Frontiers in planning optimization for lung SBRT

Impact of Maximum Point Dose Within the Planning Target Volume on Local Control of Nonsmall Cell Lung Cancer Treated With Stereotactic Body Radiotherapy

BACKGROUND

No consensus exists on the maximum dose delivered to the planning target volume (PTV) in the delivery of stereotactic body radiotherapy (SBRT) for primary lung cancer. We investigated whether higher biologically effective doses (BED) within the PTV were associated with improved tumor control.

METHODS

We reviewed patients with early-stage, node-negative nonsmall cell lung cancer who received curative-intent SBRT between 2005 and 2018. We calculated the maximum BED (maxBED) within the PTV for all patients, analyzing outcomes using the cumulative incidence method and Fine-Gray test statistics to assess prognostic impact.

RESULTS

We analyzed 171 patients (median age, 70.2; range, 43 to 90 y) with 181 lung nodules. Median follow-up was 2.7 years (range, 0.1 to 12 y) for all patients and 4.2 years (range, 0.2 to 8.4 y) for living patients. Median maximum tumor diameter was 1.9 cm (range, 0.7 to 5.6 cm). Patients received a prescription of 48 or 50 Gy in 4 or 5 fractions, respectively, except for one who received 60 Gy in 5 fractions. Median maxBED was 120 Gy (range, 101 to 171 Gy). There was no difference in the 3-year local control (LC) rate among patients treated with a maxBED<120 Gy versus ≥120 Gy ( P =0.83).

CONCLUSIONS

No significant differences in LC were observed between patients with early-stage nonsmall cell lung cancer treated with SBRT in 4 or 5 fractions with a maxBED≥120 Gy. However, a higher maxBED trended toward improved LC rates, suggesting a maxBED threshold greater than 120 Gy may be needed to improve LC rates.

Patient specific quality assurance in SBRT: a systematic review of measurement-based methods

This topical review focuses on Patient-Specific Quality Assurance (PSQA) approaches to stereotactic body radiation therapy (SBRT). SBRT requires stricter accuracy than standard radiation therapy due to the high dose per fraction and the limited number of fractions. The review considered various PSQA methods reported in 36 articles between 01/2010 and 07/2022 for SBRT treatment. In particular comparison among devices and devices designed for SBRT, sensitivity and resolution, verification methodology, gamma analysis were specifically considered. The review identified a list of essential data needed to reproduce the results in other clinics, highlighted the partial miss of data reported in scientific papers, and formulated recommendations for successful implementation of a PSQA protocol.

Difference in target dose distributions between Acuros XB and collapsed cone convolution/superposition and the impact of the tumor locations in clinical cases of stereotactic ablative body radiotherapy for lung cancer

Objectives

The objective of the study is to analyze the difference in target dose distributions between Acuros XB (AXB) and collapsed cone convolution (CCC)/superposition and the impact of the tumor locations in clinical cases of stereotactic ablative body radiotherapy (SABR) for lung cancer.

Materials and Methods

Ninety-six patients underwent SABR for lung cancers Kyushu University Hospital from 2014 to 2017. We recalculated clinical plans originally calculated by AXB using CCC with the identical monitor units (MUs) and beam arrangements. We calculated the following dosimetric parameters: maximum dose (Dmax), minimum dose (Dmin), homogeneity index (HI), conformity index (CI), and D95 of the planning target volume (PTV). We investigated the difference between the results of two calculations and examined the impact of tumor location. Moreover, we determined the target central dose using a thorax phantom and assessed the calculation accuracy of the two algorithms for each fraction.

Results

CCC significantly overestimated the dose to PTV, compared to AXB (P < 0.05). The mean differences of Dmax, Dmin, and D95 were 1.17, 1.95, and 1.85 Gy, respectively. The mean differences of HI and CI were 0.02 and - 0.06. Dmin, HI, and D95 had significant correlations with the tumor location, and the difference was greater when the PTV was included the chest wall (P < 0.05). The discrepancy between the calculated and irradiated dose was 2.48% for CCC, whereas it was 0.14% for AXB.

Conclusions

We demonstrated that CCC significantly overestimated the dose to PTV relative to AXB in clinical cases of lung SABR.

Cancer-associated fibroblasts in radiotherapy: Bystanders or protagonists?

