Page 114 - AI for Good Innovate for Impact
P. 114

AI for Good Innovate for Impact



                          Use Case 14: AI-Enabled Pathology Model for Precision Diagnosis

                      and Treatment
















                      Organization: Huawei Technologies Co., Ltd.

                      Country: China

                      Contact Person(s):
                           Primary contact: Gao Hongli gaohongli@ huawei .com
                           Secondary contact: Wu Xiaomin amy.wuxiaomin@ huawei .com
                           Any other contacts: Liang Jiani liangjiani@ huawei .com


                      1      Use Case Summary Table

                       Item           Details

                       Category       Healthcare

                       Problem        According to the latest report released by the World Health Organization
                       Addressed      (WHO)'s International Agency for Research on Cancer (IARC), the global cancer
                                      burden is increasing, with 20 million new cancer cases and 9.7 million deaths
                                      worldwide by 2022 [1]. Early detection, early diagnosis and early treatment are
                                      the key. It is urgent to expand the accessibility of pathology diagnosis, improve
                                      the accuracy of pathology diagnosis and improve the level of pathology diag-
                                      nosis at the grass-roots level.
                                      In China, the pathology sector faces several challenges, including a signifi-
                                      cant shortage of qualified professionals—with fewer than 20,000 registered
                                      pathologists and an estimated gap of 70,000 to 140,000. Pathologists are
                                      unevenly distributed, with 70% concentrated in tertiary hospitals. Addition-
                                      ally, the compliance rate for initial diagnoses in primary hospitals is low, with
                                      only 13% showing complete compliance and around 30% achieving general
                                      diagnostic agreement.

                       Key Aspects of  Huawei’s RuiPath model uses AI to analyze pathology slides, enabling faster
                       Solution       and more accurate diagnosis across 11 subspecialties. The solution supports
                                      whole slide image analysis, clinical integration and reasoning-based diagnosis,
                                      reducing diagnosis time by 75% and improving early detection. From tradi-
                                      tional microscopes to digitalization to intelligence, AI technology is used to
                                      achieve intelligent consultation and precise screening, improve the early diag-
                                      nosis rate and treatment efficiency of common diseases, reduce misdiagnosis
                                      rates, help make up for the shortage of medical resources, align with interna-
                                      tional standards, and improve global public health standards.
                       Technology     Multimodal Large Language Model for Pathology; Self-supervised Learning;
                       Keywords       Clinical Decision Support Agent





                  78
   109   110   111   112   113   114   115   116   117   118   119