Deep learning for asbestos counting.

The PCM (phase contrast microscopy) method for asbestos counting needs special sample treatments, hence it is time consuming and rather expensive. As an alternative, we implemented a deep learning procedure on images directly acquired from the untreated airborne samples using standard Mixed Cellulose Ester (MCE) filters. Several samples with a mix of chrysotile and crocidolite with different concentration loads have been prepared. Using a 20x objective lens coupled with a backlight illumination system a number of 140 images were collected from these samples, which along with additional 13 highly fibre loaded artificial images constituted the database. About 7500 fibres were manually recognised and annotated following the National Institute for Occupational Safety and Health (NIOSH) fibre counting Method 7400 as input for the training and validation of the model. The best trained model provides a total precision of 0.84 with F1-Score of 0.77 at a confidence of 0.64. A further post-detection refinement to ignore detected fibres < 5 µm in length improves the final precision. This method can be considered as a reliable and competent alternative to conventional PCM.

Asbestos in soil and water: A review of analytical techniques and methods.

In this review the main standard and novel analytical techniques and methods for sampling, sample preparation, detection and quantification of asbestos in soil and water are described, compared and discussed in terms of advantages and limitations. An overview of common analytical methods applied for identification and quantification of airborne asbestos is preliminary provided, as they have been widely studied, due to the well-known human pathologies related to fibers inhalation. Despite the presence of asbestos in soil and water may also constitute a health risk, it has been less investigated and regulated. For these environmental matrices, the methods adopted at international and national scale, covering the whole analytical process, from sampling to management of data, are reported in depth, highlighting their limitations like sensitivity, reliability and reproducibility. Finally, different promising novel/unconventional methods, that may substitute or support traditional ones for asbestos detection both in environmental and anthropic matrices, are presented and critically evaluated.

Classification and management of asbestos-containing waste: European legislation and the Italian experience.

OBJECTIVE: Production of a new classification of Asbestos Containing Products (ACPs), materials (ACM) and Asbestos Containing Waste (ACW), in addition to a correct identification of landfills where ACW should be disposed of in Europe. METHODS: Analysis of the European and Italian legislation, study of waste classification and management in the main European countries, data analysis of mapping of Italian landfills and quantification of ACW disposed there. FINDINGS: Classification according to unique criteria (physical state, substances with which asbestos minerals have been blended, function of the asbestos, etc.). Highlights of cases of incorrect management of ACW in Europe, specifying the Italian ones. Considering the significant inconsistencies between the European and national regulations and the actual implementation of those regulations, this paper provide some precise indications for the proper assignment to ACW of the European Waste Catalogue (EWC) codes. Lastly, suitable types of landfills at which ACW should be disposed of have been identified, in order to assisting the persons involved in ACW management to avoid undue exposition and their improper disposal. CONCLUSION: This study reports a useful manual for classifying worldwide ACPs based on their physical state and considering the substances with which the asbestos minerals have been blended. Moreover several clear tables allow the asbestos remediation and waste management operators to suitably classify and dispose of ACW.