1. |
- Haenssle, H A, et al.
(author)
-
Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.
- 2018
-
In: Annals of Oncology. - : Elsevier BV. - 1569-8041 .- 0923-7534. ; 29:8, s. 1836-1842
-
Journal article (peer-reviewed)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/).
|
|
2. |
- Kaur, Gurjinder, et al.
(author)
-
Cystatin C Rescues Degenerating Neurons in a Cystatin B-Knockout Mouse Model of Progressive Myoclonus Epilepsy.
- 2010
-
In: American Journal of Pathology. - : Elsevier BV. - 1525-2191 .- 0002-9440. ; 177, s. 2256-2267
-
Journal article (peer-reviewed)abstract
- In vitro studies have shown that cystatin C (CysC) is neuroprotective. Here we demonstrate that CysC is neuroprotective in vivo, in a mouse model of the inherited neurodegenerative disorder, progressive myoclonic epilepsy type 1 (EPM1). Loss-of-function mutations in the cystatin B (CysB) gene, an intracellular cysteine protease inhibitor, lead to this human disease. A CysB-knockout (CysBKO) mouse model develops symptoms that mimic EPM1. CysB deficiency in these mice results in enhanced cathepsin B and D activities, indicating lysosomal dysfunction. We show that expression of CysC is enhanced in the brains of CysBKO mice. Crossbreeding of CysBKO mice with either CysC-overexpressing transgenic mice or CysC-knockout mice demonstrates that clinical symptoms and neuropathologies, including motor coordination disorder, cerebellar atrophy, neuronal loss in the cerebellum and cerebral cortex, and gliosis caused by CysB deficiency, are rescued by CysC overexpression and exacerbated by CysC deficiency. Thus, CysC effectively rescues the CysB loss-of-function mutations, facilitating the reversal of pathophysiological changes and suggesting a novel therapeutic intervention for patients with EPM1 and other neurodegenerative disorders.
|
|
3. |
- Li, Wei, et al.
(author)
-
Autophagy dysfunction and regulatory cystatin C in macrophage death of atherosclerosis
- 2016
-
In: Journal of Cellular and Molecular Medicine. - : Wiley. - 1582-1838 .- 1582-4934. ; 20:9, s. 1664-1672
-
Journal article (peer-reviewed)abstract
- Autophagy dysfunction in mouse atherosclerosis models has been associated with increased lipid accumulation, apoptosis and inflammation. Expression of cystatin C (CysC) is decreased in human atheroma, and CysC deficiency enhances atherosclerosis in mice. Here, we first investigated the association of autophagy and CysC expression levels with atheroma plaque severity in human atherosclerotic lesions. We found that autophagy proteins Atg5 and LC3β in advanced human carotid atherosclerotic lesions are decreased, while markers of dysfunctional autophagy p62/SQSTM1 and ubiquitin are increased together with elevated levels of lipid accumulation and apoptosis. The expressions of LC3β and Atg5 were positively associated with CysC expression. Second, we investigated whether CysC expression is involved in autophagy in atherosclerotic apoE-deficient mice, demonstrating that CysC deficiency (CysC-/-) in these mice results in reduction of Atg5 and LC3β levels and induction of apoptosis. Third, macrophages isolated from CysC-/- mice displayed increased levels of p62/SQSTM1 and higher sensitivity to 7-oxysterol-mediated lysosomal membrane destabilization and apoptosis. Finally, CysC treatment minimized oxysterol-mediated cellular lipid accumulation. We conclude that autophagy dysfunction is a characteristic of advanced human atherosclerotic lesions and is associated with reduced levels of CysC. The deficiency of CysC causes autophagy dysfunction and apoptosis in macrophages and apoE-deficient mice. The results indicate that CysC plays an important regulatory role in combating cell death via the autophagic pathway in atherosclerosis. Copyright
|
|
4. |
- Tizon, Belen, et al.
(author)
-
Induction of Autophagy by Cystatin C: A Mechanism That Protects Murine Primary Cortical Neurons and Neuronal Cell Lines
- 2010
-
In: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203. ; 5:3
-
Journal article (peer-reviewed)abstract
- Cystatin C (CysC) expression in the brain is elevated in human patients with epilepsy, in animal models of neurodegenerative conditions, and in response to injury, but whether up-regulated CysC expression is a manifestation of neurodegeneration or a cellular repair response is not understood. This study demonstrates that human CysC is neuroprotective in cultures exposed to cytotoxic challenges, including nutritional-deprivation, colchicine, staurosporine, and oxidative stress. While CysC is a cysteine protease inhibitor, cathepsin B inhibition was not required for the neuroprotective action of CysC. Cells responded to CysC by inducing fully functional autophagy via the mTOR pathway, leading to enhanced proteolytic clearance of autophagy substrates by lysosomes. Neuroprotective effects of CysC were prevented by inhibiting autophagy with beclin 1 siRNA or 3-methyladenine. Our findings show that CysC plays a protective role under conditions of neuronal challenge by inducing autophagy via mTOR inhibition and are consistent with CysC being neuroprotective in neurodegenerative diseases. Thus, modulation of CysC expression has therapeutic implications for stroke, Alzheimer's disease, and other neurodegenerative disorders.
|
|