Analysis of different post mortem assessment methods for cerebral edema

Bauer, Melanie; Gerlach, Kathrin; Scheurer, Eva; Lenz, Claudia

doi:10.1016/j.forsciint.2020.110164

Cited by 6 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the refined process from W. Breakey et al [ 16 ], which showed fast and accurate results using CT images, a threshold was applied to all images using a range of 5 to 100 HU and smoothed using a 3D Gaussian kernel of 1 ( σ = 1 mm 3 ) and a fractional intensity of 0.35. The code performs a cranial segmentation, whereas the output of the pipeline is a binary segmentation mask and a dataset illustrating only the brain inside the skull, as also demonstrated by Bauer et al [ 17 ]. Since the FSL algorithm did perform some image processing (normalization, Gaussian blurring) on the CT images to support the segmentation process, the original values (in HU) were modified.…”

Section: Methodsmentioning

confidence: 99%

Automated detection of fatal cerebral haemorrhage in postmortem CT data

Zirn,

Scheurer,

Lenz

2024

Int J Legal Med

Self Cite

View full text Add to dashboard Cite

During the last years, the detection of different causes of death based on postmortem imaging findings became more and more relevant. Especially postmortem computed tomography (PMCT) as a non-invasive, relatively cheap, and fast technique is progressively used as an important imaging tool for supporting autopsies. Additionally, previous works showed that deep learning applications yielded robust results for in vivo medical imaging interpretation. In this work, we propose a pipeline to identify fatal cerebral haemorrhage on three-dimensional PMCT data. We retrospectively selected 81 PMCT cases from the database of our institute, whereby 36 cases suffered from a fatal cerebral haemorrhage as confirmed by autopsy. The remaining 45 cases were considered as neurologically healthy. Based on these datasets, six machine learning classifiers (k-nearest neighbour, Gaussian naive Bayes, logistic regression, decision tree, linear discriminant analysis, and support vector machine) were executed and two deep learning models, namely a convolutional neural network (CNN) and a densely connected convolutional network (DenseNet), were trained. For all algorithms, 80% of the data was randomly selected for training and 20% for validation purposes and a five-fold cross-validation was executed. The best-performing classification algorithm for fatal cerebral haemorrhage was the artificial neural network CNN, which resulted in an accuracy of 0.94 for all folds. In the future, artificial neural network algorithms may be applied by forensic pathologists as a helpful computer-assisted diagnostics tool supporting PMCT-based evaluation of cause of death.

show abstract

Section: Methodsmentioning

confidence: 99%

Automated detection of fatal cerebral haemorrhage in postmortem CT data

Zirn,

Scheurer,

Lenz

2024

Int J Legal Med

Self Cite

View full text Add to dashboard Cite

show abstract

Forensic Imaging: A New Subspeciality of Radiology

Grabherr¹,

Heinze

Scheurer

et al. 2022

Forensic Imaging

View full text Add to dashboard Cite

Forensic neuropathology in the past decade: a scoping literature review

Oura

Hakkarainen

Sajantila

2023

Forensic Sci Med Pathol

View full text Add to dashboard Cite

While there has been notable research activity in the field of clinical neuropathology over the recent years, forensic approaches have been less frequent. This scoping literature review explored original research on forensic neuropathology over the past decade (January 1, 2010, until February 12, 2022) using the MEDLINE database. The aims were to (1) analyze the volume of research on the topic, (2) describe meta-level attributes and sample characteristics, and (3) summarize key research themes and methods. Of 5053 initial hits, 2864 fell within the target timeframe, and 122 were included in the review. Only 3–17 articles were published per year globally. Most articles originated from the Europe (39.3%) and Asia (36.1%) and were published in forensic journals (57.4%). A median sample included 57 subjects aged between 16 and 80 years. The most common research theme was traumatic intracranial injury (24.6%), followed by anatomy (12.3%) and substance abuse (11.5%). Key methods included immunotechniques (31.1%) and macroscopic observation (21.3%). Although a number of novel findings were reported, most were of preliminary nature and will require further validation. In order to reach breakthroughs and validate novel tools for routine use, more research input is urged from researchers across the world. It would be necessary to ensure appropriate sample sizes and make use of control groups.

show abstract

Analysis of different post mortem assessment methods for cerebral edema

Cited by 6 publications

References 20 publications

Automated detection of fatal cerebral haemorrhage in postmortem CT data

Automated detection of fatal cerebral haemorrhage in postmortem CT data

Forensic Imaging: A New Subspeciality of Radiology

Forensic neuropathology in the past decade: a scoping literature review

Contact Info

Product

Resources

About