Breast cancer is the most common cancer worldwide, and it is also the second leading cause of cancer-related death. Histopathological diagnosis, which directs treatment and prognosis, is the cornerstone of a breast cancer workup. However, as more is learned about the complicated nature of cancer and personalised treatments become available, prospects for improving diagnostic precision have emerged. The molecular characterization of tumour tissue samples is becoming increasingly important in cancer care. Studies are carried out to see how and how the DNA in the tumour tissue has improved, as well as the gene and protein expression in the tissue sample. Simultaneously, researchers are becoming more aware that cancer progression is closely linked to intercellular cross-talk and the association of neoplastic cells with surrounding tissue, including the immune system. While microscopic techniques allow for a high level of spatial detail in biological processes, they only allow for a small measurement of molecular markers. Proteins or DNA extracted from tissue are used to establish these. As a result, spatial precision is impossible to achieve, and the relationship between these markers and microscopic structures is often ambiguous. Artificial intelligence has been used to create a new tissue-section analysis method for diagnosing breast cancer (AI). For the first time, morphological, genetic, and histological information is combined in a single study. In addition, heatmaps provide a visual representation of the AI decision-making process. The method of converting histopathology slides into digital images using whole-slide scanners and then analysing these digitised images is known as digital pathology.

Media Contact:

John Robert
Journal of Medical and Surgical Pathology
ISSN: 2472-4971 | NLM ID: 101245791