1. |
|
|
2. |
- Holst, Holger, et al.
(author)
-
An independent evaluation of a new method for automated interpretation of lung scintigrams using artificial neural networks
- 2001
-
In: European Journal Of Nuclear Medicine. - : Springer Science and Business Media LLC. - 0340-6997 .- 1619-7089. ; 28:1, s. 33-38
-
Journal article (peer-reviewed)abstract
- The purpose of this study was to evaluate a new automated method for the interpretation of lung perfusion scintigrams using patients from a hospital other than that where the method was developed, and then to compare the performance of the technique against that of experienced physicians. A total of 1,087 scintigrams from patients with suspected pulmonary embolism comprised the training group. The test group consisted of scintigrams from 140 patients collected in a hospital different to that from which the training group had been drawn. An artificial neural network was trained using 18 automatically obtained features from each set of perfusion scintigrams. The image processing techniques included alignment to templates, construction of quotient images based on the perfusion/template images, and finally calculation of features describing segmental perfusion defects in the quotient images. The templates represented lungs of normal size and shape without any pathological changes. The performance of the neural network was compared with that of three experienced physicians who read the same test scintigrams according to the modified PIOPED criteria using, in addition to perfusion images, ventilation images when available and chest radiographs for all patients. Performances were measured as area under the receiver operating characteristic curve. The performance of the neural network evaluated in the test group was 0.88 (95% confidence limits 0.81–0.94). The performance of the three experienced experts was in the range 0.87–0.93 when using the perfusion images, chest radiographs and ventilation images when available. Perfusion scintigrams can be interpreted regarding the diagnosis of pulmonary embolism by the use of an automated method also in a hospital other than that where it was developed. The performance of this method is similar to that of experienced physicians even though the physicians, in addition to perfusion images, also had access to ventilation images for most patients and chest radiographs for all patients. These results show the high potential for the method as a clinical decision support system.
|
|
3. |
|
|
4. |
- Måre, Klas, 1942-, et al.
(author)
-
Quality assurance system feedback
- 2001
-
In: Röntgenveckan i Umeå 20-24 augusti 2001,2001. ; , s. 29-30
-
Conference paper (peer-reviewed)
|
|
5. |
- Nilsson, Tage, et al.
(author)
-
Value of structured clinical and scintigraphic protocols in acute pulmonary embolism
- 2001
-
In: Journal of Internal Medicine. - : Wiley. - 0954-6820 .- 1365-2796. ; 250:3, s. 213-218
-
Journal article (peer-reviewed)abstract
- Purpose. To study the use of a combination of a clinical and scintigraphic protocol in relation to the final outcome diagnosis in patients with clinical suspicion of acute pulmonary embolism (PE). Material and methods. A total of 170 patients with clinical suspicion of acute PE were all examined with ECG, blood chemistry, chest X-ray, pulmonary scintigraphy and selective pulmonary arteriography. The scintigraphic and clinical probabilities of PE were estimated on visual analogue scales (VASs) by different readers unaware of each others' results. The follow-up time was 6 months. In order to establish the final diagnosis a final outcome committee was created. They analysed in retrospect all the clinical and laboratory data and established whether the patient had had PE or not. Results. The final outcome committee concluded that 53 patients had PE. When the scintigraphic and clinical probability judgements were congruent, a combined probability of 1-25% (i.e low probability) had a negative predictive value of 98%. When the combined probability was 26-75% (i.e. intermediate) half of the cases had PE. With a combined probability of 76-100% (i.e. high) the positive predictive value was 100%. Conclusion. By applying a model of combined clinical and scintigraphic probabilities for PE, the diagnosis is ruled in when the combined probability is high, and ruled out when the combined probability is low. However, nearly half of the patients will still have an uncertain diagnosis for which further diagnostic procedures may be allocated.
|
|
6. |
|
|