Radiological Physics and Technology最新文献

{"title":"Development of a tissue water fraction analysis method using quantitative parameter mapping for magnetic resonance imaging.","authors":"Shunsuke Uotani, Yuki Kanazawa, Akihiro Haga, Yo Taniguchi, Masahiro Takizawa, Motoharu Sasaki, Masafumi Harada","doi":"10.1007/s12194-025-00913-2","DOIUrl":"10.1007/s12194-025-00913-2","url":null,"abstract":"<p><p>The myelin sheath is a multilayered structure that surrounds the axons of nerve cells. It acts as an insulator to ensure rapid and accurate transmission of electrical signals in the nervous system. Myelin water fraction (MWF) serves as a biomarker for the myelin sheath. Several methods for determining the MWF have been proposed; however, the inconsistency of MWF values is a challenge. In this study, we attempted to derive the MWF using quantitative parameter mapping (QPM). QPM ensures reproducibility by maintaining consistent imaging conditions across different scanners, enabling stable acquisition of quantitative parameters. This is expected to improve the reliability of the MWF measurements. Additionally, a significant correlation between QPM-derived parameters and the MWF has been reported. Five healthy volunteers were included in this study. QPM-MRI was performed using a 3-Tesla MR scanner with a three-dimensional radio frequency-spoiled steady-state gradient-echo (3D-RSSG) method. Using the derived quantitative values, pseudo-intensity images were generated for arbitrary continuous echo time values. Subsequently, a model equation for the brain tissue was defined. The generated signals were fitted with triexponential curve to estimate the amplitudes of each tissue component. Finally, the MWF was calculated using the amplitude ratio of each tissue. The mean MWF values for white matter and gray matter were 8.20 ± 4.97% and 7.99 ± 3.45%, respectively. This method using QPM allows for 3D data collection within a scan time applicable to standard clinical examinations and provides high accuracy in relaxation time estimation, thereby enabling stable quantification of MWF and suggesting its potential for clinical implementation.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"633-643"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144057612","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":"Generalizable AI approach for detecting projection type and left-right reversal in chest X-rays.","authors":"Yukino Ohta, Yutaka Katayama, Takao Ichida, Akane Utsunomiya, Takayuki Ishida","doi":"10.1007/s12194-025-00914-1","DOIUrl":"10.1007/s12194-025-00914-1","url":null,"abstract":"<p><p>The verification of chest X-ray images involves several checkpoints, including orientation and reversal. To address the challenges of manual verification, this study developed an artificial intelligence (AI)-based system using a deep convolutional neural network (DCNN) to automatically verify the consistency between the imaging direction and examination orders. The system classified the chest X-ray images into four categories: anteroposterior (AP), posteroanterior (PA), flipped AP, and flipped PA. To evaluate the impact of internal and external datasets on the classification accuracy, the DCNN was trained using multiple publicly available chest X-ray datasets and tested on both internal and external data. The results demonstrated that the DCNN accurately classified the imaging directions and detected image reversal. However, the classification accuracy was strongly influenced by the training dataset. When trained exclusively on NIH data, the network achieved an accuracy of 98.9% on the same dataset; however, this reduced to 87.8% when evaluated with PADChest data. When trained on a mixed dataset, the accuracy improved to 96.4%; however, it decreased to 76.0% when tested on an external COVID-CXNet dataset. Further, using Grad-CAM, we visualized the decision-making process of the network, highlighting the areas of influence, such as the cardiac silhouette and arm positioning, depending on the imaging direction. Thus, this study demonstrated the potential of AI in assisting in automating the verification of imaging direction and positioning in chest X-rays. However, the network must be fine-tuned to local data characteristics to achieve optimal performance.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"644-652"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144129034","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":"Human glioblastoma (U87) cells grown in 3D culture showed a radio-resistance to X-ray and proton radiation.","authors":"Dea A Kartini, Pharewa Karoon, Yuwadee Malad, Thititip Tippayamontri, Taweap Sanghangthum, Chutima Talabnin, Chinorat Kobdaj","doi":"10.1007/s12194-025-00921-2","DOIUrl":"10.1007/s12194-025-00921-2","url":null,"abstract":"<p><p>Glioblastoma multiforme is the most malignant brain tumor and is resistant to conventional radiotherapy. Proton radiotherapy utilizes accelerated proton beams to irradiate deep-seated tumors with minimum ionization in the entrance channel, thanks to its inverted dose profile. This work aims to investigate the response of human glioma (U87) cells cultured in a 3D culture after X-ray and proton irradiation. U87 cells have been cultured in 3D bio-phantom where cells were grown in Matrigel matrix inside a 96-well plate. The morphology of U87 cells in 3D culture has been observed for 48 h, and cells have grown in their natural shape. The response of cells in 3D bio-phantom was evaluated by exposing the cells to 6 MV X-ray and 70 MeV monoenergetic proton beams. Post-irradiation, the surviving cells were determined by a colony formation assay, and the survival curve of cells in 3D culture was compared with the cells grown in 2D monolayer culture. The response of cells in the 3D bio-phantom following X-ray and proton radiation demonstrated an increased survival fraction in the high-dose region than those in 2D monolayer. However, U87 cells showed more sensitivity towards proton irradiation compared to X-rays, regardless of the culture setup. Finally, we obtained the RBE <math><mmultiscripts><mrow></mrow> <mrow><mn>10</mn> <mo>%</mo></mrow> <mrow></mrow></mmultiscripts> </math> value of 1.15 for cells in 3D bio-phantom and 1.29 for cells in 2D monolayer. Therefore, U87 cells grown in our 3D culture setup demonstrate radio-resistant behavior and exhibit higher sensitivity towards proton irradiation compared to X-ray irradiation in our clonogenic assay.