Medical physics最新文献

{"title":"Multi-pathway fusion network for early-stage breast tumor segmentation from MRI.","authors":"Yeru Xia, Ning Qu, Yongzhong Lin, Wenzhi Zhao, Fei Teng, Wenlong Liu","doi":"10.1002/mp.17823","DOIUrl":"https://doi.org/10.1002/mp.17823","url":null,"abstract":"<p><strong>Background: </strong>Breast cancer is one of the most common cancers in women, with a notably high mortality rate. Early diagnosis can improve survival rates. However, early-stage breast tumors suffer challenges for accurate detection and are hard to detect due to their tiny sizes and blurry edges, thereby obtaining degraded performance.</p><p><strong>Purpose: </strong>To solve the above issues, this study aims to develop a robust model for the early-stage breast tumor segmentation from magnetic resonance imaging (MRI) and to provide a quality assessment for early-stage breast cancer.</p><p><strong>Methods: </strong>We propose an early-stage breast tumor segmentation method named MPNet, which utilizes a multi-pathway fusion strategy, focusing on preserving tumor boundary information while processing their contextual information. Our approach consists of two main pathways: the detail information pathway (DIP) and the context enhancement pathway (CEP). The DIP preserves the tumor boundary details by capturing high-resolution features, while the CEP enhances the semantic information by enlarging the receptive field and introducing quarter-scale global self-attention for global contextual information. We also design a bilateral feature fusion module to fuse the representations from different pathways, facilitating interaction between both types of features. Additionally, we collect a clinical dataset for early-stage breast cancer diagnosis, comprising 260 diverse cases.</p><p><strong>Results: </strong>Comparative experiments show the effectiveness of our method on clinical data, where the mean intersection over union and Dice similarity coefficient are 87.41% and 85.69%, respectively.</p><p><strong>Conclusions: </strong>Overall, MPNet demonstrates satisfying performance on segmenting early-stage breast tumors with tiny sizes by preserving boundary details and enhancing contextual information. Extensive experiments demonstrate that MPNet outperforms state-of-the-art methods for enhancing early breast cancer intervention.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144013013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combining frequency navigator and optical prospective motion correction for functional MRS during motor activation at 3 T: A feasibility study.","authors":"Yiling Liu, Yu Wei, Yanxing Yang, Xinyue Zhang, Jiaqi Zhao, Philip Kenneth Lee, Assaf Tal, Hao Chen, Zhiyong Zhang","doi":"10.1002/mp.17861","DOIUrl":"https://doi.org/10.1002/mp.17861","url":null,"abstract":"<p><strong>Background: </strong>Functional magnetic resonance spectroscopy (fMRS) is a powerful tool for investigating neurometabolic dynamics in response to physiological stimuli in vivo. However, fMRS is challenging due to the low SNR of the spectrum and small neurochemical changes. Many existing studies were conducted at ultrahigh field strength (7 T). To translate fMRS studies to the more common 3 T clinical field strength, averaging more transients can improve SNR. However, this results in a long scan time compounds physiological motion which incurs degradations in spectrum quality and consistency.</p><p><strong>Purpose: </strong>Investigate the feasibility of PRESS fMRS studies at 3 T assisted by the combination of prospective motion correction (PMC) system and frequency navigator.</p><p><strong>Methods: </strong>A combination of markerless PMC system and frequency navigator was applied to an fMRS study during motor activation with a clinical PRESS protocol at 3 T. Twenty-one volunteers were involved in the study. The functional task paradigm consisted of three blocks REST-TASK-REST. During the TASK period, the volunteer was asked to squeeze a hand-hold balloon according to a red rectangle flashing at 2 Hz shown centered in a black background. The same motor task was repeated twice, once with PMC ON and once with PMC OFF. The data were processed and quantified by in-house VDI software. The following two analyses were performed: a motion pattern analysis and a metabolite dynamics analysis. The motion analysis was used to compare the motion states when PMC was ON and OFF. The metabolite dynamic change was a key assessment for the fMRS study. It was estimated via <math> <semantics><mrow><mi>Δ</mi> <mo>=</mo> <mfrac> <mrow><msub><mi>μ</mi> <mrow><mi>t</mi> <mi>a</mi> <mi>s</mi> <mi>k</mi></mrow> </msub> <mo>-</mo> <msub><mi>μ</mi> <mrow><mi>r</mi> <mi>e</mi> <mi>s</mi> <mi>t</mi></mrow> </msub> </mrow> <msub><mi>μ</mi> <mrow><mi>r</mi> <mi>e</mi> <mi>s</mi> <mi>t</mi></mrow> </msub> </mfrac> <mspace></mspace> <mo>≡</mo> <mfrac><mrow><mi>Δ</mi> <mi>μ</mi></mrow> <msub><mi>μ</mi> <mrow><mi>r</mi> <mi>e</mi> <mi>s</mi> <mi>t</mi></mrow> </msub> </mfrac> </mrow> <annotation>${{Delta}} = frac{{{mu }_{task} - {mu }_{rest}}}{{{mu }_{rest}}} equiv frac{{Delta mu }}{{{mu }_{rest}}}$</annotation></semantics> </math> . p-values < 0.05 were considered significant.