Resampling-based Markovian modeling for automated cancer diagnosis
Demir, Çiğdem Gündüz
MetadataShow full item record
Please cite this item using this persistent URLhttp://hdl.handle.net/11693/15738
Correct diagnosis and grading of cancer is very crucial for planning an effective treatment. However, cancer diagnosis on biopsy images involves visual interpretation of a pathologist, which is highly subjective. This subjectivity may, however, lead to selecting suboptimal treatment plans. In order to circumvent this problem, it has been proposed to use automatic diagnosis and grading systems that help decrease the subjectivity levels by providing quantitative measures. However, one major challenge for designing these systems is the existence of high variance observed in the biopsy images due to the nature of biopsies. Thus, for successful classifications of unseen images, these systems should be trained with a large number of labeled images. However, most of the training sets in this domain have limited size of labeled data since it is quite difficult to collect and label histopathological images. In this thesis, we successfully address this issue by presenting a new resampling framework. This framework relies on increasing the generalization capacity of a classifier by augmenting the size and variation in the training set. To this end, we generate multiple sequences from an image, each of which corresponds to a perturbed sample of the image. Each perturbed sample characterizes different parts of the image, and hence, they are slightly different from each other. The use of these perturbed samples for representing the image increases the size and variability of the training set. These samples are modeled with Markov processes which are used to classify unseen image. Working with histopathological tissue images, our experiments demonstrate that the proposed framework is more effective for both larger and smaller training sets compared against other approaches. Additionally, they show that the use of perturbed samples is effective in a voting scheme which boosts the performance of the classifier.