Histogram of hosoya index (HoH) features for quantitative histomorphometry

摘要

Methods, apparatus, and other embodiments associated with classifying a region of cancerous tissue using a Histogram of Hosoya are described. One example apparatus includes a set of logics that acquires an image of a region of tissue demonstrating cancerous pathology, constructs a cell graph of the region of tissue, decomposes the cell graph into a set of subgraphs, computes a Hosoya Index for a subgraph, constructs a Histogram of Hosoya for the image based on the distribution of the subgraphs, and classifies the image based on the Histogram of Hosoya. Embodiments of example apparatus may generate and display the Histogram of Hosoya for the image. A prognosis for the patient may be provided based on the distribution of the histogram.

主权项

1. A non-transitory computer-readable storage medium storing computer executable instructions that when executed by a computer control the computer to perform a method for classifying a region of cancerous tissue, the method comprising:
accessing an image of a region of cancerous tissue; constructing a cell graph (CG) of the image, where a node of the CG includes a cluster of nuclei, and where the probability that a first node in the CG will be connected to a second node in the CG is based on a probabilistic decaying function of the Euclidean distance between the first node and the second node; decomposing the CG into a set of disconnected subgraphs I, where I={G1, G2, . . . Gm}; computing a Hosoya Index Z(Gm) for a subgraph Gm, where Z(Gm)≧0, and where Z(Gm) is defined as the number of subsets of a set of edges E(Gm) in which no two edges in Gm are adjacent; upon determining that Z(Gm) is within a range, assigning Z(Gm) to a bin associated with the range; constructing a histogram of Z(Gm); and controlling a computer aided diagnosis (CADx) system to classify the image based, at least in part, on the histogram.