Journal of Applied Clinical Medical Physics最新文献

{"title":"Fluence smoothing evaluation for whole-breast automatically generated treatment plans.","authors":"Giulianne Rivelli R Zaratim, Luis Felipe Oliveira E Silva, Ricardo G Dos Reis, Cristiano Jacques M R Mendes, Marília Miranda F Gomes","doi":"10.1002/acm2.14564","DOIUrl":"https://doi.org/10.1002/acm2.14564","url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to identify the fluence smoothing threshold that preserves the dosimetric quality of planning for breast cancer intensity-modulated radiation therapy (IMRT).</p><p><strong>Material and methods: </strong>We conducted automated treatment planning for 60 breast cancer patients using the Eclipse Scripting Application Programming Interface. The plans included four-field IMRT, emphasizing smoothing weight combinations while maintaining a 4:3 aspect ratio between the X and Y directions. Four weight sets (40 × 30, 100 × 75, 150 × 115.2, and 200 × 150) were tested, resulting in four plans per patient. A total dose of 40.05 Gy over 15 fractions was prescribed. Optimization weigths were dynamically adjusted based on dosimetric evaluations, with the maximum coverage priority set at 200. Statistical analyses were used to assess the dosimetric data.</p><p><strong>Results: </strong>The median planning target volume (PTV) coverage varied across smoothing levels, with default smoothing (40 × 30) providing superior median PTV coverage. Lung constraints showed significant differences mainly at higher smoothing levels. Heart constraints exhibited less variation between smoothing levels, with significant differences primarily in the maximum and mean doses for right-sided patients and between default and higher smoothing levels for left-sided patients. No significant differences were observed in contralateral breast constraints among all smoothing levels, except at the maximum level for right-sided patients. Monitor units decreased with increasing smoothing weight, showing significant differences between default and other settings. For right-sided patients, the median number of monitor units varied from 1346 (40 × 30) to 754 (200 × 150), and for left-sided patients, from 1333 (40 × 30) to 804 (200 × 150). Chi-square tests revealed differences in dose constraint adherence between default and maximum smoothing levels, particularly in target coverage.</p><p><strong>Conclusion: </strong>Our findings suggest that using a ratio of smoothing weights to target priorities between 1:1.5 and 1:1.6 leads to a favorable balance between complexity and dosimetric plan quality, with no significant impacts on dose constraint adherence.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14564"},"PeriodicalIF":2.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142750977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of clinical feasibility:offline adaptive radiotherapy for lung cancer utilizing kV iCBCT and UNet++ based deep learning model.","authors":"Hongwei Zeng, Qi Chen, Xiangyu E, Yue Feng, Minghe Lv, Su Zeng, Wenhao Shen, Wenhui Guan, Yang Zhang, Ruping Zhao, Shaobin Wang, Jingping Yu","doi":"10.1002/acm2.14582","DOIUrl":"https://doi.org/10.1002/acm2.14582","url":null,"abstract":"<p><strong>Background: </strong>Lung cancer poses a significant global health challenge. Adaptive radiotherapy (ART) addresses uncertainties due to lung tumor dynamics. We aimed to investigate a comprehensively and systematically validated offline ART regimen with high clinical feasibility for lung cancer.</p><p><strong>Methods: </strong>This study enrolled 102 lung cancer patients, who underwent kV iterative cone-beam computed tomography (iCBCT). Data collection included iCBCT and planning CT (pCT) scans. Among these, data from 70 patients were employed for training the UNet++ based deep learning model, while 15 patients were allocated for testing the model. The model transformed iCBCT into adaptive CT (aCT). Clinical radiotherapy feasibility was verified in 17 patients. The dosimetric evaluation encompassed GTV, organs at risk (OARs), and monitor units (MU), while delivery accuracy was validated using ArcCHECK and thermoluminescent dosimeter (TLD) detectors.</p><p><strong>Results: </strong>The UNet++ based deep learning model substantially improved image quality, reducing mean absolute error (MAE) by 70.05%, increasing peak signal-to-noise ratio (PSNR) by 17.97%, structural similarity (SSIM) by 7.41%, and the Hounsfield Units (HU) of aCT approaching a closer proximity to pCT compared to kV iCBCT. There were no significant differences observed in the dosimetric parameters of GTV and OARs between the aCT and pCT plans, confirming the accuracy of the dose maps in ART plans. Similarly, MU manifested no notable disparities, underscoring the consistency in treatment efficiency. Gamma passing rates for intensity-modulated radiation therapy (IMRT) and volumetric-modulated arc therapy (VMAT) plans derived from aCT and pCT exceeded 98%, while the deviations in TLD measurements (within 2% to 7%) also exhibited no significant differences, thus corroborating the precision of dose delivery.