[Detection of white blood cells in microscopic leucorrhea images based on deep active learning]

[An improved Vision Transformer model for the recognition of blood cells]

Leukemia is a common, multiple and dangerous blood disease, whose early diagnosis and treatment are very important. At present, the diagnosis of leukemia heavily relies on morphological examination of blood cell images by pathologists, which is tedious and time-consuming. Meanwhile, the diagnostic results are highly subjective, which may lead to misdiagnosis and missed diagnosis. To address the gap above, we proposed an improved Vision Transformer model for blood cell recognition. First, a faster R-CNN network was used to locate and extract individual blood cell slices from original images. Then, we split the single-cell image into multiple image patches and put them into the encoder layer for feature extraction. Based on the self-attention mechanism of the Transformer, we proposed a sparse attention module which could focus on the discriminative parts of blood cell images and improve the fine-grained feature representation ability of the model. Finally, a contrastive loss function was adopted to further increase the inter-class difference and intra-class consistency of the extracted features. Experimental results showed that the proposed module outperformed the other approaches and significantly improved the accuracy to 91.96% on the Munich single-cell morphological dataset of leukocytes, which is expected to provide a reference for physicians' clinical diagnosis.

Medical Image Recognition Technology in the Effect of Substituting Soybean Meal for Fish Meal on the Diversity of Intestinal Microflora in Channa argus

Purpose

To study the application of medical image recognition technology based on backpropagation neural network (BPNN) in the effect of soybean meal replacing fish meal on intestinal microbial diversity of Channa argus and to evaluate the application value of this intelligent algorithm, Channa argus was fed with different contents of soybean meal instead of fish meal.

Methods

After intestinal samples were collected and bacteria were isolated, microscopic imaging was performed, and the images were classified and identified. BPNN was constructed to perform denoising, smoothing, and segmentation.

Results

After BPNN processing, the bacteria were completely separated from the original image background, and the bacteria was in the closed state, which was beneficial to feature extraction and species recognition. If there were 2 hidden layer nodes, the segmentation accuracy of bacterial microscopic images was the highest, up to 97.3%. With the replacement ratio of fish meal increased, the species of intestinal microbiome gradually enriched, and the relative abundance of intestinal microbiome was higher after fish meal was completely replaced by soybean meal (replacement). The intestinal microbial enzyme activities were affected by different fish meal and soybean meal contents in the diet. The glutamate transaminase and adenosine deaminase activities were increased after the replacement and were higher than those before the replacement, with statistically significant differences (P < 0.05).

Conclusion

Replacement of fish meal with soybean meal has a significant effect on the intestinal flora diversity of Channa argus, and there is a close relationship between them. The image recognition technology based on BPNN has high recognition rate and segmentation accuracy for microbiological microscopic images.