Nuclear Morphology Optimized Deep Hybrid Learning (NUMODRIL): A novel architecture for accurate diagnosis/prognosis of Ovarian Cancer

Abstract

AbstractNuclear morphological features are potent determining factors for clinical diagnostic approaches adopted by pathologists to analyse the malignant potential of cancer cells. Considering the structural alteration of nucleus in cancer cells, various groups have developed machine learning techniques based on variation in nuclear morphometric information like nuclear shape, size, nucleus-cytoplasm ratio and various non-parametric methods like deep learning have also been tested for analysing immunohistochemistry images of tissue samples for diagnosing various cancers. Our aim is to study the morphometric distribution of nuclear lamin proteins as a specific parameter in ovarian cancer tissues. Besides being the principal mechanical component of the nucleus, lamins also present a platform for binding of proteins and chromatin thereby serving a wide range of nuclear functions like maintenance of genome stability, chromatin regulation. Altered expression of lamins in different subtypes of cancer is now evident from data across the world. It has already been elucidated that in ovarian cancer, extent of alteration in nuclear shape and morphology can determine degree of genetic changes and thus can be utilized to predict the outcome of low to high form of serous carcinoma. In this work, we have performed exhaustive imaging of ovarian cancer versus normal tissue and introduced a novel Deep Hybrid Learning approach on the basis of the distribution of lamin proteins. Although developed with ovarian cancer datasets in view, this architecture would be of immense importance in accurate and fast diagnosis and prognosis of all types of cancer associated with lamin induced morphological changes and would perform across small/medium to large datasets with equal efficiency.Significance StatementWe have developed a novel Deep Hybrid Learning approach based on nuclear morphology to classify normal and ovarian cancer tissues with highest possible accuracy and speed. Ovarian cancer cells can be easily distinguished from their enlarged nuclear morphology as is evident from lamin A & B distribution pattern. This is the first report to invoke specific nuclear markers like lamin A & B instead of classical haematoxylin-eosin staining in an effort to build parametric datasets. Our approach has been shown to outperform the existing deep learning techniques in training and validation of datasets over a wide range. Therefore this method could be used as a robust model to predict malignant transformations of benign nuclei and thus be implemented in the diagnosis and prognosis of ovarian cancer in future. Most importantly, this method can be perceived as a generalized approach in the diagnosis for all types of cancer.