Displaying all 15 publications

Abstract:
Sort:
  1. Yap LM, Jamalludin Z, Ng AH, Ung NM
    Phys Eng Sci Med, 2023 Sep;46(3):1331-1340.
    PMID: 37470929 DOI: 10.1007/s13246-023-01303-x
    The survey is to assess the current state of adaptive radiation therapy (ART) for head and neck (H&N) cases among radiotherapy centers in Malaysia and to identify any implementation limitations. An online questionnaire was sent to all radiotherapy centers in Malaysia. The 24-question questionnaire consists of general information about the center, ART practices, and limitations faced in implementing ART. 28 out of 36 radiotherapy centers responded, resulting in an overall response rate of 78%. About 52% of the responding centers rescanned and replanned less than 5% of their H&N patients. The majority (88.9%) of the respondents reported the use Cone Beam Computed Tomography alone or in combination with other modalities to trigger the ART process. The main reasons cited for adopting ART were weight loss, changes in the immobilization fitting, and anatomical variation. The adaptation process typically occurred during week 3 or week 4 of treatment. More than half of the respondents require three days or more from re-simulation to starting a new treatment plan. Both target and organ at risk delineation on new planning CT relied heavily on manual delineation by physicians and physicists, respectively. All centers perform patient-specific quality assurance for their new adaptive plans. Two main limitations in implementing ART are "limited financial resources or equipment" and "limitation on technical knowledge". There is a need for a common consensus to standardize the practice of ART and address these limitations to improve the implementation of ART in Malaysia.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods
  2. Chua GWY, Ho BS, Ng YY, Master ZR, Sultana R, Cheah P, et al.
    Int J Radiat Oncol Biol Phys, 2023 Oct 01;117(2S):e169-e170.
    PMID: 37784773 DOI: 10.1016/j.ijrobp.2023.06.1010
    PURPOSE/OBJECTIVE(S): Radiotherapy of synchronous bilateral breast cancer poses some technical challenges with regards to dose coverage and sparing of organs at risk (OAR). In this study, we aimed to evaluate dosimetric characteristics of 3 different techniques, IMPT vs photon (VMAT and HT). We hypothesized that IMPT would result in lower doses to organs at risk, as compared to the other 2 techniques.

    MATERIALS/METHODS: A total of 10 patients with synchronous bilateral breast cancer who were treated with VMAT at our institution were retrospectively analyzed. Clinical target volume (CTV) included chest wall and regional nodes (supraclavicular fossa and internal mammary chain) and prescription dose was 40.05 Gy in 15 daily fractions. HT and IMPT plans were generated for each patient. Dose-volume statistics, including planning target volume (PTV) coverage and dose to OAR: lungs, heart, thyroid, spinal cord, brachial plexus and esophagus, were compared between modalities using a paired T-test.

    RESULTS: Mean age of patients was 61 years (43-84). Majority of the patients (80%) were ER+ PR+ and HER2-. 40% of patients underwent breast reconstruction following surgery. All 3 techniques provided adequate target volume distribution and OAR sparing. Compared to VMAT and HT plans, IMPT had better heart and lung sparing effects, resulting in lower mean and V25 Gy heart dose; mean, V20 Gy and V5 Gy lung dose (p<0.0001). There was no significant difference in VMAT and HT plans for mean heart and lung dose. VMAT plans showed significantly lower V25 Gy heart dose on average (p = 0.04). V5 Gy lung dose was slightly lower in HT compared to VMAT plans, approaching statistical significance (p = 0.08). PTV coverage was adequate for all 3 techniques. All techniques fulfilled cord, esophagus, thyroid and brachial plexus constraints.

    CONCLUSION: IMPT plans showed significantly better OAR sparing compared to photon techniques. All 3 techniques met OAR constraints, and resulted in adequate target volume coverage. As IMPT is significantly more costly than VMAT or HT techniques, appropriate patient selection is important to deliver treatment in the most resource-effective manner for patients who would derive the most benefit, for example those with young age or existing heart or lung comorbidities.

