Abstract
Advanced medical imaging algorithms (such as bone removal, vessel segmentation, or a lung nodule detection) can provide extremely valuable information to the radiologists, but they might sometimes be very time consuming. Being able to run the algorithms in advance can be a possible solution. However, we do not know which algorithm to run on a given dataset before it is actually used. It is possible to manually insert matching rules for preprocessing algorithms, but it requires high maintenance and does not work well in practice. This paper presents a dynamic machine learning solution for predicting which advanced visualization (AV) algorithm needs to be applied on a given series. The system gets a handful of free text DICOM tags as an input and builds a model in the clinical setting. It incorporates a Bag of Words (BOW) feature extractor and a Random Forest classifier. The approach was tested on two datasets from clinical sites which use different languages and varying scanner models. We show that even without feature extraction, sensitivity of above 90% can be reached on both of them. By using BOW feature extractor, precision and sensitivity can usually be further improved. Even on a noisy and highly unbalanced dataset, only around 100 samples were needed to reach sensitivity of above 80% and specificity of above 97%. We show how the solution can be part of a Smart Preprocessing mechanism in a viewing software. Using such a system will ultimately minimize the time to launch studies and improve radiologists reading time efficiency.
Similar content being viewed by others
References
Baeza-Yates R, Ribeiro-Neto B. Modern information retrieval, vol 463. New York: ACM Press ; 1999.
Bhargavan M, Kaye AH, Forman HP, Sunshine JH. Workload of radiologists in united states in 2006-2007 and trends since 1991-1992. Radiology 2009;252(2):458–467. doi:10.1148/radiol.2522081895.
Breiman L. Random forests. Mach Learn 2001;45(1):5–32. doi:10.1023/A:1010933404324.
Bui AAT, McNitt-Gray MF, Goldin JG, Cardenas AF, Aberle DR. Problem-oriented prefetching for an integrated clinical imaging workstation. J Am Med Inform Assn 2001;8(3):242–253. doi:10.1136/jamia.2001.0080242 10.1136/jamia.2001.0080242.
Criminisi A, Shotton J Eds. Decision Forests for Computer Vision and Medical Image Analysis. Springer Science & Business Media, 2013 10.1007/978-1-4471-4929-3.
Díaz-Uriart R, De Andres SA. Gene selection and classification of microarray data using random forest. BMC Bioinformatics 2006;7(1):1. doi:10.1186/1471-2105-7-3.
DICOM Homepage. Dicom homepage. http://medical.nema.org/. cited 2016 October 14, 2016.
Mabotuwana T, Qian Y: Determining scanned body part from dicom study descrip on for relevant prior study matching. MedInfo, 2013 pp 67–71.
Morioka CA, Valentino DJ, Duckwiler G, El-Saden S, Sinha U, Bui A, Kangarloo H. 2001. Disease specific intelligent pre-fetch and hanging protocol for diagnostic neuroradiology workstations.
Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Inform Process Manag 2009;45(4):427–437. doi:10.1016/j.ipm.2009.03.002.
Viana-Ferreira C, Ribeiro L, Matos S, Costa C. Pattern recognition for cache management in distributed medical imaging environments. IJCARS 2015;11(2):327–336. doi:10.1007/s11548-015-1272-4.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fadida-Specktor, B. Preprocessing Prediction of Advanced Algorithms for Medical Imaging. J Digit Imaging 31, 42–50 (2018). https://doi.org/10.1007/s10278-017-9999-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-017-9999-9