RESUMEN
The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consuming, any real world application requires some form of automation. Several approaches exist for automated vessel segmentation, but judging their relative merits is difficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20 CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentation algorithms from both academia and industry. Twenty algorithms participated in the VESSEL12 challenge, held at International Symposium on Biomedical Imaging (ISBI) 2012. All results have been published at the VESSEL12 website http://vessel12.grand-challenge.org. The challenge remains ongoing and open to new participants. Our three contributions are: (1) an annotated reference dataset available online for evaluation of new algorithms; (2) a quantitative scoring system for objective comparison of algorithms; and (3) performance analysis of the strengths and weaknesses of the various vessel segmentation methods in the presence of various lung diseases.
Asunto(s)
Algoritmos , Pulmón/irrigación sanguínea , Pulmón/diagnóstico por imagen , Interpretación de Imagen Radiográfica Asistida por Computador/métodos , Tomografía Computarizada por Rayos X/métodos , Medios de Contraste , Humanos , Países Bajos , Reconocimiento de Normas Patrones Automatizadas , Sensibilidad y Especificidad , EspañaRESUMEN
BACKGROUND: End-expiratory lung volume measurement by the nitrogen washin-washout technique (EELVWI-WO) may help titrating positive end-expiratory pressure (PEEP) during acute respiratory distress syndrome (ARDS). Validation of this technique has been previously performed using computed tomography (EELVCT), but at mild PEEP levels, and relatively low fraction of inspired oxygen (FiO2), which may have insufficiently challenged the validity of this technique. The aims of this study were (1) to evaluate the reliability of EELVWI-WO measurements at different PEEP and V T during experimental ARDS and (2) to evaluate trending ability of EELVWI-WO to detect EELV changes over time. METHODS: ARDS was induced in 14 piglets by saline lavage. Optimal PEEP was selected during a decremental PEEP trial, based on best compliance, best EELVWI-WO, or a PEEP-FiO2 table. Eight V T (4 to 20 mL · kg(-1)) were finally applied at optimal PEEP. EELVWI-WO and EELVCT were determined after ARDS onset, at variable PEEP and V T. RESULTS: EELVWI-WO underestimated EELVCT with a non-constant linear bias, as it decreased with increasing EELV. Limits of agreement for bias were ±398 mL. Bias between methods was greater at high PEEP, and further increased when high PEEP was combined with low V T. Concordance rate of EELV changes between consecutive measurements was fair (79%). Diagnostic accuracy was good for detection of absolute EELV changes above 200 mL (AUC = 0.79). CONCLUSIONS: The reliability of the WI-WO technique is critically dependent on ventilatory settings, but sufficient to accurately detect EELV change greater than 200 mL.
RESUMEN
This work deals with the segmentation of the arterial lumen in cross-sections of CT angiography (CTA) images, by means of active contours. Within the context of the fast-marching method, a new speed-control function is proposed in order to cope with strongly variable contrasts along the perimeter of the contour. This function was devised to guarantee the existence of a time T at which the fast-marching front fits the actual boundary of the vessel lumen, despite calcifications and other neighboring structures. Instead of using the magnitude of the image intensity gradient alone, this function includes exponential factors that strongly decrease the propagation speed when the front moves beyond the local maxima of the gradient magnitude and beyond the range of luminal intensities in CTA images. The propagation is stopped when the the growth of the area A encompassed by the front becomes very slow, which is characterized by a large value of dT/dA . The segmentation was evaluated in 65 cross-sections of carotid arteries from 13 different patients, by comparison with contours traced by a radiologist. The mean sensitivity was 0.849 and the mean positive predictive value was 0.797.