION Automatic AI detection has high accuracy in determining benign and malignant BI-RADS 4 breast nodules.Conventional ultrasound BI-RADS classification combined with AI automatic detection can reduce the biopsy rate of BI-RADS 4 breast nodules.
