8 Result(s)
-
Chapter and Conference Paper
Morph-Net: End-to-End Prediction of Nuclear Morphological Features from Histology Images
Analysis using morphological features of different types of nuclei have been shown to be useful for many different tasks in computational pathology. To obtain morphological features of nuclei in an image, a ne...
-
Chapter and Conference Paper
Cross-Stream Interactions: Segmentation of Lung Adenocarcinoma Growth Patterns
Lung adenocarcinoma has histologically distinct growth patterns that have been associated with patient prognosis. Precision segmentation of growth patterns in routine histology samples is challenging due to th...
-
Chapter and Conference Paper
Nuclear Segmentation and Classification: On Color and Compression Generalization
Since the introduction of digital and computational pathology as a field, one of the major problems in the clinical application of algorithms has been the struggle to generalize well to examples outside the di...
-
Chapter and Conference Paper
A Novel Framework for Coarse-Grained Semantic Segmentation of Whole-Slide Images
Semantic segmentation of multi-gigapixel whole-slide images (WSI) is fundamental to computational pathology, as segmentation of different tissue types and layers is a prerequisite for several downstream histol...
-
Chapter and Conference Paper
HydraMix-Net: A Deep Multi-task Semi-supervised Learning Approach for Cell Detection and Classification
Semi-supervised techniques have removed the barriers of large scale labelled set by exploiting unlabelled data to improve the performance of a model. In this paper, we propose a semi-supervised deep multi-task...
-
Chapter and Conference Paper
MIMONet: Gland Segmentation Using Multi-Input-Multi-Output Convolutional Neural Network
Morphological assessment of glands in histopathology images is very important in cancer grading. However, this is labour intensive, requires highly trained pathologists and has limited reproducibility. Digitis...
-
Chapter and Conference Paper
A Novel Cell Orientation Congruence Descriptor for Superpixel Based Epithelium Segmentation in Endometrial Histology Images
Recurrent miscarriage can be caused by an abnormally high number of Uterine Natural Killer (UNK) cells in human female uterus lining. Recently a diagnosis protocol has been developed based on the ratio of UNK ...
-
Chapter and Conference Paper
A Spatially Constrained Deep Learning Framework for Detection of Epithelial Tumor Nuclei in Cancer Histology Images
Detection of epithelial tumor nuclei in standard Hematoxylin & Eosin stained histology images is an essential step for the analysis of tissue architecture. The problem is quite challenging due to the high chro...
