Detection and quantification of pulmonary embolism with artificial intelligence: The SFR 2022 artificial intelligence data challenge.

PURPOSE: In 2022, the French Society of Radiology together with the French Society of Thoracic Imaging and CentraleSupelec organized their 13th data challenge. The aim was to aid in the diagnosis of pulmonary embolism, by identifying the presence of pulmonary embolism and by estimating the ratio between right and left ventricular (RV/LV) diameters, and an arterial obstruction index (Qanadli's score) using artificial intelligence. MATERIALS AND METHODS: The data challenge was composed of three tasks: the detection of pulmonary embolism, the RV/LV diameter ratio, and Qanadli's score. Sixteen centers all over France participated in the inclusion of the cases. A health data hosting certified web platform was established to facilitate the inclusion process of the anonymized CT examinations in compliance with general data protection regulation. CT pulmonary angiography images were collected. Each center provided the CT examinations with their annotations. A randomization process was established to pool the scans from different centers. Each team was required to have at least a radiologist, a data scientist, and an engineer. Data were provided in three batches to the teams, two for training and one for evaluation. The evaluation of the results was determined to rank the participants on the three tasks. RESULTS: A total of 1268 CT examinations were collected from the 16 centers following the inclusion criteria. The dataset was split into three batches of 310, 580 and 378 C T examinations provided to the participants respectively on September 5, 2022, October 7, 2022 and October 9, 2022. Seventy percent of the data from each center were used for training, and 30% for the evaluation. Seven teams with a total of 48 participants including data scientists, researchers, radiologists and engineering students were registered for participation. The metrics chosen for evaluation included areas under receiver operating characteristic curves, specificity and sensitivity for the classification task, and the coefficient of determination r2 for the regression tasks. The winning team achieved an overall score of 0.784. CONCLUSION: This multicenter study suggests that the use of artificial intelligence for the diagnosis of pulmonary embolism is possible on real data. Moreover, providing quantitative measures is mandatory for the interpretability of the results, and is of great aid to the radiologists especially in emergency settings.

A Preventive Role of RANTES Genetic Variation against Undifferentiated Schizophrenia.

AIM: Due to conflicting data from relevant studies, evidence for chemokine alterations in the pathophysiology of schizophrenia (Scz) remains inconclusive. Thus, we aimed to investigate the impact of rs2107538, rs2280788, and rs2280789 polymorphisms in CCL5 gene, as well as rs333 within CCR5 gene and the development of Scz in a Tunisian cohort. METHODS: We performed a case-control study composed of 200 patients and 200 controls using RFLP-PCR. RESULTS: Among the analyzed polymorphisms, only rs2107538 imparted protection against Scz and more specifically to male sex. This protective effect remained valid for the undifferentiated form. Moreover, this SNP had an impact on patients' symptomatology. When focusing on haplotypes, we noticed that the rs2107538-rs2280788-rs2280789 ACT genetic combination, with only one mutated allele rs2107538A, displayed reduced frequency in both Scz (as a whole group) and undifferentiated subtype. The haplotype distribution profile implies that the A allele at rs2107538 could induce a protective effect by increasing RANTES production. CONCLUSION: Additional independent analyses are required to corroborate these findings and elucidate the functional implications of the discovered preventing genotypes and haplotypes in Scz.

Association of VEGF-A and KDR polymorphisms with the development of schizophrenia.

AIM: Several approaches indicate different blood flow disturbances in schizophrenia. VEGF-A is widely recognized as one of the key molecules involved in the angiogenesis process through mainly its receptor KDR. The current work was designed to investigate the potential association between three polymorphisms (rs699947; rs833061 and rs3025039) in VEGF-A gene and two SNPs (rs2305948 and rs1870377) within KDR gene and predisposition to schizophrenia among the Tunisian cohort. METHODS: We carried-out a case-control study composed of 200 patients with schizophrenia and 200 healthy subjects using PCR-RFLP. RESULTS: Of all analyzed polymorphisms, only rs833061, rs3025039 and rs1870377) showed a significant risk for schizophrenia (PAdjusted = 0.04, PAdjusted=<0.001, PAdjusted = 0.005 respectively). Following the stratified analysis, rs3025039 was more prevalent among undifferentiated form (PAdjusted=<0.001) and more specifically with male sex (PAdjusted=<0.001). Yet, rs1870377 was correlated with paranoid subtype (PAdjusted = 0.002) and particularly with male sex (PAdjusted = 0.005). We found also that rs699947 is associated to negative symptoms before and after treatment (P = 0.004; P = 0.001 respectively) and rs3025039 had an impact on positive and negative symptoms only after treatment (P = 0.03; P = 0.008 respectively). Haplotype analysis revealed a strong LD between rs833061 and rs3025039 only for controls and undifferentiated patients (P = 0.005). Moreover, the rs699947*C âˆ¼ rs833061*T âˆ¼ rs3025039*T haplotype, with only one mutated allele rs3025039*T, conferred a high risk to schizophrenia (P = 0.016) and, in particular, to undifferentiated and paranoid forms (P = 0.03; P = 0.02 respectively). Among the last-mentioned subgroup, we noticed another overrepresented haplotype (rs699947*A âˆ¼ rs833061*T âˆ¼ rs3025039*T; P = 0.01). Furthermore, the rs2305948*G âˆ¼ rs1870377*T haplotype carrying the minor allele rs1870377*T displayed increased frequencies in the whole group of patients and particularly among paranoid subtype (P = 0.013; P=<0.001 respectively). CONCLUSION: Our results show that all SNPs associated with the development or the severity of schizophrenia, were subsequently correlated with a decrease in the VEGF-A levels or influence KDR binding affinity. These data need to be strengthened by further independent analyses.

Inteurleukin-8 gene variations and the susceptibility to schizophrenia.

The relevance of Interleukin-8 (IL-8) cytokine alteration in the peripheral and central system has been widely shown in psychosis while variation in the IL-8 gene remains largely unexplored and to the best of our knowledge, IL-8 polymorphisms have never been specifically targeted in Schizophrenia (Scz). Thus, we set out to search a potential correlation between rs4073, rs2227306 and rs1126647 polymorphisms in IL-8 gene and the development of Scz in a sample of the Tunisian population in a candidate gene approach. Targeted polymorphisms were analysed in 206 patients and 195 controls using PCR-RFLP method. Among all analysed polymorphisms, only rs1126647 showed a significant risk for Scz. After stratification analysis, we noted a significant association of TT genotype and T allele at rs1126647 with paranoid form, and more specifically with female sex. We find that the rare haplotypes at rs4073-rs2227306-rs1126647 of TTT, ACT and TCT, each containing the risk allele rs1126647T, were associated with increased risk for paranoid Scz while only the TCT combination constituted a risk factor for Scz more generally. Our findings support that IL-8 gene may be involved in susceptibility to Scz but this still preliminary and needs to be strengthened by further independent analyses.