Fatal obstructive asphyxia: Trans-pulmonary density gradient characteristic as relevant identifier in postmortem CT

To investigate effects of obstructive asphyxia on the postmortem computed tomography (PMCT) appearance of lungs, we matched 24 cases of obstructive asphyxia with age-sex matched controls. The initial qualitative impression was that obstructive asphyxia typically appeared to correlate with absence or reduced postmortem hypostasis as well as increased pulmonary radiotranslucency. Categories initially included within obstructive asphyxia were fatal aspiration of gastric contents into lungs, fatally blocked trachea or bronchi due to foreign body, fatal ligature strangulation, fatal manual strangulation and smothering. Method: We manually placed density profile vectors, with start at positionally dependent locations of each lung to derive PMCT densities for multivariate statistics. As fatal gastric content aspiration cases did not significantly differ from the controls, they were re-grouped into the control group for further testing. Results: Quantitatively, the obstructive asphyxia case group featured reduced or absent postmortem hypostasis in the lungs and an overall lower density. Linear multivariate statistics (general linear models, linear discriminant analysis) performed relatively poorly, whereas ”shallow” neural networks yielded significantly better discrimination. With disjunct training and test sets, neural networks achieved correct recognition rates (CRR) of obstructive asphyxia cases of over 95%. Conclusions: Within a more narrowly defined collective of obstructive asphyxia, pulmonary PMCT data appears to contain sufficient information to justify its use in a screening process. This questions the value of an exclusively death scene focused decision making for further investigations and may justify a wider use of PMCT. Conversely, obstructive asphyxia remains difficult to diagnose conclusively based on PMCT alone, so a full autopsy including toxicological analysis are recommended in such cases.