Feature Generalization for Breast Cancer Detection in Histopathological Images.

Recent period has witnessed benchmarked performance of transfer learning using deep architectures in computer-aided diagnosis (CAD) of breast cancer. In this perspective, the pre-trained neural network needs to be fine-tuned with relevant data to extract useful features from the dataset. However, in addition to the computational overhead, it suffers the curse of overfitting in case of feature extraction from smaller datasets. Handcrafted feature extraction techniques as well as feature extraction using pre-trained deep networks come into rescue in aforementioned situation and have proved to be much more efficient and lightweight compared to deep architecture-based transfer learning techniques. This research has identified the competence of classifying breast cancer images using feature engineering and representation learning over the established and contemporary notion of using transfer learning techniques. Moreover, it has revealed superior feature learning capacity with feature fusion in contrast to the conventional belief of understanding unknown feature patterns better with representation learning alone. Experiments have been conducted on two different and popular breast cancer image datasets, namely, KIMIA Path960 and BreakHis datasets. A comparison of image-level accuracy is performed on these datasets using the above-mentioned feature extraction techniques. Image level accuracy of 97.81% is achieved for KIMIA Path960 dataset using individual features extracted with handcrafted (color histogram) technique. Fusion of uniform Local Binary Pattern (uLBP) and color histogram features has resulted in 99.17% of highest accuracy for the same dataset. Experimentation with BreakHis dataset has resulted in highest classification accuracy of 88.41% with color histogram features for images with 200X magnification factor. Finally, the results are contrasted to that of state-of-the-art and superior performances are observed on many occasions with the proposed fusion-based techniques. In case of BreakHis dataset, the highest accuracies 87.60% (with least standard deviation) and 85.77% are recorded for 200X and 400X magnification factors, respectively, and the results for the aforesaid magnification factors of images have exceeded the state-of-the-art.

Multi technique amalgamation for enhanced information identification with content based image data.

Image data has emerged as a resourceful foundation for information with proliferation of image capturing devices and social media. Diverse applications of images in areas including biomedicine, military, commerce, education have resulted in huge image repositories. Semantically analogous images can be fruitfully recognized by means of content based image identification. However, the success of the technique has been largely dependent on extraction of robust feature vectors from the image content. The paper has introduced three different techniques of content based feature extraction based on image binarization, image transform and morphological operator respectively. The techniques were tested with four public datasets namely, Wang Dataset, Oliva Torralba (OT Scene) Dataset, Corel Dataset and Caltech Dataset. The multi technique feature extraction process was further integrated for decision fusion of image identification to boost up the recognition rate. Classification result with the proposed technique has shown an average increase of 14.5 % in Precision compared to the existing techniques and the retrieval result with the introduced technique has shown an average increase of 6.54 % in Precision over state-of-the art techniques.