Publications by authors named "Rashika Mishra"
Pathological estimation of tumor necrosis after chemotherapy is essential for patients with osteosarcoma. This study reports the first fully automated tool to assess viable and necrotic tumor in osteosarcoma, employing advances in histopathology digitization and automated learning. We selected 40 digitized whole slide images representing the heterogeneity of osteosarcoma and chemotherapy response.
View Article and Find Full Text PDFPathologists often deal with high complexity and sometimes disagreement over osteosarcoma tumor classification due to cellular heterogeneity in the dataset. Segmentation and classification of histology tissue in H&E stained tumor image datasets is a challenging task because of intra-class variations, inter-class similarity, crowded context, and noisy data. In recent years, deep learning approaches have led to encouraging results in breast cancer and prostate cancer analysis.
View Article and Find Full Text PDFArticle Synopsis
- Osteosarcoma is a prevalent bone cancer in children, and assessing treatment response traditionally relies on manual evaluation of H&E stained slides by pathologists, which can be time-consuming and biased.
- A digital image analysis method is introduced to automate the process of segmenting vital tumor regions in high-resolution Whole Slide Images (WSIs), using a combination of pixel-based and object-based techniques alongside K-Means clustering and Otsu segmentation.
- The proposed approach yields high accuracy rates, achieving 100% success in identifying viable tumor and coagulative necrosis, with around 90% accuracy for fibrosis, ultimately aiming to enhance diagnostic accuracy and reduce variability among observers.