Image-guided Radiotherapy Research Articles

Real-time lung extraction from synthesized x-rays improves pulmonary image-guided radiotherapy

Objective.Lung tumors can be obscured in x-rays, preventing accurate and robust localization. To improve lung conspicuity for image-guided procedures, we isolate the lungs in the anterior-posterior (AP) x-rays using a lung extraction network (LeX-net) that virtually removes overlapping thoracic structures, including ribs, diaphragm, liver, heart, and trachea.Approach.73 965 thoracic 3DCTs and 106 thoracic 4DCTs were included. The 3D lung volume was extracted using an open-source lung volume segmentation model. AP digitally reconstructed radiographs (DRRs) of the full anatomy CT and extracted lungs were computed as the input and reference to train a network (LeX-net) to generate lung-extracted DRRs (LeX-net DRRs) from full anatomy DRRs, which adopted a Swin-UNet model with conditional GAN. Subsequently, the trained LeX-net on 3DCT was applied to 4DCT-derived DRRs. Lung tumor tracking was then performed on DRRs using a template-matching method on a holdoff 4DCT test set of 79 patients whose gross tumor volumes were smaller than 20 cm3.Main results. LeX-net successfully isolated the lungs in DRRs, achieving an SSIM of 0.9581 ± 0.0151 and a PSNR of 30.78 ± 2.50 on the testing set of 3DCT-derived DRRs. Its performance declined slightly when applied to the 4DCT but maintained useable lung-only 2D views. On the challenging test set including cases of organ overlap, high tumor mobility, and small tumor size, the individual tumor tracking error for LeX-net DRRs was 0.97 ± 0.86 mm, significantly lower than that of 3.13 ± 5.82 mm using the full anatomy DRRs. LeX-net improved success rates of using 5 mm, 3 mm, and 1 mm tracking windows from 88.1%, 80.0%, and 58.7% to 98.1%, 94.2%, and 73.8%, respectively.Significance. LeX-net removes overlapping anatomies and enhances visualization of the lungs in x-rays. The model trained using 3DCTs is generalizable to 4DCT-derived DRRs, achieving significantly improved tumor tracking outcome.

Non-medicinal oral contrast in upper abdominal MRI for MR-guided radiotherapy: A scoping review.

Using non-medicinal oral contrast agents may aid safe delivery of magnetic resonance image-guided (MR-guided) radiotherapy by improving the ability to visualise and avoid excessive radiation dose to adjacent bowel/stomach. This scoping review aims to map the literature on non-medicinal oral contrasts used in upper-abdominal diagnostic or therapeutic magnetic resonance imaging (MRI) to find potential candidates for employing in MR-guided radiotherapy and identify gaps in knowledge for further study. A scoping review of non-medicinal oral contrast used in upper-abdominal MRI research followed a pre-defined protocol based on Arksey and O'Malley's framework. Data were charted and reported in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses for Scoping Reviews reporting guidelines. Forty-seven studies from 1955 screened abstracts were charted. Thirty-one distinct non-medicinal oral contrast were identified, used primarily to enhance tissue visualisation (89%) or observe motility (11%) in diagnostic studies. All studies reported to be predominantly quantitative; only 13% included participant experience via questionnaires and none used qualitative methods. No studies have examined the efficacy of non-medicinal oral contrasts in MR-guided radiotherapy planning or delivery. Non-medicinal oral contrasts have been extensively investigated in diagnostic MRI to enhance gastrointestinal visualisation and assess motility. However, non-medicinal oral contrasts have not been investigated in the context of radiotherapy planning and treatment. Qualitative evaluation of the patient experience of non-medicinal oral contrasts in magnetic resonance image-guided radiotherapy should be considered alongside studies quantifying the potential clinical benefit. This review summarises the properties of non-medicinal oral contrasts and identifies critical gaps in the current evidence, particularly the absence of qualitative research in this domain and the unexplored potential for their application in MR-guided radiotherapy planning and delivery.

Deep Learning-Based Multi-View Projection Synthesis Approach for Improving the Quality of Sparse-View CBCT in Image-Guided Radiotherapy.

