Improving Workflow Efficiency for Mammography Using Machine Learning

Kyono, Trent; Gilbert, Fiona J.; Schaar, Mihaela van der

doi:10.1016/j.jacr.2019.05.012

Cited by 68 publications

(43 citation statements)

References 18 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, the most common approach being investigated is the automated identification of normal cases that either do not need to be evaluated by radiologists at all, or that could be single read instead of double read (in the common double reading screening scenario in Europe) [ [36] , [37] , [38] , [39] ]. In this light, Rodriguez Ruiz et al., in another study with the same dataset mentioned earlier, evaluated the impact on the overall outcome when the cases with the lowest AI-generated probability-of-malignancy scores are pre-designated as normal and therefore not interpreted by radiologists.…”

Section: Options For Use As Stand-alonementioning

confidence: 99%

See 1 more Smart Citation

Stand-alone artificial intelligence - The future of breast cancer screening?

Sechopoulos

Mann

2020

The Breast

View full text Add to dashboard Cite

Although computers have had a role in interpretation of mammograms for at least two decades, their impact on performance has not lived up to expectations. However, in the last five years, the field of medical image analysis has undergone a revolution due to the introduction of deep learning convolutional neural networks – a form of artificial intelligence (AI). Because of their considerably higher performance compared to conventional computer aided detection methods, these AI algorithms have resulted in renewed interest in their potential for interpreting breast images in stand-alone mode. For this, first the actual capability of the algorithms, compared to breast radiologists, needs to be well understood. Although early studies have pointed to the comparable performance between AI systems and breast radiologists in interpreting mammograms, these comparisons have been performed in laboratory conditions with limited, enriched datasets. AI algorithms with performance comparable to breast radiologists could be used in a number of different ways, the most impactful being pre-selection, or triaging, of normal screening mammograms that would not need human interpretation. Initial studies evaluating this proposed use have shown very promising results, with the resulting accuracy of the complete screening process not being affected, but with a significant reduction in workload. There is a need to perform additional studies, especially prospective ones, with large screening data sets, to both gauge the actual stand-alone performance of these new algorithms, and the impact of the different implementation possibilities on screening programs.

show abstract

Section: Options For Use As Stand-alonementioning

confidence: 99%

“…Finally, Kyono et al. also developed an AI algorithm optimized for this purpose [ 39 ]. Using a portion of the TOMMY tomosynthesis trial dataset [ 28 ], the authors determined the proportion of non-cancer cases that would be correctly labelled as normal by their developed algorithm.…”

Section: Options For Use As Stand-alonementioning

confidence: 99%

Stand-alone artificial intelligence - The future of breast cancer screening?

Sechopoulos

Mann

2020

The Breast

View full text Add to dashboard Cite

show abstract

“…As a subset of ML, deep learning (DL) is based on artificial neural networks and is able to automatically extract hierarchical features of multiple source data to use them in different clinical applications, including imaging, volume contouring, and treatment planning [ 8 , 9 ]. AI and DL are progressively integrated in breast cancer diagnosis including imaging and pathology [ 10 ]. Data from multiple sources (mammography, ultrasound, CT, MRI, pathology, surgical reports, radiation therapy, follow-up imaging) are processed by bioinformatics technology to predict outcomes and to guide multidisciplinary therapeutic approaches, including radiation therapy (RT).…”

Section: Introductionmentioning

confidence: 99%

Winter is over: The use of Artificial Intelligence to individualise radiation therapy for breast cancer

et al. 2020

View full text Add to dashboard Cite

Artificial intelligence demonstrated its value for automated contouring of organs at risk and target volumes as well as for auto-planning of radiation dose distributions in terms of saving time, increasing consistency, and improving dose-volumes parameters. Future developments include incorporating dose/outcome data to optimise dose distributions with optimal coverage of the high-risk areas, while at the same time limiting doses to low-risk areas. An infinite gradient of volumes and doses to deliver spatially-adjusted radiation can be generated, allowing to avoid unnecessary radiation to organs at risk. Therefore, data about patient-, tumour-, and treatment-related factors have to be combined with dose distributions and outcome-containing databases.

show abstract

“…A convolutional neural network (CNN) proposed by researchers at the University of Toronto at the 2012 ImageNet Large Scale Visual Recognition Challenge (Hijazi, Kumar & Rowen, 2015) had significant impact on society when it achieved an approximately 10% improvement in error rate compared to previous methods. This technological development has made image classification widely known for its effectiveness, and its applications in the medical field are rapidly advancing (Zhou et al, 2017;Kyono, Gilbert & Van der Schaar, 2020;Poplin et al, 2018), e.g., classification of computed tomography images and mammographs, along with the prediction of cardiovascular risk from retinal fundus photographs.…”

Section: Introductionmentioning

confidence: 99%

Effects of data count and image scaling on Deep Learning training

Hirahara¹,

Takaya

Takahara

et al. 2020

PeerJ Computer Science

View full text Add to dashboard Cite

Background Deep learning using convolutional neural networks (CNN) has achieved significant results in various fields that use images. Deep learning can automatically extract features from data, and CNN extracts image features by convolution processing. We assumed that increasing the image size using interpolation methods would result in an effective feature extraction. To investigate how interpolation methods change as the number of data increases, we examined and compared the effectiveness of data augmentation by inversion or rotation with image augmentation by interpolation when the image data for training were small. Further, we clarified whether image augmentation by interpolation was useful for CNN training. To examine the usefulness of interpolation methods in medical images, we used a Gender01 data set, which is a sex classification data set, on chest radiographs. For comparison of image enlargement using an interpolation method with data augmentation by inversion and rotation, we examined the results of two- and four-fold enlargement using a Bilinear method. Results The average classification accuracy improved by expanding the image size using the interpolation method. The biggest improvement was noted when the number of training data was 100, and the average classification accuracy of the training model with the original data was 0.563. However, upon increasing the image size by four times using the interpolation method, the average classification accuracy significantly improved to 0.715. Compared with the data augmentation by inversion and rotation, the model trained using the Bilinear method showed an improvement in the average classification accuracy by 0.095 with 100 training data and 0.015 with 50,000 training data. Comparisons of the average classification accuracy of the chest X-ray images showed a stable and high-average classification accuracy using the interpolation method. Conclusion Training the CNN by increasing the image size using the interpolation method is a useful method. In the future, we aim to conduct additional verifications using various medical images to further clarify the reason why image size is important.

show abstract

Improving Workflow Efficiency for Mammography Using Machine Learning

Abstract: We know of no conflicts of interest associated with this publication, and there has been no significant financial support for this work that could have influenced its outcome.

Cited by 68 publications

References 18 publications

Stand-alone artificial intelligence - The future of breast cancer screening?

Stand-alone artificial intelligence - The future of breast cancer screening?

Winter is over: The use of Artificial Intelligence to individualise radiation therapy for breast cancer

Effects of data count and image scaling on Deep Learning training

Contact Info

Product

Resources

About