Classifying Microscopic Acute and Old Myocardial Infarction Using Convolutional Neural Networks.

ABSTRACT: Convolutional neural network (CNN) has advanced in recent years and translated from research into medical practice, most notably in clinical radiology and histopathology. Research on CNNs in forensic/postmortem pathology is almost exclusive to postmortem computed tomography despite the wealth of research into CNNs in surgical/anatomical histopathology. This study was carried out to investigate whether CNNs are able to identify and age myocardial infarction (a common example of forensic/postmortem histopathology) from histology slides. As a proof of concept, this study compared 4 CNNs commonly used in surgical/anatomical histopathology to identify normal myocardium from myocardial infarction. A total of 150 images of the myocardium (50 images each for normal myocardium, acute myocardial infarction, and old myocardial infarction) were used to train and test each CNN. One of the CNNs used (InceptionResNet v2) was able to show a greater than 95% accuracy in classifying normal myocardium from acute and old myocardial infarction. The result of this study is promising and demonstrates that CNN technology has potential applications as a screening and computer-assisted diagnostics tool in forensic/postmortem histopathology.

Hemorrhagic Pseudocyst: A Rare Cerebral Mass Lesion Causing Death. A Case Report and Brief Review of Literature.

ABSTRACT: Mass lesions in the brain encompass a wide range neoplastic and nonneoplastic entities. These can present as a diagnostic pitfall, with nonspecific, overlapping symptoms and similar appearances on radiology. They may cause death through varied mechanisms, either specific to the underlying pathophysiology or due to the space-occupying effect of the lesion. We report a case of fatal hemorrhagic cerebral pseudocyst, a rare mass lesion, associated with a cerebral varix, causing death in a morbidly obese individual. To the best of our knowledge, there is no previous documentation in the postmortem literature of this entity as a cause of death. This case aims to document this rare entity in the differential diagnosis of a tumor-like lesion in the brain, highlight the clinical difficulty in its assessment, and demonstrate an uncommon mechanism of death, of a mass lesion acting as a focus causing seizures, with resulting hypoxia due to effects of morbid obesity and heart failure.

Phlegmonous Psoas Muscle Infection Causing Sepsis and Death With Missing Postmortem Computed Tomography Scan Correlation.

ABSTRACT: Infection of the psoas muscle is a rare pathology, which carries a high risk of sepsis and is a potential cause of death. Classic symptoms include back pain and fever and it may be diagnosed premortem on computed tomography or magnetic resonance imaging, where abscess formation may be identified as a discrete rim enhancing and low-attenuation lesion. Infections without abscess formation, such as phlegmonous infection, may be more difficult to identify however, particularly if there is absence of other nonspecific findings, such as gas bubbles. We report a case of Staphylococcus aureus phlegmonous psoas muscle causing sepsis and death with no postmortem computed tomography scan correlation, where clinical history of back pain and an unknown source of sepsis was the only prompt for psoas dissection. This case highlights a potential postmortem computed tomography blind spot in abdominal pathology and we recommend dissecting the psoas muscle if sepsis is suspected but a definitive septic focus is unable to be identified.

Identifying gross post-mortem organ images using a pre-trained convolutional neural network.

Identifying organs/tissue and pathology on radiological and microscopic images can be performed using convolutional neural networks (CNN). However, there are scant studies on applying CNN to post-mortem gross images of visceral organs. This proof-of-concept study used 537 gross post-mortem images of dissected brain, heart, lung, liver, spleen, and kidney, which were randomly divided into a training and teaching datasets for the pre-trained CNN Xception. The CNN was trained using the training dataset and subsequently tested on the testing dataset. The overall accuracies were >95% percent for both training and testing datasets and have an F1 score of >0.95 for all dissected organs. This study showed that small datasets of post-mortem images can be classified with a very high accuracy using a pre-trained CNN. This novel area has the potential for future application in data mining, education and teaching, case review, research, quality assurance, auditing purposes, and identifying pathology.

