Improving labeling efficiency in automatic quality control of MRSI data.

Da Silva Mendes Pedrosa, Nuno Miguel; McKinley, Richard; Wiest, Roland; Slotboom, Johannes (2017). Improving labeling efficiency in automatic quality control of MRSI data. Magnetic resonance in medicine, 78(6), pp. 2399-2405. Wiley-Liss 10.1002/mrm.26618

[img] Text
Barros_et_al-2017-Magnetic_Resonance_in_Medicine.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (816kB) | Request a copy

PURPOSE To improve the efficiency of the labeling task in automatic quality control of MR spectroscopy imaging data. METHODS 28'432 short and long echo time (TE) spectra (1.5 tesla; point resolved spectroscopy (PRESS); repetition time (TR)= 1,500 ms) from 18 different brain tumor patients were labeled by two experts as either accept or reject, depending on their quality. For each spectrum, 47 signal features were extracted. The data was then used to run several simulations and test an active learning approach using uncertainty sampling. The performance of the classifiers was evaluated as a function of the number of patients in the training set, number of spectra in the training set, and a parameter α used to control the level of classification uncertainty required for a new spectrum to be selected for labeling. RESULTS The results showed that the proposed strategy allows reductions of up to 72.97% for short TE and 62.09% for long TE in the amount of data that needs to be labeled, without significant impact in classification accuracy. Further reductions are possible with significant but minimal impact in performance. CONCLUSION Active learning using uncertainty sampling is an effective way to increase the labeling efficiency for training automatic quality control classifiers. Magn Reson Med, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

Item Type:

Journal Article (Original Article)


04 Faculty of Medicine > Department of Radiology, Neuroradiology and Nuclear Medicine (DRNN) > Institute of Diagnostic and Interventional Neuroradiology

UniBE Contributor:

Da Silva Mendes Pedrosa, Nuno Miguel; McKinley, Richard; Wiest, Roland and Slotboom, Johannes


600 Technology > 610 Medicine & health








Martin Zbinden

Date Deposited:

28 Jul 2017 08:46

Last Modified:

15 Nov 2017 01:30

Publisher DOI:


PubMed ID:


Uncontrolled Keywords:

MRSI; active learning; artifact detection; labeling efficiency; machine learning; quality control




Actions (login required)

Edit item Edit item
Provide Feedback