| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Haenssle, H A, et al.
(författare)
-
Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.
- 2018
-
Ingår i: Annals of Oncology. - : Elsevier BV. - 1569-8041 .- 0923-7534. ; 29:8, s. 1836-1842
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking.Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge.In level-I dermatologists achieved a mean (±standard deviation) sensitivity and specificity for lesion classification of 86.6% (±9.3%) and 71.3% (±11.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (±9.6%, P=0.19) and specificity to 75.7% (±11.7%, P<0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P<0.01) and level-II (75.7%, P<0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P<0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge.For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists were outperformed by the CNN. Irrespective of any physicians' experience, they may benefit from assistance by a CNN's image classification.This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; https://www.drks.de/drks_web/).
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
- Fiath, Richard, et al.
(författare)
-
Large-scale recording of thalamocortical circuits : in vivo electrophysiology with the two-dimensional electronic depth control silicon probe
- 2016
-
Ingår i: Journal of Neurophysiology. - : American Physiological Society. - 0022-3077 .- 1522-1598. ; 116:5, s. 2312-2330
-
Tidskriftsartikel (refereegranskat)abstract
- Recording simultaneous activity of a large number of neurons in distributed neuronal networks is crucial to understand higher order brain functions. We demonstrate the in vivo performance of a recently developed electrophysiological recording system comprising a two-dimensional, multi-shank, high-density silicon probe with integrated complementary metal-oxide semiconductor electronics. The system implements the concept of electronic depth control (EDC), which enables the electronic selection of a limited number of recording sites on each of the probe shafts. This innovative feature of the system permits simultaneous recording of local field potentials (LFP) and single-and multiple-unit activity (SUA and MUA, respectively) from multiple brain sites with high quality and without the actual physical movement of the probe. To evaluate the in vivo recording capabilities of the EDC probe, we recorded LFP, MUA, and SUA in acute experiments from cortical and thalamic brain areas of anesthetized rats and mice. The advantages of large-scale recording with the EDC probe are illustrated by investigating the spatiotemporal dynamics of pharmacologically induced thalamocortical slow-wave activity in rats and by the two-dimensional tonotopic mapping of the auditory thalamus. In mice, spatial distribution of thalamic responses to optogenetic stimulation of the neocortex was examined. Utilizing the benefits of the EDC system may result in a higher yield of useful data from a single experiment compared with traditional passive multielectrode arrays, and thus in the reduction of animals needed for a research study.
|
|
| 11. |
|
|
| 12. |
|
|
| 13. |
|
|
| 14. |
- Testa, A. C., et al.
(författare)
-
Intravenous contrast ultrasound examination using contrast-tuned imaging (CnTI (TM)) and the contrast medium SonoVue (R) for discrimination between benign and malignant adnexal masses with solid components
- 2009
-
Ingår i: Ultrasound in Obstetrics & Gynecology. - : Wiley. - 1469-0705 .- 0960-7692. ; 34:6, s. 699-710
-
Tidskriftsartikel (refereegranskat)abstract
- Objective To determine whether intravenous contrast ultrasound examination is superior to gray-scale or power Doppler ultrasound for discrimination between benign and malignant adnexal masses with complex ultrasound morphology. Methods In an international multicenter study, 134 patients with an ovarian mass with solid components or a multilocular cyst with more than 10 cyst locules, underwent a standardized transvaginal ultrasound examination followed by contrast examination using the contrast-tuned imaging technique and intravenous injection of the contrast medium SonoVue (R). Time intensity curves were constructed, and peak intensity, area under the intensity curve, time to peak, sharpness and half wash-out time were calculated. The sensitivity and specificity with regard to malignancy were calculated and receiver-operating characteristics (ROC) curves were drawn for gray-scale, power Doppler and contrast variables and for pattern recognition (subjective assignment of a certainly benign, probably benign, uncertain or malignant diagnosis, using gray-scale and power Doppler ultrasound findings). The gold standard was the histological diagnosis of the surgically removed tumors. Results After exclusions (surgical removal of the mass > 3 months after the ultrasound examination, technical problems), 72 adnexal masses with solid components were used in our statistical analyses. The values for peak contrast signal intensity and area under the contrast signal intensity curve in malignant tumors were significantly higher than those in borderline tumors and benign tumors, while those for the benign and borderline tumors were similar. The area under the ROC curve of the best contrast variable with regard to diagnosing borderline or invasive malignancy (0.84) was larger than that of the best gray-scale (0.75) and power Doppler ultrasound variable (0.79) but smaller than that of pattern recognition (0.93). Conclusion Findings on ultrasound contrast examination differed between benign and malignant tumors but there was a substantial overlap in contrast findings between benign and borderline tumors. It appears that ultrasound contrast examination is not superior to conventional ultrasound techniques, which also have difficulty in distinguishing between benign and borderline tumors, but can easily differentiate invasive malignancies from other tumors. Copyright (C) 2009 ISUOG. Published by John Wiley & Sons, Ltd.
|
|
| 15. |
|
|
