Search

Convolutional neural networks (CNNs) have demonstrated expert-level performance in cutaneous tumour classification using clinical images, but most previous studies have focused on dermatologist-versus-CNN comparisons rather than their combination. The objective of our study was to evaluate the potential impact of CNN assistance on dermatologists for clinical image interpretation.A multi-class CNN was trained and validated using a dataset of 25,773 clinical images comprising 10 categories of cutaneous tumours. The CNN's performance was tested on an independent dataset of 2107 images. A total of 400 images (40 per category) were randomly selected from the test dataset. A fully crossed, self-control, multi-reader multi-case (MRMC) study was conducted to compare the performance of 18 board-certified dermatologists (experience: 13/18 ≤ 10 years; 5/18＞10 years) in interpreting the 400 clinical images with or without CNN assistance.The CNN achieved an overall accuracy of 78.45% and kappa of 0.73 in the classification of 10 types of cutaneous tumours on 2107 images. CNN-assisted dermatologists achieved a higher accuracy (76.60% vs. 62.78%, P 0.001) and kappa (0.74 vs. 0.59, P 0.001) than unassisted dermatologists in interpreting the 400 clinical images. Dermatologists with less experience benefited more from CNN assistance. At the binary classification level (malignant or benign), the sensitivity (89.56% vs. 83.21%, P 0.001) and specificity (87.90% vs. 80.92%, P 0.001) of dermatologists with CNN assistance were also significantly improved than those without.CNN assistance improved dermatologist accuracy in interpreting cutaneous tumours and could further boost the acceptance of this new technique.

Reductive transformation of 2,4-dichlorophenoxyacetic acid (2,4-D) by nanoscale and microscale Fe3O4 was investigated and compared. Disappearance of the parent species and formation of reaction intermediates and products were kinetically analyzed. Results suggest that the transformation of 2,4-D followed a primary pathway of its complete reduction to phenol and a secondary pathway of sequential reductive hydrogenolysis to 2,4-dichlorophenol (2,4-DCP), chlorophenol (2-CP, 4-CP) and phenol. About 65% of 2,4-D with initial concentration of 50 μ M was transformed within 48 h in the presence of 300 mg L−1 nanoscale Fe3O4, and the reaction rates increased with increasing dosage of nanoscale Fe3O4. The decomposition of 2,4-D proceeded rapidly at optimum pH 3.0. Chloride was identified as a reduction product for 2,4-D in the magnetite–water system. Reductive transformation of 2,4-D by microscale Fe3O4 was slower than that by nanoscale Fe3O4. The reactions apparently followed pseudo-first-order kinetics with respe...

Reductive transformation of 2,4-dichlorophenoxyacetic acid (2,4-D) by nanoscale and microscale Fe(3)O(4) was investigated and compared. Disappearance of the parent species and formation of reaction intermediates and products were kinetically analyzed. Results suggest that the transformation of 2,4-D followed a primary pathway of its complete reduction to phenol and a secondary pathway of sequential reductive hydrogenolysis to 2,4-dichlorophenol (2,4-DCP), chlorophenol (2-CP, 4-CP) and phenol. About 65% of 2,4-D with initial concentration of 50 micro M was transformed within 48 h in the presence of 300 mg L(-1) nanoscale Fe(3)O(4), and the reaction rates increased with increasing dosage of nanoscale Fe(3)O(4). The decomposition of 2,4-D proceeded rapidly at optimum pH 3.0. Chloride was identified as a reduction product for 2,4-D in the magnetite-water system. Reductive transformation of 2,4-D by microscale Fe(3)O(4) was slower than that by nanoscale Fe(3)O(4). The reactions apparently followed pseudo-first-order kinetics with respect to the 2,4-D transformation. The degradation rate of 2,4-D decreased with the increase of initial 2,4-D concentration. In addition, anions had a significant adverse impact on the degradation efficiency of 2,4-D.