An efficient method for building a database of diatom populations for drowning site inference using a deep learning algorithm

A diagnostic strategy for pulmonary fat embolism based on routine H&E staining using computational pathology

Pulmonary fat embolism (PFE) as a cause of death often occurs in trauma cases such as fractures and soft tissue contusions. Traditional PFE diagnosis relies on subjective methods and special stains like oil red O. This study utilizes computational pathology, combining digital pathology and deep learning algorithms, to precisely quantify fat emboli in whole slide images using conventional hematoxylin-eosin (H&E) staining. The results demonstrate deep learning's ability to identify fat droplet morphology in lung microvessels, achieving an area under the receiver operating characteristic (ROC) curve (AUC) of 0.98. The AI-quantified fat globules generally matched the Falzi scoring system with oil red O staining. The relative quantity of fat emboli against lung area was calculated by the algorithm, determining a diagnostic threshold of 8.275% for fatal PFE. A diagnostic strategy based on this threshold achieved a high AUC of 0.984, similar to manual identification with special stains but surpassing H&E staining. This demonstrates computational pathology's potential as an affordable, rapid, and precise method for fatal PFE diagnosis in forensic practice.

A comparative assessment of time-consuming and laborious diatom analysis：Brief experimentation with suggestion of automatic identification

Diatom testing is considered a useful method for providing supportive evidence for the diagnosis of drowning in forensic pathology. However, various factors remain controversial for recognizing diatoms, such as being time-consuming and laborious and influencing the consistency of the results. Given the absence of precise and well-defined studies on this subject, this study aimed to determine the relationship between the ability to identify diatoms and researchers with different technical backgrounds. A total of 55 samples from 18 cases, including water, lungs, liver, and kidneys, were treated using the microwave digestion-vacuum filtration-automated scanning electron microscopy (MD-VF-Auto SEM), which was used to compare diatom analyses among three groups of well-trained forensic pathologists (FPs), trained junior employees (JEs), and new trainees (TEs). In addition to achieving similar accuracy of positive findings from drowning cases, counting efficiency was evaluated based on taxonomy records and counting time after viewing more than 5500 diatom images. In contrast to the higher counting efficiency of the JE group than that of the TE group, we observed a statistically significant difference (p < 0.05) in the diatom classification between these two groups. Based on our experiments, an efficient analysis for automatically identifying and classifying diatoms is urgently required.

Artificial intelligence-driven microbiome data analysis for estimation of postmortem interval and crime location

Microbial communities, demonstrating dynamic changes in cadavers and the surroundings, provide invaluable insights for forensic investigations. Conventional methodologies for microbiome sequencing data analysis face obstacles due to subjectivity and inefficiency. Artificial Intelligence (AI) presents an efficient and accurate tool, with the ability to autonomously process and analyze high-throughput data, and assimilate multi-omics data, encompassing metagenomics, transcriptomics, and proteomics. This facilitates accurate and efficient estimation of the postmortem interval (PMI), detection of crime location, and elucidation of microbial functionalities. This review presents an overview of microorganisms from cadavers and crime scenes, emphasizes the importance of microbiome, and summarizes the application of AI in high-throughput microbiome data processing in forensic microbiology.

Inference of drowning sites using bacterial composition and random forest algorithm

Diagnosing the drowning site is a major challenge in forensic practice, particularly when corpses are recovered from flowing rivers. Recently, forensic experts have focused on aquatic microorganisms, including bacteria, which can enter the bloodstream during drowning and may proliferate in corpses. The emergence of 16S ribosomal RNA gene (16S rDNA) amplicon sequencing has provided a new method for analyzing bacterial composition and has facilitated the development of forensic microbiology. We propose that 16S rDNA amplicon sequencing could be a useful tool for inferring drowning sites. Our study found significant differences in bacterial composition in different regions of the Guangzhou section of the Pearl River, which led to differences in bacteria of drowned rabbit lungs at different drowning sites. Using the genus level of bacteria in the lung tissue of drowned rabbits, we constructed a random forest model that accurately predicted the drowning site in a test set with 100% accuracy. Furthermore, we discovered that bacterial species endemic to the water were not always present in the corresponding drowned lung tissue. Our findings demonstrate the potential of a random forest model based on bacterial genus and composition in drowned lung tissues for inferring drowning sites.

DiatomNet v1.0: A novel approach for automatic diatom testing for drowning diagnosis in forensically biomedical application

BACKGROUND AND OBJECTIVE

Diatom testing is supportive for drowning diagnosis in forensic medicine. However, it is very time-consuming and labor-intensive for technicians to identify microscopically a handful of diatoms in sample smears, especially under complex observable backgrounds. Recently, we successfully developed a software, named DiatomNet v1.0 intended to automatically identify diatom frustules in a whole slide under a clear background. Here, we introduced this new software and performed a validation study to elucidate how DiatomNet v1.0 improved its performance with the influence of visible impurities.

METHODS

DiatomNet v1.0 has an intuitive, user-friendly and easy-to-learn graphical user interface (GUI) built in the Drupal and its core architecture for slide analysis including a convolutional neural network (CNN) is written in Python language. The build-in CNN model was evaluated for diatom identification under very complex observable backgrounds with mixtures of common impurities, including carbon pigments and sand sediments. Compared to the original model, the enhanced model following optimization with limited new datasets was evaluated systematically by independent testing and random control trials (RCTs).

RESULTS

In independent testing, the original DiatomNet v1.0 was moderately affected, especially when higher densities of impurities existed, and achieved a low recall of 0.817 and F1 score of 0.858 but good precision of 0.905. Following transfer learning with limited new datasets, the enhanced version had better results, with recall and F1 score values of 0.968. A comparative study on real slides showed that the upgraded DiatomNet v1.0 obtained F1 scores of 0.86 and 0.84 for carbon pigment and sand sediment, respectively, slightly worse than manual identification (carbon pigment: 0.91; sand sediment: 0.86), but much less time was needed.

CONCLUSIONS

The study verified that forensic diatom testing with aid of DiatomNet v1.0 is much more efficient than traditionally manual identification even under complex observable backgrounds. In terms of forensic diatom testing, we proposed a suggested standard on build-in model optimization and evaluation to strengthen the software's generalization in potentially complex conditions.

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.

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

The diatom test is a forensic technique that can provide supportive evidence in the diagnosis of drowning but requires the laborious observation and counting of diatoms using a microscopy with too much effort, and therefore it is promising to introduce artificial intelligence (AI) to make the test process automatic. In this article, we propose an artificial intelligence solution based on the YOLOv5 framework for the automatic detection and recognition of the diatom genera. To evaluate the performance of this AI solution in different scenarios, we collected five lab-grown diatom genera and samples of some organic tissues from drowning cases to investigate the potential upper/lower limits of the capability in detecting the diatoms and recognizing their genera. Based on the study of the article, a recall score of 0.95 together with the corresponding precision score of 0.9 were achieved on the samples of the five lab-grown diatom genera via cross-validation, and the accuracy of the evaluation in the cases of kidney and liver is above 0.85 based on the precision and recall scores, which demonstrate the effectiveness of the AI solution to be used in drowning forensic routine.