Back to overview Show all

Original article (peer-reviewed)

Journal Magnetic Resonance in Medicine
Title of proceedings Magnetic Resonance in Medicine


Purpose: To improve the efficiency of the labelling task in automatic quality control of MRSI data. Methods: 28’432 short and long-TE spectra (1.5T, PRESS, TR=1500ms), from 18 different brain-tumour patients, were labelled by two experts in 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 labelling. 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 labelled, 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 of increasing the labelling efficiency for training automatic quality control classifiers.