BloodNet: An attention-based deep network for accurate, efficient, and costless bloodstain time since deposition inference.

The time since deposition (TSD) of a bloodstain, i.e., the time of a bloodstain formation is an essential piece of biological evidence in crime scene investigation. The practical usage of some existing microscopic methods (e.g., spectroscopy or RNA analysis technology) is limited, as their performance strongly relies on high-end instrumentation and/or rigorous laboratory conditions. This paper presents a practically applicable deep learning-based method (i.e., BloodNet) for efficient, accurate, and costless TSD inference from a macroscopic view, i.e., by using easily accessible bloodstain photos. To this end, we established a benchmark database containing around 50,000 photos of bloodstains with varying TSDs. Capitalizing on such a large-scale database, BloodNet adopted attention mechanisms to learn from relatively high-resolution input images the localized fine-grained feature representations that were highly discriminative between different TSD periods. Also, the visual analysis of the learned deep networks based on the Smooth Grad-CAM tool demonstrated that our BloodNet can stably capture the unique local patterns of bloodstains with specific TSDs, suggesting the efficacy of the utilized attention mechanism in learning fine-grained representations for TSD inference. As a paired study for BloodNet, we further conducted a microscopic analysis using Raman spectroscopic data and a machine learning method based on Bayesian optimization. Although the experimental results show that such a new microscopic-level approach outperformed the state-of-the-art by a large margin, its inference accuracy is significantly lower than BloodNet, which further justifies the efficacy of deep learning techniques in the challenging task of bloodstain TSD inference. Our code is publically accessible via https://github.com/shenxiaochenn/BloodNet. Our datasets and pre-trained models can be freely accessed via https://figshare.com/articles/dataset/21291825.

An Emerging Strategy for Muscle Evanescent Trauma Discrimination by Spectroscopy and Chemometrics.

Trauma is one of the most common conditions in the biomedical field. It is important to identify it quickly and accurately. However, when evanescent trauma occurs, it presents a great challenge to professionals. There are few reports on the establishment of a rapid and accurate trauma identification and prediction model. In this study, Fourier transform infrared spectroscopy (FTIR) and microscopic spectroscopy (micro-IR) combined with chemometrics were used to establish prediction models for the rapid identification of muscle trauma in humans and rats. The results of the average spectrum, principal component analysis (PCA) and loading maps showed that the differences between the rat muscle trauma group and the rat control group were mainly related to biological macromolecules, such as proteins, nucleic acids and carbohydrates. The differences between the human muscle trauma group and the human control group were mainly related to proteins, polysaccharides, phospholipids and phosphates. Then, a partial least squares discriminant analysis (PLS-DA) was used to evaluate the classification ability of the training and test datasets. The classification accuracies were 99.10% and 93.69%, respectively. Moreover, a trauma classification and recognition model of human muscle tissue was constructed, and a good classification effect was obtained. The classification accuracies were 99.52% and 91.95%. In conclusion, spectroscopy and stoichiometry have the advantages of being rapid, accurate and objective and of having high resolution and a strong recognition ability, and they are emerging strategies for the identification of evanescent trauma. In addition, the combination of spectroscopy and stoichiometry has great potential in the application of medicine and criminal law under practical conditions.

Ante- and Post-Mortem Fracture Identification Protocol Based on Low- and High-Level Fusion Using Fourier Transform Infrared Spectroscopy and Raman Spectroscopy Association.

