Physics and Imaging in Radiation Oncology, Год журнала: 2024, Номер 32, С. 100650 - 100650
Опубликована: Сен. 17, 2024
Язык: Английский
La radiologia medica, Год журнала: 2021, Номер 126(12), С. 1571 - 1583
Опубликована: Дек. 1, 2021
Язык: Английский
Процитировано
159
Biomolecules, Год журнала: 2020, Номер 10(7), С. 984 - 984
Опубликована: Июль 1, 2020
In this study, we used panoramic X-ray images to classify and clarify the accuracy of different dental implant brands via deep convolutional neural networks (CNNs) with transfer-learning strategies. For objective labeling, 8859 11 systems were from digital radiographs obtained patients who underwent treatment at Kagawa Prefectural Central Hospital, Japan, between 2005 2019. Five CNN models (specifically, a basic three layers, VGG16 VGG19 models, finely tuned VGG19) evaluated for classification. Among five model exhibited highest classification performance. The was second best, followed by normal VGG16. We confirmed that CNNs could accurately types images.
Язык: Английский
Процитировано
149
British Journal of Radiology, Год журнала: 2020, Номер 93(1106)
Опубликована: Янв. 22, 2020
Advances in computing hardware and software platforms have led to the recent resurgence artificial intelligence (AI) touching almost every aspect of our daily lives by its capability for automating complex tasks or providing superior predictive analytics. AI applications are currently spanning many diverse fields from economics entertainment, manufacturing, as well medicine. Since modern AI’s inception decades ago, practitioners radiological sciences been pioneering development implementation medicine, particularly areas related diagnostic imaging therapy. In this anniversary article, we embark on a journey reflect learned lessons past chequered history. We further summarize current status sciences, highlighting, with examples, impressive achievements effect re-shaping practice medical radiotherapy computer-aided detection, diagnosis, prognosis, decision support. Moving beyond commercial hype into reality, discuss challenges overcome, achieve promised hope better precision healthcare each patient while reducing cost burden their families society at large.
Язык: Английский
Процитировано
84
Physica Medica, Год журнала: 2021, Номер 85, С. 175 - 191
Опубликована: Май 1, 2021
Язык: Английский
Процитировано
81
Radiation Oncology, Год журнала: 2023, Номер 18(1)
Опубликована: Март 14, 2023
Abstract Recent years have seen both a fresh knowledge of cancer and impressive advancements in its treatment. However, the clinical treatment paradigm is still difficult to implement twenty-first century due rise prevalence. Radiotherapy (RT) crucial component that helpful for almost all types. The accuracy RT dosage delivery increasing as result quick development computer imaging technology. use image-guided radiation (IGRT) has improved outcomes decreased toxicity. Online adaptive radiotherapy will be made possible by magnetic resonance imaging-guided (MRgRT) using linear accelerator (MR-Linac), which enhance visibility malignancies. This review's objectives are examine benefits MR-Linac approach from perspective various patients' prognoses suggest prospective areas additional study.
Язык: Английский
Процитировано
24
Advances in healthcare information systems and administration book series, Год журнала: 2024, Номер unknown, С. 89 - 110
Опубликована: Фев. 9, 2024
Radiation therapy (or radiation oncology) plays a crucial role in the treatment of cancer, requiring advanced medical practices and strong health literacy on part healthcare professionals. This chapter aims to explore with literature review how emerging technologies can be integrated into improve patient effectiveness practice. The application such as virtual reality, artificial intelligence, digital communication radiotherapy highlights their implications for professional education attitude, treatment, development optimization protocols. Nowadays, knowledge has become tool meet challenges an increasingly digitized society. Staying up-to-date understanding key navigating this landscape. ability learn adapt quickly also valuable skill during constant change global
Язык: Английский
Процитировано
15
Radiation Oncology, Год журнала: 2021, Номер 16(1)
Опубликована: Фев. 25, 2021
In breast cancer patients receiving radiotherapy (RT), accurate target delineation and reduction of radiation doses to the nearby normal organs is important. However, manual clinical volume (CTV) organs-at-risk (OARs) segmentation for treatment planning increases physicians' workload inter-physician variability considerably. this study, we evaluated potential benefits deep learning-based auto-segmented contours by comparing them manually delineated patients.CTVs bilateral breasts, regional lymph nodes, OARs (including heart, lungs, esophagus, spinal cord, thyroid) were on computed tomography scans 111 who received breast-conserving surgery. Subsequently, a two-stage convolutional neural network algorithm was used. Quantitative metrics, including Dice similarity coefficient (DSC) 95% Hausdorff distance, qualitative scoring two panels from 10 institutions used analysis. Inter-observer time assessed; furthermore, dose-volume histograms dosimetric parameters also analyzed using another set patient data.The correlation between acceptable OARs, with mean DSC higher than 0.80 all OARs. addition, CTVs showed favorable results, DSCs 0.70 node CTVs. Furthermore, subjective that results median score at least 8 (possible range: 0-10) (1) differences (2) extent which auto-segmentation would assist physicians in practice. The minimal.The feasibility RT demonstrated. Although cannot be substitute oncologists, it useful tool excellent assisting oncologists future. Trial registration Retrospectively registered.
Язык: Английский
Процитировано
54
Radiotherapy and Oncology, Год журнала: 2022, Номер 173, С. 62 - 68
Опубликована: Май 23, 2022
Язык: Английский
Процитировано
35
Applied Sciences, Год журнала: 2022, Номер 12(7), С. 3223 - 3223
Опубликована: Март 22, 2022
In recent decades, artificial intelligence (AI) tools have been applied in many medical fields, opening the possibility of finding novel solutions for managing very complex and multifactorial problems, such as those commonly encountered radiotherapy (RT). We conducted a PubMed Scopus search to identify AI application field RT limited last four years. total, 1824 original papers were identified, 921 analyzed by considering phase workflow according approaches. permits processing large quantities information, data, images stored oncology information systems, process that is not manageable individuals or groups. allows iterative tasks datasets (e.g., delineating normal tissues optimal planning solutions) might support entire community working various sectors RT, summarized this overview. AI-based are now on roadmap workflow, mainly segmentation, generation synthetic images, outcome prediction. Several concerns raised, including need harmonization while overcoming ethical, legal, skill barriers.
Язык: Английский
Процитировано
33
Sensors, Год журнала: 2025, Номер 25(2), С. 531 - 531
Опубликована: Янв. 17, 2025
The integration of deep learning (DL) into image processing has driven transformative advancements, enabling capabilities far beyond the reach traditional methodologies. This survey offers an in-depth exploration DL approaches that have redefined processing, tracing their evolution from early innovations to latest state-of-the-art developments. It also analyzes progression architectural designs and paradigms significantly enhanced ability process interpret complex visual data. Key such as techniques improving model efficiency, generalization, robustness, are examined, showcasing DL's address increasingly sophisticated image-processing tasks across diverse domains. Metrics used for rigorous evaluation discussed, underscoring importance performance assessment in varied application contexts. impact is highlighted through its tackle challenges generate actionable insights. Finally, this identifies potential future directions, including emerging technologies like quantum computing neuromorphic architectures efficiency federated privacy-preserving training. Additionally, it highlights combining with edge explainable artificial intelligence (AI) scalability interpretability challenges. These advancements positioned further extend applications DL, driving innovation processing.
Язык: Английский
Процитировано
1