While radiation hazards induced by cone-beam computed tomography (CBCT) in image-guided radiotherapy (IGRT) can be reduced by sparse-view sampling, the image quality is inevitably degraded. We propose a deep learning-based multi-view projection synthesis (DLMPS) approach to improve the quality of sparse-view low-dose CBCT images. In the proposed DLMPS approach, linear interpolation was first applied to sparse-view projections and the projections were rearranged into sinograms; these sinograms were processed with a sinogram restoration model and then rearranged back into projections. The sinogram restoration model was modified from the 2D U-Net by incorporating dynamic convolutional layers and residual learning techniques. The DLMPS approach was trained, validated, and tested on CBCT data from 163, 30, and 30 real patients respectively. Sparse-view projection datasets with 1/4 and 1/8 of the original sampling rate were simulated, and the corresponding full-view projection datasets were restored via the DLMPS approach. Tomographic images were reconstructed using the Feldkamp-Davis-Kress algorithm. Quantitative metrics including root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM) were calculated in both the projection and image domains to evaluate the performance of the DLMPS approach. The DLMPS approach was compared with 11 state-of-the-art (SOTA) models, including CNN and Transformer architectures. For 1/4 sparse-view reconstruction task, the proposed DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0271, 45.93 dB, 0.9817, and 0.9587 in the projection domain, and 0.000885, 37.63 dB, 0.9074, and 0.9885 in the image domain, respectively. For 1/8 sparse-view reconstruction task, the DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0304, 44.85 dB, 0.9785, and 0.9524 in the projection domain, and 0.001057, 36.05 dB, 0.8786, and 0.9774 in the image domain, respectively. The DLMPS approach outperformed all the 11 SOTA models in both the projection and image domains for 1/4 and 1/8 sparse-view reconstruction tasks. The proposed DLMPS approach effectively improves the quality of sparse-view CBCT images in IGRT by accurately synthesizing missing projections, exhibiting potential in substantially reducing imaging dose to patients with minimal loss of image quality.

Hypofractionated image-guided radiotherapy with 70 Gy in 28 fractions for prostate cancer confined to the pelvis: a single institute experience in Taiwan

BackgroundThe incidence of prostate cancer is increasing in Asian countries. Although moderately hypofractionated radiotherapy is not inferior to conventional fractionated radiation according to the updated guidelines, data regarding its efficacy and safety in Taiwan are currently lacking. The aim of this study was to investigate the outcomes of prostate cancer patients treated with hypofractionated image-guided radiotherapy at a single institution in Taiwan.MethodsWe retrospectively included patients with prostate cancer across all risk groups who were treated with hypofractionated image-guided radiotherapy 70 Gy (Gy) in 28 fractions (at 2.5 Gy/fraction) between 2007 and 2022. We analyzed treatment efficacy by assessing overall survival, prostate cancer-specific survival, event-free survival, biochemical failure, locoregional recurrence, and distant metastasis. The safety of the treatment was evaluated through acute and late gastrointestinal (GI) and genitourinary (GU) toxicity grading based on the Radiation Therapy Oncology Group criteria. Event-free survival, overall survival, prostate cancer-specific survival, biochemical failure, locoregional recurrence, and distant metastasis were evaluated using the Kaplan–Meier method.ResultsWe identified 150 consecutive men with prostate cancer: 12.7% were at low risk, 32.7% were at intermediate risk, 44.6% were at high risk, and 10% had N1 disease. The median follow-up time was 68.9 months (range: 2.3–172 months). The 5-year overall survival rate was 91.7% for the entire cohort, with rates of 100%, 94.3%, 93.3% and 71.1% for the low-risk, intermediate-risk, high-risk, and N1-disease groups, respectively (p < 0.001). The 5-year event-free survival rate for all patients was 75.8%. Among the risk groups, the 5-year event-free survival rates were 100%, 86.3%, 68.3% and 52.5% for the low-risk, intermediate-risk, high-risk, and N1 disease groups, respectively (p < 0.001). Grade ≥ 2 late GI toxicity was rare (0.7%), and grade ≥ 2 late GU toxicity was observed in 9.3% of the patients.ConclusionsHypofractionated image-guided radiotherapy, delivering 70 Gy at 2.5 Gy per fraction, is both effective and safe for Taiwanese patients with prostate cancer across all risk groups, consistent with findings from existing large randomized trials. Therefore, as a solution to enhance patient convenience, hypofractionated radiotherapy is a reasonable option for the definitive treatment of prostate cancer.Trial registrationNot applicable.

