Medical physics最新文献

Background: Sparse-view CT shortens scan time and reduces radiation dose but results in severe streak artifacts due to insufficient sampling data. Deep learning methods can now suppress these artifacts and improve image quality in sparse-view CT reconstruction.

Purpose: The quality of sparse-view CT reconstructed images can still be improved. Additionally, the interpretability of deep learning-based optimization methods for these reconstruction images is lacking, and the role of different network layers in artifact removal requires further study. Moreover, the optimization capability of these methods for reconstruction images from various sparse views needs enhancement. This study aims to improve the network's optimization ability for sparse-view reconstructed images, enhance interpretability, and boost generalization by establishing multiple network structures and datasets.

Methods: In this paper, we developed a sparse-view CT reconstruction images improvement network (SRII-Net) based on U-Net. We added a copy pathway in the network and designed a residual image output block to boost the network's performance. Multiple networks with different connectivity structures were established using SRII-Net to analyze the contribution of each layer to artifact removal, improving the network's interpretability. Additionally, we created multiple datasets with reconstructed images of various sampling views to train and test the proposed network, investigating how these datasets from different sampling views affect the network's generalization ability.

Results: The results show that the proposed method outperforms current networks, with significant improvements in metrics like PSNR and SSIM. Image optimization time is at the millisecond level. By comparing the performance of different network structures, we've identified the impact of various hierarchical structures. The image detail information learned by shallow layers and the high-level abstract feature information learned by deep layers play a crucial role in optimizing sparse-view CT reconstruction images. Training the network with multiple mixed datasets revealed that, under a certain amount of data, selecting the appropriate categories of sampling views and their corresponding samples can effectively enhance the network's optimization ability for reconstructing images with different sampling views.

Conclusions: The network in this paper effectively suppresses artifacts in reconstructed images with different sparse views, improving generalization. We have also created diverse network structures and datasets to deepen the understanding of artifact removal in deep learning networks, offering insights for noise reduction and image enhancement in other imaging methods.

Background: Proton pencil beam scanning (PBS) treatment planning for head and neck (H&N) cancers is a time-consuming and experience-demanding task where a large number of potentially conflicting planning objectives are involved. Deep reinforcement learning (DRL) has recently been introduced to the planning processes of intensity-modulated radiation therapy (IMRT) and brachytherapy for prostate, lung, and cervical cancers. However, existing DRL planning models are built upon the Q-learning framework and rely on weighted linear combinations of clinical metrics for reward calculation. These approaches suffer from poor scalability and flexibility, that is, they are only capable of adjusting a limited number of planning objectives in discrete action spaces and therefore fail to generalize to more complex planning problems.

Purpose: Here we propose an automatic treatment planning model using the proximal policy optimization (PPO) algorithm in the policy gradient framework of DRL and a dose distribution-based reward function for proton PBS treatment planning of H&N cancers.

Methods: The planning process is formulated as an optimization problem. A set of empirical rules is used to create auxiliary planning structures from target volumes and organs-at-risk (OARs), along with their associated planning objectives. Special attention is given to overlapping structures with potentially conflicting objectives. These planning objectives are fed into an in-house optimization engine to generate the spot monitor unit (MU) values. A decision-making policy network trained using PPO is developed to iteratively adjust the involved planning objective parameters. The policy network predicts actions in a continuous action space and guides the treatment planning system to refine the PBS treatment plans using a novel dose distribution-based reward function. A total of 34 H&N patients (30 for training and 4 for test) and 26 liver patients (20 for training, 6 for test) are included in this study to train and verify the effectiveness and generalizability of the proposed method.

Results: Proton H&N treatment plans generated by the model show improved OAR sparing with equal or superior target coverage when compared with human-generated plans. Moreover, additional experiments on liver cancer demonstrate that the proposed method can be successfully generalized to other treatment sites.

Conclusions: The automatic treatment planning model can generate complex H&N plans with quality comparable or superior to those produced by experienced human planners. Compared with existing works, our method is capable of handling more planning objectives in continuous action spaces. To the best of our knowledge, this is the first DRL-based automatic treatment planning model capable of achieving human-level performance for H&N cancers.

Background: Novel motion-compensated treatment techniques on the MR-linac can address adverse intra-fraction motion effects. These techniques involve beam gating or intra-fraction adaptations of the treatment plan based on real-time magnetic resonance imaging (MRI) performed during treatment. For quality assurance (QA) of these workflows, a multi-purpose motion platform is desirable. This platform should accommodate various phantoms, enabling multiple QA workflows.

Purpose: This study aims to evaluate the new IBA QUASAR Motion MR Platform for use in the 1.5 T MR-linac.

Methods: The motion platform was assessed for several magnetic resonance (MR) characteristics, including spurious noise generation and B0&B1 homogeneity. In addition, the motion platform's motion accuracy and beam attenuation were assessed. An application was shown with a ScandiDos Delta4 Phantom+ MR demonstrating patient-specific plan QA of gated treatments using time-resolved dosimetry that includes motion based on a patient's respiratory motion trace.

Results: All MR characterization measurements were within the set tolerances for MRI QA. The motion platform motion accuracy showed excellent agreement with the reference, with a standard deviation of the amplitude of 0.01  mm (20 kg load) for the motor's self-estimated positions and 0.22 mm (no load) for the images acquired with the electronic portal imager. Beam attenuation was found to be 11.8%. The combination of the motion platform and Delta4 demonstrated motion-included dosimetry at high temporal and spatial resolutions. Motion influenced the measured dose in non-gated treatments by up to -20.1%, while gated deliveries showed differences of up to -1.7% for selected diodes.

