University of Twente Student Theses

Login

Artificial Intelligence driven assessment of asbestos exposed patients

Groot Lipman, K.B.W. (2020) Artificial Intelligence driven assessment of asbestos exposed patients.

Full text not available from this repository.

Full Text Status:Access to this publication is restricted
Embargo date:14 October 2022
Abstract:Even though asbestos has been banned for a long time, patients are still presenting with asbestos-related diseases due to the long incubation time. To assist clinicians in quantifying these diseases, we developed three AI models to assess asbestos-exposed patients. First, an AI model detected the morphological lung anomalies, where the model returns an anomaly heatmap. The results suggest that these methods can be employed to detect large morphological anomalies in the lungs. Second, we developed an AI model to classify asbestosis in patients, which yielded excellent diagnostic accuracy. The results suggest that the implementation of this model in the clinical setting could benefit the patient and clinicians in terms of reproducibility, consistency, and speed of the assessment of asbestosis. Clinical validation of this AI model is currently ongoing. Third, we developed an AI model for the automatic segmentation of the pleural plaques in CT scans to estimate the volume. The predicted volume showed a high correlation to expert readers' segmentation, but overlapping measures were lacking. We tested the relation between the lung function and the pleural plaque volume, which suggests that patients with a higher volume of plaques have a worse lung function.
Item Type:Essay (Master)
Faculty:TNW: Science and Technology
Subject:44 medicine, 50 technical science in general
Programme:Technical Medicine MSc (60033)
Link to this item:http://purl.utwente.nl/essays/84100
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page