{"title":"Decision support using machine learning for predicting adequate bladder filling in prostate radiotherapy: a feasibility study.","authors":"Nipon Saiyo, Kritsrun Assawanuwat, Patthra Janthawanno, Sumana Paduka, Kantamanee Prempetch, Thammasak Chanphol, Bualookkaew Sakchatchawan, Sangutid Thongsawad","doi":"10.1007/s12194-025-00916-z","DOIUrl":"https://doi.org/10.1007/s12194-025-00916-z","url":null,"abstract":"<p><p>This study aimed to develop a model for predicting the bladder volume ratio between daily CBCT and CT to determine adequate bladder filling in patients undergoing treatment for prostate cancer with external beam radiation therapy (EBRT). The model was trained using 465 datasets obtained from 34 prostate cancer patients. A total of 16 features were collected as input data, which included basic patient information, patient health status, blood examination laboratory results, and specific radiation therapy information. The ratio of the bladder volume between daily CBCT (dCBCT) and planning CT (pCT) was used as the model response. The model was trained using a bootstrap aggregation (bagging) algorithm with two machine learning (ML) approaches: classification and regression. The model accuracy was validated using other 93 datasets. For the regression approach, the accuracy of the model was evaluated based on the root mean square error (RMSE) and mean absolute error (MAE). By contrast, the model performance of the classification approach was assessed using sensitivity, specificity, and accuracy scores. The ML model showed promising results in the prediction of the bladder volume ratio between dCBCT and pCT, with an RMSE of 0.244 and MAE of 0.172 for the regression approach, sensitivity of 95.24%, specificity of 92.16%, and accuracy of 93.55% for the classification approach. The prediction model could potentially help the radiological technologist determine whether the bladder is full before treatment, thereby reducing the requirement for re-scan CBCT. HIGHLIGHTS: The bagging model demonstrates strong performance in predicting optimal bladder filling. The model achieves promising results with 95.24% sensitivity and 92.16% specificity. It supports therapists in assessing bladder fullness prior to treatment. It helps reduce the risk of requiring repeat CBCT scans.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144209825","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}
Murat Gurger, Omer Esmez, Sefa Key, Abdul Hafeez-Baig, Sengul Dogan, Turker Tuncer
{"title":"MobileTurkerNeXt: investigating the detection of Bankart and SLAP lesions using magnetic resonance images.","authors":"Murat Gurger, Omer Esmez, Sefa Key, Abdul Hafeez-Baig, Sengul Dogan, Turker Tuncer","doi":"10.1007/s12194-025-00918-x","DOIUrl":"https://doi.org/10.1007/s12194-025-00918-x","url":null,"abstract":"<p><p>The landscape of computer vision is predominantly shaped by two groundbreaking methodologies: transformers and convolutional neural networks (CNNs). In this study, we aim to introduce an innovative mobile CNN architecture designed for orthopedic imaging that efficiently identifies both Bankart and SLAP lesions. Our approach involved the collection of two distinct magnetic resonance (MR) image datasets, with the primary goal of automating the detection of Bankart and SLAP lesions. A novel mobile CNN, dubbed MobileTurkerNeXt, forms the cornerstone of this research. This newly developed model, comprising roughly 1 million trainable parameters, unfolds across four principal stages: the stem, main, downsampling, and output phases. The stem phase incorporates three convolutional layers to initiate feature extraction. In the main phase, we introduce an innovative block, drawing inspiration from ConvNeXt, EfficientNet, and ResNet architectures. The downsampling phase utilizes patchify average pooling and pixel-wise convolution to effectively reduce spatial dimensions, while the output phase is meticulously engineered to yield classification outcomes. Our experimentation with MobileTurkerNeXt spanned three comparative scenarios: Bankart versus normal, SLAP versus normal, and a tripartite comparison of Bankart, SLAP, and normal cases. The model demonstrated exemplary performance, achieving test classification accuracies exceeding 96% across these scenarios. The empirical results underscore the MobileTurkerNeXt's superior classification process in differentiating among Bankart, SLAP, and normal conditions in orthopedic imaging. This underscores the potential of our proposed mobile CNN in advancing diagnostic capabilities and contributing significantly to the field of medical image analysis.