Calibration and Distraction Mining Network for Aortic True Lumen segmentation
Authors: Fan, Xin | Tian, Shengwei | Yu, Long | Han, Min | Liu, Lu | Cheng, Junlong | Wu, Weidong | Kang, Xiaojing | Zhang, Dezhi
Article Type: Research Article
Abstract: Automatic segmentation of aortic true lumen based on deep learning can save the time for diagnosis of aortic dissection. However, fuzzy boundary, small true lumen region, and high similarity usually leads to inaccurate prediction. To make better use of the details supplemented by the encoder to restore boundaries, we decompose the recovery of detail features in the decoder into two sub-processes: calibration and distraction mining. And we propose a novel calibration and distraction mining (CDM) module. It utilizes deep features to calibrate shallow features so that features are concentrated in the main region. Then, it leverages the distraction mining procedure …to extract false-negative features as a supplement to calibrated features and recover details of the segmentation object. We construct CDM-Net and verify its performance on the Aorta-CT dataset (private dataset), it achieves the Dice similarity coefficient of 96.94% and the Jaccard index coefficient of 94.08%, which is the best compared with 10 latest methods. Similarly, we explore its robustness on three more public datasets, including ISIC 2018 dataset (skin lesion segmentation), the 2018 data science bowl dataset (nucleus segmentation), LUNA dataset (lung segmentation). Experimental results prove that our method produces competitive results on all three data sets. Through quantitative and qualitative research, the proposed CDM-Net has good performance and can process aortic slices with complex semantic features, additional experiments show that it has good robustness, and it has the potential to be applied and expanded conveniently. Show more
Keywords: Aortic true lumen, semantic segmentation, calibration, distraction mining
DOI: 10.3233/JIFS-220242
Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 6, pp. 7863-7875, 2022
Brain-Reactive Autoantibodies Prevalent in Human Sera Increase Intraneuronal Amyloid-β 1-42 Deposition
Authors: Nagele, Robert G. | Clifford, Peter M. | Siu, Gilbert | Levin, Eli C. | Acharya, Nimish K. | Han, Min | Kosciuk, Mary C. | Venkataraman, Venkat | Zavareh, Semah | Zarrabi, Shabnam | Kinsler, Kristin | Thaker, Nikhil G. | Nagele, Eric P. | Dash, Jacqueline | Wang, Hoau Y. | Levitas, Andrew
Article Type: Research Article
Abstract: Previous studies have reported immunoglobulin-positive neurons in Alzheimer's disease (AD) brains, an observation indicative of blood-brain barrier (BBB) breakdown. Recently, we demonstrated the nearly ubiquitous presence of brain-reactive autoantibodies in human sera. The significance of these observations to AD pathology is unknown. Here, we show that IgG-immunopositive neurons are abundant in brain regions exhibiting AD pathology, including intraneuronal amyloid-β42 (Aβ42 ) and amyloid plaques, and confirm by western analysis that brain-reactive autoantibodies are nearly ubiquitous in human serum. To investigate a possible interrelationship between neuronal antibody binding and Aβ pathology, we tested the effects of human serum autoantibodies on the …intraneuronal deposition of soluble Aβ42 peptide in adult mouse neurons in vitro (organotypic brain slice cultures). Binding of human autoantibodies to mouse neurons dramatically increased the rate and extent of intraneuronal Aβ42 accumulation in the mouse cerebral cortex and hippocampus. Additionally, individual sera exhibited variable potency related to their capacity to enhance intraneuronal Aβ42 peptide accumulation and immunolabel neurons in AD brain sections. Replacement of human sera with antibodies targeting abundant neuronal surface proteins resulted in a comparable enhancement of Aβ42 accumulation in mouse neurons. Overall, results suggest that brain-reactive autoantibodies are ubiquitous in the blood and that a defective BBB allows these antibodies to access the brain interstitium, bind to neuronal surfaces and enhance intraneuronal deposition of Aβ42 in AD brains. Thus, in the context of BBB compromise, brain-reactive autoantibodies may be an important risk factor for the initiation and/or progression of AD as well as other neurodegenerative diseases. Show more
Keywords: Alzheimer's disease, amyloid, autoantibodies, autoimmunity, blood brain barrier, neurodegenerative disease
DOI: 10.3233/JAD-2011-110098
Citation: Journal of Alzheimer's Disease, vol. 25, no. 4, pp. 605-622, 2011
Diabetes and Hypercholesterolemia Increase Blood-Brain Barrier Permeability and Brain Amyloid Deposition: Beneficial Effects of the LpPLA2 Inhibitor Darapladib
Authors: Acharya, Nimish K. | Levin, Eli C. | Clifford, Peter M. | Han, Min | Tourtellotte, Ryan | Chamberlain, Dean | Pollaro, Michael | Coretti, Nicholas J. | Kosciuk, Mary C. | Nagele, Eric P. | DeMarshall, Cassandra | Freeman, Theresa | Shi, Yi | Guan, Chenbing | Macphee, Colin H. | Wilensky, Robert L. | Nagele, Robert G.
Article Type: Research Article
Abstract: Diabetes mellitus (DM) and hypercholesterolemia (HC) have emerged as major risk factors for Alzheimer's disease, highlighting the importance of vascular health to normal brain functioning. Our previous study showed that DM and HC favor the development of advanced coronary atherosclerosis in a porcine model, and that treatment with darapladib, an inhibitor of lipoprotein-associated phospholipase A2 , blocks atherosclerosis progression and improves animal alertness and activity levels. In the present study, we examined the effects of DM and HC on the permeability of the blood-brain barrier (BBB) using immunoglobulin G (IgG) as a biomarker. DMHC increased BBB permeability and the leak …of microvascular IgG into the brain interstitium, which was bound preferentially to pyramidal neurons in the cerebral cortex. We also examined the effects of DMHC on the brain deposition of amyloid peptide (Aβ42 ), a well-known pathological feature of Alzheimer's disease. Nearly all detectable Aβ42 was contained within cortical pyramidal neurons and DMHC increased the density of Aβ42 -loaded neurons. Treatment of DMHC animals with darapladib reduced the amount of IgG-immunopositive material that leaked into the brain as well as the density of Aβ42 -containing neurons. Overall, these results suggest that a prolonged state of DMHC may have chronic deleterious effects on the functional integrity of the BBB and that, in this DMHC pig model, darapladib reduces BBB permeability. Also, the preferential binding of IgG and coincident accumulation of Aβ42 in the same neurons suggests a mechanistic link between the leak of IgG through the BBB and intraneuronal deposition of Aβ42 in the brain. Show more
Keywords: Alzheimer's disease, amyloid-β, autoantibodies, blood-brain barrier, cholesterol, darapladib, diabetes mellitus, immunoglobulin, lipoprotein-associated phospholipase-A2 (LpPLA2), microvasculature
DOI: 10.3233/JAD-122254
Citation: Journal of Alzheimer's Disease, vol. 35, no. 1, pp. 179-198, 2013