BACKGROUND

The primary goal of radiotherapy (RT) is to induce cellular damage on malignant cells; however, it is becoming increasingly recognized the important role played by the tumor microenvironment (TME) in therapy outcomes. Therapeutic irradiation of tumor lesions provokes profound cellular and biological reconfigurations within the TME that ultimately may influence the fate of the therapy.

MAIN CONTENT

Cancer-associated fibroblasts (CAFs) are known to participate in all stages of cancer progression and are increasingly acknowledged to contribute to therapy resistance. Accumulated evidence suggests that, upon radiation, fibroblasts/CAFs avoid cell death but instead enter a permanent senescent state, which in turn may influence the behavior of tumor cells and other components of the TME. Despite the proposed participation of senescent fibroblasts on tumor radioprotection, it is still incompletely understood the impact that RT has on CAFs and the ultimate role that irradiated CAFs have on therapy outcomes. Some of the current controversies may emerge from generalizing observations obtained using normal fibroblasts and CAFs, which are different cell entities that may respond differently to radiation exposure.

CONCLUSION

In this review we present current knowledge on the field of CAFs role in radiotherapy; we discuss the potential tumorigenic functions of radiation-induced senescent fibroblasts and CAFs and we make an effort to integrate the knowledge emerging from preclinical experimentation with observations from the clinics. Video Abstract.

Treatment plan comparison of volumetric-modulated arc therapy to intensity-modulated radiotherapy in lung stereotactic body radiotherapy using either 6- or 10-MV photon energies

Purpose

The aim of this study was to dosimetrically compare volumetric‐modulated arc therapy (VMAT) with intensity‐modulated radiotherapy (IMRT) techniques using either 6‐ or 10‐MV photon beam energies in lung stereotactic body radiation therapy (SBRT) plans.

Methods

Thirty patients with primary or metastatic lung tumors eligible for SBRT were randomly selected. VMAT and IMRT treatment plans using either 6‐ or 10‐MV photon energies were generated through automatic SBRT planning software in the RayStation treatment planning system.

Results

For planning target volume, there was no difference in D_95% for all plans, whereas D_2% and D_50% were significantly increased by 5.22%–5.98% and 2.47%–2.59%, respectively, using VMAT_6/10‐MV plans compared to IMRT_6/10‐MV plans. When comparing the D_max of organs at risk (OARs), VMAT_6/10‐MV was 18.32%–47.95% lower than IMRT_6/10‐MV for almost all OARs. VMAT_6/10‐MV obviously decreased D_mean, V_5Gy, V_10Gy, and V_20Gy of whole lung by 9.68%–20.92% than IMRT_6/10‐MV. Similar results were found when comparing VMAT_6‐MV with IMRT_10‐MV or VMAT_10‐MV with IMRT_6‐MV. The differences in the D_2%, heterogeneity index, and conformity index between 6‐ and 10‐MV plans are not statistically significant. Plans using 6‐MV performed 4.68%–8.91% lower levels of D_max of spinal cord, esophagus, great vessels, and trachea and proximal bronchial tree than those using 10‐MV plans. Similarly, D_mean, V_5Gy, V_10Gy, and V_20Gy of whole lung were also reduced by 2.79%–5.25% using 6‐MV. For dose fall‐off analysis, the D_2cm and R_50% of VMAT_6/10‐MV were lower than those of IMRT_6/10‐MV. Dose fall‐off curve based on 10 rings was steeper for VMAT plans than IMRT plans regardless of the energy used.

Conclusions

For lung SBRT plans, VMAT‐based plans significantly reduced OARs dose and steepened dose fall‐off curves compared to IMRT‐based plans. A 6‐MV energy level was a better choice than 10‐MV for lung SBRT. In addition, the dose differences between different techniques were more obvious than those between different energy levels.

Investigation of optimum minimum segment width on VMAT plan quality and deliverability: A comprehensive dosimetric and clinical evaluation using DVH analysis

Purpose

Minimum segment width (MSW) plays a fundamental role in the shaping of optimized apertures and creation of segments of varying sizes and shapes in complex radiotherapy treatment plans. The purpose of this work was to study the effect of MSW on dose distribution in patients planned with VMAT for various treatment sites using dose volume histogram (DVH) analysis.

