An Update on Artificial Intelligence and Its Application in Orthopedics: A Narrative Review DOI

Jitendra Nath Pal

Deleted Journal, Год журнала: 2024, Номер 32(2), С. 66 - 70

Опубликована: Июль 1, 2024

Abstract Background: Prerequisites of artificial intelligence (AI) are a huge unbiased data set, linking them with different “clouds,” powerful computer high processing ability, and application statistical methods to produce complex algorithm. The concept “can machine think” developed in the early 1940s turning rule. progress was slow till 2000 then steadily increased accelerated since 2012. Data scientists used mathematics engineers machines that allow learning, deep neural network as subsets AI. These nodes layers can send feedback refine its own decision. Among various fields, applications orthopedics stage validation. Clinical growing fast. Use orthopedic subfields such joint disorders arthroplasty, spine, fractures, sports medicine, oncology promising. Aims Objectives: Orthopedic clinicians have limited scope be accustomed enmeshed basis. They will more interested AI their practice. This review article is focused on some historical background applicability ML models domains. future benefits limitations also outlined. Methodology: In this descriptive narrative exploratory review, qualitative information collected randomly from variety sources. Conclusion: revolution industrial development. It has reached present state by efforts endeavors scientists. Its utility been validated fields ready use regular However, ethical issues including “Job-Killing” effect, identification accountable persons situations where makes mistakes, biased not yet addressed. Regulating bodies working it.

Язык: Английский

Artificial Intelligence in Spinal Imaging and Patient Care: A Review of Recent Advances DOI Creative Commons
Sungwon Lee, Joon‐Yong Jung, Akaworn Mahatthanatrakul

и другие.

Neurospine, Год журнала: 2024, Номер 21(2), С. 474 - 486

Опубликована: Июнь 27, 2024

Artificial intelligence (AI) is transforming spinal imaging and patient care through automated analysis enhanced decision-making. This review presents a clinical task-based evaluation, highlighting the specific impact of AI techniques on different aspects care. We first discuss how can potentially improve image quality like denoising or artifact reduction. then explore enables efficient quantification anatomical measurements, curvature parameters, vertebral segmentation, disc grading. facilitates objective, accurate interpretation diagnosis. models now reliably detect key pathologies, achieving expert-level performance in tasks identifying fractures, stenosis, infections, tumors. Beyond diagnosis, also assists surgical planning via synthetic computed tomography generation, augmented reality systems, robotic guidance. Furthermore, combined with data personalized predictions to guide treatment decisions, such as forecasting spine surgery outcomes. However, challenges still need be addressed implementing clinically, including model interpretability, generalizability, limitations. Multicenter collaboration using large, diverse datasets critical advance field further. While adoption barriers persist, transformative opportunity revolutionize workflows, empowering clinicians translate into actionable insights for improved

Язык: Английский

Процитировано

9
Medical students’ perceptions of an artificial intelligence (AI) assisted diagnosing program DOI

Emely Robleto,

Ali Habashi,

Mary-Ann Benites Kaplan

и другие.

Medical Teacher, Год журнала: 2024, Номер 46(9), С. 1180 - 1186

Опубликована: Фев. 2, 2024

As artificial intelligence (AI) assisted diagnosing systems become accessible and user-friendly, evaluating how first-year medical students perceive such holds substantial importance in education. This study aimed to assess students' perceptions of an AI-assisted diagnostic tool known as 'Glass AI.' Data was collected from first year enrolled a 1.5-week Cell Physiology pre-clerkship unit. Students voluntarily participated activity that involved implementation Glass AI solve clinical case. A questionnaire designed using 3 domains: 1) immediate experience with AI, 2) potential for utilization education, 3) student deliberations future healthcare environments. 73/202 (36.10%) completed the survey. 96% participants noted increased confidence diagnosis, 43% thought lacked sufficient explanation, 68% expressed risk concerns physician workforce. positive outlooks involving healthcare, provided strict regulations, are set protect patient privacy safety, address legal liability, remove system biases, improve quality care. In conclusion, aware will play role their careers physicians.

Язык: Английский

Процитировано

3
KI in der Wirbelsäulenchirurgie: Die Macht der Vorhersage DOI
Aldemar Andrés Hegewald

Die Wirbelsäule, Год журнала: 2025, Номер 09(02), С. 77 - 90

Опубликована: Апрель 1, 2025

Zusammenfassung Die Kunst der Vorhersage ist seit jeher ein wesentlicher Bestandteil des ärztlichen Handelns. In frühen Geschichte eher intuitiv und mit übersinnlichen verknüpft, vertrauen Patienten heute auf unsere wissenschaftlich-medizinischen Kenntnisse, um verlässliche medizinische Vorhersagen zu erhalten. Dabei gilt es Wahrscheinlichkeiten einzuschätzen, ob bestimmter Gesundheitszustand vorliegt – Diagnostik, bestimmtes Ereignis in Zukunft eintreten wird Prognostik. Künstliche Intelligenz (KI) gerade dabei eine unschlagbare Vorhersage-Kompetenz Medizin entwickeln Potenzial, das wir zum Wohle unserer nutzen können. Gleichzeitig stellt diese Entwicklung Herausforderung für ärztliche Selbstverständnis dar. Diese narrative Übersichtsarbeit beleuchtet die Rolle von KI Wirbelsäulenchirurgie, besonderem Fokus klinischer Ergebnisse. Ziel es, dem Leser Verständnis aktuellen Entwicklungen vermitteln, sie einzuordnen ihre Bedeutung unseres Berufsbildes reflektieren.

