Browsing by Author "Kanfade, A."

Now showing 1 - 3 of 3

A robust method for nuclei segmentation of HE stained histopathology images
(Institute of Electrical and Electronics Engineers Inc., 2020) Lal, S.; Desouza, R.; Maneesh, M.; Kanfade, A.; Kumar, A.; Perayil, G.; Alabhya, K.; Chanchal, A.K.; Kini, J.
Segmentation of histopathology images is an initial and vital step for image understanding. To increase the throughput and to maintain high accuracy, we have to go for an automatic image segmentation method. Here, a robust method for segmentation of cell nuclei in Hematoxylin and Eosin (HE) stained histopathology images is proposed. The proposed segmentation step consists of an initial pre-processing step containing adaptive colour de-convolution and a succession of morphological operations, followed by multilevel thresholding and post-processing steps. Minimum region size is the one parameter which is necessary for this method and set according to the resolution of histopathology image. The proposed nuclei segmentation method does not require any assumptions or prior information about cell morphology. Hence, proposed method applies to the analysis of a wide range of tissues such as liver, kidney, breast, gastric mucosa, and bone marrow and HE stained liver histopathology images from the Hospital. Results yield that proposed nuclei segmentation provides better results in terms of quantitatively and qualitatively on two datasets. Â© 2020 IEEE.
Detecting Document Versions and Their Ordering in a Collection
(Springer Science and Business Media Deutschland GmbH, 2021) Modani, N.; Maurya, A.; Verma, G.; Nair, I.; Patil, V.; Kanfade, A.
Given the iterative and collaborative nature of authoring and the need to adapt the documents for different audience, people end up with a large number of versions of their documents. These additional versions of documents increase the required cognitive effort for various tasks for humans (such as finding the latest version of a document, or organizing documents), and may degrade the performance of machine tasks such as clustering or recommendation of documents. To the best of our knowledge, the task of identifying and ordering the versions of documents from a collection of documents has not been addressed in prior literature. We propose a three-stage approach for the task of identifying versions and ordering them correctly in this paper. We also create a novel dataset for this purpose from Wikipedia, which we are releasing to the research community (https://github.com/natwar-modani/versions ). We show that our proposed approach significantly outperforms state-of-the-art approach adapted for this task from the closest previously known task of Near Duplicate Detection, which justifies defining this problem as a novel challenge. Â© 2021, Springer Nature Switzerland AG.
NucleiSegNet: Robust deep learning architecture for the nuclei segmentation of liver cancer histopathology images
(Elsevier Ltd, 2021) Lal, S.; Das, D.; Alabhya, K.; Kanfade, A.; Kumar, A.; Kini, J.R.
The nuclei segmentation of hematoxylin and eosin (H&E) stained histopathology images is an important prerequisite in designing a computer-aided diagnostics (CAD) system for cancer diagnosis and prognosis. Automated nuclei segmentation methods enable the qualitative and quantitative analysis of tens of thousands of nuclei within H&E stained histopathology images. However, a major challenge during nuclei segmentation is the segmentation of variable sized, touching nuclei. To address this challenge, we present NucleiSegNet - a robust deep learning network architecture for the nuclei segmentation of H&E stained liver cancer histopathology images. Our proposed architecture includes three blocks: a robust residual block, a bottleneck block, and an attention decoder block. The robust residual block is a newly proposed block for the efficient extraction of high-level semantic maps. The attention decoder block uses a new attention mechanism for efficient object localization, and it improves the proposed architecture's performance by reducing false positives. When applied to nuclei segmentation tasks, the proposed deep-learning architecture yielded superior results compared to state-of-the-art nuclei segmentation methods. We applied our proposed deep learning architecture for nuclei segmentation to a set of H&E stained histopathology images from two datasets, and our comprehensive results show that our proposed architecture outperforms state-of-the-art methods. As part of this work, we also introduced a new liver dataset (KMC liver dataset) of H&E stained liver cancer histopathology image tiles, containing 80 images with annotated nuclei procured from Kasturba Medical College (KMC), Mangalore, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, India. The proposed model's source code is available at https://github.com/shyamfec/NucleiSegNet. © 2020 Elsevier Ltd