Alzheimer's disease detection from structural MRI using conditional deep triplet network

Orouskhani, Maysam; Zhu, Chengcheng; Rostamian, Sahar; Zadeh, Firoozeh Shomal; Shafiei, Mehrzad; Orouskhani, Yasin

doi:10.1016/j.neuri.2022.100066

Cited by 52 publications

(22 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al 67 local structure preservation sparse representation classifier (LMLS-SRC) No dementia , V.Mild, Mild, Moderate 85.54 86.19 86.15 84.51 1000 MRI sample of Kaggle datasets M. Orouskhani et. al 68 deep triplet network No dementia , V.Mild, Mild, Moderate 99.41 85.2 – – 382 MRI sample of Kaggle datasets S. Liang et. al 69 a WSL-based deep learning No dementia , V.Mild, Mild, Moderate 98.7 98 99 99.5 6400 MRI sample of Kaggle datasets H. Ni et.…”

Section: Resultsmentioning

confidence: 99%

A new strategy for the early detection of alzheimer disease stages using multifractal geometry analysis based on K-Nearest Neighbor algorithm

Elgammal

Zahran

Abdelsalam

2022

Sci Rep

View full text Add to dashboard Cite

Alzheimer's Disease (AD) is considered one of the most diseases that much prevalent among elderly people all over the world. AD is an incurable neurodegenerative disease affecting cognitive functions and were characterized by progressive and collective functions deteriorating. Remarkably, early detection of AD is essential for the development of new and invented treatment strategies. As Dementia causes irreversible damage to the brain neurons and leads to changes in its structure that can be described adequately within the framework of multifractals. Hence, the present work focus on developing a promising and efficient computing technique to pre-process and classify the AD disease especially in the early stages using multifractal geometry to extract the most changeable features due to AD. Then, A machine learning classification algorithm (K-Nearest Neighbor) has been implemented in order to classify and detect the main four early stages of AD. Two datasets have been used to ensure the validation of the proposed methodology. The proposed technique has achieved 99.4% accuracy and 100% sensitivity. The comparative results show that the proposed classification technique outperforms is recent techniques in terms of performance measures.

show abstract

Section: Resultsmentioning

confidence: 99%

A new strategy for the early detection of alzheimer disease stages using multifractal geometry analysis based on K-Nearest Neighbor algorithm

Elgammal

Zahran

Abdelsalam

2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The approach is used in clinical practice and clinical studies to diagnose and monitor disease activity, guide therapy decisions, and assess treatment response. However, clinical MRI is still employed for qualitative, subjective interpretation of macrostructural characteristics rather than quantitative analyses that consider numerous pathophysiological aspects [28]. But quantitative imaging and imaging biomarker development is maturing.…”

Section: Role Of Mrimentioning

confidence: 99%

Artificial intelligence for radiomics; diagnostic biomarkers for neuro-oncology

Vahedifard¹,

Hassani²,

Afrasiabi³

et al. 2022

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

Recent advances in medical image analysis have been made to improve our understanding of how disease develops, behaves, and responds to treatment. Magnetic resonance imaging (MRI) and positron emission tomography (PET) advanced imaging strategies provide structural and functional phenotypic biomarkers that correlate with key disease processes. Through radiomics and radiogenomics, ML-medical imaging has opened up new perspectives in high-grade glioma diagnosis. As a result, non-invasive and in vivo biomarkers for patient survival, tumor recurrence, and genomics are identified. Tumor genomic imaging signatures can help identify patients who benefit from targeted therapies. Molecular characterization of gliomas and prediction of their evolution would allow treatment optimization. Radiomics-based biomarkers allow for a more in-depth analysis of pathophysiologic processes and insights into diagnosing better, classifying, stratifying, and prognosticating brain tumors and assessing their response to therapy. Radiomics is a new data-driven approach that can help answer clinical questions like diagnosis, prognosis, and treatment response. With encouraging outcomes in brain tumor patients, radiomics and deep learning are still not widely used in clinical practice, requiring more extensive and practical clinical studies.

show abstract

“…Accompanying psychiatric issues, including anxiety and depression, were assessed by HADS [16,17]. There are different trending modalities for depression and anxiety, from traditional drugs and also new neuromodulators [18][19][20], which have fewer side effects than opioids.…”

Section: Uneducated Not Cooperativementioning

confidence: 99%

Opioid for in-hospital admitted patient analgesics; which demographics and psychiatric profiles need more pain drugs?

Mohammadi¹,

Sharafi²,

Atieh³

et al. 2022

World J. Bio. Pharm. Health Sci.

View full text Add to dashboard Cite

Introduction: The prevalence of substance use disorders is higher in patients receiving opioid analgesics, and pain management in these patients is more challenging. This study aimed to investigate the pattern of analgesic drug administration and evaluate the associated factors. Method: The cross-sectional study was performed on 230 patients admitted to General Hospital ( internal medicine, surgery, and cancer wards). Result: The most used analgesic drug was morphine (59.4%), and a mean dose of 27 mg, then pethidine and methadone. Most pain control methods were intravenous (68.1%) and PRN pattern (61.1%). Using analgesics in patients who do not have risk factors for drug abuse, or addiction, can be considered safe. In our subjects, 95.6% of analgesic users did not become addicted or had any misuse. Discussion and Conclusion: For effective and low-risk treatment of these patients, there is a need for clinical skills, knowledge of opioid administration, assessment, and risk management of substance abuse and addiction. In patients with substance abuse, analgesics should be prescribed in a particular setting, under supervision, and with careful monitoring. Structured and planned administration of opioid agonists (such as methadone or buprenorphine) seems appropriate according to a structured schedule. These plans are recommended: · Increasing the awareness of clinicians about prescribing narcotic analgesics. · Prescribing narcotic analgesics with a regular pattern against PRN. · Evaluating patients for a history of substance abuse. · Closely monitoring them, and if necessary. · Counseling. Identifying high-risk groups such as women, youth, and psychiatric patients are also recommended, and performing early interventions.

show abstract

Alzheimer's disease detection from structural MRI using conditional deep triplet network

Cited by 52 publications

References 29 publications

A new strategy for the early detection of alzheimer disease stages using multifractal geometry analysis based on K-Nearest Neighbor algorithm

A new strategy for the early detection of alzheimer disease stages using multifractal geometry analysis based on K-Nearest Neighbor algorithm

Artificial intelligence for radiomics; diagnostic biomarkers for neuro-oncology

Opioid for in-hospital admitted patient analgesics; which demographics and psychiatric profiles need more pain drugs?

Contact Info

Product

Resources

About