PRISM method improves leukemia classification via perinuclear image segmentation

Researchers have developed a new method called PRISM for segmenting images of blood cells to classify Acute Lymphoblastic Leukemia (ALL). This approach focuses on adaptive concentric zones around the nucleus rather than precise cell boundaries, which are often difficult to discern in low-contrast images. PRISM extracts cytoplasmic descriptors using color and texture information, feeding them into a stacked ensemble of traditional classifiers. The method achieved a high accuracy of 98.46% and a precision-recall AUC of 0.9937 on its classification task. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a novel image segmentation technique that could improve diagnostic accuracy for blood-related diseases.

RANK_REASON Publication of an academic paper detailing a new method for image segmentation and classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• PRISM
• Acute Lymphoblastic Leukemia
• Larissa Rodrigues Moreira

• paper
• other