Search

BackgroundThe progress in Colorectal cancer (CRC) screening and management has resulted in an unprecedented caseload for histopathological diagnosis. While artificial intelligence (AI) presents a potential solution, the predominant emphasis on slide-level aggregation performance without thorough verification of cancer in each location, impedes both explainability and transparency. Effectively addressing these challenges is crucial to ensuring the reliability and efficacy of AI in histology applications.MethodIn this study, we created an innovative AI algorithm using transfer learning from a polyp segmentation model in endoscopy. The algorithm precisely localized CRC targets within 0.25 mm² grids from whole slide imaging (WSI). We assessed the CRC detection capabilities at this fine granularity and examined the influence of AI on the diagnostic behavior of pathologists. The evaluation utilized an extensive dataset comprising 858 consecutive patient cases with 1418 WSIs obtained from an external center.ResultsOur results underscore a notable sensitivity of 90.25% and specificity of 96.60% at the grid level, accompanied by a commendable area under the curve (AUC) of 0.962. This translates to an impressive 99.39% sensitivity at the slide level, coupled with a negative likelihood ratio of

BackgroundThe clinical characteristics of primary liver cancer (PLC) patients are changing, maybe due to hepatitis viral vaccination and lifestyle changes, etc. The linkage between these changes and outcomes among these PLCs has not yet been fully elucidated.MethodsIt was identified total of 1691 PLC cases diagnosed between 2000 ~ 2020. Cox proportional hazards models were utilized to determine the connections between the clinical presentations and their close risk factor(s) from PLC patients.ResultsThe average age of PLC patients increased gradually from 52.74 ± 0.5 years in 2000 ~ 2004 to 58.63 ± 0.44 years in 2017 ~ 2020, accompanied by an increased proportion of females from 11.11% to 22.46%, and non-viral hepatitis-related PLC was raised from 1.5% to 22.35%. 840 (49.67%) PLC patients with alpha-fetoprotein (AFP) < 20ng/mL (AFP-negative). The mortality was 285 (16.85%) or 532 (31.46%) PLC patients with alanine transaminase (ALT) between 40 ~ 60 IU/L or ALT > 60 IU/L. The PLC patients with pre-diabetes/diabetes or dyslipidemia also increased from 4.29% or 11.1% in 2000 ~ 2004 to 22.34% or 46.83% in 2017 ~ 2020. The survival period of the PLC patients with normoglycemia or normolipidemic was 2.18 or 3.14 folds longer than those patients with pre-diabetes/diabetes or hyperlipidemia (P

Breast cancer is still a major concern due to its relatively poor prognosis in women, although there are many approaches being developed for the management of breast cancer. Extensive studies demonstrate that the development of breast cancer is determined by pro versus anti tumorigenesis factors, which are closely related to host immunity. IL-35 and IL-37, anti-inflammatory cytokines, play an important role in the maintenance of immune homeostasis. The current review focuses on the correlation between clinical presentations and the expression of IL-35 and IL-37, as well as the potential underlying mechanism during the development of breast cancer in vitro and in vivo. IL-35 is inversely correlated the differentiation and prognosis in breast cancer patients; whereas IL-37 shows dual roles during the development of breast cancer, and may be breast cancer stage dependent. Such information might be useful for both basic scientists and medical practitioners in the management of breast cancer patients.