DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI

Abstract

Lobar cerebral microbleeds (CMBs) and localized non-hemorrhage iron deposits in the basal ganglia have been associated with brain aging, vascular disease and neurodegenerative disorders. Particularly, CMBs are small lesions and require multiple neuroimaging modalities for accurate detection. Quantitative susceptibility mapping (QSM) derived from in vivo magnetic resonance imaging (MRI) is necessary to differentiate between iron content and mineralization. We set out to develop a deep learning-based segmentation method suitable for segmenting both CMBs and iron deposits. We included a convenience sample of 24 participants from the MESA cohort and used T2-weighted images, susceptibility weighted imaging (SWI), and QSM to segment the two types of lesions. We developed a protocol for simultaneous manual annotation of CMBs and non-hemorrhage iron deposits in the basal ganglia. This manual annotation was then used to train a deep convolution neural network (CNN). Specifically, we adapted the U-Net model with a higher number of resolution layers to be able to detect small lesions such as CMBs from standard resolution MRI. We tested different combinations of the three modalities to determine the most informative data sources for the detection tasks. In the detection of CMBs using single class and multiclass models, we achieved an average sensitivity and precision of between 0.84-0.88 and 0.40-0.59, respectively. The same framework detected non-hemorrhage iron deposits with an average sensitivity and precision of about 0.75-0.81 and 0.62-0.75, respectively. Our results showed that deep learning could automate the detection of small vessel disease lesions and including multimodal MR data (particularly QSM) can improve the detection of CMB and non-hemorrhage iron deposits with sensitivity and precision that is compatible with use in large-scale research studies.

Figure 1

(A) Segmentations of CMBs by a model trained with SWI, QSM and T2w. (Top) An example of the correct segmentation of a small microbleed (red arrow). (Bottom) Magnified view of microbleed with segmentation mask (single red pixel). (B) An example of QSM being used to distinguish iron deposits from calcifications in the basal ganglia. (Top row) The SWI for TE = 7.5 ms, SWI for TE = 22.5 ms and QSM of the basal ganglia. The yellow arrow points to hypo-intense voxels which are likely calcifications and the green arrow points to basal ganglia iron deposits. (Bottom row) The segmentation mask (green labels) of the iron deposits. For both (A, B), the segmentations were generated by the multiclass model trained with SWI, QSM and T2w.

Figure 2

Joint scatterplots of the sensitivity vs precision of all single class experiments predicting CMBs and non-hemorrhage iron deposits. (Left) all CMB only experiments and (Right) all iron deposits only experiments. In each subplot, the round points indicate the individual participants’ sensitivity and precision evaluated with leave-one-out cross-validation, and the X indicates the mean sensitivity and precision. The legend at the upper left corner of each subplot shows the coordinates of X. In each subplot, histograms of the sensitivity and precision are displayed along the upper and right axes.

Figure 3

Joint scatterplots of the sensitivity vs precision of all multiclass experiments predicting CMBs and non-hemorrhage iron deposits. (Left) all evaluations for CMBs and (Right) all evaluations for iron deposits. In each subplot, the round points indicate the individual participants’ sensitivity and precision evaluated with leave-one-out cross-validation, and the X indicates the mean sensitivity and precision. The legend at the upper left corner of each subplot shows the coordinates of X. In each subplot, histograms of the sensitivity and precision are displayed along the upper and right axes.

Figure 4

This figure shows examples of cerebral microbleeds and basal ganglia iron deposition in SWI for TE = 7.5 ms (left column), SWI for TE = 22.5 ms (middle left column), QSM (middle right column) and T2w (right column). (A, C) Show the lesions in two different brains, and (B, D) show the corresponding human expert labeling of the CMBs (red) and iron deposits (green).

Figure 5

Overview of the cross-validation process (one-fold) that is repeated n times. In each fold, the model that was used to predict the test participant was trained on the remaining n − 1 samples in order to avoid data leakage. Within the training stage, 25% of the n − 1 participants were used as the validation set. The model with the highest validation accuracy was chosen to predict the left-out participant sample.

Figure 6

U-Net architecture using padded convolutions for both single class and multiclass predictions.