Automated Left Ventricular Dimension Assessment Using Artificial Intelligence Developed and Validated by a UK-Wide Collaborative.

BACKGROUND: requires training and validation to standards expected of humans. We developed an online platform and established the Unity Collaborative to build a dataset of expertise from 17 hospitals for training, validation, and standardization of such techniques. METHODS: The training dataset consisted of 2056 individual frames drawn at random from 1265 parasternal long-axis video-loops of patients undergoing clinical echocardiography in 2015 to 2016. Nine experts labeled these images using our online platform. From this, we trained a convolutional neural network to identify keypoints. Subsequently, 13 experts labeled a validation dataset of the end-systolic and end-diastolic frame from 100 new video-loops, twice each. The 26-opinion consensus was used as the reference standard. The primary outcome was precision SD, the SD of the differences between AI measurement and expert consensus. RESULTS: In the validation dataset, the AI's precision SD for left ventricular internal dimension was 3.5 mm. For context, precision SD of individual expert measurements against the expert consensus was 4.4 mm. Intraclass correlation coefficient between AI and expert consensus was 0.926 (95% CI, 0.904-0.944), compared with 0.817 (0.778-0.954) between individual experts and expert consensus. For interventricular septum thickness, precision SD was 1.8 mm for AI (intraclass correlation coefficient, 0.809; 0.729-0.967), versus 2.0 mm for individuals (intraclass correlation coefficient, 0.641; 0.568-0.716). For posterior wall thickness, precision SD was 1.4 mm for AI (intraclass correlation coefficient, 0.535 [95% CI, 0.379-0.661]), versus 2.2 mm for individuals (0.366 [0.288-0.462]). We present all images and annotations. This highlights challenging cases, including poor image quality and tapered ventricles. CONCLUSIONS: Experts at multiple institutions successfully cooperated to build a collaborative AI. This performed as well as individual experts. Future echocardiographic AI research should use a consensus of experts as a reference. Our collaborative welcomes new partners who share our commitment to publish all methods, code, annotations, and results openly.

Insulin-like growth factors are more effective than progastrin in reversing proapoptotic effects of curcumin: critical role of p38MAPK.

Progastrin and insulin-like growth factors (IGFs) stimulate hyperproliferation of intestinal epithelial cells (IECs) via endocrine/paracrine routes; hyperproliferation is a known risk factor for colon carcinogenesis. In the present study, inhibitory potency of curcumin in the presence or absence of progastrin and/or IGF-II was examined. Progastrin and IGF-II significantly increased proliferation of an immortalized IEC cell line, IEC-18, whereas curcumin decreased the proliferation in a dose-dependent manner. IGF-II was significantly more effective than progastrin in reversing antiproliferative effects of curcumin and reversed proapoptotic effects of curcumin by >80%; progastrin was relatively ineffective toward reversing proapoptotic effects of curcumin. IEC-18 clones were generated to overexpress either progastrin (IEC-PG) or hIGF-II (IEC-IGF). Proliferation of IEC-PG and IEC-IGF clones was increased, compared with that of control clones. Curcumin significantly reduced proliferation of IEC-PG, but not IEC-IGF, clones. Similarly, a human colon cancer cell line, Caco-2 (which expresses autocrine IGF-II), was relatively resistant to inhibitory effects of curcumin. However, Caco-2 cells treated with anti-IGF-II-antibodies were rendered sensitive to inhibitory effects of curcumin. Significant differences in inhibitory potency of curcumin against PG- vs. IGF-II-stimulated growth of IEC-18 cells were not reflected by differences in curcumin-mediated inhibition of activated (phosphorylated) ERKs/IKK(alpha/beta)/p65NF-kappaB and c-Src in wild-type (wt)IEC-18 cells, in response to the two growth factors. Surprisingly, curcumin was almost ineffective in reducing IGF-II-stimulated activation of p38MAPK but significantly reduced progastrin-stimulated phosphorylation of p38. Treatment with a p38MAPK inhibitor resulted in loss of protective effects of IGF-II against inhibitory effects of curcumin. These novel findings suggest that growth factor profile of patients and tumors may dictate inhibitory potency of curcumin and that combination of curcumin + p38MAPK inhibitor may be required for reducing hyperproliferative or tumorigenic response of IECs to endocrine and autocrine IGFs.

Methylene blue modulates functional connectivity in the human brain.

Methylene blue USP (MB) is a FDA-grandfathered drug used in clinics to treat methemoglobinemia, carbon monoxide poisoning and cyanide poisoning that has been shown to increase fMRI evoked blood oxygenation level dependent (BOLD) response in rodents. Low dose MB also has memory enhancing effect in rodents and humans. However, the neural correlates of the effects of MB in the human brain are unknown. We tested the hypothesis that a single low oral dose of MB modulates the functional connectivity of neural networks in healthy adults. Task-based and task-free fMRI were performed before and one hour after MB or placebo administration utilizing a randomized, double-blinded, placebo-controlled design. MB administration was associated with a reduction in cerebral blood flow in a task-related network during a visuomotor task, and with stronger resting-state functional connectivity in multiple regions linking perception and memory functions. These findings demonstrate for the first time that low-dose MB can modulate task-related and resting-state neural networks in the human brain. These neuroimaging findings support further investigations in healthy and disease populations.