Assessment of U-Net in the segmentation of short tracts: transferring to clinical MRI routine

• Ano de defesa: 2023
• Autor(a) principal: Konell, Hohana Gabriela
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Biblioteca Digitais de Teses e Dissertações da USP
• Palavras-chave em Português: Aprendizado profundo; Deep learning; Diffusion weighted images; Imagens ponderadas em difusão; Segmentação da substância branca; Short tracts; Tractografia; Tractography; Tratos de curta extensão; White matter segmentation
• Link de acesso: https://www.teses.usp.br/teses/disponiveis/59/59135/tde-02012024-090035/

Accurately studying structural connectivity requires precise tract segmentation strategies. The U-Net network has been widely recognized for its exceptional capacity in image segmentation tasks. It has demonstrated remarkable results in segmenting large tracts using high-quality diffusion-weighted imaging (DWI) data. However, short tracts, which are associated with various neurological diseases, pose specific challenges, particularly when considering the DWI data acquisition within clinical settings. The objective of this work was to evaluate the capability of the U-Net network in segmenting short tracts using DWI data acquired in different experimental conditions. To accomplish this, we conducted three different types of training experiments with a total of 350 healthy subjects and 11 white matter tracts, including anterior, posterior, and hippocampal commissure, fornix, and uncinated fasciculus. In the first experiment, the model was exclusively trained using high-quality data from the Human Connectome Project (HCP) dataset. The second experiment focused on images of healthy subjects acquired from a local hospital dataset, representing a typical clinical routine acquisition. In the third experiment, a hybrid training approach was employed, combining images from the HCP and local hospital datasets. Finally, the best model was also tested in unseen DWIs of 10 epilepsy patients of the local hospital and 10 subjects acquired on a scanner from another company. The outcomes of the third experiment demonstrated a notable enhancement in performance when contrasted with the preceding trials. Specifically, the short tracts within the local hospital dataset achieved dice scores ranging between 0.60 and 0.75. Similar intervals were obtained with HCP data in the first experiment and a substantial improvement compared to the scores of 0.37 and 0.50 obtained with the local hospital dataset at the same experiment. This improvement persisted when the method was applied to diverse scenarios, including different scanner acquisitions and epilepsy patients. This outcome strongly indicates that the fusion of datasets from various sources, coupled with resolution standardization, significantly fortifies the neural network\'s capacity to generalize predictions across a spectrum of datasets. It\'s crucial, however, to recognize that the performance of short tract segmentation is intricately linked to the composition of the training, validation, and testing data. Moreover, the segmentation of shorter and intricately curved tracts introduces added complexities due to their intricate structural nature. Although this approach has shown promising results, caution is essential when extrapolating its application to datasets acquired under distinct experimental conditions, even when dealing with higher-quality data or analyzing long or short tracts.