Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Capítulo o parte de un libro (BookPart)

Image-Based Bronchial Anatomy Codification for Biopsy Guiding in Video Bronchoscopy

  • Ramírez, Esmitt|||0000-0001-7573-631X
  • Sánchez Ramos, Carles|||0000-0003-3435-9882
  • Borràs, Agnés|||0000-0002-7747-9924
  • Diez-Ferrer, Marta|||0000-0002-0207-8157
  • Rosell Gratacos, Antoni|||0000-0003-0877-7191
  • Gil, Debora|||0000-0002-2770-4767
Bronchoscopy examinations allow biopsy of pulmonary nodules with minimum risk for the patient. Even for experienced bronchoscopists, it is difficult to guide the bronchoscope to most distal lesions and obtain an accurate diagnosis. This paper presents an image-based codification of the bronchial anatomy for bronchoscopy biopsy guiding. The 3D anatomy of each patient is codified as a binary tree with nodes representing bronchial levels and edges labeled using their position on images projecting the 3D anatomy from a set of branching points. The paths from the root to leaves provide a codification of navigation routes with spatially consistent labels according to the anatomy observes in video bronchoscopy explorations. We evaluate our labeling approach as a guiding system in terms of the number of bronchial levels correctly codified, also in the number of labels-based instructions correctly supplied, using generalized mixed models and computer-generated data. Results obtained for three independent observers prove the consistency and reproducibility of our guiding system. We trust that our codification based on viewer's projection might be used as a foundation for the navigation process in Virtual Bronchoscopy systems.
Dipòsit Digital de Documents de la UAB
Publicación Capítulo o parte de un libro (BookPart)

Localizing Pulmonary Lesions Using Fuzzy Deep Learning

  • Ramírez, Esmitt|||0000-0001-7573-631X
  • Sánchez Ramos, Carles|||0000-0003-3435-9882
  • Gil, Debora|||0000-0002-2770-4767
The usage of medical images is part of the clinical daily in several healthcare centers around the world. Particularly, Computer Tomography (CT) images are an important key in the early detection of suspicious lung lesions. The CT image exploration allows the detection of lung lesions before any invasive procedure (e.g. bronchoscopy, biopsy). The effective localization of lesions is performed using different image processing and computer vision techniques. Lately, the usage of deep learning models into medical imaging from detection to prediction shown that is a powerful tool for Computeraided software. In this paper, we present an approach to localize pulmonary lung lesion using fuzzy deep learning. Our approach uses a simple convolutional neural network based using the LIDC-IDRI dataset. Each image is divided into patches associated a probability vector (fuzzy) according their belonging to anatomical structures on a CT. We showcase our approach as part of a full CAD system to exploration, planning, guiding and detection of pulmonary lesions.