Effect of independent multiple reading of mammograms on detection performance

Karssemeijer, Nico; Otten, J.D.M.; Roelofs, A.A.J.; Woudenberg, Sander van; Hendriks, Jan H. C. L.

doi:10.1117/12.535225

Cited by 9 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When ensembling these models, the score of an image was the average score of the individual models. This approach has been motivated by a previous study on independent human readers, and it has proven reasonably effective, while simple and flexible 14 .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Detecting and classifying lesions in mammograms with Deep Learning

Ribli

Horváth

Unger

et al. 2018

Sci Rep

568

355

View full text Add to dashboard Cite

In the last two decades, Computer Aided Detection (CAD) systems were developed to help radiologists analyse screening mammograms, however benefits of current CAD technologies appear to be contradictory, therefore they should be improved to be ultimately considered useful. Since 2012, deep convolutional neural networks (CNN) have been a tremendous success in image recognition, reaching human performance. These methods have greatly surpassed the traditional approaches, which are similar to currently used CAD solutions. Deep CNN-s have the potential to revolutionize medical image analysis. We propose a CAD system based on one of the most successful object detection frameworks, Faster R-CNN. The system detects and classifies malignant or benign lesions on a mammogram without any human intervention. The proposed method sets the state of the art classification performance on the public INbreast database, AUC = 0.95. The approach described here has achieved 2nd place in the Digital Mammography DREAM Challenge with AUC = 0.85. When used as a detector, the system reaches high sensitivity with very few false positive marks per image on the INbreast dataset. Source code, the trained model and an OsiriX plugin are published online at https://github.com/riblidezso/frcnn_cad.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Double reading was found to improve the performance of mammographic evaluation and it had been implemented in many countries 13 . Multiple reading can further improve diagnostic performance up to more than 10 readers, proving that there is room for improvement in mammogram evaluation beyond double reading 14 .…”

Section: Screening Mammographymentioning

confidence: 99%

Detecting and classifying lesions in mammograms with Deep Learning

Ribli

Horváth

Unger

et al. 2018

Sci Rep

568

355

View full text Add to dashboard Cite

show abstract

“…De acuerdo con lo anterior, los sistemas CAD ofrecen una asistencia tecnológica sustancial al especialista, al dotar de mayor certeza su toma de decisiones, y a su vez esclarecer el diagnóstico de una enfermedad evitable, así como reducir la probabilidad de un falso diagnóstico positivo de cáncer, y por lo tanto sus implicaciones (Karssemeijer et al, 2004). El objetivo primordial de estos sistemas es el de reducir el esfuerzo requerido para realizar el diagnóstico y el de disminuir el número de falsos positivos que puedan presentarse en éste (Li et al, 2018;Tsochatzidis et al, 2017).…”

unclassified