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"688-697"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144295101","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":"Predicting perceived exertion during high-intensity exercise using quantitative MRI: insights from T2* value and muscle cross-sectional area.","authors":"Shuhei Shibukawa, Daisuke Yoshimaru, Yoshinori Hiyama, Tatsunori Saho, Takuya Ozawa, Keisuke Usui, Masami Goto, Hajime Sakamoto, Shinsuke Kyogoku, Hiroyuki Daida","doi":"10.1007/s12194-025-00927-w","DOIUrl":"10.1007/s12194-025-00927-w","url":null,"abstract":"<p><p>This study aimedto investigate the relationship between MRI-derived skeletal muscle biomarkers and subjective exercise intensity, measured by the Rating of Perceived Exertion (RPE). Both T2* value and CSA showed significant time-dependent changes following exercise. The percent change (PC) in T2* immediately after exercise (T2* PC-post/pre) was most strongly associated with RPE (ρ = 0.45,p < 0.01), while CSA showed a weaker correlation. Muscle strength was not significantly associated with RPE.Random forest analysis identified T2* PC-post/pre as the most important predictor of RPE, supported by partial dependence plots showing a nonlinear increase in RPE with higher T2* value changes. T2* value changes after exercise reflect metabolic stress and serve as a more specific predictor of RPE than CSA or muscle strength. These findings highlight the potential of T2* value as a non-invasive biomarker for assessing subjective exercise intensity.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"746-755"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144303263","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":"Issues in radiation dose measurement using electronic personal dosimeters during disaster relief activities.","authors":"Akira Suzuki, Yoshiaki Hirofuji, Noriaki Miyaji, Ayaka Oikawa, Kentarou Funashima, Isami Takahashi","doi":"10.1007/s12194-025-00934-x","DOIUrl":"10.1007/s12194-025-00934-x","url":null,"abstract":"<p><strong>Purpose: </strong>In this study, we measured the radiation exposure of the medical relief team of the Japanese Red Cross Society (JRCS) members during the Noto Peninsula earthquake using electronic personal dosimeters (EPDs) and investigated the frequency of electromagnetic interference (EMI) events that caused abnormally high dose readings.</p><p><strong>Methods: </strong>Six JRCS medical relief team members (two physicians, three nurses, and one logistics officer) involved in the Noto Peninsula earthquake disaster relief activities were provided with EPDs to measure their radiation exposure during the activity period. A background radiation dosimeter was also installed on-site to record ambient radiation levels.</p><p><strong>Results: </strong>Over 2.5 days of disaster relief activities, the background radiation dose was 3.0 ± 3.0 μSv. However, the highest recorded dose among the team members was 2075.0 ± 207.5 μSv for a nurse, while the average dose for the other members was 40.0 ± 39.5 μSv. A significant radiation dose was observed despite no radioactive material dispersion.</p><p><strong>Conclusions: </strong>Among the four individuals who exhibited abnormally high dose readings, three were operating digital devices at the time of measurement, suggesting a strong likelihood that electromagnetic interference was the cause. The effective management of radiation doses using EPDs during nuclear disasters requires the implementation of countermeasures against EMI from digital devices.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"805-811"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144592623","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":"Quantification and comparison of the reference dose measurements using IAEA TRS-398 protocols and its revised version.","authors":"Mohammad Abdul Fatha, Sathiya Raj, Y S Pawar, Sathiyan Saminathan","doi":"10.1007/s12194-025-00925-y","DOIUrl":"10.1007/s12194-025-00925-y","url":null,"abstract":"<p><p>The International Atomic Energy Agency (IAEA) released a protocol named Technical Report Series (TRS-398) to measure the absorbed dose in water for external radiotherapy beams. It provides a unified approach for using calibrated ionization chambers that are traceable to standard laboratories in determining the absorbed dose to water. The objective of the study was to compare the reference dosimetry [dose at 10 cm depth ( <math><msub><mi>D</mi> <mn>10</mn></msub> </math> )] between TRS-398 and its revised version. Reference dosimetry was performed for flattened photon beam with nominal energies of 6, 10, and 15 MV as well as flattening filter free (FFF) beam of energies 6 FFF and 10 FFF based on the guidelines of both TRS-398 and its revised version using two different ionization chambers of varying sensitive volumes such as 0.65 cm³ (FC65-G) & 0.13 cm³ (CC13) IBA ionization chambers with calibration coefficient traceable to absorbed dose