Yazar "Fadlallah, Nouran" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Artificial Intelligence in Cancer: A SWOT Analysis
    (İzmir Academy Association, 2024) Torkay, Gülşah; Fadlallah, Nouran; Karagöz, Ahmet; Canlı, Mesut; Saydam, Ezgi; Mete, Ayşenur; Kızılışık, Furkan
    Cancer, a collection of maladies that has undergone extensive examination over centuries, remains a formidable challenge. Despite the array of available pharmacological and therapeutic interventions, the intricate molecular dynamics and heterogeneity of cancer continue to challenge the scientific community. Artificial Intelligence (AI) emerges as a promising avenue, offering the potential for expedited, precise diagnostics devoid of human expertise. Additionally, AI facilitates the tailoring of patient-specific therapeutic strategies targeting various facets of cancer, spanning macroscopic to microscopic levels. Nonetheless, it is imperative to scrutinize the potential benefits and limitations of AI technologies in this context. This review undertakes a comprehensive Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis of AI's application in cancer. An extensive compilation of AI applications encompasses predictive modeling, diagnostic capabilities, prognostic assessments, and personalized therapeutic modalities, spanning genomic analyses to individualized treatment regimens. The synthesis of evidence suggests that the advantages of AI outweigh its drawbacks; nevertheless, obstacles to its widespread integration persist.
  • Küçük Resim
    Öğe
    Diagnosis and prognosis of Covid-19 from medical images using deep learning
    (İstanbul Bilgi Üniversitesi, 2022) Fadlallah, Nouran; Denker, Ahmet
    ABSTRACT: Covid-19, with its high death rate, was discovered nearly three years ago. New variants resistant to vaccines still emerge while travel and export restrictions can not be held for longer. An accurate and fast diagnosis of such a disease is crucial to reducing its global spread. Computed Tomography CT scans have shown to be the most precise method for covid-19 diagnosis. However, it is a slow process to read and diagnose a disease from a CT scan due to the scarcity of skilled radiologists and the limited information and data available about covid-19. Computer vision has been successfully used in assisting professionals in diagnosis tasks both in terms of speed and accuracy when trained on large datasets. This work is an effort to develop a fast and accurate AI model for covid-19 diagnosis trained on a small dataset. We developed an ensemble model consisting of a 3D CNN LeNet-based model and a 2D Convolutional-Like Vision transformer to diagnose CT scans as covid-19 and healthy. A total of 508 CT scans were used to train the model as a subset of the publicly available MosMed dataset. This results in an accuracy of 90%, specificity of 92%, and a sensitivity of 88%.