</p><p><strong>Conclusion: </strong>An offline ART regimen utilizing kV iCBCT and UNet++ based deep learning model is clinically feasible for lung cancer treatment. This approach provides enhanced image quality, comparable treatment plans to pCT, and precise dose delivery.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14582"},"PeriodicalIF":2.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142750829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CT-based whole lung radiomics nomogram to identify middle-aged and elderly COVID-19 patients at high risk of progressing to critical disease.","authors":"Xin'ang Jiang, Jun Hu, Qinling Jiang, Taohu Zhou, Fei Yao, Yi Sun, Chao Zhou, Qianyun Ma, Jingyi Zhao, Kang Shi, Wen Yang, Xiuxiu Zhou, Yun Wang, Shiyuan Liu, Xiaoyan Xin, Li Fan","doi":"10.1002/acm2.14562","DOIUrl":"https://doi.org/10.1002/acm2.14562","url":null,"abstract":"<p><strong>Background: </strong>COVID-19 remains widespread and poses a threat to people's physical and mental health, especially middle-aged and elderly individuals. Early identification of COVID-19 patients at high risk of progressing to critical disease helps improve overall patient outcomes and healthcare efficiency.</p><p><strong>Purpose: </strong>To develop a radiomics nomogram to predict the risk of newly admitted middle-aged and elderly COVID-19 patients progressing to critical disease.</p><p><strong>Methods: </strong>A total of 794 patients (aged 40 years or above) were retrospectively included in the study from two institutions, all of them were with non-critical COVID-19 on admission. At follow-up, patients were divided into non-critical group and critical group. About 443 patients (384 non-critical and 59 critical) from the first hospital were randomly assigned to the training (n = 311) and internal validation (n = 132) set in a 7:3 ratio. Additionally, an independent external cohort of 351 patients (292 non-critical and 59 critical) from another hospital was evaluated. Radiomics signatures and clinical indicators were used to build a radiomics model and a clinical model after computed tomography (CT) image processing, CT whole-lung segmentation, feature extraction, and feature selection. The radiomics nomogram model integrated radiomics model and clinical model. The receiver operating characteristic curve (AUC) was used to assess the performance of the proposed models. Calibration curves and decision curve analysis were used to assess the performance of the radiomics nomogram.</p><p><strong>Results: </strong>For the training, internal validation, and external validation sets, the AUC values of the radiomic nomogram for the prediction of COVID-19 progression were 0.916, 0.917, and 0.890, respectively. Calibration curves indicated that there was no significant departure between prediction and observation in three sets. The decision curve image demonstrated the clinical utility of the nomogram model.</p><p><strong>Conclusions: </strong>Our nomogram model incorporates radiomics features and clinical indicators, it provides a new pathway to increase predictive accuracy or clinical utility, further helping to provide personalized management for middle-aged and elderly patients with COVID-19.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14562"},"PeriodicalIF":2.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142750926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A predictive model for Gamma Knife intermediate dose spill: R50%_Analytic-GK.","authors":"Ivan L Cordrey, Sare Kucuk, Chester Ramsey, Joseph Bowling, Dharmin D Desai","doi":"10.1002/acm2.14579","DOIUrl":"https://doi.org/10.1002/acm2.14579","url":null,"abstract":"<p><strong>Purpose: </strong>Minimizing intermediate dose spill in stereotactic radiosurgery (SRS) for brain treatment is crucial. Intermediate dose spill correlates with the exposure of normal brain tissue to high doses, which increases the risk of radionecrosis. R50%, defined as the volume of the 50% of prescription isodose cloud/planning target volume, is one metric for intermediate dose spill. A predictive model for R50% in linear accelerator VMAT-delivered SRS has been developed Desai et al. (2020) and is called R50%_Analytic. This study extends the R50%_Analytic model to Gamma Knife (GK) delivered SRS, resulting in the R50%_Analytic-GK model.</p><p><strong>Methods: </strong>Phantom calculations were performed on 11 spherical target volumes ranging from 0.001  to 44 cm³ to develop the R50%_Analytic-GK model. R50%_Analytic-GK was tested against clinical data from 18 brain metastasis cases with one to 11 targets treated on GK Icon and planned in GammaPlan with lightning dose optimizer. Thirty-five targets with volumes between 0.011  and 27.4 cm³ were analyzed by extracting the R50% achieved clinically (R50%_Clinical) for comparison to the predicted intermediate dose spill from R50%_Analytic-GK.