Background characteristics and neuropathology findings of medico-legal autopsy cases with and without ß-amyloid precursor protein positive diffuse traumatic axonal injury.

The postmortem diagnosis of diffuse traumatic axonal injury (dTAI) relies on ß-amyloid precursor protein (ß-APP) immunohistochemistry. Most reports of factors associating with dTAI are decades old. We compared background characteristics and neuropathology findings of today's Finnish medico-legal autopsy cases with and without ß-APP-positive dTAI (dTAI+ and dTAI-, respectively). The cases had suffered a head injury prior to death and underwent a full neuropathological examination including ß-APP stain. Background and circumstantial data as well as neuropathology findings were collected from police documents, medical records, and autopsy and neuropathology reports. Prevalence ratios were calculated for each factor to facilitate comparisons between the dTAI+ and dTAI- groups. The dataset comprised 57 cases (66.7% males), with 17 classified as dTAI+ and 40 as dTAI-. Based on prevalence ratios, the factors that had at least two-fold prevalence among dTAI+ cases compared to dTAI- cases were: an unknown injury mechanism; concurrent epidural or subdural haemorrhage; and an accidental manner of death. In contrast, the factors that had at least two-fold prevalence among dTAI- cases compared to dTAI+ cases were: a short postinjury survival (<30 min); concurrent intracerebral/ventricular haemorrhage or contusion; vermal atrophy; and a natural or homicidal manner of death. This study revealed differences in circumstantial features and neuropathology findings between dTAI+ and dTAI- cases in today's medico-legal autopsy material. Data on typical case profiles may help estimate the prior probability of dTAI not only in medico-legal autopsies but also among living patients with head injuries.

Deep Learning Neural Network-Guided Detection of Asbestos Bodies in Bronchoalveolar Lavage Samples.

INTRODUCTION: Asbestos is a global occupational health hazard, and exposure to it by inhalation predisposes to interstitial as well as malignant pulmonary morbidity. Over time, asbestos fibers embedded in lung tissue can become coated with iron-rich proteins and mucopolysaccharides, after which they are called asbestos bodies (ABs) and can be detected in light microscopy (LM). Bronchoalveolar lavage, a cytological sample from the lower airways, is one of the methods for diagnosing lung asbestosis and related morbidity. Search for ABs in these samples is generally laborious and time-consuming. We describe a novel diagnostic method, which implements deep learning neural network technology for the detection of ABs in bronchoalveolar lavage samples (BALs). METHODS: BALs with suspicion of asbestos exposure were scanned as whole slide images (WSIs) and uploaded to a cloud-based virtual microscopy platform with a neural network training interface. The images were used for training and testing a neural network model capable of recognizing ABs. To prioritize the model's sensitivity, we allowed it to also make false-positive suggestions. To test the model, we compared its performance to standard LM diagnostic data as well as the ground truth (GT) number of ABs, which we established by a thorough manual search of the WSIs. RESULTS: We were able to reach overall sensitivity of 93.4% (95% CI: 90.3-95.7%) in the detection of ABs in comparison to their GT number. Compared to standard LM diagnostic data, our model showed equal to or higher sensitivity in most cases. CONCLUSION: Our results indicate that deep learning neural network technology offers promising diagnostic tools for routine assessment of BALs. However, at this stage, a human expert is required to confirm the findings.