Combining autoencoder with clustering analysis for anomaly detection in radiotherapy plans

Huang, Peng; Yan, Hui; Song, Zhiyue; Ye, Xu; Hu, Zhihui; Dai, Jing

doi:10.21037/qims-22-825

Cited by 2 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unsupervised learning has been used in medical imaging analysis for various tasks, such as image registration, data compression, and dimensionality reduction [ 72 , 73 ]. Some examples of unsupervised learning algorithms that have been used in medical imaging analysis include k-means clustering, principal component analysis (PCA), and autoencoders [ 74 , 75 , 76 ].…”

Section: Convolutional Neural Network Supervised Learning and Unsuper...mentioning

confidence: 99%

Artificial Intelligence Frameworks to Detect and Investigate the Pathophysiology of Spaceflight Associated Neuro-Ocular Syndrome (SANS)

Ong,

Waisberg,

Masalkhi

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

Spaceflight associated neuro-ocular syndrome (SANS) is a unique phenomenon that has been observed in astronauts who have undergone long-duration spaceflight (LDSF). The syndrome is characterized by distinct imaging and clinical findings including optic disc edema, hyperopic refractive shift, posterior globe flattening, and choroidal folds. SANS serves a large barrier to planetary spaceflight such as a mission to Mars and has been noted by the National Aeronautics and Space Administration (NASA) as a high risk based on its likelihood to occur and its severity to human health and mission performance. While it is a large barrier to future spaceflight, the underlying etiology of SANS is not well understood. Current ophthalmic imaging onboard the International Space Station (ISS) has provided further insights into SANS. However, the spaceflight environment presents with unique challenges and limitations to further understand this microgravity-induced phenomenon. The advent of artificial intelligence (AI) has revolutionized the field of imaging in ophthalmology, particularly in detection and monitoring. In this manuscript, we describe the current hypothesized pathophysiology of SANS and the medical diagnostic limitations during spaceflight to further understand its pathogenesis. We then introduce and describe various AI frameworks that can be applied to ophthalmic imaging onboard the ISS to further understand SANS including supervised/unsupervised learning, generative adversarial networks, and transfer learning. We conclude by describing current research in this area to further understand SANS with the goal of enabling deeper insights into SANS and safer spaceflight for future missions.

show abstract

Section: Convolutional Neural Network Supervised Learning and Unsuper...mentioning

confidence: 99%

Artificial Intelligence Frameworks to Detect and Investigate the Pathophysiology of Spaceflight Associated Neuro-Ocular Syndrome (SANS)

Ong,

Waisberg,

Masalkhi

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

show abstract

Unsupervised machine learning model for detecting anomalous volumetric modulated arc therapy plans for lung cancer patients

Huang,

Shang,

Fan

et al. 2024

Front. Big Data

View full text Add to dashboard Cite

PurposeVolumetric modulated arc therapy (VMAT) is a new treatment modality in modern radiotherapy. To ensure the quality of the radiotherapy plan, a physics plan review is routinely conducted by senior clinicians; however, this process is less efficient and less accurate. In this study, a multi-task AutoEncoder (AE) is proposed to automate anomaly detection of VMAT plans for lung cancer patients.MethodsThe feature maps are first extracted from a VMAT plan. Then, a multi-task AE is trained based on the input of a feature map, and its output is the two targets (beam aperture and prescribed dose). Based on the distribution of reconstruction errors on the training set, a detection threshold value is obtained. For a testing sample, its reconstruction error is calculated using the AE model and compared with the threshold value to determine its classes (anomaly or regular). The proposed multi-task AE model is compared to the other existing AE models, including Vanilla AE, Contractive AE, and Variational AE. The area under the receiver operating characteristic curve (AUC) and the other statistics are used to evaluate the performance of these models.ResultsAmong the four tested AE models, the proposed multi-task AE model achieves the highest values in AUC (0.964), accuracy (0.821), precision (0.471), and F1 score (0.632), and the lowest value in FPR (0.206).ConclusionThe proposed multi-task AE model using two-dimensional (2D) feature maps can effectively detect anomalies in radiotherapy plans for lung cancer patients. Compared to the other existing AE models, the multi-task AE is more accurate and efficient. The proposed model provides a feasible way to carry out automated anomaly detection of VMAT plans in radiotherapy.

show abstract

Combining autoencoder with clustering analysis for anomaly detection in radiotherapy plans

Cited by 2 publications

References 41 publications

Artificial Intelligence Frameworks to Detect and Investigate the Pathophysiology of Spaceflight Associated Neuro-Ocular Syndrome (SANS)

Artificial Intelligence Frameworks to Detect and Investigate the Pathophysiology of Spaceflight Associated Neuro-Ocular Syndrome (SANS)

Unsupervised machine learning model for detecting anomalous volumetric modulated arc therapy plans for lung cancer patients

Contact Info

Product

Resources

About