polito.it
Politecnico di Torino (logo)

Use of apriori information for anatomical segmentation of medical images

Emilio Ippoliti

Use of apriori information for anatomical segmentation of medical images.

Rel. Santa Di Cataldo, Edoardo Patti. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Biomedica, 2021

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (11MB) | Preview
Abstract:

In this thesis, we investigated how in medical image segmentation, apriori information about objects’ shape knowledge can be used to guide the lungs segmentation from chest X-ray images. We propose a deep convolutional neural network for lung segmentation, where shape information is represented by a statistical representation, based on principal components analysis of lung masks computed using the training dataset and described by their Signed Distance Functions. In this regard we provide a nonlinear extension, considering the expediency of KernelPCA and the related kernel functions. As a result, the proposed network learns to predict shapes instead of learning pixel-wise classification. The segmentation method named Shape Predictor Network (SP-Net) was applied to chest X-ray images of Covid-19 positive patients where shape could be of utmost importance. Results showed that SP-Net could constrain the predicted shape to resemble a pulmonary-like structure in those cases where the pixel-wise segmentation methods failed in the presence of a significant image artifact. Finally, we compared SP-Net with state-of-the-art methods. U-net, a convolutional neural network particularly effective for medical image segmentation.

Relatori: Santa Di Cataldo, Edoardo Patti
Anno accademico: 2020/21
Tipo di pubblicazione: Elettronica
Numero di pagine: 194
Soggetti:
Corso di laurea: Corso di laurea magistrale in Ingegneria Biomedica
Classe di laurea: Nuovo ordinamento > Laurea magistrale > LM-21 - INGEGNERIA BIOMEDICA
Aziende collaboratrici: Bracco Imaging Spa
URI: http://webthesis.biblio.polito.it/id/eprint/19636
Modifica (riservato agli operatori) Modifica (riservato agli operatori)