</p><p><strong>Results: </strong>A statistically significant increase in Glx of 5.73% when the PMC was switched on was observed. No statistically significant increase in any of the metabolites with PMC OFF was observed. The major singlets (tCho, tCr, and tNAA) for both PMC ON and OFF keep constant.</p><p><strong>Conclusions: </strong>With a markerless PMC system and frequency navigator, PRESS fMRS at 3 T is capable of detecting small changes of a few percent in Glx concentration during functional activation.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144050653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Continuous representation-based reconstruction for computed tomography.","authors":"Minwoo Yu, Junhyun Ahn, Jongduk Baek","doi":"10.1002/mp.17849","DOIUrl":"https://doi.org/10.1002/mp.17849","url":null,"abstract":"<p><strong>Background: </strong>Computed tomography (CT) imaging has been developed to acquire a higher resolution image for detecting early-stage lesions. However, the lack of spatial resolution of CT images is still a limitation to fully utilize the capabilities of display devices for radiologists.</p><p><strong>Purpose: </strong>This limitation can be addressed by improving the quality of the reconstructed image using super-resolution (SR) techniques without changing data acquisition protocols. In particular, local implicit representation-based techniques proposed in the field of low-level computer vision have shown promising performance, but their integration into CT image reconstruction is limited by considerable memory and runtime requirements due to excessive input data size.</p><p><strong>Methods: </strong>To address these limitations, we propose a continuous image representation-based CT image reconstruction (CRET) structure. Our CRET ensures fast and memory-efficient reconstruction for the specific region of interest (ROI) image by adapting our proposed sinogram squeezing and decoding via a set of sinusoidal basis functions. Furthermore, post-restoration step can be employed to mitigate residual artifacts and blurring effects, leading to improve image quality.</p><p><strong>Results: </strong>Our proposed method shows superior image quality than other local implicit representation methods and can be further improved with additional post-processing. In addition proposed structure achieves superior performance in terms of anthropomorphic observer model evaluation compared to conventional techniques. This results highlights that CRET can be used to improve diagnostic capabilities by setting the reconstruction resolution higher than the ground truth images in training.</p><p><strong>Conclusions: </strong>Our proposed CRET method offers a promising solution for improving CT image resolution while addressing excessive memory and runtime consumption. The source code of our proposed CRET is available at https://github.com/minwoo-yu/CRET.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144046748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Universal mapping and patient-specific prior implicit neural representation for enhanced high-resolution MRI in MRI-guided radiotherapy.","authors":"Yunxiang Li, Jie Deng, You Zhang","doi":"10.1002/mp.17863","DOIUrl":"https://doi.org/10.1002/mp.17863","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Magnetic resonance imaging (MRI), known for its superior soft tissue contrast, plays a crucial role in radiation therapy (RT). The introduction of MR-LINAC systems enables the use of on-board MRI for adaptive radiotherapy (ART) on the day of treatment to maximize treatment accuracy.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;Due to patient comfort considerations and the time constraints associated with adaptive radiation therapy (ART), reducing the resolution of on-board MRI to accelerate image acquisition can improve efficiency, especially when acquiring multiple MRIs with different contrast weightings. However, the low-resolution imaging makes it challenging to identify key anatomical structures, potentially limiting treatment precision. To address this challenge, super-resolution of on-board MRI has emerged as a viable solution.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;To achieve super-resolution for on-board MRI, this study proposed a universal anatomical mapping and patient-specific prior implicit neural representation (USINR) framework. Unlike traditional methods that interpolate solely based on individual on-board MR images, USINR can fully utilize the patient-specific anatomical information from a high-resolution prior MRI. In addition, USINR leverages knowledge about universal mapping between population-based prior MRIs and on-board MRIs, elevating the upper bound of super-resolution performance and enabling faster on-board fine-tuning.