Convolutional Neural Network Classification of Basal Cell Carcinoma in Harmonically Generated Microscopy Images

Yu, Zheng-Han; Lee, Gwo Giun Chris; Liao, Yu-Sheng; Sun, Chia‐Liang

doi:10.1109/aicas54282.2022.9869921

Cited by 1 publication

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1illustrated Algorithm. Food images taken from smartphone were initially processed by the ' AI food image recognition' , which was lightweight deep learning algorithmic software based on proprietary machine learning techniques [12][13][14][15][16] . Then the 'ingredient categorization' , a deep analytics algorithm, decomposed the images, identified the food contents, and categorized food contents by ingredients.…”

Section: Methodsmentioning

confidence: 99%

Effect of a novel telehealth device for dietary cognitive behavioral intervention in overweight or obesity care

Fang

Lee

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Obesity has become a major public health issue which relate to numerous physical problems and highly comorbid with depression and anxiety. Recently, some studies of technology-based interventions for weight reduction emerged to overcome the barriers from time, cost and distance. Mood component and eating behavior related to obesity are less discussed so far with technology-based intervention though. This pilot study was aimed to investigate the effect of telehealth assisted intervention on weight reduction, mood status, and eating behavior change under a smartphone application (app) with novel 3D food picture recognition and incorporated with cognitive behavioral training programs. Adult aged 30–60 years old with overweight were recruited and randomly assigned to control-first group and intervention-first group. In period 1, control-first group had regular life and intervention-first group underwent app intervention; in period 2, two groups went crossover. Body composition and psychological/behavioral questionnaires were collected at baseline, end of period 1, and end of period 2. Nonparametric statistics was performed for data analyzing. A total of 20 participants were enrolled. In control-first group, there were statistically significant reduction in body weight (− 0.55 kg, p = 0.02) and change of body weight percentage (− 0.6%, p = 0.02) after App use. In intervention-first group, the fat percentage decreased by 0.4% after App use in period 1, and increased by 0.05% in period 2. The integrated crossover data revealed that subjects of App group had significant improvements in mindful eating behavior. This pilot study showed the effectiveness in using CogniNU app for weight control and eating behavior. The difference of short-term and long-term effectiveness of technology-based weight control intervention deserves more investigation in the future.Clinical Trial Registration: ISRCTN16082909.

show abstract