Cancer remains one of the most challenging afflictions facing humanity, lacking a definitive cure. Among its prevalent forms, breast cancer stands as a significant health concern, disproportionately affecting women aged 20-59. Nonetheless, mortality rates can be mitigated through timely screening and treatment interventions. The intricacies of breast cancer detection and classification, particularly distinguishing between cancerous and healthy cells, pose formidable challenges. This study proposes an innovative approach harnessing artificial intelligence (AI) in conjunction with the Internet of Medical Things (IoMT) to address early-stage breast cancer detection and classification. The devised artificial intelligence-enabled heuristic framework (AI-HF) leverages machine intelligence techniques (MIT) to identify cancerous cells by analyzing shape and texture-based features. Subsequently, machine learning (ML) classification techniques, notably support vector machines (SVMs) are employed to discern cancerous cells from healthy ones. Experimental findings, derived from real datasets, underscore the efficacy of the proposed method, achieving a commendable accuracy rate of 98.0% in detecting and categorizing abnormal cells within breast cancer images. Importantly, theAI-HF classifier emerges as a swift and efficient model, outperforming traditional approaches by swiftly distinguishing between cancerous and healthy cells based on extracted cell image attributes. © 2025 Elsevier B.V., All rights reserved.