    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods
  3. Yahya N, Ebert MA, Bulsara M, Haworth A, Kearvell R, Foo K, et al.
    Radiat Oncol, 2014;9:282.
    PMID: 25498565 DOI: 10.1186/s13014-014-0282-7
    To assess the impact of incremental modifications of treatment planning and delivery technique, as well as patient anatomical factors, on late gastrointestinal toxicity using data from the TROG 03.04 RADAR prostate radiotherapy trial.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods*
  4. Aminah M, Ng KH, Abdullah BJ, Jamal N
    Australas Phys Eng Sci Med, 2010 Dec;33(4):329-34.
    PMID: 20938762 DOI: 10.1007/s13246-010-0035-3
    The performance of a digital mammography system (Siemens Mammomat Novation) using different target/filter combinations and tube voltage has been assessed. The objective of this study is to optimize beam quality selection based on contrast-to-noise ratio (CNR) and mean glandular dose (MGD). Three composition of breast were studied with composition of glandular/adipose of 30/70, 50/50, and 70/30. CNR was measured using 2, 4 and 6 cm-thick simulated breast phantoms with an aluminium sheet of 0.1 mm thickness placed on top of the phantom. Three target/filter combinations, namely molybdenum/molybdenum (Mo/Mo), molybdenum/rhodium (Mo/Rh) and tungsten/rhodium (W/Rh) with various tube voltage and mAs were tested. MGD was measured for each exposure. For 50/50 breast composition, Mo/Rh combination with tube voltage 26 kVp is optimal for 2 cm-thick breast. W/Rh combination with tube voltage 27 and 28 kVp are optimal for 4 and 6 cm-thick breast, respectively. For both 30/70 and 70/30 breast composition, W/Rh combination is optimal with tube voltage 25, 26 and 27 kVp, respectively. From our study it was shown that there are potential of dose reduction up to 11% for a set CNR of 3.0 by using beam quality other than that are determined by AEC selection. Under the constraint of lowest MGD, for a particular breast composition, calcification detection is optimized by using a softer X-ray beam for thin breast and harder X-ray beam for thick breast. These experimental results also indicate that for breast with high fibroglandular tissues (70/30), the use of higher beam quality does not always increase calcification detection due to additional structured noise caused by the fibroglandular tissues itself.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods*
  5. Jafari SM, Jordan TJ, Distefano G, Bradley DA, Spyrou NM, Nisbet A, et al.
    Br J Radiol, 2015;88(1055):20140804.
    PMID: 26258442 DOI: 10.1259/bjr.20140804
    To investigate the feasibility of using glass beads as novel thermoluminescent dosemeters (TLDs) for radiotherapy treatment plan verification.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods*
  6. Samat SB, Evans CJ, Kadni T, Dolah MT
    Br J Radiol, 2000 Aug;73(872):867-77.
    PMID: 11026863
    A cylindrical gamma-ray 60Co source of activity alpha is predicted to produce an exposure rate X at a distance d in vacuum, given by X = gamma(T)(alpha/d2), where gamma(T) is the specific gamma-ray constant. It has been documented that this formula may be used to approximate X with an accuracy of 1% from a source of length l, provided that d/l > or = 5. It is shown that the formula is accurate to 0.1% under these conditions, provided that the distance is measured from the centre of the source. When absorption in the source and scattering in the collimator are considered, the position of the origin d = 0 can shift by a distance of the order of centimetres. Absorption in air between the source and the ionization chamber adds an exponential factor to the formula. It is shown that even when these modifications are included the discrepancy in the results, although generally less than 1%, is still large compared with the measurement errors. Some suggestions are made for the origin of this discrepancy.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods*
  7. Farayola MF, Shafie S, Mohd Siam F, Khan I
    Comput Methods Programs Biomed, 2020 Apr;187:105202.
    PMID: 31835107 DOI: 10.1016/j.cmpb.2019.105202
    Background This paper presents a numerical simulation of normal and cancer cells' population dynamics during radiotherapy. The model used for the simulation was the improved cancer treatment model with radiotherapy. The model simulated the population changes during a fractionated cancer treatment process. The results gave the final populations of the cells, which provided the final volumes of the tumor and normal cells. Method The improved model was obtained by integrating the previous cancer treatment model with the Caputo fractional derivative. In addition, the cells' population decay due to radiation was accounted for by coupling the linear-quadratic model into the improved model. The simulation of the treatment process was done with numerical variables, numerical parameters, and radiation parameters. The numerical variables include the populations of the cells and the time of treatment. The numerical parameters were the model factors which included the proliferation rates of cells, competition coefficients of cells, and perturbation constant for normal cells. The radiation parameters were clinical data based on the treatment procedure. The numerical parameters were obtained from the previous literature while the numerical variables and radiation parameters, which were clinical data, were obtained from reported data of four cancer patients treated with radiotherapy. The four cancer patients had tumor volumes of 28.4 cm3, 18.8 cm3, 30.6 cm3, and 12.6 cm3 and were treated with different treatment plans and a fractionated dose of 1.8 Gy each. The initial populations of cells were obtained by using the tumor volumes. The computer simulations were done with MATLAB. Results The final volumes of the tumors, from the results of the simulations, were 5.67 cm3, 4.36 cm3, 5.74 cm3, and 6.15 cm3 while the normal cells' volumes were 28.17 cm3, 18.68 cm3, 30.34 cm3, and 12.54 cm3. The powers of the derivatives were 0.16774, 0.16557, 0.16835, and 0.16. A variance-based sensitivity analysis was done to corroborate the model with the clinical data. The result showed that the most sensitive factors were the power of the derivative and the cancer cells' proliferation rate. Conclusion The model provided information concerning the status of treatments and can also predict outcomes of other treatment plans.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods