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144209826","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 multi-institutional survey on technical variations in total body irradiation in Japan.","authors":"Masayasu Kitagawa, Ryoichi Notake, Ryuta Nakahara, Shogo Hatanaka, Tatsunori Saho, Kengo Matsuda","doi":"10.1007/s12194-025-00894-2","DOIUrl":"10.1007/s12194-025-00894-2","url":null,"abstract":"<p><p>This study aimed to survey technical variations in total body irradiation (TBI) across Japan. A web-based questionnaire investigating technical aspects (irradiation method, in vivo dosimetry, organ shielding, and boluses) of TBI was distributed via the authors' acquaintances in each region of Japan using snowball sampling, and 73 institutions responded. The data were collected from January to April 2024. Three institutions used two distinct irradiation methods, yielding 76 reported techniques. The reported irradiation techniques included long source-to-surface distance (SSD) techniques, which involve using a large field and extended distance; helical intensity-modulated radiation therapy (IMRT) using specialized equipment (e.g., TomoTherapy), moving couch techniques, and volumetric modulated arc therapy (VMAT) using a standard C-arm linac, with responses totaling 60 (79%), 10 (13%), 4 (5%), and 2 (3%), respectively. All institutions performing IMRT-based (helical IMRT and VMAT) TBI used computed tomography simulation with the patient in the supine position and utilized a 6 MV photon beam. Conversely, the long SSD technique exhibited significant variation; while 47 institutions treated patients exclusively in the supine position, others reported using the prone and lateral positions. Furthermore, the photon beam energies varied, with 10 MV (41 responses), 6 MV (20 responses), and 4 MV (1 response) reported. Notably, 17 institutions using long SSD techniques did not perform in vivo dosimetry and 32 did not use boluses. The differences in the methods used to shield the organs were also reported. These variations highlight the need for standardization of in vivo dosimetry, dose homogeneity strategies, and organ-shielding in TBI.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"347-357"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143630883","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":"Investigation of imaging conditions for dental MRI using 3T-MRI system with microscopy coil in clinical situation.","authors":"Toshiyuki Zaike, Shinya Kotaki, Marino Araragi, Yoshiko Ariji, Shigeyoshi Saito","doi":"10.1007/s12194-025-00910-5","DOIUrl":"10.1007/s12194-025-00910-5","url":null,"abstract":"<p><p>Magnetic resonance imaging (MRI) has been employed to obtain high-resolution images of dental structures using intraoral and dedicated coils; however, reports on microscopy coils are limited. Furthermore, no reports have detailed the imaging conditions for the clinical application of T<sub>1</sub>-weighted (T<sub>1</sub>W), T<sub>2</sub>-weighted (T<sub>2</sub>W), and proton density-weighted (PDW) sequences in dental MRI. This study investigated the optimal imaging conditions for clinical dental MRI. Phantoms simulating the dental pulp and bone marrow were constructed, and imaging was performed using a 3T-MRI system and a microscopy coil with varying T<sub>1</sub>W, T<sub>2</sub>W, and PDW parameters to determine the trends in change. Subsequently, we imaged the left mandibular first molar region of 21 healthy volunteers using clinically feasible parameters. Tooth visibility was assessed for the T<sub>1</sub>W, T<sub>2</sub>W, and PDW images, while contrast ratio (CR) and signal-to-noise ratio (SNR) were calculated and statistically analyzed. Results showed that PDW significantly outperformed T<sub>1</sub>W and T<sub>2</sub>W in terms of tooth visibility, CR, and SNR. Under the specified imaging conditions, PDW was optimal for tooth and periodontal tissue morphology evaluation. A statistically significant difference in CR and tooth visibility evaluation was observed between T<sub>1</sub>W and T<sub>2</sub>W in the dental pulp. This statistically significant difference suggested that T<sub>2</sub>W can be used to evaluate the dental pulp, and T<sub>1</sub>W can be used to evaluate the inferior alveolar nerve and bone marrow properties.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"570-581"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144001212","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":"Optimization of imaging conditions for infant hip imaging using flat panel detectors.","authors":"Akira Suzuki, Yoshiaki Hirofuji, Noriaki Miyaji, Kentarou Funashima, Isami Takahashi","doi":"10.1007/s12194-025-00890-6","DOIUrl":"10.1007/s12194-025-00890-6","url":null,"abstract":"<p><p>To investigate the optimal low-dose imaging conditions for infant hip radiography, using a commercially available infant phantom, and to identify conditions that are satisfactory to orthopedic surgeons, using a combination of low tube voltage, mAs, and Cu filters. Hip joint radiographs were taken with Cu filters (0, 0.1, 0.2 mm) at tube voltages from 40 to 70 kV in 5 kV increments. Seven radiographers graded the images, and the five images with the lowest dose and an average score of 3.5 or higher were selected. These images were then subjected to paired comparisons by six orthopedic surgeons. The selected acquisition settings all used low tube voltages (40-55 kV), and none used a 0.2-mm Cu filter. The optimal imaging condition was identified as 40 kV, 5 mAs, and a 0.1-mm Cu filter, giving the patient entrance surface dose of 11 μGy, which was the lowest dose investigated and was highly preferred by the orthopedic surgeons. Low-dose imaging using a Cu filter at low tube voltage can produce images that are satisfactory for orthopedic surgeons, with lower radiation doses than previously possible.