Mapping homicide by 3-D modelling of bloodstain patterns at crime scene

Кислов, М. А.; Chauhan, Mohit; Khanna, Sunil K.; Leonov, Sergey V.; Леонова, Е. Н.; Nagornov, M N; Berezovsky, Berezovskiy D; Lomakin, Yurij V; Bychkov, A A; Stepanov, S A; Krupin, Konstantin; Sergeevna, ZM

doi:10.1177/00258172221145782

Cited by 1 publication

(1 citation statement)

References 7 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The microscopic evaluation for the differentiation of human blood cells from other species is a laborious task, and it requires the services of highly qualified health professionals. The rising demand and deficiency of experts in this field create an opportunity for application of the artificial intelligence [9,10]. The application of artificial intelligence in this field of medicine could be helpful in improving the quality of results and may also reduce error possibilities attributed to human factors.…”

Section: Introductionmentioning

confidence: 99%

The Evaluation of Artificial Intelligence Technology for the Differentiation of Fresh Human Blood Cells From Other Species Blood in the Investigation of Crime Scenes

Shah,

Elmorsy,

Othman

et al. 2024

Cureus

View full text Add to dashboard Cite

Objectives: The current study used the deep machine learning approach to differentiate human blood specimens from cow, goat, and chicken blood stains based on cell morphology. Methods: A total of 1,955 known Giemsa-stained digitized images were acquired from the blood of humans, cows, goats, and chickens. To train the deep learning models, the well-known VGG16, Resnet18, and Resnet34 algorithms were used. Based on the image analysis, confusion matrices were generated.Results: Findings showed that the F1 score for the chicken, cow, goat, and human classes were all equal to 1.0 for each of the three algorithms. The Matthews correlation coefficient (MCC) was 1 for chickens, cows, and humans in all three algorithms, while the MCC score was 0.989 for goats by ResNet18, and it was 0.994 for both ResNet34 and VGG16 algorithms. The three algorithms showed 100% sensitivity, specificity, and positive and negative predictive values for the human, cow, and chicken cells. For the goat cells, the data showed 100% sensitivity and negative predictive values with specificity and positive predictive values ranging from 98.5% to 99.6%. Conclusion: These data showed the importance of deep learning as a potential tool for the differentiation of the species of origin of fresh crime scene blood stains.

show abstract

Section: Introductionmentioning

confidence: 99%