Publications by authors named "Taimoor Shakeel Sheikh"
Segmentation of Variants of Nuclei on Whole Slide Images by Using Radiomic Features.
Bioengineering (Basel)
March 2024
Article Synopsis
- The study addresses the difficulty of distinguishing between different nuclear types in histopathology, which is crucial for accurate diagnosis.
- A new framework was introduced that enhances the segmentation of nuclei by utilizing radiomic features to analyze their characteristics and train classifiers.
- Testing on the MoNuSAC2020 dataset showed that this framework achieved top-tier performance in segmenting various nuclear types, demonstrating its effectiveness across different organ images and types of radiomic features.
Unsupervised Learning Based on Multiple Descriptors for WSIs Diagnosis.
Diagnostics (Basel)
June 2022
An automatic pathological diagnosis is a challenging task because histopathological images with different cellular heterogeneity representations are sometimes limited. To overcome this, we investigated how the holistic and local appearance features with limited information can be fused to enhance the analysis performance. We propose an unsupervised deep learning model for whole-slide image diagnosis, which uses stacked autoencoders simultaneously feeding multiple-image descriptors such as the histogram of oriented gradients and local binary patterns along with the original image to fuse the heterogeneous features.
View Article and Find Full Text PDFAnomaly Detection Based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation.
IEEE Trans Neural Netw Learn Syst
January 2022
Article Synopsis
- Anomaly detection faces challenges due to the rarity of anomalies, which leads to unbalanced data issues; synthetic anomalies are proposed as a potential solution for this problem.
- The article introduces a two-level hierarchical latent space representation using autoencoders to create robust feature representations for generating synthetic anomalies without prior examples.
- The proposed method successfully generates pseudo outlier samples, enabling the training of effective binary classifiers for real anomaly detection, and shows strong performance across multiple benchmarking tests.
Diagnosis of pathologies using histopathological images can be time-consuming when many images with different magnification levels need to be analyzed. State-of-the-art computer vision and machine learning methods can help automate the diagnostic pathology workflow and thus reduce the analysis time. Automated systems can also be more efficient and accurate, and can increase the objectivity of diagnosis by reducing operator variability.
View Article and Find Full Text PDF