  8. Hashikin NAA, Yeong CH, Guatelli S, Abdullah BJJ, Ng KH, Malaroda A, et al.
    Phys Med Biol, 2017 Aug 22;62(18):7342-7356.
    PMID: 28686171 DOI: 10.1088/1361-6560/aa7e5b
    We aimed to investigate the validity of the partition model (PM) in estimating the absorbed doses to liver tumour ([Formula: see text]), normal liver tissue ([Formula: see text]) and lungs ([Formula: see text]), when cross-fire irradiations between these compartments are being considered. MIRD-5 phantom incorporated with various treatment parameters, i.e. tumour involvement (TI), tumour-to-normal liver uptake ratio (T/N) and lung shunting (LS), were simulated using the Geant4 Monte Carlo (MC) toolkit. 108track histories were generated for each combination of the three parameters to obtain the absorbed dose per activity uptake in each compartment ([Formula: see text], [Formula: see text], and [Formula: see text]). The administered activities, A were estimated using PM, so as to achieve either limiting doses to normal liver, [Formula: see text] or lungs, [Formula: see text] (70 or 30 Gy, respectively). Using these administered activities, the activity uptake in each compartment ([Formula: see text], [Formula: see text], and [Formula: see text]) was estimated and multiplied with the absorbed dose per activity uptake attained using the MC simulations, to obtain the actual dose received by each compartment. PM overestimated [Formula: see text] by 11.7% in all cases, due to the escaped particles from the lungs. [Formula: see text] and [Formula: see text] by MC were largely affected by T/N, which were not considered by PM due to cross-fire exclusion at the tumour-normal liver boundary. These have resulted in the overestimation of [Formula: see text] by up to 8% and underestimation of [Formula: see text] by as high as  -78%, by PM. When [Formula: see text] was estimated via PM, the MC simulations showed significantly higher [Formula: see text] for cases with higher T/N, and LS  ⩽  10%. All [Formula: see text] and [Formula: see text] by MC were overestimated by PM, thus [Formula: see text] were never exceeded. PM leads to inaccurate dose estimations due to the exclusion of cross-fire irradiation, i.e. between the tumour and normal liver tissue. Caution should be taken for cases with higher TI and T/N, and lower LS, as they contribute to major underestimation of [Formula: see text]. For [Formula: see text], a different correction factor for dose calculation may be used for improved accuracy.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods*
  9. Entezam A, Fielding A, Bradley D, Fontanarosa D
    PLoS One, 2023;18(2):e0280765.
    PMID: 36730280 DOI: 10.1371/journal.pone.0280765
    Computed tomography (CT) derived Monte Carlo (MC) phantoms allow dose determination within small animal models that is not feasible with in-vivo dosimetry. The aim of this study was to develop a CT-derived MC phantom generated from a mouse with a xenograft tumour that could then be used to calculate both the dose heterogeneity in the tumour volume and out of field scattered dose for pre-clinical small animal irradiation experiments. A BEAMnrc Monte-Carlo model has been built of our irradiation system that comprises a lead collimator with a 1 cm diameter aperture fitted to a Cs-137 gamma irradiator. The MC model of the irradiation system was validated by comparing the calculated dose results with dosimetric film measurement in a polymethyl methacrylate (PMMA) phantom using a 1D gamma-index analysis. Dose distributions in the MC mouse phantom were calculated and visualized on the CT-image data. Dose volume histograms (DVHs) were generated for the tumour and organs at risk (OARs). The effect of the xenographic tumour volume on the scattered out of field dose was also investigated. The defined gamma index analysis criteria were met, indicating that our MC simulation is a valid model for MC mouse phantom dose calculations. MC dose calculations showed a maximum out of field dose to the mouse of 7% of Dmax. Absorbed dose to the tumour varies in the range 60%-100% of Dmax. DVH analysis demonstrated that tumour received an inhomogeneous dose of 12 Gy-20 Gy (for 20 Gy prescribed dose) while out of field doses to all OARs were minimized (1.29 Gy-1.38 Gy). Variation of the xenographic tumour volume exhibited no significant effect on the out of field scattered dose to OARs. The CT derived MC mouse model presented here is a useful tool for tumour dose verifications as well as investigating the doses to normal tissue (in out of field) for preclinical radiobiological research.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods
  10. Rasmussen ME, Akbarov K, Titovich E, Nijkamp JA, Van Elmpt W, Primdahl H, et al.
    JCO Glob Oncol, 2024 Aug;10:e2400173.
    PMID: 39236283 DOI: 10.1200/GO.24.00173
    PURPOSE: Most research on artificial intelligence-based auto-contouring as template (AI-assisted contouring) for organs-at-risk (OARs) stem from high-income countries. The effect and safety are, however, likely to depend on local factors. This study aimed to investigate the effects of AI-assisted contouring and teaching on contouring time and contour quality among radiation oncologists (ROs) working in low- and middle-income countries (LMICs).

