A machine learning approach to intestinal motility assessment with capsule endoscopy

Tesis doctoral de Fernando Vilariño Freire

Intestinal motility assessment with video capsule endoscopy arises as a novel and challenging clinical fieldwork. This technique is based on the analysis of the patterns of intestinal contractions obtained by labelling all the motility events present in a video provided by a capsule with a wireless micro-camera, which is ingested by the patient. However, the visual analysis of these video sequences presents several important drawbacks, mainly related to both the large amount of time needed for the visualization process, and the low prevalence of intestinal contractions in video. in this work we propose a machine learning system to automatically detect the intestinal contractions in video capsule endoscopy, driving a very useful but not feasible clinical routine into a feasible clinical procedure. Our proposal is divided into two different parts: the first part tackles the problem of the automatic detection of phasic contractions in capsule endoscopy videos. Phasic contractions are dynamic events spanning about 4-5 seconds, which show visual patterns with a high variability. our proposal is based on a sequential design which involves the analysis of textural, color and blob features with powerful classifiers such as svm. This approach appears to cope with two basic aims: the reduction of the imbalance rate of the data set, and the modular construction of the system, which adds the capability of including domain knowledge as new stages in the cascade. The second part of the current work tackles the problem of the automatic detection of tonic contractions. Tonic contractions manifest in capsule endoscopy as a sustained pattern of the folds and wrinkles of the intestine, which may be prolonged for an undetermined span of time. Our proposal is based on the analysis of the wrinkle patterns, presenting a comparative study of diverse features and classification methods, and providing a set of appropriate descriptors for their characteriza

 

Datos académicos de la tesis doctoral «A machine learning approach to intestinal motility assessment with capsule endoscopy«

  • Título de la tesis:  A machine learning approach to intestinal motility assessment with capsule endoscopy
  • Autor:  Fernando Vilariño Freire
  • Universidad:  Autónoma de barcelona
  • Fecha de lectura de la tesis:  12/06/2006

 

Dirección y tribunal

  • Director de la tesis
    • Petia Radeva
  • Tribunal
    • Presidente del tribunal: Juan jose Villanueva pipaón
    • Manuel González penedo (vocal)
    • Fernando Azpiroz vidaur (vocal)
    • daniel Rueckert (vocal)

 

Deja un comentario

Tu dirección de correo electrónico no será publicada. Los campos obligatorios están marcados con *

Scroll al inicio