Materials and methods

For the validation of optimum MSW, 125 clinical treatment plans were evaluated. Five groups were identified (brain, head and neck, thorax, pelvis, and extremity), and five cases were chosen from each group. For each case, five plans were created with different MSW (0.5, 0.8, 1.0, 1.25, and 1.5 cm). The quality of treatment plans created using different MSW were compared using dosimetric indicators such as target coverage (D₉₈—dose to 98% of the planning target volume (PTV), maximum dose (D₂—maximum dose to 2% of the PTV), monitor units (MU), and DVH parameters related to organs at risk (OAR). The effect of the MSW on delivery accuracy was quantitatively analyzed using the measured fluence utilizing ionization chamber‐based transmission detector and model‐based dose verification system. Traditional global gamma analysis (2%, 2 mm) and dose volume information was gathered for the PTV and organs at risk and compared for different MSWs.

Results

A total of 125 plans were created and compared across five groups. In terms of treatment plan quality, the plans using MSW of 0.5 cm was found to be superior in all groups. PTV coverage (D₉₈) decreased significantly (p < 0.05) as the MSW increased. Similarly, the maximum dose (D₂) was found to be increased significantly (p < 0.05) as the MSW increased from 0.5 cm, with MSW of 1.5 cm being the least in terms of plan quality for both PTVs and OARs. In terms of plan deliverability using DVH analysis, treatment planning system (TPS) compared to measured fluence, VMAT plans produced with MSW of 0.5 cm showed a better dosimetric index and a smaller deviation for both PTVs and OARs. The deliverability of the plans deteriorated as the MSW increased.

Conclusion

Dose volume histogram (DVH) analysis demonstrated that treatment plans with minimal MSW showed better plan quality and deliverability and provided clinical relevance as compared to gamma index analysis.

Automation and integration of a novel restricted single-isocenter stereotactic body radiotherapy (a-RESIST) method for synchronous two lung lesions

Synchronous treatment of two lung lesions using a single-isocenter volumetric modulated arc therapy (VMAT) stereotactic body radiation therapy (SBRT) plan can decrease treatment time and reduce the impact of intrafraction motion. However, alignment of both lesions on a single cone beam CT (CBCT) can prove difficult and may lead to setup errors and unacceptable target coverage loss. A Restricted Single-Isocenter Stereotactic Body Radiotherapy (RESIST) method was created to minimize setup uncertainties and provide treatment delivery flexibility. RESIST utilizes a single-isocenter placed at patient's midline and allows both lesions to be planned separately but treated in the same session. Herein is described a process of automation of this novel RESIST method. Automation of RESIST significantly reduced treatment planning time while maintaining the benefits of RESIST. To demonstrate feasibility, ten patients with two lung lesions previously treated with a single-isocenter clinical VMAT plan were replanned manually with RESIST (m-RESIST) and with automated RESIST (a-RESIST). a-RESIST method automatically sets isocenter, creates beam geometry, chooses appropriate dose calculation algorithms, and performs VMAT optimization using an in-house trained knowledge-based planning model for lung SBRT. Both m-RESIST and a-RESIST showed lower dose to normal tissues compared to manually planned clinical VMAT although a-RESIST provided slightly inferior, but still clinically acceptable, dose conformity and gradient indices. However, a-RESIST significantly reduced the treatment planning time to less than 20 min and provided a higher dose to the lung tumors. The a-RESIST method provides guidance for inexperienced planners by standardizing beam geometry and plan optimization using DVH estimates. It produces clinically acceptable two lesions VMAT lung SBRT plans efficiently. We have further validated a-RESIST on phantom measurement and independent pretreatment dose verification of another four selected 2-lesions lung SBRT patients and implemented clinically. Further development of a-RESIST for more than two lung lesions and refining this approach for extracranial oligometastastic abdominal/pelvic SBRT, including development of automated simulated collision detection algorithm, merits future investigation.

Application of discrete cosine transform to assess the effect of tumor motion variations on the definition of ITV in lung and liver SBRT

PURPOSE

To use Discrete Cosine Transform to include tumor motion variations on ITV definition of SBRT patients.

METHODS

Data from 66 patients was collected. 2D planar fluoroscopy images (FI) were available for 54 patients. Daily CBCT projections (CBCTp) from 29 patients were employed to measure interfraction amplitude variability. Systematic amplitude variations were obtained from 17 patients with data from both FI and CBCTp. Tumor motion curves obtained from FI were characterized with a Cosine model (CM), based on cosine functions to the power of 2, 4 or 6, and DCT. Performance of both models was evaluated by means of R² coefficient and by comparing their results on Internal Target Volume (ITV) margins against those calculated from original tumor motion curves. Amplitude variations from CBCTp, as well as estimations of baseline shift variations were added to the DCT model to account for their effect on ITV margins.

