An improved automated diatom detection method based on YOLOv5 framework and its preliminary study for taxonomy recognition in the forensic diatom test

U2-Net and ResNet50-Based Automatic Pipeline for Bacterial Colony Counting

In this paper, an automatic colony counting system based on an improved image preprocessing algorithm and convolutional neural network (CNN)-assisted automatic counting method was developed. Firstly, we assembled an LED backlighting illumination platform as an image capturing system to obtain photographs of laboratory cultures. Consequently, a dataset was introduced consisting of 390 photos of agar plate cultures, which included 8 microorganisms. Secondly, we implemented a new algorithm for image preprocessing based on light intensity correction, which facilitated clearer differentiation between colony and media areas. Thirdly, a U2-Net was used to predict the probability distribution of the edge of the Petri dish in images to locate region of interest (ROI), and then threshold segmentation was applied to separate it. This U2-Net achieved an F1 score of 99.5% and a mean absolute error (MAE) of 0.0033 on the validation set. Then, another U2-Net was used to separate the colony region within the ROI. This U2-Net achieved an F1 score of 96.5% and an MAE of 0.005 on the validation set. After that, the colony area was segmented into multiple components containing single or adhesive colonies. Finally, the colony components (CC) were innovatively rotated and the image crops were resized as the input (with 14,921 image crops in the training set and 4281 image crops in the validation set) for the ResNet50 network to automatically count the number of colonies. Our method achieved an overall recovery of 97.82% for colony counting and exhibited excellent performance in adhesion classification. To the best of our knowledge, the proposed "light intensity correction-based image preprocessing→U2-Net segmentation for Petri dish edge→U2-Net segmentation for colony region→ResNet50-based counting" scheme represents a new attempt and demonstrates a high degree of automation and accuracy in recognizing and counting single-colony and multi-colony targets.

Validation and optimization of the diatom L/D ratio as a diagnostic marker for drowning

If a dead body is discovered in water, it nearly always raises the question about the cause of death, often associated with the persistent problem to differentiate between a drowning incident and post-mortem immersion. In numerous cases, a reliable confirmation of death by drowning is often only possible by a combination of diagnoses obtained from autopsy and additional investigations. As to the latter, the use of diatoms has been suggested (and debated) since decades. Based on the consideration that diatoms are present in almost every natural waterbody and are unavoidably incorporated when water is inhaled, their presence in the lung and other tissues can provide evidence of drowning. However, the traditional diatom test methods are still subject of controversial discussion and suspected of erroneous outcome, predominantly through contamination. A promising alternative to minimize the risk of erroneous outcome seems to be disclosed by the recently suggested MD-VF-Auto SEM technique. Especially the establishment of a new diagnostic marker (L/D ratio), which represents the factorial proportion between the diatom concentration in lung tissue and the drowning medium, allows for clearer distinction of drowning and post-mortal immersion and is largely robust to contamination. However, this highly elaborated technique requires specific devices which are frequently unavailable. We therefore developed a modified method of SEM-based diatom testing to enable the use on more routinely available equipment. Process steps such as digestion, filtration, and image acquisition were thoroughly broken down, optimized, and ultimately validated in five confirmed drowning cases. Taking certain limitations into consideration, L/D ratio analysis provided promising results, even in cases of advanced decomposition. We conclude that our modified protocol indeed opens a way for a broader use of the method in forensic drowning investigation.

Apple-Net: A Model Based on Improved YOLOv5 to Detect the Apple Leaf Diseases

Effective identification of apple leaf diseases can reduce pesticide spraying and improve apple fruit yield, which is significant to agriculture. However, the existing apple leaf disease detection models lack consideration of disease diversity and accuracy, which hinders the application of intelligent agriculture in the apple industry. In this paper, we explore an accurate and robust detection model for apple leaf disease called Apple-Net, improving the conventional YOLOv5 network by adding the Feature Enhancement Module (FEM) and Coordinate Attention (CA) methods. The combination of the feature pyramid and pan in YOLOv5 can obtain richer semantic information and enhance the semantic information of low-level feature maps but lacks the output of multi-scale information. Thus, the FEM was adopted to improve the output of multi-scale information, and the CA was used to improve the detection efficiency. The experimental results show that Apple-Net achieves a higher mAP@0.5 (95.9%) and precision (93.1%) than four classic target detection models, thus proving that Apple-Net achieves more competitive results on apple leaf disease identification.