to water (D_w) standards. The comparison of absorbed dose at 10 cm ( <math><msub><mi>D</mi> <mn>10</mn></msub> </math> ) depth using both protocols with FC65-G chamber shows a difference ranging from 0.40 to 0.63% in FF beams and 0.03 to 0.05% in FFF beams. For CC13 chamber, the difference ranged from -0.60 to -0.77% in FF beams and -0.40 to -0.50% in FFF beams. The differences in absorbed dose between TRS-398 old and revised protocols were evaluated and a variation of up to 0.63% in <math><msub><mi>D</mi> <mn>10</mn></msub> </math> was observed for FC65-G and -0.77% in <math><msub><mi>D</mi> <mn>10</mn></msub> </math> was observed for CC13 chamber. The use of old <math><msub><mi>k</mi> <mrow><mi>Q</mi> <mo>,</mo> <msub><mi>Q</mi> <mi>O</mi></msub> </mrow> </msub> </math> value affects the reference dose measurements, which overestimates the results by an average of 0.5%. The use of cross-calibrated chamber following the old protocol in determining the <math><msub><mi>D</mi> <mn>10</mn></msub> </math> underestimates the results by maximum of -0.77% in FF beams and -0.5% in FFF beams.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"726-733"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144276195","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":"Assessment of lens absorbed dose by radiological technologists during mobile X-ray radiography: a comparison between computed radiography and flat panel detector systems.","authors":"Satoe Konta, Saya Ohno, Ryota Shindo, Keisuke Yamamoto, Yoshihiro Haga, Toshiki Kato, Masahiro Sota, Yuji Kaga, Mitsuya Abe, Koichi Chida","doi":"10.1007/s12194-025-00930-1","DOIUrl":"10.1007/s12194-025-00930-1","url":null,"abstract":"<p><p>Mobile X-ray radiography is crucial for imaging patients with limited mobility; however, radiological technologists (RTs) may be positioned closer to patients and thus be at risk of harmful radiation doses owing to scattered radiation. As X-ray systems transitioned from digital computed radiography (CR) to flat panel detector (FPD) systems, we studied the RTs' eye lens and neck radiation doses over 2 years. Three RTs participated in measurements using a CR system, and five RTs participated in measurements using a FPD system. We measured radiation exposure with neck dosimeters (glass badges) and lens dosimeters (DOSIRIS®). The results showed a 66% reduction in lens dose after switching from the CR system to the FPD system. Comparisons of specific RT members also revealed significantly lower doses for the FPD system than for the CR system. Two main factors contributed to this decrease: the FPD system used a virtual grid instead of a scatter removal grid, and the RTs' awareness of radiation exposure increased with experience. Although the lens dose was significantly reduced, RTs should still wear protective eyewear and equipment when frequent imaging is expected or when working close to patients.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"766-774"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144477162","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":"Dose-volume histogram-based comparison of conventional and hypofractionated radiotherapy: lifetime attributable risk estimation in Indian breast carcinoma patients.","authors":"Amal Jose, Desh Deepak Ladia, Anju George, Abhishek Pratap Singh, Vandana Dahiya","doi":"10.1007/s12194-025-00924-z","DOIUrl":"10.1007/s12194-025-00924-z","url":null,"abstract":"<p><strong>Aim: </strong>This study investigates secondary cancer risks in the contralateral breast (CB) and ipsilateral lung (IL) in postmastectomy radiotherapy (PMRT) patients treated with forward-planned intensity-modulated radiation therapy (IMRT). It is the first analysis of Dose-Volume Histogram (DVH)-based secondary cancer risks for patients undergoing forward-planned IMRT for PMRT. The objective is to compare cancer risks between conventional fractionated (CF) IMRT and hypofractionated (HF) IMRT. A retrospective analysis was conducted on 20 patients (aged 37-69 years) treated with 6 MV forward-planned IMRT. Treatment plans included CF IMRT (50 Gy in 25 fractions) and HF IMRT (42.56 Gy in 16 fractions). Organ equivalent doses (OED), excess absolute risk (EAR), lifetime attributable risk (LAR), and Relative Risk (RR) were calculated for CB and IL using Schneider non-linear mechanistic model & differential DVH. HF IMRT demonstrated a significant reduction in IL secondary cancer risk compared to CF IMRT (P = 0.0001), with LAR values decreasing from 54.9%-75.5% (CF) to 48.3%-66.5% (HF). The RR for IL cancer induction also declined from 10.16-13.6 (CF) to 9.06-12.1 (HF). In contrast, CB cancer risks exhibited minimal change, with LAR values slightly reducing from 1.08%-6.9% (CF) to 0.96%-6.1% (HF) (P = 0.52). The RR for CB remained relatively stable at 1.10-1.55 (CF) and 1.09-1.48 (HF). HF IMRT is more effective in reducing IL secondary cancer risk compared to CF IMRT, presenting it as a safer PMRT option. However, CB cancer risks remained largely unchanged, suggesting the need for further dose optimization research.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":" ","pages":"717-725"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144295100","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":"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":"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":"901-911"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","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}

{"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":"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":"653-669"},"PeriodicalIF":1.5,"publicationDate":"2025-09-01","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}