RESULTS

DCT replicated tumor motion curves with a mean R² values for all patients of 0.86, 0.91 and 0.96 for the lateral (LAT), anterior-posterior (AP) and cranio-caudal (CC) directions respectively. CM yielded worst results, with R² values of 0.64, 0.61 and 0.74 in the three directions. Interfraction amplitude variation increased ITV margins by a 9%, while baseline shift variability implied a 40% and 80-100% increase for normalized values of baseline shift of 0.2 and 0.4 respectively.

CONCLUSIONS

Probability distribution functions of tumor positions can be successfully characterized with DCT. This permits to include tumor motion variablilities obtained from patient population into patient specific ITVs.

Lean Thinking to manage a national working group on physics aspects of Stereotactic Body Radiation Therapy

PURPOSE

To report how the adoption of a Lean Thinking mindset in the management of a national working group (WG) on the physics of stereotactic body radiation therapy (SBRT) contributed to achieve SBRT standardization objectives.

METHODS

Vision for the WG has been established as fragmentation reduction and process harmonization enhancement in SBRT for Italian centers. Two main research themes of the technical aspects of SBRT emerged as areas with major standardization improvement needs, small field dosimetry and SBRT planning comparisons, to be investigated through multi-institutional studies. The management of the WG leveraged on the Lean concept of fostering self-organization in a non-hierarchical environment. Four progressive involvement levels were defined for each study. No specific "scientific" pre-experience was required to propose and coordinate a project, just requiring a voluntary commitment. People engagement was measured in terms of number of published articles. The standardization goals have been conducted through a simplified "5S" (Sort, Set in Order, Shine, Standardize, and Sustain) methodology, first considering a phase of awareness (the first three "S"), then identifying and implementing standardization actions (the last two "S").

RESULTS

Since the beginning, 157 medical physicists joined the AIFM/SBRT-WG. Twenty-four papers/reviews/letters have been published in the period 2014-2019 on major radiation oncology journals, authored by >100 physicists (>50% working in small hospitals). Six over 12 first authors worked in peripheral/small hospitals, with no prior publication as first author. These studies contributed to the awareness and standardization phases for both small-field dosimetry and planning. In particular, errors in small-field measurements in 8% of centers were detected thanks to a generalized output factor curve in function of the effective field size created by averaging data available from different Linacs. Furthermore, planner's experience in SBRT was correlated with dosimetric parameters in the awareness phase; while sharing median dose volume histograms (DVHs) reduced variability among centers while keeping the same level of plan complexity. Finally, all the dosimetric parameters statistically significant to the planner experience during the awareness phase, were no longer significantly different in the standardization phase.

CONCLUSIONS

The experience of our SBRT-WG has shown how a Lean Thinking mindset could foster the SBRT procedure standardization and spread the physics of SBRT knowledge, enhancing personal growth. Our expectation is to inspire other scientific societies that have to deal with fragmented contexts or pursue processes harmonization through Lean principles.

Cleaning the dose falloff in lung SBRT plan

PURPOSE

To investigate a planning technique that can possibly reduce low-to-intermediate dose spillage (measured by R50%, D2cm values) in lung SBRT plans.

MATERIALS AND METHODS

Dose falloff outside the target was studied retrospectively in 102 SBRT VMAT plans of lung tumor. Plans having R50% and/or D2cm higher than recommended tolerances in RTOG protocols 0813 and 0915 were replanned with new optimization constraints using novel shell structures and novel constraints. Violations in the RTOG R50% value can be rectified with a dose constraint to a novel shell structure ("OptiForR50"). The construction of structure OptiForR50% and the novel optimization criteria translate the RTOG goals for R50% into direct inputs for the optimizer. Violations in the D2cm can be rectified using constraints on a 0.5 cm thick shell structure with inner surface 2cm from the PTV surface. Wilcoxon signed-rank test was used to compare differences in dose conformity, volume of hot spots, R50%, D2cm of the target in addition to the OAR doses. A two-sided P-value of 0.05 was used to assess statistical significance.

RESULTS

Among 102 lung SBRT plans with PTV sizes ranging from 5 to 179 cc, 32 plans with violations in R50% or D2cm were reoptimized. The mean reduction in R50% (4.68 vs 3.89) and D2cm (56.49 vs 52.51) was statistically significant both having P < 0.01. Target conformity index, volume of 105% isodose contour outside PTV, normal lung V20, and mean dose to heart and aorta were significantly lowered with P < 0.05.