</p><p><strong>Results: </strong>The predicted R50%_Analytic-GK values generally represent a lower bound for the R50%_Clinical values as the model would predict. The Difference, R50%_Clinical - R50%_Analytic-GK, has a median value of 0.92, which quantifies the lower bound nature of R50%_Analytic-GK. The model reflected the character of intermediate dose spill for the clinical cases. A few outliers were likely due to specific planning complexities.</p><p><strong>Conclusion: </strong>The R50%_Analytic-GK model for intermediate dose spill successfully extends the theoretical framework of R50%_Analytic to GK-delivered SRS. It provides a method to predict the intermediate dose spill for GK Icon treatments. This model can aid in assessing SRS treatment plans by providing a benchmark for the intermediate dose spill for comparison.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14579"},"PeriodicalIF":2.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142750823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dosimetric advantages of dual arc increments for head and neck volumetric-modulated arc therapy in the Monaco treatment planning system.","authors":"Jin Hwa Choi, Hyejo Ryu, Do Hoon Oh, Lee Yoo, Minsoo Chun","doi":"10.1002/acm2.14571","DOIUrl":"https://doi.org/10.1002/acm2.14571","url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to assess the dosimetric advantages of dual arc increments in head and neck volumetric-modulated arc therapy (VMAT) in the Monaco treatment planning system (TPS).</p><p><strong>Methods: </strong>Three VMAT plans were created for each of the 10 patients by prescribing 70 Gy in 35 fractions with arc increment combinations of 30°/30°, 15°/15°, and 30°/15° in the Monaco TPS. The dose to 0.03 cm³ volume (D_0.03cc), conformity number, and homogeneity and gradient indices was compared for the planning target volume (PTV), and the D_0.03cc and mean dose (D_mean) of the spinal cord, brain stem, parotid glands were compared. For plan complexity evaluation, the monitor unit and various related metrics were compared. Wilcoxon signed-rank tests were performed across plans for the evaluated indicators.</p><p><strong>Results: </strong>For PTV, plans with 30°/15° showed comparable D_0.03cc and homogeneity and gradient indices to those of plans with 30°/30° and 15°/15° while exhibiting a better conformity number. The D_0.03cc for spinal cord and brain stem for plans with 30°/15° were 26.0% and 20.8% less than those with 30°/30° and 16.8% and 19.0% less than those with 15°/15°, respectively. The D_mean for the left and right parotid glands under plans with 30°/15° were 17.4% and 13.2% less than those with 30°/30° and 14.0% and 9.8% less than those with 15°/15°, respectively. The total monitor unit in plans with 30°/15° was less than that in other plans but with no significance. The plans with 30°/15° showed higher modulation complexity and plan-averaged irregularity, while no significant differences observed in both plan-averaged area and modulation compared with other plans.</p><p><strong>Conclusion: </strong>In head and neck VMAT, a dual arc increment of 30°/15° seems advisable because it can substantially reduce doses to normal tissues with comparable delivery efficiency while maintaining target dose coverage.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14571"},"PeriodicalIF":2.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142750927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beam quality correction factors for dose measurements around ¹⁹²Ir brachytherapy sources.","authors":"Zoi Thrapsanioti, Vasiliki Peppa, Costas J Hourdakis, Pantelis Karaiskos, Aristea Lekatou, Evaggelos Pantelis","doi":"10.1002/acm2.14575","DOIUrl":"https://doi.org/10.1002/acm2.14575","url":null,"abstract":"<p><strong>Purpose: </strong>To provide beam quality correction factors ( <math> <semantics><msub><mi>k</mi> <mrow><mi>Q</mi> <mo>,</mo> <mi>Q</mi> <mi>o</mi></mrow> </msub> <annotation>${k}_{Q,Qo}$</annotation></semantics> </math> ) for detectors used in ¹⁹²Ir brachytherapy dosimetry measurements.</p><p><strong>Materials and methods: </strong>Ten detectors were studied, including the PTW 30013 and Exrading12 Farmer large cavity chambers, seven medium (0.1-0.3 cm³) and small (< 0.1 cm³) cavity chambers, and a synthetic microdiamond detector. The k_Q,Qo correction factors were calculated at distances from 1 to 10 cm away from an ¹⁹²Ir source, using the EGSnrc Monte Carlo (MC) code. All detectors were calibrated in a ⁶⁰Co 10 × 10 cm² reference field provided by standard calibration laboratories. The impact of the central electrode, stem and wall on the detectors' responses in ¹⁹²Ir photon energies was investigated. An experimental procedure was additionally applied for dose measurements around a microSelectron-v2 ¹⁹²Ir high dose rate (HDR) brachytherapy source using a motorized water phantom.