    MATERIALS AND METHODS: Ninety-seven ROs were randomly assigned to either manual or AI-assisted contouring of eight OARs for two head-and-neck cancer cases with an in-between teaching session on contouring guidelines. Thereby, the effect of teaching (yes/no) and AI-assisted contouring (yes/no) was quantified. Second, ROs completed short-term and long-term follow-up cases all using AI assistance. Contour quality was quantified with Dice Similarity Coefficient (DSC) between ROs' contours and expert consensus contours. Groups were compared using absolute differences in medians with 95% CIs.

    RESULTS: AI-assisted contouring without previous teaching increased absolute DSC for optic nerve (by 0.05 [0.01; 0.10]), oral cavity (0.10 [0.06; 0.13]), parotid (0.07 [0.05; 0.12]), spinal cord (0.04 [0.01; 0.06]), and mandible (0.02 [0.01; 0.03]). Contouring time decreased for brain stem (-1.41 [-2.44; -0.25]), mandible (-6.60 [-8.09; -3.35]), optic nerve (-0.19 [-0.47; -0.02]), parotid (-1.80 [-2.66; -0.32]), and thyroid (-1.03 [-2.18; -0.05]). Without AI-assisted contouring, teaching increased DSC for oral cavity (0.05 [0.01; 0.09]) and thyroid (0.04 [0.02; 0.07]), and contouring time increased for mandible (2.36 [-0.51; 5.14]), oral cavity (1.42 [-0.08; 4.14]), and thyroid (1.60 [-0.04; 2.22]).

    CONCLUSION: The study suggested that AI-assisted contouring is safe and beneficial to ROs working in LMICs. Prospective clinical trials on AI-assisted contouring should, however, be conducted upon clinical implementation to confirm the effects.