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;USINR was evaluated on three datasets, including IXI, BraTS, and an in-house abdominal dataset. It achieved state-of-the-art performance on all of them. For example, on the BraTS dataset, USINR was trained on 1151 paired training samples (for universal anatomical mapping) and tested on 50 patients. It achieved average SSIM, PSNR, and LPIPS scores of 0.9656, 37.12, and 0.0214, respectively, significantly outperforming the published state-of-the-art method SuperFormer, whose corresponding scores were 0.9488, 35.83, and 0.0388. Furthermore, USINR can complete patient-specific training in less than one minute, rendering it a favorable solution in time-constrained ART workflows. In addition to large-scale dataset evaluations, a case study was conducted on an in-house patient at UT Southwestern Medical Center. This case study included two MRI scans (a prior scan for plan simulation and a new one for on-board imaging) from a single patient with a long interval between two scans, during which the tumor size underwent a significant change. Despite these substantial anatomical changes between prior and on-board imaging, USINR was able to accurately capture the change in tumor size, highlighting its robustness for clinical applications.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;By combining knowledge of universal anatomical mapping with patient-specific prior implicit neural representation, USINR offers a novel and reliable approach for MRI super-resolution. This method enhances","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144060727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Instantaneous in vivo distal edge verification in intensity-modulated proton therapy by means of PET imaging.","authors":"Brian Zapien-Campos, Zahra Ahmadi Ganjeh, Giuliano Perotti-Bernardini, Jeffrey Free, Stefan Both, Peter Dendooven","doi":"10.1002/mp.17850","DOIUrl":"https://doi.org/10.1002/mp.17850","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Intensity-modulated proton therapy (IMPT) holds promise for improving outcomes in head-and-neck cancer (HNC) patients by enhancing organ-at-risk (OAR) sparing. A key challenge in IMPT is ensuring an accurate dose delivery at the distal edge of the tumor, where the steep dose gradients make treatment precision highly sensitive to uncertainties in both proton range and patient setup. Thus, IMPT conformality is increased by incorporating robust margins in the treatment optimization. However, an increment in the plan robustness could lead to an OAR overdosing. Therefore, an accurate distal edge verification during dose delivery is crucial to increase IMPT conformality by reducing optimization settings in treatment planning.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;This work aims to evaluate, in a quasi-clinical setting, a novel approach for accurate instantaneous proton beam distal edge verification in IMPT by means of spot-by-spot positron emission tomography (PET) imaging.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;An anthropomorphic head and neck phantom CIRS-731 HN was irradiated at the head and neck region. The targets were defined as 4 cm diameter spheres. A 60-ms delay was introduced between the proton beam spots in order to enable the spot-by-spot coincidence detection of the 511-keV photons resulting from positron annihilation following the positron emission from very short-lived positron-emitting, mainly &lt;sup&gt;12&lt;/sup&gt;N (T&lt;sub&gt;1/2&lt;/sub&gt; &lt;sub&gt; &lt;/sub&gt;= 11.0 ms). Additionally, modified irradiations were carried out using solid water slabs of 2 and 5 mm thickness in the beam path to assess the precision of the approach for detecting range deviations. The positron activity range (PAR) was determined from the 50% distal fall-off position of the 1D longitudinal positron activity profile derived from the 2D image reconstructions. Furthermore, Monte Carlo (MC) simulations were performed using an in-house RayStation/GATE MC framework to predict the positron activity images and verify the PAR measurements.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;PAR measurements achieved a precision between 1.5 and 3.6 mm (at 1.5σ clinical level) at the beam spot level within sub-second time scales. Measured PAR shifts of 1.6-2.1  and 4.2--.7 mm were observed with the 2- and 5-mm thickness range shifters, respectively, aligning with the corresponding proton dose range (PDR) shifts of 1.3-1.8 and 3.9-4.3 mm. The simulated PAR agrees with the measured PARs, showing an average range difference of ∼0.4 mm.