In this study, the application of low-level fusion (LLF) and high-level fusion (HLF) strategies using a combination of Fourier transform infrared spectroscopy (FT-IR) and Raman spectroscopy in the identification of antemortem and postmortem fracture at different postmortem intervals (PMIs) was investigated. On a technical level, the same hard tissue sample can be detected using a mix of FT-IR and Raman techniques. At the method level, two cutting-edge chemometrics approaches (LLF and HLF) combining FT-IR and Raman spectroscopic data are explored. The models were ranked in accordance with their parametric quality as follows: HLF and LLF + HLF models > LLF single model > Raman single model > FT-IR single model. The LLF model performed marginally better than the Raman model, however, when compared to other models, the HLF model performed considerably better. The HLF model achieved the best performance, with both cross-validation accuracy and test data set accuracy of 0.88. The importance of the feature wavelengths in the model construction process was subsequently evaluated by intersection fusion, and it was found that the absorbance bands of amide I, PO43- ν1 ν3, and CH2 in FT-IR and phenylalanine, CO32- ν1- PO43- ν3, and amide III in Raman have outstanding contributions to the construction of antemortem and postmortem fractures identification models. Overall, the combination of FT-IR and Raman with the HLF strategy is a novel and promising approach for developing antemortem and postmortem fracture identification models at different PMIs.

Accurate identification of traumatic lung injury (TLI) by ATR-FTIR spectroscopy combined with chemometrics.

Traumatic lung injury (TLI), which is a common mechanical injury, is receiving increasing attention because of its serious hazards. In forensic practices, accurately identifying TLI is of great importance for investigations and case trials. The main goal of this research was to identify TLI utilizing attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy in combination with chemometrics. The macroscopic appearance of lung tissue showed that identifying TLI in lung tissue at the decomposition stage is not feasible by only visualization, and significant pulmonary hypostasis was observed in the lungs regardless of whether the lung tissue was injured. Average spectra and principal component analysis (PCA) suggested that the biochemical difference between injured lung tissue samples from the TLI group and noninjured lung tissue samples from the negative control group was mainly attributed to the different structures and contents of proteins. Partial least squares discriminant analysis (PLS-DA) was then utilized to identify TLI with an accuracy of 96.4% and 98.6% based on the training set and the test set, respectively. Next, we focused on samples that were misclassified in the model and proposed that the misclassification could be caused by the pulmonary hypostasis effect. Therefore, two additional PCA and PLS-DA models were created to identify the pulmonary hypostatic areas between the TLI group and the negative control group and the nonpulmonary hypostatic areas between the TLI group and the negative control group. The PCA results indicated that the biochemical difference between the two groups was still associated with proteins, and the two PLS-DA models achieved 100% accuracy based on both the training and test sets. This result indicated that when pulmonary hypostasis was considered and the lung tissue was divided into pulmonary hypostatic areas and nonpulmonary hypostatic areas for separate comparisons, TLI identification was achieved with a greater accuracy than that obtained when the two areas were combined. This research confirms that the combined application of ATR-FTIR spectroscopy and chemometrics can be utilized to accurately identify TLI.

Pathological and ATR-FTIR spectral changes of delayed splenic rupture and medical significance.

Traumatic delayed splenic rupture often follows by a "latent period" without typical symptoms after injury. During this period, though there are no obvious symptoms, the injury is still present and changing. In this study, we constructed an SD rat model of delayed splenic rupture; evaluated the model by HE staining, Perl's staining, Masson trichrome staining and immunohistochemical staining; observed the pathological changes of spleen tissue in delayed splenic rupture at different times after splenic injury; we found that pathological change of injured tissues were different from non-injured, and has phases-change patterns, it can be roughly divided into three phases: 2-7 d, 10-14 d, and 18-28.We then investigated the relationship between the pathological changes and FTIR spectroscopy by chemometric methods. The main distinction of injured and non-injured tissue was the protein secondary structure of amide I, and the main distinctions of different phases of delayed splenic rupture were protein secondary structures and content of amide I and amide II.A classification model developed by SVM-DA was used to infer three phases (2-7 days, 10-12 days and 14-28 days). According to the most probable class, the accuracy of external validation is 96.7%. The results indicate that FTIR spectroscopy combined with various types of pathological staining has a potential for forensic identification and can provide theoretical support and diagnostic reference on clinical persistent injury.