Classifying tissue samples from measurements on cells with within-class tissue sample heterogeneity

Abstract

We consider here the problem of classifying a macro-level object based on measurements of embedded (micro-level) observations within each object, for example, classifying a patient based on measurements on a collection of a random number of their cells. Classification problems with this hierarchical, nested structure have not received the same statistical understanding as the general classification problem. Some heuristic approaches have been developed and a few authors have proposed formal statistical models. We focus on the problem where heterogeneity exists between the macro-level objects within a class. We propose a model-based statistical methodology that models the log-odds of the macro-level object belonging to a class using a latent-class variable model to account for this heterogeneity. The latent classes are estimated by clustering the macro-level object density estimates. We apply this method to the detection of patients with cervical neoplasia based on quantitative cytology measurements on cells in a Papanicolaou smear. Quantitative cytology is much cheaper and potentially can take less time than the current standard of care. The results show that the automated quantitative cytology using the proposed method is roughly equivalent to clinical cytopathology and shows significant improvement over a statistical model that does not account for the heterogeneity of the data.

Prediction using hierarchical data: Applications for automated detection of cervical cancer

“…The extension of the CLO 1 method assumes the existence of an unobserved latent variable U , and that the features are i.i.d. given the class and the latent variable . Thus, the log‐odds of having the disease given the feature vector is …”

“…Given the estimated latent classes, f ( x | u , Y ) is estimated for each latent class u and disease state Y using the kernel density estimate of the pooled cells for all patients in that cluster. More details are given in .…”

“…The cumulative log-odds (CLO) method assumes that given the disease state, the cellular measurements share an identical distribution and are independent of each other, modeled by the posterior log-odds of disease [22]. An extension of this method relaxes the assumption, allowing for heterogeneity of the distributions of the data within a disease state [23]. These methods are briefly described here.…”

Research on the Indices for Demonstrating Cell Conditions

“…The lack of indices for cellular conditions causes deficiencies in the explanation of the conditions even if cell pictures or data results exist [5,6].…”