* If you want to update the article please login/register
Stargardt disease is a common retina disorder that can occur in children and young adults' eyes. Atrophy is the main sign of late-stage Stargardt disease. Different degrees of inflammation can be caused by Stargardt disease, as well as other outer retinal layers. This review explores artificial intelligence deep learning techniques for the Stargardt atrophy screening and segmentation of fundus autofluorescence images, as well as a review of the automated retinal layer segmentation with atrophic-appearing lesions and fleck features using an artificial intelligence deep learning framework. The paper concludes with a discussion of artificial intelligence used in the hopes of determining early risk factors or biomarkers that may assist in the prediction of Stargardt disease progression.
Source link: https://europepmc.org/article/MED/35662193
Rheumatoid Arthritis' treatment, non-steroidal anti-inflammatory drugs, have played a key role in the treatment of Rheumatoid Arthritis, and a considerable amount of effort has been spent to develop novel localized drug delivery systems to improve their bioavailability and minimize side effects. Hence, the aim of this research was to discover, analyze, and optimize targeted in-situ forming nano particles for IA delivery of piroxicam using Design u00ae Expert as an AI-based application in which a 3 3/3 full factorial experimental approach was adopted. Also, the optimized-ISNs' once-a-week IA process resulted in a significant decrease in both STAT-3 and RANKL's protein expression, as well as a drastic decrease in the TNF-u03b1's content, relative to the positive control. In conclusion, the use of ISNs for intra-articular injection has demonstrated their effectiveness in piroxicam administration for RA therapy.
Source link: https://europepmc.org/article/MED/35532141
This paper is a general summary of artificial intelligence/machine learning algorithms in the field of peritoneal dialysis. Methods We looked at reviews that used AI/ML in PD, which were categorized based on the type of algorithm and PD question. However, clinical experts' analysis of AI/ML algorithms in PD also requires large databases and interpretation.
Source link: https://europepmc.org/article/MED/35469549
Objectives We want to investigate how computed tomography-based radiomics, as well as artificial intelligence, can help predict early recurrence in patients with clinical stage 0-IA non-small cell lung cancer. 39 AI imaging factors, including 17 factors from the AI ground-glass nodule review and 22 radiomic characteristics from nodule characterization analysis, were extracted from the AI software Beta Version 39 AI imaging factors, including 17 factors from the AI ground-glass nodule analysis and 22 radiomic characteristics from the nodule characterization study. According to receiver operating characteristics results, the area under the curve and optimal cutoff values pertaining to recurrence were 0. 07 and 1. 49 cm for solid part size, and 0. 710 and 22. 9% for solid part volume ratio, respectively. Patients in the validation set with high part size u2264 1. 49 cm and > 1. 49 cm were 92. 2% and 74% respectively, while those for patients with higher part volume ratios u2264 26. 7 percent and > 22. 9% were 97. 8% and 77%, respectively, respectively.
Source link: https://europepmc.org/article/MED/36070112
Purpose: When used alone or in combination with digital breast tomosynthesis photographs, compare the reader's results of artificial intelligence computer-aided detection synthesized mammograms to those of digital mammograms. The mean AUC values for DM, AI CAD SM, DM + DBT, and AI CAD SM + DBT were 0. 863, 0. 895, 0. 802, and 0. 902, respectively, according to the respective studies. The mean AUC of AI CAD SM was significantly higher than that of DM. The mean AUC of AI CAD SM+ DBT was higher than that of DM+ DBT. Since using AI CAD SM + DBT instead of the one using DM + DBT, a significant reduction in the reading time was observed. Conclusion The AI CAD SM + DBT may be more cost-effective than DM+ DBT in a screening setting due to its lower radiation dose, noninferiority, and shorter reading time relative to DM+ DBT.
Source link: https://europepmc.org/article/MED/36068450
Purpose: Intraoperative ultrasonography of the liver is a vital component of any liver transplant and can have a large effect on intraoperative surgical decisions. In IOUS, we describe the construction and evaluation of an artificial intelligence device to detect focal liver lesions. Methods During liver transplants performed between November 2020 and November 2021, IOUS photographs were gathered during liver resections. The images were described as normal liver tissue by radiologists and surgeons versus liver lesions photos. The Algorithm's results were tested in terms of area under the curves, accuracy, sensitivity, specificity, F1 score, positive predictive value, and negative predictive value. Overall, the study contained 543 IOUS images from 16 patients. Of these, 2576 were classified as normal liver tissue and 2467 as containing focal liver lesions. Conclusions This report provides for the first time a proof of concept for the use of AI in IOUS and demonstrates that high accuracy can be achieved.
Source link: https://europepmc.org/article/MED/36068378
* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions