| Title: | Role of ventilation scintigraphy in diagnosis of acute pulmonary embolism. An evaluation using artificial neural networks |
| Fulltext: |  |
| Authors: | Evander, Eva and Holst, Holger and Järund, Andreas and Ohlsson, Mattias and Wollmer, Per and Åström, Kalle and Edenbrandt, Lars |
| Year: | 2003 |
| Publication: | Eur J Nucl Med Mol Imaging |
| Volume: | 30 |
| Issue: | 7 |
| Pages: | 961--965 |
| Document Type: | Journal Paper |
| Status: | Published |
| Refereed: | Yes |
| Keywords: | mage processing, Artificial neural net- works, Pulmonary embolism |
| Publisher: | Springer |
| BibTeX item: |  |
| Extra: | labib, lth-mc-mig |
| Abstract: | The purpose of this study was to assess the value of the ventilation study in the diagnosis of acute pulmonary embolism using a new automated method. Either perfusion scintigrams alone or two different com- binations of ventilation/perfusion scintigrams were used as the only source of information regarding pulmonary embolism. A completely automated method based on computerised image processing and artificial neural net- works was used for the interpretation. Three artificial neural networks were trained for the diagnosis of pulmo- nary embolism. Each network was trained with 18 auto- matically obtained features. Three different sets of fea- tures originating from three sets of scintigrams were used. One network was trained using features obtained from each set of perfusion scintigrams, including six projections. The second network was trained using fea- tures from each set of (joint) ventilation and perfusion studies in six projections. A third network was trained using features from the perfusion study in six projections combined with a single ventilation image from the poste- rior view. A total of 1,087 scintigrams from patients with suspected pulmonary embolism were used for network training. The test group consisted of 102 patients who had undergone both scintigraphy and pulmonary angiog- raphy. Performances in the test group were measured as area under the receiver operation characteristic curve. The performance of the neural network in interpreting perfusion scintigrams alone was 0.79 (95% confidence limits 0.71–0.86). When one ventilation image (posterior view) was added to the perfusion study, the performance was 0.84 (0.77–0.90). This increase was statistically sig- nificant (P=0.022). The performance increased to 0.87(0.81–0.93) when all perfusion and ventilation images were used, and the increase in performance from 0.79 to 0.87 was also statistically significant (P=0.016). The au- tomated method presented here for the interpretation of lung scintigrams shows a significant increase in perfor- mance when one or all ventilation images are added to the six perfusion images. Thus, the ventilation study has a significant role in the diagnosis of acute lung embo- lism. |
Similar Publications
- Conference paper:
An Automated System for Analysis of Renal Scintigraphy Images
Matilda Landgren
Karl Sjöstrand
Lars Edenbrandt - Conference paper:
Node Localization in Unsynchronized Time of Arrival Sensor Networks
Simon Burgess
Yubin Kuang
Kalle Åström - Conference paper:
An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images
Matilda Landgren
Karl Sjöstrand
Mattias Ohlsson
Daniel Ståhl
Niels Christian Overgaard
Kalle Åström
Rune Sixt
Lars Edenbrandt
Questions: webmaster
Last updated: 2012-01-17
Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Phone: 046-222 00 00