2-SiMDoM: A 2-Sieve model for detection of mitosis in multispectral breast cancer imagery

Abstract

In this paper, we propose a 2-Sieve model for the detection of mitosis in breast cancer multispectral images. Multiresolution wavelet features & Gray Level Entropy Matrix (GLEM) features have been computed for each candidate on all the spectral bands. A novel dimensionality selection algorithm has been introduced and its performance compared with other existing algorithms. Data imbalance and data cleaning have been taken care of using classical data mining techniques. Furthermore, a Second Sieve classification is performed to increase the Positive Predictive Value (PPV) with minimal loss in Sensitivity. A final Sensitivity and PPV of 82.35% & 73.04% respectively was achieved over the testing set using the proposed scheme.

Efficient deep learning model for mitosis detection using breast histopathology images

“…They suggested that there should be a sufficient number of the training dataset. A. S. Tripathi et al,(2013) proposed a 2-Sieve model for mitosis detection. They have extracted Gray Level Entropy Matrix features and Multiresolution wavelet features on all the spectral bands.…”

“…Classical data mining technique and dimensionality selection technique had been used in this model. Their results show positive predictive value 73.04% and sensitivity 82.35% [29]. The approach presented in [30], uses the whole slide histological images for mitotic cell extraction and visualization, using the multi-resolution graph-based technique.…”

Automated mitosis detection in histopathology based on non-gaussian modeling of complex wavelet coefficients

“…Wouwer et al also computed the DWT-based energy parameters for the automated identification of neoplastic nuclei in digitalized microscopic images and yielded good classification results in grading of invasive breast cancer. Tripathi et al investigated the ability of multi-level Daubechies wavelets, a commonly used form of DWT, to extract texture features for detecting mitosis in breast histopathological images, and showed a remarkable increase in the sensitivity measure over previous studies [27]. Lopez and Agaian combined wavelet and fractal features for Gleason grading of prostate cancer in histopathology images [28].…”