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"399-406"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144034341","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":"Evaluation of femoral bone mineral density in patients with hip osteoarthritis using material density image in dual-energy computed tomography.","authors":"Takuya Tani, Hiroki Mitsuzono, Kazuhiro Sadasue, Yuma Tsubaki, Osamu Jouno, Kojiro Nishijima, Shohei Kudomi","doi":"10.1007/s12194-025-00912-3","DOIUrl":"10.1007/s12194-025-00912-3","url":null,"abstract":"<p><p>Bone mineral density (BMD) around the implant may decrease post-total hip arthroplasty (THA), and it is important to evaluate changes in BMD pre- and post-THA. Dual-energy X-ray absorptiometry (DXA) is commonly used to evaluate BMD. However, in patients with hip osteoarthritis (OA), BMD obtained from DXA may be affected by bone deformities. Dual-energy computed tomography (DECT) can be used to produce material density image (MDI) that provide the material density values for arbitrary materials. This study aimed to determine the clinical utility of BMD assessment using DECT in patients with OA. The subjects were 80 patients (136 femurs) who underwent DECT and DXA of the femur between January 2021 and September 2023 and were classified into groups with and without OA. Calcium-water (Ca/W) density images were used for MDI. Correlation coefficients between the material density values obtained from Ca/W density images and DXA-obtained BMD were determined at the femoral neck, greater trochanter, and shaft. The femoral material density values obtained from Ca/W density images positively correlated with the DXA-obtained BMD. The correlation coefficients were 0.803 for the femoral neck, 0.762 for the femoral greater trochanter, and 0.598 for the femoral shaft in the group without OA, and 0.629 for the femoral neck, 0.825 for the femoral greater trochanter, and 0.634 for the femoral shaft in the group with OA. Our current study demonstrates that the density values obtained from the Ca/W density image suggest that it could serve as an indicator of femoral BMD.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"606-614"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144053734","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}
Masayuki Hattori, Hongbo Chai, Toshitada Hiraka, Koji Suzuki, Tetsuya Yuasa
{"title":"Cone-beam computed tomography (CBCT) image-quality improvement using a denoising diffusion probabilistic model conditioned by pseudo-CBCT of pelvic regions.","authors":"Masayuki Hattori, Hongbo Chai, Toshitada Hiraka, Koji Suzuki, Tetsuya Yuasa","doi":"10.1007/s12194-025-00892-4","DOIUrl":"10.1007/s12194-025-00892-4","url":null,"abstract":"<p><p>Cone-beam computed tomography (CBCT) is widely used in radiotherapy to image patient configuration before treatment but its image quality is lower than planning CT due to scattering, motion, and reconstruction methods. This reduces the accuracy of Hounsfield units (HU) and limits its use in adaptive radiation therapy (ART). However, synthetic CT (sCT) generation using deep learning methods for CBCT intensity correction faces challenges due to deformation. To address these issues, we propose enhancing CBCT quality using a conditional denoising diffusion probability model (CDDPM), which is trained on pseudo-CBCT created by adding pseudo-scatter to planning CT. The CDDPM transforms CBCT into high-quality sCT, improving HU accuracy while preserving anatomical configuration. The performance evaluation of the proposed sCT showed a reduction in mean absolute error (MAE) from 81.19 HU for CBCT to 24.89 HU for the sCT. Peak signal-to-noise ratio (PSNR) improved from 31.20 dB for CBCT to 33.81 dB for the sCT. The Dice and Jaccard coefficients between CBCT and sCT for the colon, prostate, and bladder ranged from 0.69 to 0.91. When compared to other deep learning models, the proposed sCT outperformed them in terms of accuracy and anatomical preservation. The dosimetry analysis for prostate cancer revealed a dose error of over 10% with CBCT but nearly 0% with the sCT. Gamma pass rates for the proposed sCT exceeded 90% for all dose criteria, indicating high agreement with CT-based dose distributions. These results show that the proposed sCT improves image quality, dosimetry accuracy, and treatment planning, advancing ART for pelvic cancer.