Abstract

Detection and classification of cells in histological images is a challenging task because of the large intra-class variation in the visual appearance of various types of biological cells. In this paper, we propose a discriminative dictionary learning paradigm, termed as Cell Words, for modelling the visual appearance of cells which includes colour, shape, texture and context in a unified manner. The proposed framework is capable of distinguishing mitotic cells from non-mitotic cells (apoptotic, necrotic, epithelial) in breast histology images with high accuracy.

---

Schematic Illustration

The proposed paradigm for learning the visual appearance of cells.

---

Results

The proposed method has been evaluated on the publicly available MITOS dataset for mitosis detections in breast cancer histopathology images.

Learned discriminative dictionaries between mitotic and non-miotic cells. Mitotic cell words in mitotic dictionary are representative of various phases of cell mitosis.

Classification Performance based on the Learned Dictionary.

---

Code

Please contact Nasir Rajpoot for the source code of Cell Words.

---

Reference

Cell words: Modelling the visual appearance of cells in histopathology images
K. Sirinukunwattana , A.M. Khan, and N. M. Rajpoot,
Computerized Medical Imaging and Graphics, Elsevier
doi: 10.1016/j.compmedimag.2014.11.008 [link]