Many methods have been proposed for tissue segmentation in brain MRI scans. The multitude of methods proposed complicates the choice of one method above others. We have therefore established the MRBrainS online evaluation framework for evaluating (semi)automatic algorithms that segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) on 3T brain MRI scans of elderly subjects (65–80 y). Participants apply their algorithms to the provided data, after which their results are evaluated and ranked. Full manual segmentations of GM, WM, and CSF are available for all scans and used as the reference standard. Five datasets are provided for training and fifteen for testing. The evaluated methods are ranked based on their overall performance to segment GM, WM, and CSF and evaluated using three evaluation metrics (Dice, H95, and AVD) and the results are published on the MRBrainS13 website. We present the results of eleven segmentation algorithms that participated in the MRBrainS13 challenge workshop at MICCAI, where the framework was launched, and three commonly used freeware packages: FreeSurfer, FSL, and SPM. The MRBrainS evaluation framework provides an objective and direct comparison of all evaluated algorithms and can aid in selecting the best performing method for the segmentation goal at hand.

Hyperthermia therapy (40–44 °C) is a promising option to increase efficacy of radiotherapy/chemotherapy for brain tumours, in particular paediatric brain tumours. The Chalmers Hyperthermia Helmet is developed for this purpose. Hyperthermia treatment planning is required for treatment optimisation, but current planning systems do not involve a physically correct model of cerebrospinal fluid (CSF). This study investigates the necessity of fluid modelling for treatment planning. We made treatments plans using the Helmet for both pre-operative and post-operative cases, comparing temperature distributions predicted with three CSF models: a convective “fluid” model, a non-convective “solid” CSF model, and CSF models with increased effective thermal conductivity (“high-k”). Treatment plans were evaluated by T₉₀, T₅₀ and T₁₀ target temperatures and treatment-limiting hot spots. Adequate heating is possible with the helmet. In the pre-operative case, treatment plan quality was comparable for all three models. In the post-operative case, the high-k models were more accurate than the solid model. Predictions to within ±1 °C were obtained by a 10–20-fold increased effective thermal conductivity. Accurate modelling of the temperature in CSF requires fluid dynamics, but modelling CSF as a solid with enhanced effective thermal conductivity might be a practical alternative for a convective fluid model for many applications.

A breast phantom developed at the Supelec Institute was interrogated to study its suitability for microwave tomography measurements. A microwave measurement system based on 16 monopole antennas and a vector network analyzer was used to study how the S-parameters are influenced by insertion of the phantom. The phantom is a 3D-printed structure consisting of plastic shells that can be filled with tissue mimicking liquids. The phantom was filled with different liquids and tested with the measurement system to determine whether the plastic has any effects on the recovered images or not. Measurements of the phantom when it is filled with the same liquid as the surrounding coupling medium are of particular interest. In this case, the phantom plastic has a substantial effects on the measurements which ultimately detracts from the desired images.

Early, preferably prehospital, detection of intracranial bleeding after trauma or stroke would dramatically improve the acute care of these large patient groups. In this paper, we use simulated microwave transmission data to investigate the performance of a machine learning classification algorithm based on subspace distances for the detection of intracranial bleeding. A computational model, consisting of realistic human head models of patients with bleeding, as well as healthy subjects, was inserted in an antenna array model. The Finite-Difference Time-Domain (FDTD) method was then used to generate simulated transmission coefficients between all possible combinations of antenna pairs. These transmission data were used both to train and evaluate the performance of the classification algorithm and to investigate its ability to distinguish patients with versus without intracranial bleeding. We studied how classification results were affected by the number of healthy subjects and patients used to train the algorithm, and in particular, we were interested in investigating how many samples were needed in the training dataset to obtain classification results better than chance. Our results indicated that at least 200 subjects, i.e., 100 each of the healthy subjects and bleeding patients, were needed to obtain classification results consistently better than chance (p < 0.05 using Student’s t-test). The results also showed that classification results improved with the number of subjects in the training data. With a sample size that approached 1000 subjects, classifications results characterized as area under the receiver operating curve (AUC) approached 1.0, indicating very high sensitivity and specificity.