Deep Learning-Based Automatic Detection of Poorly Positioned Mammograms to Minimize Patient Return Visits for Repeat Imaging: A Real-World Application

Gupta, Vikas; Taylor, Clayton; Bonnet, Sarah; Prevedello, Luciano M.; Hawley, Jeffrey R.; White, Richard D.; Flores, Mona G.; Erdal, Barbaros S.

doi:10.48550/arxiv.2009.13580

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By combining the results of the separately implemented classifiers, we can predict whether the breast is well positioned or not with an accuracy of 96.5% for CC and 93.3% for MLO views through the overall built systems. Our approach offers promising results compared to the previous study [12], proposing to combine techniques from deep learning and feature-based machine learning algorithms to recognize inadequately positioned mammograms. Furthermore, the proposed models provided these classification results with minimal computational time and power, as we used an NVIDIA GTX 1080 graphics card in our study and the maximum time to train one network was about 12 h (the exact training times and learning parameters for each model can be found in the previous sections).…”

Section: Discussionmentioning

confidence: 90%

“…The assessment of positioning quality has so far received relatively little attention in medical image analysis and none of the available studies have achieved high performance in this area, despite its importance for effective breast cancer detection. In the last year, an interesting research paper has been published, presenting a deep learning algorithm for automatic detection of poorly positioned mammograms [12]. In this approach, not all standard defined quality criteria related to breast positioning were evaluated.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automated Assessment of Breast Positioning Quality in Screening Mammography

Brahim

Westerkamp

Hempel

et al. 2022

Cancers

View full text Add to dashboard Cite

Screening mammography is a widely used approach for early breast cancer detection, effectively increasing the survival rate of affected patients. According to the Food and Drug Administration’s Mammography Quality Standards Act and Program statistics, approximately 39 million mammography procedures are performed in the United States each year. Therefore, breast cancer screening is among the most common radiological tasks. Interpretation of screening mammograms by a specialist radiologist includes primarily the review of breast positioning quality, which is a key factor affecting the sensitivity of mammography and thus the diagnostic performance. Each mammogram with inadequate positioning may lead to a missed cancer or, in case of false positive signal interpretation, to follow-up activities, increased emotional burden and potential over-therapy and must be repeated, requiring the return of the patient. In this study, we have developed deep convolutional neuronal networks to differentiate mammograms with inadequate breast positioning from the adequate ones. The aim of the proposed automated positioning quality evaluation is to assist radiology technologists in detecting poorly positioned mammograms during patient visits, improve mammography performance, and decrease the recall rate. The implemented models have achieved 96.5% accuracy in cranio-caudal view classification and 93.3% accuracy in mediolateral oblique view regarding breast positioning quality. In addition to these results, we developed a software module that allows the study to be applied in practice by presenting the implemented model predictions and informing the technologist about the missing quality criteria.

show abstract

Section: Discussionmentioning

confidence: 90%

Section: Introduction and Related Workmentioning

confidence: 99%

Automated Assessment of Breast Positioning Quality in Screening Mammography

Brahim

Westerkamp

Hempel

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…It is advantageous and necessary to use a number of datasets, each of which supports a range of parameters and a predetermined composition problem, in order to assess the efficiency of the suggested algorithms. There are many object detection datasets that are readily available in the research domain: COCO [37] [23] [24] [35,36] http://cocodataset.org/ and PASCAL VOC [23] [76][77][78][79][80] http://humanpose.mpi-inf.mpg.de/ , and imagine [81][82][83][84][85] https://imagenet.org/index.php. Some researchers have rarely relied on datasets that are generated synthetically.…”

Section: B Investigated Datasetsmentioning

confidence: 99%

A Review of Lightweight Object Detection Algorithms for Mobile Augmented Reality

Nafea¹,

Tan²,

Jubair³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Augmented Reality (AR) has led to several technologies being at the forefront of innovation and change in every sector and industry. Accelerated advances in Computer Vision (CV), AR, and object detection refined the process of analyzing and comprehending the environment. Object detection has recently drawn a lot of attention as one of the most fundamental and difficult computer vision topics. The traditional object detection techniques are fully computer-based and typically need massive Graphics Processing Unit (GPU) power, while they aren't usually real-time. However, an AR application required real-time superimposed digital data to enable users to improve their field of view. This paper provides a comprehensive review of most of the recent lightweight object detection algorithms that are suitable to be used in AR applications. Four sources including Web of Science, Scopus, IEEE Xplore, and ScienceDirect were included in this review study. A total of ten papers were discussed and analyzed from four perspectives: accuracy, speed, small object detection, and model size. Several interesting challenges are discussed as recommendations for future work in the object detection field.

show abstract

“…O mamilo é uma estrutura de interesse a ser observada nos exames de mamografia. Essa estrutura auxilia o mamógrafo a verificar a qualidade do posicionamento de um exame, o que pode minimizar a necessidade do paciente retornar para repetir o exame devido ao mau posicionamento [29]. No entanto, detectar essa estrutura não é trivial, pois, além de ser uma estrutura pequena, nem sempre aparece com clareza nas imagens.…”

Section: Caso De Uso 2: Banco De Dados De Exames De Mamografiaunclassified

Habilitando Anotações De Dados Autônomos: Uma Abordagem De Aprendizado Por Reforço Com Humano No Loop

CRUZ¹

View full text Add to dashboard Cite

Deep Learning-Based Automatic Detection of Poorly Positioned Mammograms to Minimize Patient Return Visits for Repeat Imaging: A Real-World Application

Cited by 3 publications

References 0 publications

Automated Assessment of Breast Positioning Quality in Screening Mammography

Automated Assessment of Breast Positioning Quality in Screening Mammography

A Review of Lightweight Object Detection Algorithms for Mobile Augmented Reality

Habilitando Anotações De Dados Autônomos: Uma Abordagem De Aprendizado Por Reforço Com Humano No Loop

Contact Info

Product

Resources

About