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;This study demonstrated the feasibility of instantaneous distal edge verification using PET imaging by introducing beam spot delays during dose delivery. The findings represent a first step toward the clinical implementation of instantaneous in vivo distal edge verification. The approach contributes to the development of real-time range verification aimed at improving IMPT treatments by mitigating range and setup uncertainties, ther","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144055904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multimodal fusion network based on variational autoencoder for distinguishing SCLC brain metastases from NSCLC brain metastases.","authors":"Xue Linyan, Cao Jie, Zhou Kexuan, Chen Houquan, Qi Chaoyi, Yin Xiaosong, Wang Jianing, Yang Kun","doi":"10.1002/mp.17816","DOIUrl":"https://doi.org/10.1002/mp.17816","url":null,"abstract":"<p><strong>Background: </strong>Distinguishing small cell lung cancer brain metastases from non-small cell lung cancer brain metastases in MRI sequence images is crucial for the accurate diagnosis and treatment of lung cancer brain metastases. Multi-MRI modalities provide complementary and comprehensive information, but efficiently merging these sequences to achieve modality complementarity is challenging due to redundant information within radiomic features and heterogeneity across different modalities.</p><p><strong>Purpose: </strong>To address these challenges, we propose a novel multimodal fusion network, termed MFN-VAE, which utilizes a variational auto-encoder (VAE) to compress and aggregate radiomic features derived from MRI images.</p><p><strong>Methods: </strong>Initially, we extract radiomic features from areas of interest in MRI images across T1WI, FLAIR, and DWI modalities. A VAE encoder is then constructed to project these multimodal features into a latent space, where they are decoded into reconstruction features using a decoder. The encoder-decoder network is trained to extract the underlying feature representation of each modality, capturing both the consistency and specificity of each domain.</p><p><strong>Results: </strong>Experimental results on our collected dataset of lung cancer brain metastases demonstrate the encouraging performance of our proposed MFN-VAE. The method achieved a 0.888 accuracy and a 0.920 AUC (area under the curve), outperforming state-of-the-art methods across different modal combinations.</p><p><strong>Conclusions: </strong>In this study, we introduce the MFN-VAE, a new multimodal fusion network for differentiating small cell from non-small cell lung cancer brain metastases. Tested on a private dataset, MFN-VAE demonstrated high accuracy (ACC: 0.888; AUC: 0.920), effectively distinguishing between small cell lung cancer brain metastases (SCLC) and non-small cell lung cancer (NSCLC). The SHapley Additive explanation (SHAP) method was used to enhance model interpretability, providing clinicians with a reliable diagnostic tool. Overall, MFN-VAE shows great potential in improving the diagnosis and treatment of lung cancer brain metastases.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144028467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"X-ray CT metal artifact reduction using neural attenuation field prior.","authors":"Jooho Lee, Seongjun Kim, Junhyun Ahn, Adam S Wang, Jongduk Baek","doi":"10.1002/mp.17859","DOIUrl":"https://doi.org/10.1002/mp.17859","url":null,"abstract":"<p><strong>Background: </strong>The presence of metal objects in computed tomography (CT) imaging introduces severe artifacts that degrade image quality and hinder accurate diagnosis. While several deep learning-based metal artifact reduction (MAR) methods have been proposed, they often exhibit poor performance on unseen data and require large datasets to train neural networks.</p><p><strong>Purpose: </strong>In this work, we propose a sinogram inpainting method for metal artifact reduction that leverages a neural attenuation field (NAF) as a prior. This new method, dubbed NAFMAR, operates in a self-supervised manner by optimizing a model-based neural field, thus eliminating the need for large training datasets.</p><p><strong>Methods: </strong>NAF is optimized to generate prior images, which are then used to inpaint metal traces in the original sinogram. To address the corruption of x-ray projections caused by metal objects, a 3D forward projection of the original corrupted image is performed to identify metal traces. Consequently, NAF is optimized using a metal trace-masked ray sampling strategy that selectively utilizes uncorrupted rays to supervise the network. Moreover, a metal-aware loss function is proposed to prioritize metal-associated regions during optimization, thereby enhancing the network to learn more informed representations of anatomical features. After optimization, the NAF images are rendered to generate NAF prior images, which serve as priors to correct original projections through interpolation. Experiments are conducted to compare NAFMAR with other prior-based inpainting MAR methods.