Theory of sampling and its application in tissue based diagnosis

Abstract

Background: A general theory of sampling and its application in tissue based diagnosis is presented. Sampling is defined as extraction of information from certain limited spaces and its transformation into a statement or measure that is valid for the entire (reference) space. The procedure should be reproducible in time and space, i.e. give the same results when applied under similar circumstances. Sampling includes two different aspects, the procedure of sample selection and the efficiency of its performance. The practical performance of sample selection focuses on search for localization of specific compartments within the basic space, and search for presence of specific compartments.

A model for predicting pathologist's velocity profiles when navigating virtual slides

“…It is worthy to point out here that our model was focused on the scanning phase of the microscopical exploration because the magnification changes take much less time in terms of navigation (Krupinski et al, 2006). Moreover, these predictions could be included into the whole strategy by using smart sampling procedures (Kayser et al, 2009).…”

“…In addition, such observation path should follow optimal sampling strategies (Kayser et al, 2009) which improve the diagnosis times, that is to say, a minimal number of RoIs would drive the navi-gation. In that scenario, a pathologist would achieve a diagnosis using this technology and spending a minimal time, so the pathologist workflow could be highly accelerated basically because it would be possible to prefetch the whole examination path at the very navigation beginning and little additional information would be needed to accomplish such diagnosis.…”

Micro‐structural tissue analysis for automatic histopathological image annotation

“…These systems have supported diagnosis by generating statements about specific microscopic field of views that contain the most significant information about an organ or tissue section. Traditionally, this information corresponds exclusively to ''the pathological content,'' but the examined tissue may also contain normal structures, whose features are also relevant to final diagnosis (Kayser et al, 2009). The fact is that the diagnosis process is determined not only by what is abnormal, but also by what is normal and the particular arrangement of these components.…”

Sistemas de microscopía virtual: análisis y perspectivas

“…Las navegaciones deberían realizarse usando un número mínimo de ventanas de interés, una tarea que puede ser el resultado de la determinación automática de regiones de interés (50), usando mapas de probabilidad asociados a la imagen y que, además, se basen en estrategias óptimas de muestreo (51). En estas circunstancias, un patólogo debería lograr un diagnóstico usando sistemas de microscopía virtual en un tiempo mínimo, de manera que el volumen de trabajo del patólogo pueda ser acelerado, tras anticipar y precargar el camino de observación al inicio de la navegación, de tal manera que se necesite muy poca información adicional para hacer el diagnóstico.…”