Hadi Vahedi

Dr. Hadi Vahedi

Ophthalmology, Tabriz University of Medical Sciences, Tabrīz, Āz̄arbāyjān-e Sharqī, Iran
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 March 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
MKMahdieh Taiyeb Khosroshahi
Mahdieh Taiyeb Khosroshahi
SMSoroush Morsali
Soroush Morsali
SGSohrab Gharakhanlou
Sohrab Gharakhanlou
AAAlireza Motamedi Alanagh
Alireza Motamedi Alanagh
SHSaeid Hassanbaghlou
Saeid Hassanbaghlou
Ali JafarizadehAli Jafarizadeh
Ali Jafarizadeh
Alzheimer’s disease (AD) remains a significant global health challenge, affecting millions worldwide and imposing substantial burdens on healthcare systems. Advances in artificial intelligence (AI), particularly in deep learning and machine learning, have revolutionized neuroimaging-based AD diagnosis. However, the complexity and lack of interpretability of these models limit their clinical applicability. Explainable Artificial Intelligence (XAI) addresses this challenge by providing insights into model decision-making, enhancing transparency, and fostering trust in AI-driven diagnostics. This review explores the role of XAI in AD neuroimaging, highlighting key techniques such as SHAP, LIME, Grad-CAM, and Layer-wise Relevance Propagation (LRP). We examine their applications in identifying critical biomarkers, tracking disease progression, and distinguishing AD stages using various imaging modalities, including MRI and PET. Additionally, we discuss current challenges, including dataset limitations, regulatory concerns, and standardization issues, and propose future research directions to improve XAI’s integration into clinical practice. By bridging the gap between AI and clinical interpretability, XAI holds the potential to refine AD diagnostics, personalize treatment strategies, and advance neuroimaging-based research.
3

18 January 2025 in Heliyon
Verified
Journal Article
Open access
Hadi VahediHadi Vahedi
Hadi Vahedi
MAMirsaeed Abdollahi
Mirsaeed Abdollahi
RMReza Moshfeghinia
Reza Moshfeghinia
SEShima Emami
Shima Emami
Navid SobhiNavid Sobhi
Navid Sobhi
Ali JafarizadehAli Jafarizadeh
Ali Jafarizadeh
This systematic review and meta-analysis aimed to assess the changes in retinal layer thickness and vascular density in patients diagnosed with keratoconus (KC). We conducted a thorough search in PubMed, Scopus, Embase, and Web of Science, encompassing all observational studies from January 1990 to February 2024. We analyzed the data using STATA software 17 and the random effects model with the restricted maximum likelihood (REML) or maximum likelihood (ML) method to pool the standardized mean difference (SMD) and the weighted mean difference (WMD) of retinal thickness and vascular density compared to non-KC eyes. From 4608 records, 16 primary studies met our inclusion criteria, involving 1932 eyes in two groups. The meta-analysis revealed a significant reduction in retinal nerve fiber layer (RNFL) thickness (SMD: −0.30 [-0.52, −0.08]), perifoveal macular thickness in the nasal region (SMD: −0.32 [-0.55, −0.09]) and superior region (SMD: −0.24 [-0.47, −0.02]), and superior capillary plexus (SCP) density (SMD: −1.52 [-2.27, −0.77]) of KC eyes. Additionally, there was a mildly to moderately significant increase in the optic nerve head (ONH) disk area (SMD: 0.40 [0.06, 0.75]). However, there were no significant changes in foveal macular thickness, parafoveal macular thickness, or deep capillary plexus (DCP) density. In KC patients, significant alterations in retinal structure and vascular density have been observed. Although these changes do not currently influence treatment strategies, they offer valuable insights into the relationship between the retina and the cornea. Understanding these changes may be essential for future research focused on early detection, potential prognosis markers, and further exploration of the retina-corneal connection in KC.
3