</p><p><strong>Results: </strong>The proposed method provides an accurate prior without requiring extensive datasets. Images corrected using NAFMAR showed sharp features and preserved anatomical structures. Our comprehensive evaluation, involving simulated dental CT and clinical pelvic CT images, demonstrated the effectiveness of NAF prior compared to other prior information, including the linear interpolation and data-driven convolutional neural networks (CNNs). NAFMAR outperformed all compared baselines in terms of structural similarity index measure (SSIM) values, and its peak signal-to-noise ratio (PSNR) value was comparable to that of the dual-domain CNN method.</p><p><strong>Conclusions: </strong>NAFMAR presents an effective, high-fidelity solution for metal artifact reduction in 3D tomographic imaging without the need for large datasets.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144002146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Segmentation-assisted vessel centerline extraction from cerebral CT Angiography.","authors":"Sijie Liu, Ruisheng Su, Jianghang Su, Wim H van Zwam, Pieter Jan van Doormaal, Aad van der Lugt, Wiro J Niessen, Theo van Walsum","doi":"10.1002/mp.17855","DOIUrl":"https://doi.org/10.1002/mp.17855","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The accurate automated extraction of brain vessel centerlines from Computed tomographic angiography (CTA) images plays an important role in diagnosing and treating cerebrovascular diseases such as stroke. Despite its significance, this task is complicated by the complex cerebrovascular structure and heterogeneous imaging quality.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;This study aims to develop and validate a segmentation-assisted framework designed to improve the accuracy and efficiency of brain vessel centerline extraction from CTA images. We streamline the process of lumen segmentation generation without additional annotation effort from physicians, enhancing the effectiveness of centerline extraction.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The framework integrates four modules: (1) pre-processing techniques that register CTA images with a CT atlas and divide these images into input patches, (2) lumen segmentation generation from annotated vessel centerlines using graph cuts and robust kernel regression, (3) a dual-branch topology-aware UNet (DTUNet) that optimizes the use of the annotated vessel centerlines and the generated lumen segmentation via a topology-aware loss (TAL) and its dual-branch structure, and (4) post-processing methods that skeletonize and refine the lumen segmentation predicted by the DTUNet.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;An in-house dataset derived from a subset of the MR CLEAN Registry is used to evaluate the proposed framework. The dataset comprises 10 intracranial CTA images, and 40 cube CTA sub-images with a resolution of &lt;math&gt; &lt;semantics&gt;&lt;mrow&gt;&lt;mn&gt;128&lt;/mn&gt; &lt;mo&gt;×&lt;/mo&gt; &lt;mn&gt;128&lt;/mn&gt; &lt;mo&gt;×&lt;/mo&gt; &lt;mn&gt;128&lt;/mn&gt;&lt;/mrow&gt; &lt;annotation&gt;$128 times 128 times 128$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; voxels. Via five-fold cross-validation on this dataset, we demonstrate that the proposed framework consistently outperforms state-of-the-art methods in terms of average symmetric centerline distance (ASCD) and overlap (OV). Specifically, it achieves an ASCD of 0.84, an &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;OV&lt;/mi&gt; &lt;mn&gt;1.0&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$textrm {OV}_{1.0}$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; of 0.839, and an &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;OV&lt;/mi&gt; &lt;mn&gt;1.5&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$textrm {OV}_{1.5}$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; of 0.885 for intracranial CTA images, and obtains an ASCD of 1.26, an &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;OV&lt;/mi&gt; &lt;mn&gt;1.0&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$textrm {OV}_{1.0}$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; of 0.779, and an &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;OV&lt;/mi&gt; &lt;mn&gt;1.5&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$textrm {OV}_{1.5}$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; of 0.824 for cube CTA sub-images. Subgroup analyses further suggest that the proposed framework holds promise in clinical applications for stroke diagnosis and treatment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;By automating the process of lumen segmentation generation and optimizing the network design of vessel centerline extraction, DTUnet achieves high performance without introduci","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144039437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-sequence brain tumor segmentation boosted by deep semantic features.","authors":"Ziman Yin, Zhengze Ni, Yuxiang Ren, Dong Nie, Zhenyu Tang","doi":"10.1002/mp.17845","DOIUrl":"https://doi.org/10.1002/mp.17845","url":null,"abstract":"<p><strong>Background: </strong>The main task of deep learning (DL) based brain tumor segmentation is to get accurate projection from learned image features to their corresponding semantic labels (i.e., brain tumor sub-regions). To achieve this goal, segmentation networks are required to learn image features with high intra-class consistency. However, brain tumor are known to be heterogeneous, and it often causes high diversity in image gray values which further influences the learned image features. Therefore, projecting such diverse image features (i.e., low intra-class consistency) to the same semantic label is often difficult and inefficient.