Parallel-stream fusion of scan-specific and scan-general priors for learning deep MRI reconstruction in low-data regimes

Dar, Salman Ul Hassan; Öztürk, Şaban; Özbey, Muzaffer; Oguz, Kader Karli; Çukur, Tolga

doi:10.1016/j.compbiomed.2023.107610

Cited by 4 publications

(1 citation statement)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of artificial intelligence (AI) in medical image processing, including convolutional neural network (CNN) algorithms, assists in disease screening and diagnosis in various clinical settings [ 21 , 22 , 23 , 24 ]. Previously, machine learning and CNN algorithms were integrated with a smartphone application for automated digital image assessment of stool consistency in diapers [ 25 , 26 ].…”

Section: Introductionmentioning

confidence: 99%

The Effectiveness of Artificial Intelligence in Assisting Mothers with Assessing Infant Stool Consistency in a Breastfeeding Cohort Study in China

Wu,

Dong,

Sun

et al. 2024

Nutrients

View full text Add to dashboard Cite

Breastfeeding is widely recognized as the gold standard for infant nutrition, benefitting infants’ gastrointestinal tracts. Stool analysis helps in understanding pediatric gastrointestinal health, but the effectiveness of automated fecal consistency evaluation by parents of breastfeeding infants has not been investigated. Photographs of one-month-old infants’ feces on diapers were taken via a smartphone app and independently categorized by Artificial Intelligence (AI), parents, and researchers. The accuracy of the evaluations of the AI and the parents was assessed and compared. The factors contributing to assessment bias and app user characteristics were also explored. A total of 98 mother–infant pairs contributed 905 fecal images, 94.0% of which were identified as loose feces. AI and standard scores agreed in 95.8% of cases, demonstrating good agreement (intraclass correlation coefficient (ICC) = 0.782, Kendall’s coefficient of concordance W (Kendall’s W) = 0.840, Kendall’s tau = 0.690), whereas only 66.9% of parental scores agreed with standard scores, demonstrating low agreement (ICC = 0.070, Kendall’s W = 0.523, Kendall’s tau = 0.058). The more often a mother had one or more of the following characteristics, unemployment, education level of junior college or below, cesarean section, and risk for postpartum depression (PPD), the more her appraisal tended to be inaccurate (p < 0.05). Each point increase in the Edinburgh Postnatal Depression Scale (EPDS) score increased the deviation by 0.023 points (p < 0.05), which was significant only in employed or cesarean section mothers (p < 0.05). An AI-based stool evaluation service has the potential to assist mothers in assessing infant stool consistency by providing an accurate, automated, and objective assessment, thereby helping to monitor and ensure the well-being of infants.

show abstract