Biparametric prostate MRI: impact of a deep learning-based software and of quantitative ADC values on the inter-reader agreement of experienced and inexperienced readers

Objective

To investigate the impact of an artificial intelligence (AI) software and quantitative ADC (qADC) on the inter-reader agreement, diagnostic performance, and reporting times of prostate biparametric MRI (bpMRI) for experienced and inexperienced readers.

Materials and methods

A total of 170 multiparametric MRI (mpMRI) of patients with suspicion of prostate cancer (PCa) were retrospectively reviewed by one experienced and one inexperienced reader three times, following a wash-out period. First, only the bpMRI sequences, including T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI) sequences, and apparent diffusion coefficient (ADC) maps, were used. Then, bpMRI and quantitative ADC values were used. Lastly, bpMRI and the AI software were used. Inter-reader agreement between the two readers and between each reader and the mpMRI original reports was calculated. Detection rates and reporting times were calculated for each group.

Results

Inter-reader agreement with respect to mpMRI was moderate for bpMRI, Quantib, and qADC for both the inexperienced (weighted k of 0.42, 0.45, and 0.41, respectively) and the experienced radiologists (weighted k of 0.44, 0.46, and 0.42, respectively). Detection rate of PCa was similar between the inexperienced (0.24, 0.26, and 0.23) and the experienced reader (0.26, 0.27 and 0.27), for bpMRI, Quantib, and qADC, respectively. Reporting times were lower for Quantib (8.23, 7.11, and 9.87 min for the inexperienced reader and 5.62, 5.07, and 6.21 min for the experienced reader, for bpMRI, Quantib, and qADC, respectively).

Conclusions

AI and qADC did not have a significant impact on the diagnostic performance of both readers. The use of Quantib was associated with lower reporting times.

     

Plasma miRNA-based signatures in CRC screening programs

Colorectal cancer (CRC) screening programs help diagnose cancer precursors and early cancers and help reduce CRC mortality. However, currently recommended tests, the fecal immunochemical test (FIT) and colonoscopy, have low uptake. There is therefore a pressing need for screening strategies that are minimally invasive and consequently more acceptable to patients, most likely blood based, to increase early CRC identification. MicroRNAs (miRNAs) released from cancer cells are detectable in plasma in a remarkably stable form, making them ideal cancer biomarkers. Using plasma samples from FIT-positive (FIT+) subjects in an Italian CRC screening program, we aimed to identify plasma circulating miRNAs that detect early CRC. miRNAs were initially investigated by quantitative real-time PCR in plasma from 60 FIT+ subjects undergoing colonoscopy at Fondazione IRCCS Istituto Nazionale dei Tumori, then tested on an internal validation cohort (IVC, 201 cases) and finally in a large multicenter prospective series (external validation cohort [EVC], 1121 cases). For each endoscopic lesion (low-grade adenoma [LgA], high-grade adenoma [HgA], cancer lesion [CL]), specific signatures were identified in the IVC and confirmed on the EVC. A two-miRNA-based signature for CL and six-miRNA signatures for LgA and HgA were selected. In a multivariate analysis including sex and age at blood collection, the areas under the receiver operating characteristic curve (95% confidence interval) of the signatures were 0.644 (0.607–0.682), 0.670 (0.626–0.714) and 0.682 (0.580–0.785) for LgA, HgA and CL, respectively. A miRNA-based test could be introduced into the FIT+ workflow of CRC screening programs so as to schedule colonoscopies only for subjects likely to benefit most.     

Immune-pineal axis protects rat lungs exposed to polluted air

Environmental pollution in the form of particulate matter <2.5 μm (PM_2.5) is a major risk factor for diseases such as lung cancer, chronic respiratory infections, and major cardiovascular diseases. Our goal was to show that PM_2.5 eliciting a proinflammatory response activates the immune-pineal axis, reducing the pineal synthesis and increasing the extrapineal synthesis of melatonin. Herein, we report that the exposure of rats to polluted air for 6 hours reduced nocturnal plasma melatonin levels and increased lung melatonin levels. Melatonin synthesis in the lung reduced lipid peroxidation and increased PM_2.5 engulfment and cell viability by activating high-affinity melatonin receptors. Diesel exhaust particles (DEPs) promoted the synthesis of melatonin in a cultured cell line (RAW 264.7 cells) and rat alveolar macrophages via the expression of the gene encoding for AANAT through a mechanism dependent on activation of the NFκB pathway. Expression of the genes encoding AANAT, MT1, and MT2 was negatively correlated with cellular necroptosis, as disclosed by analysis of Gene Expression Omnibus (GEO) microarray data from the human alveolar macrophages of nonsmoking subjects. The enrichment score for antioxidant genes obtained from lung gene expression data (GTEx) was significantly correlated with the levels of AANAT and MT1 but not the MT2 melatonin receptor. Collectively, these data provide a systemic and mechanistic rationale for coordination of the pineal and extrapineal synthesis of melatonin by a standard damage-associated stimulus, which activates the immune-pineal axis and provides a new framework for understanding the effects of air pollution on lung diseases.