Combining Postmortem Cerebrospinal Fluid Biochemistry With Lung-to-Body Ratio to Aid the Diagnosis of Salt Water Drowning.

Diagnosing drowning as a cause of death can pose many challenges for the forensic pathologist and a number of ancillary tests have been proposed to assist in the diagnosis, whether the body was in salt water or fresh water. Although elevated vitreous humor sodium and chloride is a reliable marker, its limitation to prolonged immersion has resulted in the recent investigation of cerebrospinal fluid (CSF) sodium and chloride as alternative matrix in cases of longer or unknown immersion times. This study investigated postmortem CSF from lumbar puncture (CSF_L_Na_Cl) and ventricular aspiration (CSF_Vent_Na_Cl), as well as lung/body (LB) ratio in the diagnosis of salt water drowning and performed comparison and combination testing of methods to improve diagnostic accuracy of the drowning diagnosis. This study found that CSF_L_Na_Cl was the most accurate method (89%) in the given cohort, but that CSF_Vent_Na_Cl and LB combined was the second most accurate method (83%), exceeding CSF_Vent_Na_Cl (77%) and LB (81%) used alone. These findings are useful for stratifying and prioritizing postmortem samples in the investigation of salt water drowning and also have significance for future studies using this methodology to combine and compare the accuracy of different investigations.

Public perceptions of comparative effectiveness research and use of evidence in healthcare decision-making.

AIMS: This study elaborates on the public's understanding of comparative effectiveness research (CER) or patient-centered outcomes research (PCOR), attitudes toward CER/PCOR and use of evidence in healthcare decision-making. MATERIALS & METHODS: We conducted six focus groups with the general public - three with individuals actively engaged in healthcare decision-making and three with individuals more passive in their approach. RESULTS: The general public has little knowledge of CER/PCOR, and its perceptions of certain CER/PCOR concepts are inconsistent with those of researchers and policy-makers. Active healthcare consumers value information more than passive consumers and are likely to use evidence in decision-making. CONCLUSION: Providers are an important source for disseminating and communicating CER/PCOR evidence to active and passive consumers.

Enzymes and metabolites of cysteine metabolism in nonhepatic tissues of rats show little response to changes in dietary protein or sulfur amino acid levels.

In liver, cysteine dioxygenase (CDO), cysteinesulfinate decarboxylase (CSD), and gamma-glutamylcysteine synthetase (GCS) play important regulatory roles in the metabolism of cysteine to sulfate, taurine and glutathione. Because glutathione is released by the liver and degraded by peripheral tissues that express gamma-glutamyl transpeptidase, some peripheral tissues may be exposed to relatively high concentrations of cysteine. Rats were fed diets that contained low, moderate or high concentrations of protein or supplemental cysteine or methionine for 2 wk, and CDO, CSD and GCS activities, concentrations and mRNA levels and the concentrations of cysteine, taurine and glutathione were measured in liver, kidney, lung and brain. All three enzymes in liver responded to the differences in dietary protein or sulfur amino acid levels, but only CSD in kidney and none of the three enzymes in lung and brain responded. Renal CSD activity was twice as much in rats fed the low protein diet as in rats fed the other diets. Changes in renal CSD activity were correlated with changes in CSD concentration. Some significant differences in cysteine concentration in kidney and lung and glutathione and taurine concentrations in kidney were observed, with higher concentrations in rats fed higher levels of protein or sulfur amino acids. In liver, the changes in cysteine level were consistent with cysteine-mediated regulation of hepatic CDO activity, and changes in taurine level were consistent with predicted changes in cysteine catabolism due to the changes in cysteine concentration and CDO activity. Changes in renal and lung cysteine, taurine or glutathione concentrations were not associated with a similar pattern of change in CDO, CSD or GCS activity. Overall, the results confirm the importance of the liver in the maintenance of cysteine homeostasis.