</p><p><strong>Results: </strong>Farmer chambers underestimated the dose near the source due to signal volume averaging effects, resulting in k_Q,Qo values ranging from 1.177 and 1.317 at 1 cm, decreasing with distance to between 0.980 and 1.005 at 10 cm. Small cavity volume detectors should be used close to the source. The k_Q,Qo for the studied small and medium cavity volume detectors were found to be close to unity (within 1.3%), showing also a small dependence on source-to-detector distance, except for ion chambers containing high-Z materials in their construction. The presence of high-Z materials caused an overresponse in these detectors, resulting in k_Q,Qo values ranging from 0.950 at 1 cm to 0.729 at 10 cm away from the source. A dose rate constant of (1.114 ± 0.023)cGyh^-1U^-1 was found in agreement with the literature (within 0.5%).</p><p><strong>Conclusions: </strong>k_Q,Qo values were calculated for dose measurements around ¹⁹²Ir brachytherapy sources. Farmer chambers should be preferred for measurements at increased distances, whereas small or medium cavity volume detectors, not containing high-Z materials, should be used close to the source.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14575"},"PeriodicalIF":2.0,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142728869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of dedicated phantom for end-to-end testing of multiple image-guidance configurations incorporating light-section-based surface guidance system.","authors":"Naoki Hayashi, Tatsunori Saito, Kazuki Ouchi, Hiroshi Amma, Yuta Muraki, Keisuke Yasui, Masashi Nozue","doi":"10.1002/acm2.14517","DOIUrl":"https://doi.org/10.1002/acm2.14517","url":null,"abstract":"<p><strong>Purpose: </strong>Radiotherapy devices with multiple image-guidance systems, such as surface-guided radiation therapy (SGRT), have been widely used in recent years. However, in the case of SGRT devices using the light-section method, coordinate coincidence evaluation using a phantom for SGRT devices with patterned light projection is not appropriate. Hence, this study aims to develop a dedicated phantom able to evaluate both the detection accuracy and coordinate coincidence of multiple IGRT configurations, including light-section-based SGRT devices.</p><p><strong>Materials and method: </strong>First, we developed an end-to-end (E2E) phantom that can be scanned by CT and detected by a light-section-method-based SGRT device. Second, the detection accuracy of the phantom under three reference data acquisition conditions was evaluated using the E2E phantom. The three conditions were a body surface image detected by VOXELAN in the simulation CT room, a body surface image reconstructed from the volume data of the simulation CT room, and a body surface image acquired by VOXELAN in the radiotherapy room. Finally, the coordinate coincidence of the image-guidance system was evaluated using the E2E phantom.</p><p><strong>Result: </strong>Upon comparing detection accuracy among the three reference data acquisition methods, we found that the reference data generated in the CT room had the largest error (0.58 mm at maximum). The coordinate coincidences of the multiple image-guidance systems were within 1 mm for all components after the maintenance of VOXELAN using E2E phantom. Furthermore, the long-term direction stability was worse in the longitudinal direction.</p><p><strong>Conclusion: </strong>The new E2E phantom can be used to evaluate the detection accuracy of a light-section-based SGRT system and the coordinate coincidence using a Winston-Lutz-based method in multiple image-guided configurations. The detection accuracy in the three different reference images of VOXELAN using this phantom improved to within 1 mm in all directions.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14517"},"PeriodicalIF":2.0,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142728871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Brain MR-only workflow in clinical practice: A comparison among generators for quality assurance and patient positioning.","authors":"Mathilde Levardon, Damien Autret, Thomas Le Dorze, Camille Guillerminet, Stéphane Dufreneix","doi":"10.1002/acm2.14583","DOIUrl":"https://doi.org/10.1002/acm2.14583","url":null,"abstract":"<p><strong>Background and purpose: </strong>Routine quality control procedures are still required for sCT based on artificial intelligence (AI) to verify the performance of the generators. The aim of this study was to evaluate three generators based on AI or bulk density (BD) assignment for the patient-specific quality assurance (PSQA) of another AI-based generator in clinical routine. A patient positioning study based on 2D/2D kV-image comparing the performances of four sCT generators was also performed.</p><p><strong>Materials and methods: </strong>On the four generators available commercially at our institution, one was chosen as the clinical one, and the three others were used for PSQA. Several dose metrics were calculated like the mean error, dose-volume histogram metrics, and 1%/1 mm gamma analysis. A comparison against CT was considered as a reference. Translations and rotations found during patient positioning based on sCT were compared to those based on CT.