CONCLUSION

The novel planning methodology using multiple shells including the novel OptiForR50 shell with precisely calculated dimensions and optimizer constraints lead to significantly lower values of R50% and D2cm and lower dose spillage in lung SBRT plans. All plans were successfully brought into the zone of no RTOG violations.

Dose prescription in SBRT for early-stage non-small cell lung cancer: are we all speaking the same language?

INTRODUCTION

Stereotactic body radiation therapy is increasingly used in the treatment of early-stage lung cancers. Guidelines provide indications regarding the constraints to the organs at risk (OARs) and the minimum coverage of the planning target volume but do not suggest optimal dose distribution. Data on dose distribution from the different published series are not comparable due to different prescription modalities and reported dose parameters.

METHODS

We conducted a review of the published data on dose prescription, focusing on the role of homogeneity on local tumor control, and present suggestions on how to specify and report the prescriptions to permit comparisons between studies or between cases from different centers.

CONCLUSIONS

To identify the dose-prescription modality that better correlates with oncologic outcomes, future studies should guarantee a close uniformity of dose distribution between cases and complete dose parameters reporting for treatment volumes and OARs.

Impact of plan parameters and modulation indices on patient-specific QA results for standard and stereotactic VMAT

PURPOSE

To demonstrate the impact of modulation indices and plan parameters on the gamma passing rates (GPR) of patient-specific quality assurance of standard and stereotactic volumetric modulated arc therapy (VMAT) plans.

METHODS

A total of 758 patients' QA plans were utilized, including standard VMAT plans with Trilogy (n = 87, group A) and TreuBeam STx (n = 332, group B), and 339 stereotactic VMAT plans with TrueBeam STx (group C). Modulation indices were obtained considering the speed and acceleration of the multileaf collimator (MLC) (MI_s, MI_a), and MLC, gantry speed, and dose rate changes (MI_t). The mean aperture size (MA), monitor unit (MU), and amount of jaw tracking (%JT) were acquired. Gamma analysis was performed with 2 mm/2% and 1 mm/2% for the standard and stereotactic VMAT plans, respectively. Statistical analyses were performed to investigate the correlation between modulation index/plan parameters and GPR.

RESULTS

Spearman's rank correlation to GPRs with MI_s, MI_a, and MI_t, were -0.44, -0.45, and -0.46 for group A; -0.39, -0.37, and -0.38 for group B; and -0.04, -0.11, and -0.10 for group C, respectively. While MU and MA showed significant correlations in all groups, %JT showed a significant correlation only with stereotactic VMAT plans. The most influential parameter combinations were MU-MA (r_s = 0.50), MI_s-%JT (r_s = 0.43), and MU-%JT (r_s = 0.38) for groups A, B, and C, respectively.

CONCLUSIONS

MLC modulation mostly affected the GPR in the delivery of standard VMAT plans, while MU and %JT showed more importance in stereotactic VMAT plans.

EPID sensitivity to delivery errors for pre-treatment verification of lung SBRT VMAT plans

PURPOSE

To study the sensitivity of an Electronic Portal Imaging Device (EPID) in detecting delivery errors for VMAT lung stereotactic body radiotherapy (SBRT) using the Collapsed Arc method.

METHODS

Baseline VMAT plans and plans with errors intentionally introduced were generated for 15 lung SBRT patients. Three types of errors were introduced by modifying collimator angles and multi-leaf collimator (MLC) field sizes (MLCFS) and MLC shifts by ±5, ±2, and ±1° or millimeters. A total of 103 plans were measured with EPID on an Elekta Synergy Linear Accelerator (Agility MLC) and compared to both the original treatment planning system (TPS) Collapsed Arc dose matrix and the no-error plan baseline EPID measurements. Gamma analysis was performed using the OmniPro-I'mRT (IBA Dosimetry) software and gamma criteria of 1%/1 mm, 2%/1 mm, 2%/2 mm, and 3%/3.

RESULTS

When the error-introduced EPID measured dose matrices were compared to the TPS matrices, the majority of simulated errors were detected with gamma tolerance of 2%/1 mm and 1%/1 mm. When the error-introduced EPID measured dose matrices were compared to the baseline EPID measurements, all the MLCFS and MLC shift errors, and ±5°collimator errors were detected using 2%/1 mm and 1%/1 mm gamma criteria.