</p><p><strong>Purpose: </strong>The purpose of this study is to address the issue of low intra-class consistency of image features learned from heterogeneous brain tumor regions and ease the projection of image features to their corresponding semantic labels. In this way, accurate segmentation of brain tumor can be achieved.</p><p><strong>Methods: </strong>We propose a new DL-based method for brain tumor segmentation, where a semantic feature module (SFM) is introduced to consolidate image features with meaningful semantic information and enhance their intra-class consistency. Specifically, in the SFM, deep semantic vectors are derived and used as prototypes to re-encode image features learned in the segmentation network. Since the relatively consistent deep semantic vectors, diversity of the resulting image features can be reduced; moreover, semantic information in the resulting image features can also be enriched, both facilitating accurate projection to the final semantic labels.</p><p><strong>Results: </strong>In the experiment, a public brain tumor dataset, BraTS2022 containing, multi-sequence MR images of 1251 patients is used to evaluate our method in the task of brain tumor sub-region segmentation, and the experimental results demonstrate that, benefiting from the SFM, our method outperforms the state-of-the-art methods with statistical significance ( <math> <semantics><mrow><mi>p</mi> <mo><</mo> <mn>0.05</mn></mrow> <annotation>$p<0.05$</annotation></semantics> </math> using the Wilcoxon signed rank test). Further ablation study shows that the proposed SFM can yield an improvement in segmentation accuracy (Dice index) of up to 11% comparing with that without the SFM.</p><p><strong>Conclusions: </strong>In DL-based segmentation, low intra-class consistency of learned image features degrades segmentation performance. The proposed SFM can effectively enhance the intra-class consistency with high-level semantic information, making the projection of image features to their corresponding semantic labels more accurate.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Singular value decomposition based under-sampling pattern optimization for MRI reconstruction.","authors":"Xinglong Liang, Luyi Han, Xinlin Zhang, Xinnian Li, Yue Sun, Tong Tong, Tao Tan, Ritse Mann","doi":"10.1002/mp.17860","DOIUrl":"https://doi.org/10.1002/mp.17860","url":null,"abstract":"<p><strong>Background: </strong>Magnetic resonance imaging (MRI) is a crucial medical imaging technique that can determine the structural and functional status of body tissues and organs. However, the prolonged MRI acquisition time increases the scanning cost and limits its use in less developed areas.</p><p><strong>Purpose: </strong>The objective of this study is to design a lightweight, data-driven under-sampling pattern for fastMRI to achieve a balance between MRI reconstruction quality and sampling time while also being able to be integrated with deep learning to further improve reconstruction quality.</p><p><strong>Methods: </strong>In this study, we attempted to establish a connection between k-space and the corresponding MRI through singular value decomposition(SVD). Specifically, we apply SVD to MRI to decouple it into multiple components, which are sorted by energy contribution. Then, the sampling points that match the energy contribution in the k-space, which correspond to each component are selected sequentially. Finally, the sampling points obtained from all components are merged to obtain a mask. This mask can be used directly as a sampler or integrated into deep learning as an initial or fixed sampling points.</p><p><strong>Results: </strong>The experiments were conducted on two public datasets, and the results demonstrate that when the mask generated based on our method is directly used as the sampler, the MRI reconstruction quality surpasses that of state-of-the-art heuristic samplers. In addition, when integrated into the deep learning models, the models converge faster and the sampler performance is significantly improved.</p><p><strong>Conclusions: </strong>The proposed lightweight data-driven sampling approach avoids time-consuming parameter tuning and the establishment of complex mathematical models, achieving a balance between reconstruction quality and sampling time.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144016124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}