<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In the field of medical imaging, techniques like computed tomography (CT), magnetic resonance imaging (MRI), and X-rays are essential for diagnosing and monitoring diseases, particularly in pulmonary pathology. A significant development in this area is the application of automated segmentation and machine learning, enhancing the accuracy in diagnosing lung diseases, such as lung cancer. However, there remains a knowledge gap in fully understanding the potential and limitations of these technologies, especially across diverse clinical conditions and datasets. To address this gap, the paper delves into the integration of artificial intelligence with conventional imaging techniques, focusing primarily on the use of convolutional neural networks (CNNs) and transformer-based models in automated segmentation. This approach is pivotal in improving the detection rates and accuracy of diagnoses in complex pulmonary diseases. Findings indicate that AI-enhanced imaging significantly advances the early detection of pulmonary diseases, notably lung cancer, and reduces the time until diagnosis. Yet, challenges such as the necessity for diverse and comprehensive training data and the generalizability of algorithms, persist. Moreover, ethical considerations in the deployment of AI technologies in healthcare are crucial. In conclusion, while these technologies mark substantial progress in pulmonary imaging, it is essential to find the balance between technological advancements and ethical considerations. This balance is key to ensuring effective and equitable healthcare, maximizing the benefits of AI in medical imaging while maintaining patient trust and privacy.</p>
</abstract>

In the field of medical imaging, techniques like computed tomography (CT), magnetic resonance imaging (MRI), and X-rays are essential for diagnosing and monitoring diseases, particularly in pulmonary pathology. A significant development in this area is the application of automated segmentation and machine learning, enhancing the accuracy in diagnosing lung diseases, such as lung cancer. However, there remains a knowledge gap in fully understanding the potential and limitations of these technologies, especially across diverse clinical conditions and datasets. To address this gap, the paper delves into the integration of artificial intelligence with conventional imaging techniques, focusing primarily on the use of convolutional neural networks (CNNs) and transformer-based models in automated segmentation. This approach is pivotal in improving the detection rates and accuracy of diagnoses in complex pulmonary diseases. Findings indicate that AI-enhanced imaging significantly advances the early detection of pulmonary diseases, notably lung cancer, and reduces the time until diagnosis. Yet, challenges such as the necessity for diverse and comprehensive training data and the generalizability of algorithms, persist. Moreover, ethical considerations in the deployment of AI technologies in healthcare are crucial. In conclusion, while these technologies mark substantial progress in pulmonary imaging, it is essential to find the balance between technological advancements and ethical considerations. This balance is key to ensuring effective and equitable healthcare, maximizing the benefits of AI in medical imaging while maintaining patient trust and privacy.

Enhancing Pulmonary Care: The Pivotal Role of Segmentation and Automated Analysis in Advanced Pulmonary Imaging

University of Medicine and Pharmacy Carol Davila

Pneumologia

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

In the field of medical imaging, techniques like computed tomography (CT), magnetic resonance imaging (MRI), and X-rays are essential for diagnosing and...

Enhancing Pulmonary Care: The Pivotal Role of Segmentation and Automated Analysis in Advanced Pulmonary Imaging

Pubblicato online: 10 giu 2024

Pagine: 15 - 22

DOI: https://doi.org/10.2478/pneum-2024-0003

Parole chiave
pulmonary imaging, automated segmentation, machine learning, convolutional neural networks, artificial intelligence in medicine

© 2023 Radu Marian Gheorghiu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Enhancing Pulmonary Care: The Pivotal Role of Segmentation and Automated Analysis in Advanced Pulmonary Imaging

Pubblicato online: 10 giu 2024

Pagine: 15 - 22

DOI: https://doi.org/10.2478/pneum-2024-0003

Parole chiavepulmonary imaging, automated segmentation, machine learning, convolutional neural networks, artificial intelligence in medicine

© 2023 Radu Marian Gheorghiu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Parole chiave
pulmonary imaging, automated segmentation, machine learning, convolutional neural networks, artificial intelligence in medicine