This paper presents the recognition for WHO classification of acute lymphoblastic leukaemia (ALL) subtypes. The two ALL subtypes considered are T-lymphoblastic leukaemia (pre-T) and B-lymphoblastic leukaemia (pre-B). They exhibit various characteristics which make it difficult to distinguish between subtypes from their mature cells, lymphocytes. In a common approach, handcrafted features must be well designed for this complex domain-specific problem. With deep learning approach, handcrafted feature engineering can be eliminated because a deep learning method can automate this task through the multilayer architecture of a convolutional neural network (CNN). In this work, we implement a CNN classifier to explore the feasibility of deep learning approach to identify lymphocytes and ALL subtypes, and this approach is benchmarked against a dominant approach of support vector machines (SVMs) applying handcrafted feature engineering. Additionally, two traditional machine learning classifiers, multilayer perceptron (MLP), and random forest are also applied for the comparison. The experiments show that our CNN classifier delivers better performance to identify normal lymphocytes and pre-B cells. This shows a great potential for image classification with no requirement of multiple preprocessing steps from feature engineering.
16 April 2021 in Applied Computational Intelligence and Soft Computing
This paper introduces an efficient deblurring image method based on a convolution-based and an iterative concept. Our method does not require specific conditions on images, so it can be widely applied for unspecific generic images. The kernel estimation is firstly performed and then will be used to estimate a latent image in each iteration. The final deblurred image is obtained from the convolution of the blurred image with the final estimated kernel. However, image deblurring is an ill-posed problem due to the nonuniqueness of solutions. Therefore, we propose a smoothing function, unlike previous approaches that applied piecewise functions on estimating a latent image. In our approach, we employ L2-regularization on intensity and gradient prior to converging to a solution of the deblurring problem. Moreover, our work is based on the quadratic splitting method. It guarantees that each subproblem has a closed-form solution. Various experiments on synthesized and real-world images confirm that our approach outperforms several existing methods, especially on the images corrupted by noises. Moreover, our method gives more reasonable and more natural deblurred images than those of other methods.
9 December 2023 in Applied Computational Intelligence and Soft Computing
Breast cancer is one of the leading causes of cancer-related mortality among women worldwide, making early and accurate mammogram classification essential for its effective diagnosis and treatment. Data augmentation has been widely employed to improve the generalization capability of deep learning models; however, conventional augmentation methods may distort diagnostically important lesion structures or suppress critical high-intensity regions. In this study, a Lesion-Intensity Aware Augmentation (LIAA) method is proposed for mammogram classification. The proposed approach extracts a local patch from the original mammogram and pastes it into a randomly selected target position while preserving the original image’s structure outside the modified region. During the blending process, intensity-guided fusion is performed by selecting the maximum intensity value between the source patch and the corresponding target region at each pixel location. This strategy introduces localized variability while preserving high-response lesion structures and reducing the risk of lesion suppression after patch replacement. The effectiveness of the proposed method was evaluated using the CBIS-DDSM and MIAS datasets with deep learning models for benign–malignant classification. The experimental results demonstrate that LIAA achieved superior classification performance compared with conventional augmentation techniques. In particular, the proposed method obtained the highest AUC score and improved the discriminative capability of the classification models by generating more informative lesion representations while maintaining diagnostically relevant structures.