Asunto(s)
Inteligencia Artificial , Enfermedad Pulmonar Obstructiva Crónica , Índice de Severidad de la Enfermedad , Tomografía Computarizada por Rayos X , Humanos , Enfermedad Pulmonar Obstructiva Crónica/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Radiografía Torácica/métodosRESUMEN
PURPOSE: To compare radiology residents' diagnostic performances to detect pulmonary emboli (PEs) on CT pulmonary angiographies (CTPAs) with deep-learning (DL)-based algorithm support and without. METHODS: Fully anonymized CTPAs (n = 207) of patients suspected of having acute PE served as input for PE detection using a previously trained and validated DL-based algorithm. Three residents in their first three years of training, blinded to the index report and clinical history, read the CTPAs first without, and 2 months later with the help of artificial intelligence (AI) output, to diagnose PE as present, absent or indeterminate. We evaluated concordances and discordances with the consensus-reading results of two experts in chest imaging. RESULTS: Because the AI algorithm failed to analyze 11 CTPAs, 196 CTPAs were analyzed; 31 (15.8 %) were PE-positive. Good-classification performance was higher for residents with AI-algorithm support than without (AUROCs: 0.958 [95 % CI: 0.921-0.979] vs. 0.894 [95 % CI: 0.850-0.931], p < 0.001, respectively). The main finding was the increased sensitivity of residents' diagnoses using the AI algorithm (92.5 % vs. 81.7 %, respectively). Concordance between residents (kappa: 0.77 [95 % CI: 0.76-0.78]; p < 0.001) improved with AI-algorithm use (kappa: 0.88 [95 % CI: 0.87-0.89]; p < 0.001). CONCLUSION: The AI algorithm we used improved between-resident agreements to interpret CTPAs for suspected PE and, hence, their diagnostic performances.
Asunto(s)
Aprendizaje Profundo , Embolia Pulmonar , Radiología , Humanos , Inteligencia Artificial , Tomografía Computarizada por Rayos X/métodos , Embolia Pulmonar/diagnóstico por imagen , Angiografía/métodos , AlgoritmosRESUMEN
B cells and T cells collaborate in multiple sclerosis (MS) pathogenesis. IgH[MOG] mice possess a B cell repertoire skewed to recognize myelin oligodendrocyte glycoprotein (MOG). Here, we show that upon immunization with the T cell-obligate autoantigen, MOG[35-55], IgH[MOG] mice develop rapid and exacerbated experimental autoimmune encephalomyelitis (EAE) relative to wildtype (WT) counterparts, characterized by aggregation of T and B cells in the IgH[MOG] meninges and by CD4+ T helper 17 (Th17) cells in the CNS. Production of the Th17 maintenance factor IL-23 is observed from IgH[MOG] CNS-infiltrating and meningeal B cells, and in vivo blockade of IL-23p19 attenuates disease severity in IgH[MOG] mice. In the CNS parenchyma and dura mater of IgH[MOG] mice, we observe an increased frequency of CD4+PD-1+CXCR5- T cells that share numerous characteristics with the recently described T peripheral helper (Tph) cell subset. Further, CNS-infiltrating B and Tph cells from IgH[MOG] mice show increased reactive oxygen species (ROS) production. Meningeal inflammation, Tph-like cell accumulation in the CNS and B/Tph cell production of ROS were all reduced upon p19 blockade. Altogether, MOG-specific B cells promote autoimmune inflammation of the CNS parenchyma and meninges in an IL-23-dependent manner.