Процитировано

0
Deep implicit statistical shape models for 3D lumbar vertebrae image delineation DOI

Domen Ocepek,

Gašper Podobnik, Bulat Ibragimov

и другие.

Medical Imaging 2022: Image Processing, Год журнала: 2024, Номер 9351, С. 115 - 115

Опубликована: Апрель 2, 2024

Spinal imaging serves as an invaluable tool in the non-invasive visualization and evaluation of spinal pathologies. A key basis for quantitative medical image analysis pertinent to clinical diagnosis surgery planning is segmentation vertebrae computed tomography (CT) images. While fully convolutional networks general dominate over segmentation, with U-Net being architecture choice, alternative methodologies may offer potential advancements. One promising approach deep implicit statistical shape model (DISSM), known generating high-quality surfaces without discretization its robustness, underpinned by use rich explicit anatomical priors, particularly challenging cross-dataset samples. This paper explores utilization DISSM vertebra on two datasets: a collection 1005 CT spine images CTSpine1K decoder, set 319 VerSe2020 pose estimation encoders (translation, rotation, scaling principal component analysis). These their corresponding segmentations are used preparation, preprocessing, training testing DISSM. The preprocessing learning techniques based software package (AshStuff/dissm) our custom modifications. obtained results yielded overall mean Dice coefficient 0.767, average symmetric surface distance 1.93 mm, 95th percentile Hausdorff 5.71 mm. We can therefore conclude that has further advance field segmentation.

Язык: Английский

Процитировано

2
Vertebral cortical thickness and cortical bone density: an automated CT assessment - towards enhanced spine segmentation DOI Creative Commons

Florent Tomi,

Morgane Evin, Yves Godio‐Raboutet

и другие.

Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization, Год журнала: 2024, Номер 12(1)

Опубликована: Окт. 15, 2024

In this paper a non-invasive method using routine CT scan to assess the vertebral geometry through normalised Cortical Thickness (CTh) and Bone Density (CBD) is proposed. This aims propose new automated segment cortical bone measure its thickness local density. were then used as tool compare these parameters between different vertebra models (in-vivo, cadaver swine) levels. An technique was proposed, assuming two Gaussian density distribution. 42 vertebrae (3 high-thoracic, 3 low-thoracic 1 lumbar for each subject) from three sub-groups (human in-vivo, investigated. human in-vivo sub-group, level shown influence CTh CBD. The CBD found uniform within all functional areas of body (p > 0.05), while showed significant differences < 0.001). Both significantly inferior articular processes area posterior arch d 0.02 *). Vs cadaveric swine), across most 0.001 ***). proposed offers an accurate way measuring Vertebra function have influences on both characteristics. reported models. Such methodology could be image-guided surgery.

Язык: Английский

Процитировано

0
An Update on Artificial Intelligence and Its Application in Orthopedics: A Narrative Review DOI

Jitendra Nath Pal

Deleted Journal, Год журнала: 2024, Номер 32(2), С. 66 - 70

Опубликована: Июль 1, 2024

Abstract Background: Prerequisites of artificial intelligence (AI) are a huge unbiased data set, linking them with different “clouds,” powerful computer high processing ability, and application statistical methods to produce complex algorithm. The concept “can machine think” developed in the early 1940s turning rule. progress was slow till 2000 then steadily increased accelerated since 2012. Data scientists used mathematics engineers machines that allow learning, deep neural network as subsets AI. These nodes layers can send feedback refine its own decision. Among various fields, applications orthopedics stage validation. Clinical growing fast. Use orthopedic subfields such joint disorders arthroplasty, spine, fractures, sports medicine, oncology promising. Aims Objectives: Orthopedic clinicians have limited scope be accustomed enmeshed basis. They will more interested AI their practice. This review article is focused on some historical background applicability ML models domains. future benefits limitations also outlined. Methodology: In this descriptive narrative exploratory review, qualitative information collected randomly from variety sources. Conclusion: revolution industrial development. It has reached present state by efforts endeavors scientists. Its utility been validated fields ready use regular However, ethical issues including “Job-Killing” effect, identification accountable persons situations where makes mistakes, biased not yet addressed. Regulating bodies working it.

Язык: Английский

Процитировано

0