</p><p><strong>Results: </strong>Some of the metrics calculated against CT revealed patients outside the tolerances chosen (1% for point metrics; 90% for gamma pass rate). None of the generators was able to identify these outliers for all metrics studied. Performing a PSQA with other sCT generators introduced several false positives and false negatives. None of the generators was able to clearly identify, for all metrics studied, a true sCT failure caused by a metal implant. The smallest positioning deviations were found for the BD assignment sCT, the largest for the only AI generator not based on a T1 Dixon MR sequence.</p><p><strong>Conclusions: </strong>PSQA of a sCT generator with another sCT generator should be performed with great care. Patient positioning is an important aspect to consider when evaluating a sCT generator. The results of this study should help medical physicists willing to set up a MR-only workflow for the brain based on a 2D/2D kV-image patient positioning.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14583"},"PeriodicalIF":2.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142709076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Introduction to matrix-based method for analyzing hybrid multidimensional prostate MRI data.","authors":"Xiaobing Fan, Aritrick Chatterjee, Milica Medved, Tatjana Antic, Aytekin Oto, Gregory S Karczmar","doi":"10.1002/acm2.14544","DOIUrl":"https://doi.org/10.1002/acm2.14544","url":null,"abstract":"<p><p>A new approach to analysis of prostate hybrid multidimensional MRI (HM-MRI) data was introduced in this study. HM-MRI data were acquired for a combination of a few echo times (TEs) and a few b-values. Naturally, there is a matrix associated with HM-MRI data for each image pixel. To process the data, we first linearized HM-MRI data by taking the natural logarithm of the imaging signal intensity. Subsequently, a hybrid symmetric matrix was constructed by multiplying the matrix for each pixel by its own transpose. The eigenvalues for each pixel could then be calculated from the hybrid symmetric matrix. In order to compare eigenvalues between patients, three b-values and three TEs were used, because this was smallest number of b-values and TEs among all patients. The results of eigenvalues were displayed as qualitative color maps for easier visualization. For quantitative analysis, the ratio (λ_r) of eigenvalues (λ₁, λ₂, λ₃) was defined as λ_r = (λ₁/λ₂)/λ₃ to compare region of interest (ROI) between prostate cancer (PCa) and normal tissue. The results show that the combined eigenvalue maps show PCas clearly and these maps are quite different from apparent diffusion coefficient (ADC) and T2 maps of the same prostate. The PCa has significant larger λ_r, smaller ADC and smaller T2 values than normal prostate tissue (p < 0.001). This suggests that the matrix-based method for analyzing HM-MRI data provides new information that may be clinically useful. The method is easy to use and could be easily implemented in clinical practice. The eigenvalues are associated with combination of ADC and T2 values, and could aid in the identification and staging of PCa.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14544"},"PeriodicalIF":2.0,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142681962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning in image-based outcome prediction after radiotherapy: A review.","authors":"Xiaohan Yuan, Chaoqiong Ma, Mingzhe Hu, Richard L J Qiu, Elahheh Salari, Reema Martini, Xiaofeng Yang","doi":"10.1002/acm2.14559","DOIUrl":"10.1002/acm2.14559","url":null,"abstract":"<p><p>The integration of machine learning (ML) with radiotherapy has emerged as a pivotal innovation in outcome prediction, bringing novel insights amid unique challenges. This review comprehensively examines the current scope of ML applications in various treatment contexts, focusing on treatment outcomes such as patient survival, disease recurrence, and treatment-induced toxicity. It emphasizes the ascending trajectory of research efforts and the prominence of survival analysis as a clinical priority. We analyze the use of several common medical imaging modalities in conjunction with clinical data, highlighting the advantages and complexities inherent in this approach. The research reflects a commitment to advancing patient-centered care, advocating for expanded research on abdominal and pancreatic cancers. While data collection, patient privacy, standardization, and interpretability present significant challenges, leveraging ML in radiotherapy holds remarkable promise for elevating precision medicine and improving patient care outcomes.</p>","PeriodicalId":14989,"journal":{"name":"Journal of Applied Clinical Medical Physics","volume":" ","pages":"e14559"},"PeriodicalIF":2.0,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142667930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}