Aimilios Lallas

ORCID: 0000-0002-7193-0964
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Cutaneous Melanoma Detection and Management
  • Nonmelanoma Skin Cancer Studies
  • Cutaneous lymphoproliferative disorders research
  • Cancer and Skin Lesions
  • Nail Diseases and Treatments
  • Genetic and rare skin diseases.
  • Melanoma and MAPK Pathways
  • Skin Protection and Aging
  • melanin and skin pigmentation
  • Tumors and Oncological Cases
  • Autoimmune Bullous Skin Diseases
  • Infectious Diseases and Mycology
  • Optical Coherence Tomography Applications
  • AI in cancer detection
  • Dermatologic Treatments and Research
  • Psoriasis: Treatment and Pathogenesis
  • Dermatological and Skeletal Disorders
  • Dermatological diseases and infestations
  • Hedgehog Signaling Pathway Studies
  • Dermatology and Skin Diseases
  • Autoimmune and Inflammatory Disorders
  • Genital Health and Disease
  • Vascular Tumors and Angiosarcomas
  • CAR-T cell therapy research
  • Skin Diseases and Diabetes

Aristotle University of Thessaloniki
2016-2025

Hospital Venereal and Skin Diseases Thessaloniki
2010-2024

National Student Clearinghouse Research Center
2024

Ospedale Santa Maria della Misericordia di Udine
2024

University of Macedonia
2022

Shinshu University
2022

Tel Aviv Sourasky Medical Center
2022

University of Gastronomic Sciences
2022

University of Naples Federico II
2022

Nepal Medical College Teaching Hospital
2022

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 corresponding diagnoses. In comparative cross-sectional reader study 100-image test-set used (level-I: dermoscopy only; level-II: plus clinical information images). Main outcome measures were sensitivity, specificity area...

10.1093/annonc/mdy166 article EN publisher-specific-oa Annals of Oncology 2018-05-04

Skin cancer, including melanoma and non-melanoma skin cancer (NMSC), represents the most common type of malignancy in white population. The incidence rate is increasing worldwide, while associated mortality remains stable, or slightly decreasing. On other hand, for NMSC varies widely, with highest rates reported Australia. In current review, we highlight recent global trends epidemiology cancer. We discuss controversial issues raised epidemiological data, analyze important risk factors...

10.5826/dpc.0702a01 article EN cc-by-nc Dermatology Practical & Conceptual 2017-04-30

<h3>Importance</h3> Deep learning convolutional neural networks (CNNs) have shown a performance at the level of dermatologists in diagnosis melanoma. Accordingly, further exploring potential limitations CNN technology before broadly applying it is special interest. <h3>Objective</h3> To investigate association between gentian violet surgical skin markings dermoscopic images and diagnostic approved for use as medical device European market. <h3>Design Setting</h3> A cross-sectional analysis...

10.1001/jamadermatol.2019.1735 article EN JAMA Dermatology 2019-08-15

Dermoscopy is useful in evaluating skin tumours, but its applicability extends also to the field of inflammatory disorders. Plaque psoriasis (PP), dermatitis, lichen planus (LP) and pityriasis rosea (PR) are common diseases, little currently known about their dermoscopic features.To determine compare patterns associated with PP, LP PR assess validity certain criteria diagnosis PP.Patients were prospectively enrolled. The single most recently developed lesion was examined dermoscopically...

10.1111/j.1365-2133.2012.10868.x article EN British Journal of Dermatology 2012-02-01

Convolutional neural networks (CNNs) achieve expert-level accuracy in the diagnosis of pigmented melanocytic lesions. However, most common types skin cancer are nonpigmented and nonmelanocytic, more difficult to diagnose.To compare a CNN-based classifier with that physicians different levels experience.A classification model was trained on 7895 dermoscopic 5829 close-up images lesions excised at primary clinic between January 1, 2008, July 13, 2017, for combined evaluation both imaging...

10.1001/jamadermatol.2018.4378 article EN JAMA Dermatology 2018-11-28

A unique collaboration of multidisciplinary experts from the European Dermatology Forum, Association Dermato-Oncology and Organization for Research Treatment Cancer (EORTC) was formed to make recommendations on cutaneous melanoma diagnosis treatment, based systematic literature reviews experts' experience. Cutaneous melanomas are excised with 1- 2-cm safety margins. Sentinel lymph node dissection shall be performed as a staging procedure in patients tumour thickness ≥1.0 mm or ≥0.8...

10.1016/j.ejca.2019.11.015 article EN cc-by-nc-nd European Journal of Cancer 2019-12-19

BackgroundMultiple studies have compared the performance of artificial intelligence (AI)–based models for automated skin cancer classification to human experts, thus setting cornerstone a successful translation AI-based tools into clinicopathological practice.ObjectiveThe objective study was systematically analyse current state research on reader involving melanoma and assess their potential clinical relevance by evaluating three main aspects: test set characteristics...

10.1016/j.ejca.2021.06.049 article EN cc-by-nc-nd European Journal of Cancer 2021-09-08

Highlights•A market-approved convolutional neural network (CNN) trained on dermoscopic images was tested against 96 dermatologists.•Test data included a broad range of skin lesions and compiled from external sources not involved in CNN training.•Dermatologists indicated their management decisions after reviewing clinical, dermoscopic, textual case information.•In this setting dermatologists performed par with the CNN's classifications based alone.AbstractBackgroundConvolutional networks...

10.1016/j.annonc.2019.10.013 article EN publisher-specific-oa Annals of Oncology 2020-01-01

We investigated whether human preferences hold the potential to improve diagnostic artificial intelligence (AI)-based decision support using skin cancer diagnosis as a use case. utilized nonuniform rewards and penalties based on expert-generated tables, balancing benefits harms of various errors, which were applied reinforcement learning. Compared with supervised learning, learning model improved sensitivity for melanoma from 61.4% 79.5% (95% confidence interval (CI): 73.5-85.6%) basal cell...

10.1038/s41591-023-02475-5 article EN cc-by Nature Medicine 2023-07-27

A collaboration of multidisciplinary experts from the European Association Dermato-Oncology, Dermatology Forum, Academy and Venereology, Union Medical Specialists was formed to develop recommendations on AK diagnosis treatment, based current literature expert consensus. This guideline addresses epidemiology, diagnostics, risk stratification treatments in immunocompetent as well immunosuppressed patients. Actinic keratoses (AK) are potential precursors cutaneous squamous cell carcinoma (cSCC)...

10.1111/jdv.19897 article EN Journal of the European Academy of Dermatology and Venereology 2024-03-07

Abstract Background Several common inflammatory dermatoses, such as rosacea, seborrheic dermatitis ( SD ), discoid lupus erythematosus DLE ) and granulomatous skin diseases manifest erythematous macules or plaques on the facial skin. Although clinical examination represents cornerstone of diagnosis, broad variety features uncommon presentations these may cause at times diagnostic therapeutic uncertainty. Dermoscopy, in addition to its well‐documented value evaluation tumours, is continuously...

10.1111/jdv.12146 article EN Journal of the European Academy of Dermatology and Venereology 2013-03-12
Coming Soon ...