Conclusion: The motion platform was found to be usable in a 1.5 T magnetic field, and for all MR characterization experiments, no influence from the motion platform was observed. This motion platform enables to perform motion-included QA, with a measurement device of choice.

Background: Breast cancer screening via mammography plays a crucial role in early detection, significantly impacting women's health outcomes worldwide. However, the manual analysis of mammographic images is time-consuming and requires specialized expertise, presenting substantial challenges in medical practice.

Purpose: To address these challenges, we introduce a CNN-Transformer based model tailored for breast cancer classification through mammographic analysis. This model leverages both prior and current images to monitor temporal changes, aiming to enhance the efficiency and accuracy (ACC) of computer-aided diagnosis systems by mimicking the detailed examination process of radiologists.

Methods: In this study, our proposed model incorporates a novel integration of a position-wise feedforward network and multi-head self-attention, enabling it to detect abnormal or cancerous changes in mammograms over time. Additionally, the model employs positional encoding and channel attention methods to accurately highlight critical spatial features, thus precisely differentiating between normal and cancerous tissues. Our methodology utilizes focal loss (FL) to precisely address challenging instances that are difficult to classify, reducing false negatives and false positives to improve diagnostic ACC.

Results: We compared our model with eight baseline models; specifically, we utilized only current images for the single model ResNet50 while employing both prior and current images for the remaining models in terms of accuracy (ACC), sensitivity (SEN), precision (PRE), specificity (SPE), F1 score, and area under the curve (AUC). The results demonstrate that the proposed model outperforms the baseline models, achieving an ACC of 90.80%, SEN of 90.80%, PRE of 90.80%, SPE of 90.88%, an F1 score of 90.95%, and an AUC of 92.58%. The codes and related information are available at https://github.com/NabaviLab/PCTM.

Conclusions: Our proposed CNN-Transformer model integrates both prior and current images, removes long-range dependencies, and enhances its capability for nuanced classification. The application of FL reduces false positive rate (FPR) and false negative rates (FNR), improving both SEN and SPE. Furthermore, the model achieves the lowest false discovery rate and FNR across various abnormalities, including masses, calcification, and architectural distortions (ADs). These low error rates highlight the model's reliability and underscore its potential to improve early breast cancer detection in clinical practice.

Background: In X-ray computed tomography (CT), metal-induced beam hardening artifacts arise from the complex interactions between polychromatic X-ray beams and metallic objects, leading to degraded image quality and impeding accurate diagnosis. A previously proposed metal-induced beam hardening correction (MBHC) method provides a theoretical framework for addressing nonlinear artifacts through mathematical analysis, with its effectiveness demonstrated by numerical simulations and phantom experiments. However, in practical applications, this method relies on precise segmentation of highly attenuating materials and parameter estimations, which limit its ability to fully correct artifacts caused by the intricate interactions between metals and other dense materials, such as bone or teeth.

Purpose: This study aims to develop a parameter-free MBHC method that eliminates the need for accurate segmentation and parameter estimations, thereby addressing the limitations of the original MBHC approach.

Methods: The proposed method employs implicit neural representations (INR) to generate two tomographic images: one representing the monochromatic attenuation distribution at a specific energy level, and another capturing the nonlinear beam hardening effects caused by the polychromatic nature of X-ray beams. A loss function drives the generation of these images, where the predicted projection data is nonlinearly modeled by the combination of the two images. This approach eliminates the need for geometric and parameter estimation of metals, providing a more generalized solution.

Results: Numerical and phantom experiments demonstrates that the proposed method effectively reduces beam hardening artifacts caused by interactions between highly attenuating materials such as metals, bone, and teeth. Additionally, the proposed INR-based method demonstrates potential in addressing challenges related to data insufficiencies, such as photon starvation and truncated fields of view in CT imaging.

Conclusions: The proposed generalized MBHC method provides high-quality image reconstructions without requiring parameter estimations and segmentations, offering a robust solution for reducing metal-induced beam hardening artifacts in CT imaging.

Background: Computed tomography angiography (CTA) is used to screen for coronary artery calcification. As the coronary artery has complicated structure and tiny lumen, manual screening is a time-consuming task. Recently, many deep learning methods have been proposed for the segmentation (SEG) of coronary artery and calcification, however, they often neglect leveraging related anatomical prior knowledge, resulting in low accuracy and instability.

Purpose: This study aims to build a deep learning based SEG framework, which leverages anatomical prior knowledge of coronary artery and calcification, to improve the SEG accuracy. Moreover, based on the SEG results, this study also try to reveal the predictive ability of the volume ratio of coronary artery and calcification for rotational atherectomy (RA).

Methods: We present a new SEG framework, which is composed of four modules: the variational autoencoder based centerline extraction (CE) module, the self-attention (SA) module, the logic operation (LO) module, and the SEG module. Specifically, the CE module is used to crop a series of 3D CTA patches along the coronary artery, from which the continuous property of vessels can be utilized by the SA module to produce vessel-related features. According to the spatial relations between coronary artery lumen and calcification regions, the LO module with logic union and intersection is designed to refine the vessel-related features into lumen- and calcification-related features, based on which SEG results can be produced by the SEG module.

Results: Experimental results demonstrate that our framework outperforms the state-of-the-art methods on CTA image dataset of 72 patients with statistical significance. Ablation experiments confirm that the proposed modules have positive impacts to the SEG results. Moreover, based on the volume ratio of segmented coronary artery and calcification, the prediction accuracy of RA is 0.75.

Conclusions: Integrating anatomical prior knowledge of coronary artery and calcification into the deep learning based SEG framework can effectively enhance the performance. Moreover, the volume ratio of segmented coronary artery and calcification is a good predictive factor for RA.