30 November 2024 in DARU Journal of Pharmaceutical Sciences
Verified
Journal Article
Closed access
PDF file
NFNeda Feizi
Neda Feizi
MMMahsa Mohamadzadeh-Nabiei
Mahsa Mohamadzadeh-Nabiei
Hadi VahediHadi Vahedi
Hadi Vahedi
SMShadi Farabi Maleki
Shadi Farabi Maleki
Ali JafarizadehAli Jafarizadeh
Ali Jafarizadeh
3

31 January 2025 in Radiology Case Reports
Verified
Journal Article
Open access
RNReza Naseri
Reza Naseri
MHMaryam Haghighi-Morad
Maryam Haghighi-Morad
ZMZahra Mohammadi Manesh
Zahra Mohammadi Manesh
FZFarahnaz Bidari Zerehpoosh
Farahnaz Bidari Zerehpoosh
Hadi VahediHadi Vahedi
Hadi Vahedi
Hamidreza AshayeriHamidreza Ashayeri
Hamidreza Ashayeri
Cavernous malformations (CMs), also known as cavernomas or cavernous hemangiomas, are vascular lesions characterized by clusters of abnormally dilated blood vessels resembling a mulberry. In this report, we present the case of a 40-year-old man who presented with a one-year history of back pain radiating into both legs, with a preference for the left leg. An MRI initially suggested a schwannoma at the T12-L1 vertebral level, with a differential diagnosis that included meningioma—2 common intradural-extramedullary spinal tumors— with distinct management and prognostic implications. However, despite imaging findings consistent with a schwannoma, the final pathology revealed an intradural extramedullary (IDEM) cavernous hemangioma in the thoracolumbar region. Although cavernous hemangiomas are very rare in the spinal region, our case underscores the importance of considering them in the differential diagnosis of IDEMs in the thoracolumbar area.
2

24 November 2025 in Discover Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZAZahra Attarilar
Zahra Attarilar
Hadi VahediHadi Vahedi
Hadi Vahedi
TSTaha Samad-Soltani
Taha Samad-Soltani
RARamtin Neshan Alipoor
Ramtin Neshan Alipoor
Ali JafarizadehAli Jafarizadeh
Ali Jafarizadeh
Purpose: The COVID-19 pandemic has created many new challenges characterized by significant uncertainty. Fuzzy logic systems have been employed to address these uncertainties, contributing to areas such as disease detection, pandemic prediction, behavioral evaluation, healthcare management, and medical devices. Methods: A comprehensive literature review was conducted on studies published between December 2019 and April 2025. Articles were selected from databases including PubMed and Scopus, based on predefined inclusion criteria. Only English-language peer-reviewed articles were included, while review articles, conference abstracts, animal studies, and non-peer-reviewed manuscripts were excluded. Results: A total of 102 studies were included, categorized into five domains: disease detection (17 studies), management strategies (30 studies), pandemic prediction (21 studies), behavioral evaluation (21 studies), and medical devices (13 studies). Fuzzy logic systems demonstrated high diagnostic accuracy, with 11 (65%) of studies in disease detection reporting accuracy rates above 95%. In pandemic prediction, accuracy rates ranged from 80% to 98.60%, while behavioral and management studies largely provided qualitative insights. Medical devices employing fuzzy logic also showed innovations. Conclusion: Fuzzy logic has been widely used to address challenges posed by COVID-19. It has proven highly effective in disease detection and useful in pandemic prediction, behavioral analysis, and resource management by offering valuable insights under uncertain conditions. Notably, the diagnostic domain stands out with fewer qualitative outcomes and higher accuracy rates compared to other applications, highlighting fuzzy logic’s strong suitability for diagnostic purposes. Despite these promising results, further advancements in algorithm development and integration are necessary to unlock its full potential.
3

7 April 2026 in Clinical and Experimental Optometry
Verified
Journal Article
Closed access
Hadi VahediHadi Vahedi
Hadi Vahedi
Ali JafarizadehAli Jafarizadeh
Ali Jafarizadeh
3