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"425-438"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143543461","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":"Enhanced urethral identification for radiotherapy planning using fat-suppressed 3D T2-weighted magnetic resonance imaging.","authors":"Yutaka Kato, Takayoshi Nakaya, Kuniyasu Okudaira, Yumiko Noguchi, Mariko Kawamura, Shunichi Ishihara, Shinji Naganawa","doi":"10.1007/s12194-025-00903-4","DOIUrl":"10.1007/s12194-025-00903-4","url":null,"abstract":"<p><p>This study proposes a fat-suppressed three-dimensional T2-weighted (3D-T2W) sequence on magnetic resonance imaging to enhance prostatic urethral identification in radiotherapy planning. Conventional 3D-T2W and the proposed sequence were obtained to evaluate prostatic urethral identification in 13 male patients. The proposed sequence demonstrated significantly higher Dice similarity coefficients compared to conventional 3D-T2W sequence (p = 0.001) and superior contrast-to-noise ratios. The proposed sequence also achieved significantly better visibility scores in visual assessment (p = 0.001). The proposed technique uses fat suppression in a standard 3D-T2W sequence, making it a simple and clinically applicable method that does not require specialized sequence designs. Our findings suggest that this approach could be a valuable noninvasive method for enhancing prostatic urethral identification, although further research with larger sample sizes and optimization of acquisition parameters is needed.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"589-596"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12103322/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143754958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"External and internal GATE/Geant4 dosimetric calculations on voxelized phantoms.","authors":"Merai Sondes, Benrachi Fatima, Laouet Nadjet","doi":"10.1007/s12194-025-00904-3","DOIUrl":"10.1007/s12194-025-00904-3","url":null,"abstract":"<p><p>Monte Carlo simulation employing the GATE (Geant4 Application for Tomographic Emission) code plays a crucial role in radiation transport studies for dose calculations within computational phantoms. This paper presents a set of absorbed doses calculated using computational phantom Zubal and Monte Carlo GATE code version 9.3, based on two radiation exposure configurations: external (radiological accident) and internal (using <math> <mrow><mmultiscripts><mrow></mrow> <mrow></mrow> <mn>131</mn></mmultiscripts> <mi>I</mi></mrow> </math> radionuclide). The results were validated through comparison with previous studies employing different Monte Carlo codes (MCNP, EGS4), and the reference female computational model proposed by ICRP report 110. The findings demonstrate good agreement between GATE results for Zubal phantom and published data with MCNP and EGS4, as well as alignment with ICRP 110 reference phantom results, for both external and internal irradiation scenarios. In addition, the comparison between Zubal and ICRP 110 phantom reveals a minimal variation, attributed to inherent anatomical and geometrical disparities.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"514-522"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144034339","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 CT-free deep-learning-based attenuation and scatter correction for copper-64 PET in different time-point scans.","authors":"Zahra Adeli, Seyed Abolfazl Hosseini, Yazdan Salimi, Nasim Vahidfar, Peyman Sheikhzadeh","doi":"10.1007/s12194-025-00905-2","DOIUrl":"10.1007/s12194-025-00905-2","url":null,"abstract":"<p><p>This study aimed to develop and evaluate a deep-learning model for attenuation and scatter correction in whole-body 64Cu-based PET imaging. A swinUNETR model was implemented using the MONAI framework. Whole-body PET-nonAC and PET-CTAC image pairs were used for training, where PET-nonAC served as the input and PET-CTAC as the output. Due to the limited number of Cu-based PET/CT images, a model pre-trained on 51 Ga-PSMA PET images was fine-tuned on 15 Cu-based PET images via transfer learning. The model was trained without freezing layers, adapting learned features to the Cu-based dataset. For testing, six additional Cu-based PET images were used, representing 1-h, 12-h, and 48-h time points, with two images per group. The model performed best at the 12-h time point, with an MSE of 0.002 ± 0.0004 SUV<sup>2</sup>, PSNR of 43.14 ± 0.08 dB, and SSIM of 0.981 ± 0.002. At 48 h, accuracy slightly decreased (MSE = 0.036 ± 0.034 SUV<sup>2</sup>), but image quality remained high (PSNR = 44.49 ± 1.09 dB, SSIM = 0.981 ± 0.006). At 1 h, the model also showed strong results (MSE = 0.024 ± 0.002 SUV<sup>2</sup>, PSNR = 45.89 ± 5.23 dB, SSIM = 0.984 ± 0.005), demonstrating consistency across time points. Despite the limited size of the training dataset, the use of fine-tuning from a previously pre-trained model yielded acceptable performance. The results demonstrate that the proposed deep learning model can effectively generate PET-DLAC images that closely resemble PET-CTAC images, with only minor errors.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"523-533"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144054069","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}