CONCLUSION

This work demonstrates the feasibility and effectiveness of the collapsed arc technique and EPID for pre-treatment verification of lung SBRT VMAT plans. The EPID was able to detect the majority of MLC and the larger collimator errors with sensitivity to errors depending on the gamma tolerances.

SBRT planning for spinal metastasis: indications from a large multicentric study

BACKGROUND

The dosimetric variability in spine stereotactic body radiation therapy (SBRT) planning was investigated in a large number of centres to identify crowd knowledge-based solutions.

METHODS

Two spinal cases were planned by 48 planners (38 centres). The required prescription dose (PD) was 3 × 10 Gy and the planning target volume (PTV) coverage request was: V_PD > 90% (minimum request: V_PD > 80%). The dose constraints were: planning risk volume (PRV) spinal cord: V_18Gy < 0.35 cm³, V_{21.9 Gy} < 0.03 cm³; oesophagus: V_{17.7 Gy} < 5 cm³, V_{25.2 Gy} < 0.03 cm³. Planners who did not fulfil the protocol requirements were asked to re-optimize the plans, using the results of planners with the same technology. Statistical analysis was performed to assess correlations between dosimetric results and planning parameters. A quality index (QI) was defined for scoring plans.

RESULTS

In all, 12.5% of plans did not meet the protocol requirements. After re-optimization, 98% of plans fulfilled the constraints, showing the positive impact of knowledge sharing. Statistical analysis showed a significant correlation (p < 0.05) between the homogeneity index (HI) and PTV coverage for both cases, while the correlation between HI and spinal cord sparing was significant only for the single dorsal PTV case. Moreover, the multileaf collimator leaf thickness correlated with the spinal cord sparing. Planners using comparable delivery/planning system techniques produced different QI, highlighting the impact of the planner's skills in the optimization process.

CONCLUSION

Both the technology and the planner's skills are fundamentally important in spine SBRT planning optimization. Knowledge sharing helped to follow the plan objectives.

Editorial: The role of medical physics in lung SBRT

Stereotactic body radiation therapy (SBRT) has become a standard treatment for non-operable patients with early stage non-small cell lung cancer (NSCLC). In this context, medical physics community has largely helped in the starting and the growth of this technique. In fact, SBRT requires the convergence of many different features for delivering large doses in few fractions to small moving target in an heterogeneous medium. The special issue of last month, was focused on the different physics challenges in lung SBRT. Eleven reviews were presented, covering: imaging for treatment planning and for treatment assessment; dosimetry and planning optimization; treatment delivery possibilities; image guidance during delivery; radiobiology. The current cutting edge role of medical physics was reported. We aimed to give a complete overview of different aspects of lung SBRT that would be of interest to both physicists implementing this technique in their institutions and more experienced physicists that would be inspired to start research projects in areas that still need further developments. We also feel that the role that medical physicists have played in the development and safe implementation of SBRT, particularly in lung region, can be taken as an excellent example to be translated to other areas, not only in Radiation Oncology but also in other health sectors.

Impact of pixel-based machine-learning techniques on automated frameworks for delineation of gross tumor volume regions for stereotactic body radiation therapy

The aim of this study was to investigate the impact of pixel-based machine learning (ML) techniques, i.e., fuzzy-c-means clustering method (FCM), and the artificial neural network (ANN) and support vector machine (SVM), on an automated framework for delineation of gross tumor volume (GTV) regions of lung cancer for stereotactic body radiation therapy. The morphological and metabolic features for GTV regions, which were determined based on the knowledge of radiation oncologists, were fed on a pixel-by-pixel basis into the respective FCM, ANN, and SVM ML techniques. Then, the ML techniques were incorporated into the automated delineation framework of GTVs followed by an optimum contour selection (OCS) method, which we proposed in a previous study. The three-ML-based frameworks were evaluated for 16 lung cancer cases (six solid, four ground glass opacity (GGO), six part-solid GGO) with the datasets of planning computed tomography (CT) and ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/CT images using the three-dimensional Dice similarity coefficient (DSC). DSC denotes the degree of region similarity between the GTVs contoured by radiation oncologists and those estimated using the automated framework. The FCM-based framework achieved the highest DSCs of 0.79±0.06, whereas DSCs of the ANN-based and SVM-based frameworks were 0.76±0.14 and 0.73±0.14, respectively. The FCM-based framework provided the highest segmentation accuracy and precision without a learning process (lowest calculation cost). Therefore, the FCM-based framework can be useful for delineation of tumor regions in practical treatment planning.