    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods
  11. Zaman ZK, Ung NM, Malik RA, Ho GF, Phua VC, Jamalludin Z, et al.
    Phys Med, 2014 Dec;30(8):980-4.
    PMID: 25086486 DOI: 10.1016/j.ejmp.2014.07.002
    Cobalt-60 (Co-60) is a relatively new source for the application of high-dose rate (HDR) brachytherapy. Radiation dose to the rectum is often a limiting factor in achieving the full prescribed dose to the target during brachytherapy of cervical cancer. The aim of this study was to measure radiation doses to the rectum in-vivo during HDR Co-60 brachytherapy. A total of eleven HDR brachytherapy treatments of cervical cancer were recruited in this study. A series of diodes incorporated in a rectal probe was inserted into the patient's rectum during each brachytherapy procedure. Real-time measured rectal doses were compared to calculated doses by the treatment planning system (TPS). The differences between calculated and measured dose ranged from 8.5% to 41.2%. This corresponds to absolute dose differences ranging from 0.3 Gy to 1.5 Gy. A linear relationship was observed between calculated and measured doses with linear regression R(2) value of 0.88, indicating close association between the measured and calculated doses. In general, absorbed doses for the rectum as calculated by TPS were observed to be higher than the doses measured using the diode probe. In-vivo dosimetry is an important quality assurance method for HDR brachytherapy of cervical cancer. It provides information that can contribute to the reduction of errors and discrepancies in dose delivery. Our study has shown that in-vivo dosimetry is feasible and can be performed to estimate the dose to the rectum during HDR brachytherapy using Co-60.
    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods
  12. Yu L, Tang TLS, Cassim N, Livingstone A, Cassidy D, Kairn T, et al.
    J Appl Clin Med Phys, 2019 Nov;20(11):189-198.
    PMID: 31613053 DOI: 10.1002/acm2.12726
    PURPOSE: Gamma evaluation is the most commonly used technique for comparison of dose distributions for patient-specific pretreatment quality assurance in radiation therapy. Alternative dose comparison techniques have been developed but not widely implemented. This study aimed to compare and evaluate the performance of several previously published alternatives to the gamma evaluation technique, by systematically evaluating a large number of patient-specific quality assurance results.

    METHODS: The agreement indices (or pass rates) for global and local gamma evaluation, maximum allowed dose difference (MADD) and divide and conquer (D&C) techniques were calculated using a selection of acceptance criteria for 429 patient-specific pretreatment quality assurance measurements. Regression analysis was used to quantify the similarity of behavior of each technique, to determine whether possible variations in sensitivity might be present.

    RESULTS: The results demonstrated that the behavior of D&C gamma analysis and MADD box analysis differs from any other dose comparison techniques, whereas MADD gamma analysis exhibits similar performance to the standard global gamma analysis. Local gamma analysis had the least variation in behavior with criteria selection. Agreement indices calculated for 2%/2 mm and 2%/3 mm, and 3%/2 mm and 3%/3 mm were correlated for most comparison techniques.

    CONCLUSION: Radiation oncology treatment centers looking to compare between different dose comparison techniques, criteria or lower dose thresholds may apply the results of this study to estimate the expected change in calculated agreement indices and possible variation in sensitivity to delivery dose errors.

    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods*
  13. Jamalludin Z, Jong WL, Malik RA, Rosenfeld AB, Ung NM
    Phys Med, 2020 Jan;69:52-60.
    PMID: 31830631 DOI: 10.1016/j.ejmp.2019.11.025
    PURPOSE: Dose to the rectum during brachytherapy treatment may differ from an approved treatment plan which can be quantified with in vivo dosimetry (IVD). This study compares the planned with in vivo doses measured with MOSkin and PTW 9112 rectal probe in patients undergoing CT based HDR cervical brachytherapy with Co-60 source.

    METHODS: Dose measurement of a standard pear-shaped plan carried out in phantom to verify the MOSkin dose measurement accuracy. With MOSkin attached to the third diode, RP3 of the PTW 9112, both detectors were inserted into patients' rectum. The RP3 and MOSkin measured doses in 18 sessions as well as the maximum measured doses from PTW 9112, RPmax in 48 sessions were compared to the planned doses.

