Advancing Segmentation of Intracranial Structures in Brain Imaging

Thumbnail Image
Journal Title
Journal ISSN
Volume Title
School of Science | Doctoral thesis (article-based) | Defence date: 2024-03-27
Degree programme
104 + app. 40
Aalto University publication series DOCTORAL THESES, 57/2024
There are several challenges and crossroads that a researcher encounters and must navigate while conducting studies in the field of anatomical neuroimaging. These include 1) shortage of large datasets for algorithm testing and the limitations associated with small datasets, 2) finding strategies to make established algorithms more efficient, and 3) development of algorithms robust enough to generalize across different hardware and different acquisition settings. This thesis seeks to address these challenges. It explores the impact of limited datasets on volumetric analyses from Magnetic Resonance Images, introduces innovative approaches for locating intracranial structures and pathologies from Magnetic Resonance (MR) and Computed Tomography (CT) images, and examines how data selection influences analyses and algorithm performance in diverse scenarios. One aspect of the present research quantifies and proposes strategies to mitigate the influence of biases, confounders, and random variations that frequently arise in brain volumetric analyses with limited datasets. The findings emphasise the effectiveness of specific metrics in accurately distinguishing between healthy and non-healthy subjects even in the presence of bias, confounders, or random variation. This thesis also introduces a novel method for segmenting the brain from MR images. This method combines segmentation fusion with a marker-controlled watershed transform and utilizes predictions from established segmentation methods as input. Results demonstrate superior performance compared to the conventional segmentation techniques and other meta-algorithms. In the field of machine learning, the research recommends effective approaches for creating training data with the aim of segmenting intracranial blood from CT images. A neural network developed for this purpose demonstrates potential in segmenting intracranial blood from head CT images while preserving generalizability. In conclusion, the challenges posed by limited datasets require special considerations as they impact the development of both machine learning and classical image processing methods for segmenting structures within the head. While classical image processing methods may see reduced usage on their own, they will likely be increasingly integrated with machine learning approaches.
Supervising professor
Hämäläinen, Matti, Prof., Aalto University, Department of Neuroscience and Biomedical Engineering, Finland
Thesis advisor
Ilmoniemi, Risto, Prof., Aalto University, Department of Neuroscience and Biomedical Engineering, Finland
magnetic resonance imaging, computed tomography, segmentation, deep learning, intracranial haemorrhage, anatomical neuroimaging
Other note
  • [Publication 1]: Thanellas, Antonios; Peura, Heikki; Lavinto, Mikko; Ruokola, Tomi; Vieli, Moira; Staartjes, Victor; Winklhofer, Sebastian; Serra, Karlo;Regli, Luca, Korja, Miikka. Development and external validation of a deep learning algorithm to identify and localize subarachnoid hemorrhage on CT scans. In: Neurology, 2023.
    DOI: 10.1212/WNL.0000000000201710 View at publisher
  • [Publication 2]: Thanellas, Antonios; Peura, Heikki; Wennervirta, Jenni; Korja, Miikka. 2021. Foundations of brain image segmentation: Pearls and pitfalls in segmenting intracranial blood on computed tomography images. In: Springer Book Series Acta Neurochirurgica Supplements, 2022.
    DOI: 10.1007/978-3-030-85292-4_19 View at publisher
  • [Publication 3]: Thanellas, Antonios; Pollari, Mika; Alhonnoro, Tuomas; Lilja Mikko. 2016. Brain extraction from MR images using a combination of segmentation fusion and marker-controlled watershed transform. In: Nuclear Science Symposium, Medical Imaging Conference and Room-Temperature Semiconductor Detector Workshop (NSS/MIC/RTSD), Strasbourg 29 Oct.–6 Nov. 2016. IEEE. Pages 1–4. ISBN electronic 978-1-5090-1642-6.
    DOI: 10.1109/NSSMIC.2016.8069542 View at publisher
  • [Publication 4]: Thanellas, Antonios; Pollari, Mika. 2010 Sensitivity of volumetric brain analysis to systematic and random errors. In: 23rd International Symposium on Computer-Based Medical Systems (CBMS), Perth, Australia 12–15 Oct. 2010. IEEE. Pages 238–242. ISBN electronic 978-1-4244-9168-1.
    DOI: 10.1109/CBMS.2010.6042648 View at publisher