Computer-aided extraction of select MRI markers of cerebral small vessel disease: A systematic review

Jiang, Jiyang; Wang, Dadong; Song, Yang; Sachdev, Perminder S.; Wang, Wen

doi:10.1016/j.neuroimage.2022.119528

Cited by 5 publications

(6 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computer-aided measurements have been progressively incorporated into radiological practices to improve the precision and reproducibility of measurements, surpassing the challenges of manual efforts. Such computerized processes are useful in diverse medical imaging areas such as cardiovascular, musculoskeletal, and neurological imaging [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

The Role and Efficiency of an AI-Powered Software in the Evaluation of Lower Limb Radiographs before and after Total Knee Arthroplasty

Pagano,

Müller,

Götz

et al. 2023

JCM

View full text Add to dashboard Cite

The rapid evolution of artificial intelligence (AI) in medical imaging analysis has significantly impacted musculoskeletal radiology, offering enhanced accuracy and speed in radiograph evaluations. The potential of AI in clinical settings, however, remains underexplored. This research investigates the efficiency of a commercial AI tool in analyzing radiographs of patients who have undergone total knee arthroplasty. The study retrospectively analyzed 200 radiographs from 100 patients, comparing AI software measurements to expert assessments. Assessed parameters included axial alignments (MAD, AMA), femoral and tibial angles (mLPFA, mLDFA, mMPTA, mLDTA), and other key measurements including JLCA, HKA, and Mikulicz line. The tool demonstrated good to excellent agreement with expert metrics (ICC = 0.78–1.00), analyzed radiographs twice as fast (p < 0.001), yet struggled with accuracy for the JLCA (ICC = 0.79, 95% CI = 0.72–0.84), the Mikulicz line (ICC = 0.78, 95% CI = 0.32–0.90), and if patients had a body mass index higher than 30 kg/m2 (p < 0.001). It also failed to analyze 45 (22.5%) radiographs, potentially due to image overlay or unique patient characteristics. These findings underscore the AI software’s potential in musculoskeletal radiology but also highlight the necessity for further development for effective utilization in diverse clinical scenarios. Subsequent studies should explore the integration of AI tools in routine clinical practice and their impact on patient care.

show abstract

Section: Introductionmentioning

confidence: 99%

The Role and Efficiency of an AI-Powered Software in the Evaluation of Lower Limb Radiographs before and after Total Knee Arthroplasty

Pagano,

Müller,

Götz

et al. 2023

JCM

View full text Add to dashboard Cite

show abstract

“…The association between white matter hyperintensities and enlarged PVS has been recently replicated in rats [ 41 , 43 , 44 ] with distinct proteomic brain changes compared with CAA [ 44 ]. While the quantitation of PVS is becoming more common in neuroimaging studies [ 41 , 45 ], it is not a core pathology in the rubric used to assess vascular pathologies in the Vascular Cognitive Impairment Neuropathologic Guidelines (VCING), which include large infarcts, moderate to severe occipital leptomeningeal CAA and moderate to severe occipital white matter arteriosclerosis rather than white matter PVS [ 7 ]. These guidelines were designed to capture pathologies associated with cognitive impairment, with evidence that increasing enlargement of white matter PVS is a marker for increased risk of cognitive decline and dementia [ 46 ].…”

Section: Discussionmentioning

confidence: 99%

Past antihypertensive medication use is associated with lower levels of small vessel disease and lower Aβ plaque stage in the brains of older individuals

Affleck

Sachdev

Halliday

2023

Neuropathology Appl Neurobio

Self Cite

View full text Add to dashboard Cite

AimsThis study assesses the association of antihypertensive medication use on the severities of neuropathological cerebrovascular disease (CVD excluding lobar infarction) in older individuals.MethodsClinical and neuropathological data were retrieved for 149 autopsy cases >75 years old with or without CVD or Alzheimer's disease and no other neuropathological diagnoses. Clinical data included hypertension status, hypertension diagnosis, antihypertensive medication use, antihypertensive medication dose (where available) and clinical dementia rating (CDR). Neuropathological CVD severity was evaluated for differences with anti‐hypertensive medication usage.ResultsAntihypertensive medication use was associated with less severe white matter small vessel disease (SVD, mainly perivascular dilatation and rarefaction), with a 5.6–14.4 times greater likelihood of less severe SVD if medicated. No significant relationship was detected between infarction (presence, type, number and size), lacunes or cerebral amyloid angiopathy and antihypertensive medication use. Only increased white matter rarefaction/oedema and not perivascular dilation was associated with Alzheimer's pathology, with a 4.3 times greater likelihood of reduced Aβ progression through the brain if white matter rarefaction severity was none or mild. Antihypertensive medication use was associated with reduced Aβ progression but only in those with moderate to severe white matter SVD.ConclusionsThis histopathological study provides further evidence that antihypertensive medication use in older individuals is associated with white matter SVD and not with other CVD pathologies. This is mainly due to a reduction in white matter perivascular dilation and rarefaction/oedema. Even in those with moderate to severe white matter SVD, antihypertensive medication use reduced rarefaction and Aβ propagation through the brain.

show abstract

“…The latest advancements in AI technology have facilitated the automated diagnosis of dementia through conventional machine learning and deep learning algorithms. Computer-aided diagnostic, applied on brain disease [24] and extraction of CSVD MRI markers [25], acts as an essential tool to enhance accuracy and efficiency in diagnosis. CNN, known as the most utilized deep learning network type, involves the stacking of multiple convolutional and max pooling (or average pooling) layers in a successive manner [26].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Deep learning applications in vascular dementia using neuroimaging

Dong,

Hayashi

2023

Current Opinion in Psychiatry

View full text Add to dashboard Cite

Purpose of review Vascular dementia (VaD) is the second common cause of dementia after Alzheimer's disease, and deep learning has emerged as a critical tool in dementia research. The aim of this article is to highlight the current deep learning applications in VaD-related imaging biomarkers and diagnosis. Recent findings The main deep learning technology applied in VaD using neuroimaging data is convolutional neural networks (CNNs). CNN models have been widely used for lesion detection and segmentation, such as white matter hyperintensities (WMH), cerebral microbleeds (CMBs), perivascular spaces (PVS), lacunes, cortical superficial siderosis, and brain atrophy. Applications in VaD subtypes classification also showed excellent results. CNN-based deep learning models have potential for further diagnosis and prognosis of VaD. Summary Deep learning neural networks with neuroimaging data in VaD research represent significant promise for advancing early diagnosis and treatment strategies. Ongoing research and collaboration between clinicians, data scientists, and neuroimaging experts are essential to address challenges and unlock the full potential of deep learning in VaD diagnosis and management.

show abstract

Computer-aided extraction of select MRI markers of cerebral small vessel disease: A systematic review

Cited by 5 publications

References 81 publications

The Role and Efficiency of an AI-Powered Software in the Evaluation of Lower Limb Radiographs before and after Total Knee Arthroplasty

The Role and Efficiency of an AI-Powered Software in the Evaluation of Lower Limb Radiographs before and after Total Knee Arthroplasty

Past antihypertensive medication use is associated with lower levels of small vessel disease and lower Aβ plaque stage in the brains of older individuals

Deep learning applications in vascular dementia using neuroimaging

Contact Info

Product

Resources

About