CT Radiomics for Hepatocellular  Carcinoma Recurrence Risk  Prediction Aided by Deep  Learning-Based Segmentation and Detection Methods

Sousa Sotto Mayor, Teresa

http://hdl.handle.net/10362/182262

Utilize este identificador para referenciar este registo.

Nome:	Descrição:	Tamanho:	Formato:
MCCBi_Tese_Teresa_Sotto_Mayor_Final.pdf		15.08 MB	Adobe PDF	Ver/Abrir

Contacte-nos

Autores

Sousa Sotto Mayor, Teresa

Orientador(es)

Papanikolaou, Nickolas

Soares, Cláudia

Resumo(s)

"Liver cancer is the third leading cause of worldwide cancer-related deaths. Hepatocellular carcinoma (HCC) is the most common liver cancer, with recurrence rates reaching up to 70%. The field of radiomics, which consists of extracting quantitative features from a region of interest (ROI) of a medical image, has been shown to preoperatively predict recurrence risk in HCC patients. However, most studies neglect the time and labour required to manually segment the ROI and fail to use a multi-institutional dataset to comprehensively assess the utility of radiomics-based models across a variety of computed tomography (CT) scanner models.(...)"

Palavras-chave

Hepatocellular carcinoma recurrence risk radiomics lesion segmentation deep learning

URI

http://hdl.handle.net/10362/182262

Editora

Instituto de Tecnologia Química e Biológica António Xavier. Universidade NOVA de Lisboa

Coleções

ITQB: LA - Master Dissertations

Licença CC

cclicense-by

Ver registo completo