    RESULTS: Percentage dose differences ΔD (%) in phantom study for two MOSkin found to be 2.22 ± 0.07% and 2.5 ± 0.07%. IVD of 18 sessions resulted in ΔD(%) of -16.3% to 14.9% with MOSkin and ΔD(%) of -35.7% to -2.1% with RP3. In 48 sessions, RPmax recorded ΔD(%) of -37.1% to 11.0%. MOSkin_measured doses were higher in 44.4% (8/18) sessions, while RP3_measured were lower than planned doses in all sessions. RPmax_measured were lower in 87.5% of applications (42/47).

    CONCLUSIONS: The delivered doses proven to deviate from planned doses due to unavoidable shift between imaging and treatment as measured with MOSkin and PTW 9112 detectors. The integration of MOSkin on commercial PTW 9112 surface found to be feasible for rectal dose IVD during cervical HDR ICBT.

    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods
  14. Cheah SK, Matthews T, Teh BS
    Asian Pac J Cancer Prev, 2016;17(9):4233-4235.
    PMID: 27797223
    BACKGROUND: Whole brain radiotherapy (WBRT) and stereotactic radiosurgery were frequently used to palliate patients with brain metastases. It remains controversial which modality or combination of therapy is superior especially in the setting of limited number of brain metastases. The availability of newer medical therapy that improves survival highlighted the importance of reducing long term radiation toxicity associated with WBRT. In this study, we aim to demonstrate the hippocampal sparing technique with whole brain and integrated simultaneous boost Materials and Methods: Planning data from 10 patients with 1-5 brain metastases treated with SRS were identified. Based on the contouring guideline from RTOG atlas, we identified and contoured the hippocampus with 5mm isocentric expansion to form the hippocampal avoidance structure. The plan was to deliver hippocampal sparing whole brain radiotherapy (HSWBRT) of 30 Gy in 10 fractions and simultaneous boost to metastatic lesions of 30 Gy in 10 fractions each.

    RESULTS: The PTV, hippocampus and hippocampal avoidance volumes ranges between 1.00 - 39.00 cc., 2.50 - 5.30 cc and 26.47 - 36.30 cc respectively. The mean hippocampus dose for the HSWBRT and HSWBRT and SIB plans was 8.06 Gy and 12.47 respectively. The max dose of optic nerve, optic chiasm and brainstem were kept below acceptable range of 37.5 Gy.

    CONCLUSIONS: The findings from this dosimetric study demonstrated the feasibility and safety of treating limited brain metastases with HSWBRT and SIB. It is possible to achieve the best of both worlds by combining HSWBRT and SIB to achieve maximal local intracranial control while maintaining as low a dose as possible to the hippocampus thereby preserving memory and quality of life.

    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods*
  15. Yahya N, Ebert MA, Bulsara M, Kennedy A, Joseph DJ, Denham JW
    Radiother Oncol, 2016 08;120(2):339-45.
    PMID: 27370204 DOI: 10.1016/j.radonc.2016.05.010
    BACKGROUND AND PURPOSE: Most predictive models are not sufficiently validated for prospective use. We performed independent external validation of published predictive models for urinary dysfunctions following radiotherapy of the prostate.

    MATERIALS/METHODS: Multivariable models developed to predict atomised and generalised urinary symptoms, both acute and late, were considered for validation using a dataset representing 754 participants from the TROG 03.04-RADAR trial. Endpoints and features were harmonised to match the predictive models. The overall performance, calibration and discrimination were assessed.

    RESULTS: 14 models from four publications were validated. The discrimination of the predictive models in an independent external validation cohort, measured using the area under the receiver operating characteristic (ROC) curve, ranged from 0.473 to 0.695, generally lower than in internal validation. 4 models had ROC >0.6. Shrinkage was required for all predictive models' coefficients ranging from -0.309 (prediction probability was inverse to observed proportion) to 0.823. Predictive models which include baseline symptoms as a feature produced the highest discrimination. Two models produced a predicted probability of 0 and 1 for all patients.

    CONCLUSIONS: Predictive models vary in performance and transferability illustrating the need for improvements in model development and reporting. Several models showed reasonable potential but efforts should be increased to improve performance. Baseline symptoms should always be considered as potential features for predictive models.

    Matched MeSH terms: Radiotherapy Planning, Computer-Assisted/methods*
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links