The current landscape of artificial intelligence in oral and maxillofacial surgery– a narrative review

Oral and Maxillofacial Surgery, Journal Year: 2025, Volume and Issue: 29(1)

Published: Jan. 17, 2025

Language: Английский

---

Fully automated brain resection cavity delineation for radiation target volume definition in glioblastoma patients using deep learning

Radiation Oncology, Journal Year: 2020, Volume and Issue: 15(1)

Published: May 6, 2020

Abstract Background Automated brain tumor segmentation methods are computational algorithms that yield delineation from, in this case, multimodal magnetic resonance imaging (MRI). We present an automated method and its results for resection cavity (RC) glioblastoma multiforme (GBM) patients using deep learning (DL) technologies. Methods Post-operative, T1w with without contrast, T2w fluid attenuated inversion recovery MRI studies of 30 GBM were included. Three radiation oncologists manually delineated the RC to obtain a reference segmentation. developed DL method, which utilizes all four sequences learn perform delineations. evaluated terms Dice coefficient (DC) estimated volume measurements. Results Median DC three oncologist 0.85 (interquartile range [IQR]: 0.08), 0.84 (IQR: 0.07), 0.86 0.07). The automatic compared different raters 0.83 0.14), 0.81 0.12), 0.13) was significantly lower among (chi-square = 11.63, p 0.04). did not detect statistically significant difference measured volumes (Kruskal-Wallis test: chi-square 1.46, 0.69). main sources error due signal inhomogeneity similar intensity patterns between tissues. Conclusions proposed approach yields promising proof concept study. Compared human experts, still subpar.

Language: Английский

---

Artificial Intelligence in radiotherapy: state of the art and future directions

Medical Oncology, Journal Year: 2020, Volume and Issue: 37(6)

Published: April 22, 2020

Language: Английский

---

Machine learning in dental, oral and craniofacial imaging: a review of recent progress

PeerJ, Journal Year: 2021, Volume and Issue: 9, P. e11451 - e11451

Published: May 17, 2021

Artificial intelligence has been emerging as an increasingly important aspect of our daily lives and is widely applied in medical science. One major application artificial science imaging. As a component intelligence, many machine learning models are diagnosis treatment with the advancement technology imaging facilities. The popularity convolutional neural network dental, oral craniofacial heightening, it continually to broader spectrum scientific studies. Our manuscript reviews fundamental principles rationales behind learning, summarizes its research progress recent applications specifically It also problems that remain be resolved evaluates prospect future development this field study.

Language: Английский

---

Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning

Frontiers in Oncology, Journal Year: 2023, Volume and Issue: 13

Published: April 6, 2023

Organ-at-risk segmentation for head and neck cancer radiation therapy is a complex time-consuming process (requiring up to 42 individual structure, may delay start of treatment or even limit access function-preserving care. Feasibility using deep learning (DL) based autosegmentation model reduce contouring time without compromising contour accuracy assessed through blinded randomized trial oncologists (ROs) retrospective, de-identified patient data.

Language: Английский

---

Using Auto-Segmentation to Reduce Contouring and Dose Inconsistency in Clinical Trials: The Simulated Impact on RTOG 0617

International Journal of Radiation Oncology*Biology*Physics, Journal Year: 2020, Volume and Issue: 109(5), P. 1619 - 1626

Published: Nov. 13, 2020

Language: Английский

---

External validation of deep learning-based contouring of head and neck organs at risk

Physics and Imaging in Radiation Oncology, Journal Year: 2020, Volume and Issue: 15, P. 8 - 15

Published: July 1, 2020

Background and purposeHead neck (HN) radiotherapy can benefit from automatic delineation of tumor surrounding organs because the complex anatomy regular need for adaptation. The aim this study was to assess performance a commercially available deep learning contouring (DLC) model on an external validation set.Materials methodsThe CT-based DLC model, trained at University Medical Center Groningen (UMCG), applied independent set 58 patients Radboud (RUMC). results were compared RUMC manual reference using Dice similarity coefficient (DSC) 95th percentile Hausdorff distance (HD95). Craniocaudal spatial information added by calculating binned measures. In addition, qualitative evaluation acceptance contours in both groups observers.ResultsGood correspondence shown mandible (DSC 0.90; HD95 3.6 mm). Performance reasonable glandular OARs, brainstem oral cavity 0.78–0.85, 3.7–7.3 other aerodigestive tract OARs showed only moderate agreement 0.53–0.65, around 9 measures displayed largest deviations caudally and/or cranially.ConclusionsThis demonstrates that provide starting point when patient cohort. did not reveal large differences interpretation guidelines between UMCG observers.

Language: Английский

---

Automatic clinical target volume delineation for cervical cancer in CT images using deep learning

Medical Physics, Journal Year: 2021, Volume and Issue: 48(7), P. 3968 - 3981

Published: April 27, 2021

Purpose Accurately delineating clinical target volumes (CTV) is essential for completing radiotherapy plans but time‐consuming, labor‐intensive, and prone to inter‐observer variation. Automating CTV delineation has the benefits of both speeding up contouring process improving quality contours. Recently, auto‐segmentation approaches based on deep learning have achieved some improvements. However, unlike organ segmentation, contains potential tumor spread tissues or subclinical disease tissues, resulting in poorly defined margin interface irregular shape. It not reasonable directly apply segmentation algorithms tasks without considering unique characteristics shape margin. In this work, we propose a novel automatic algorithm addressing challenges. Methods Our method, called RA‐CTVNet, segments from cervical cancer CT images. RA‐CTVNet denotes our with A rea‐aware reweight strategy R ecursive refinement strategy. (1) order whole‐volume images delineate all CTVs one shot, method built upon popular 3D Unet architecture. We further extend it robust residual squeeze‐and‐excitation blocks better feature representation. (2) area‐aware which assigns different weights slices. The core adjusting model’s attention each slice. (3) terms trade‐off between providing performance improvements meeting limitations GPU memory, exploit new recursive address challenge. Results This retrospective study included 462 patients diagnosed who received June 2017 May 2019. Extensive experiments were conducted evaluate RA‐CTVNet. First, compared network architectures, Dice similarity coefficient (DSC). Second, ablation study. results showed that backbone, increased DSC by 3.3% average 1.6% average. Then, three human experts. performed than two experts while comparably third expert. Finally, multicenter evaluation was verify accuracy generalizability. Conclusions findings show able offer an efficient framework delineation. tailored can improve contours, great reducing burden increasing future, if more training data, are possible, bringing approach closer real practice.

Language: Английский

---

The future of MRI in radiation therapy: Challenges and opportunities for the MR community

Magnetic Resonance in Medicine, Journal Year: 2022, Volume and Issue: 88(6), P. 2592 - 2608

Published: Sept. 21, 2022

Abstract Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim this to achieve tumor control through the delivery ionizing radiation while preserving healthy tissues for minimal toxicity. Because relies on accurate localization target and surrounding tissues, imaging plays crucial role throughout chain. In planning phase, radiological images are essential defining volumes organs‐at‐risk, as well providing elemental composition (e.g., electron density) information dose calculations. At treatment, onboard informs patient setup could be used guide placement sites affected by motion. Imaging also an important tool response assessment plan adaptation. MRI, with its excellent soft tissue contrast capacity probe functional properties, holds great untapped potential transforming paradigms in therapy. MR Therapy ISMRM Study Group was established provide forum within community discuss unmet needs fuel opportunities further advancement MRI applications. During summer 2021, study group organized first virtual workshop, attended diverse international clinicians, scientists, clinical physicists, explore our predictions future next 25 years. This article reviews findings from event considers challenges reaching vision expanding field.

Language: Английский

---

U-net architecture with embedded Inception-ResNet-v2 image encoding modules for automatic segmentation of organs-at-risk in head and neck cancer radiation therapy based on computed tomography scans

Physics in Medicine and Biology, Journal Year: 2022, Volume and Issue: 67(11), P. 115007 - 115007

Published: Feb. 8, 2022

Purpose.The purpose of this study was to utilize a deep learning model with an advanced inception module automatically contour critical organs on the computed tomography (CT) scans head and neck cancer patients who underwent radiation therapy treatment interpret clinical suitability results through activation mapping.Materials methods.This included 25 that were delineated by expert oncologists. Contoured medical images 964 sourced from publicly available TCIA database. The proportion training, validation, testing samples for development 65%, 25%, 10% respectively. CT segmentation masks augmented shift, scale, rotate transformations. Additionally, pre-processed using contrast limited adaptive histogram equalization enhance soft tissue while contours subjected morphological operations ensure their structural integrity. based U-Net architecture embedded Inception-ResNet-v2 blocks trained over 100 epochs batch size 32 rate optimizer. loss function combined Jaccard Index binary cross entropy. performance evaluated Dice Score, Index, Hausdorff Distances. interpretability analyzed guided gradient-weighted class mapping.Results.The mean Distance averaged all structures 0.82 ± 0.10, 0.71 1.51 1.17 mm respectively data sets. Scores 86.4% compared within range or better than published interobserver variability derived multi-institutional studies. average training time 8 h per anatomical structure. full anatomy network required only 6.8 s patient.Conclusions.High accuracy obtained large, set, short clinically-realistic prediction reasoning make proposed in work feasible solution scan environment.

Language: Английский

---