Embracing the Future of Clinical Trials in Radiotherapy: An NRG Oncology CIRO Technology Retreat Whitepaper on Pioneering Technologies and AI-Driven Solutions.

This white paper examines the potential of pioneering technologies and artificial intelligence (AI)-driven solutions in advancing clinical trials involving radiotherapy. As the field of radiotherapy evolves, the integration of cutting-edge approaches such as radiopharmaceutical dosimetry, FLASH radiotherapy, image-guided radiation therapy (IGRT), and AI promises to improve treatment planning, patient care, and outcomes. Additionally, recent advancements in quantum science, linear energy transfer/relative biological effect (LET/RBE), and the combination of radiotherapy and immunotherapy create new avenues for innovation in clinical trials. The paper aims to provide an overview of these emerging technologies and discuss their challenges and opportunities in shaping the future of radiation oncology clinical trials. By synthesizing knowledge from experts across various disciplines, this white paper aims to present a foundation for the successful integration of these innovations into radiotherapy research and practice, ultimately enhancing patient outcomes and revolutionizing cancer care.

Locally Advanced Cervical Cancer in a Patient with Epidermolysis Bullosa Treated with Concurrent Chemoradiotherapy and Electronic Brachytherapy

Purpose: The purpose of this report is to investigate the feasibility of combined modality treatment in a case of locally advanced cervical cancer in a patient with inherited epidermolysis bullosa as well as to suggest a protocol for cervical electronic brachytherapy. Materials and Methods: The patient was treated with image-guided external beam radiotherapy and concomitant chemotherapy to a dose of 45 Gy in 25 fractions with a simultaneously integrated boost of 55 Gy in involved lymph nodes. The maximal skin dose was 34.09 Gy. Intracavitary electronic brachytherapy was applied to the uterine cervix in 4 fractions of 7 Gy and contributed no dose to the skin. Results: The treatment was tolerated well with no early toxicity. During the 3-month period of follow-up, no adverse events of grade 2 or higher were detected, and no exacerbation of skin lesions was noted. Conclusions: This is the first report of treatment of cervical cancer in a patient with inherited epidermolysis bullosa where combined concurrent chemoradiotherapy and intracavitary electronic brachytherapy demonstrated feasibility and safety. The followed institutional protocol for treatment planning and delivery ensured low doses to organs and risk and reproducibility.

Validation of clearcalc for efficient patient specific QA.

Uganda's only radiotherapy center is a very busy facility treating about 210 patients daily on three linear accelerators making it sometimes hard to have machine time for pretreatment QAs. This study was aimed at validating an independent calculation software, ClearCalc (ICS) for second checks of the treatment planning system (TPS) calculations. The validation of ICS started with simple phantom test plans consisting of square, irregular, open and wedged fields designed in the TPS and measured in phantoms. Doses and monitor units (MUs) calculated by ICS were compared with TPS calculated doses and with measured doses. ICS was then validated on clinically approved treatment plans: comparison with TPS calculations and with pretreatment QA measurements performed with electronic portal imaging devices (EPIDs) and analyzed using Gamma passing criteria of 3%/3 mm and 3%/2 mm. Results for test plans were within the passing level of 3.0% except for 2 outliers (-3.1% and 3.1%). As for the clinically approved treatment plans, they show good agreement between MUs (0.2 ± 1.8%), reference point doses (0.2 ±1.5%) and mean PTV doses (0.5 ± 1.4%). ICS calculated (3D) mean gamma pass rates were 98.1±1.6% and 98.4±1.0% for 3%/2 mm and 3%/3 mm criteria. No correlation was seen between gamma analysis results from ICS and EPID. This study validated ClearCalc on phantom and clinically approved plans. The result show that ICS based patients specific QA is quick, promising and potentially allows significant time saving that can be utilized for patient treatments.

Relationship Between Radiation Therapy and Fecal Incontinence in Patients Treated for Localized Prostate Cancer: Results of the French ICONES Study.

Radiation-induced late fecal incontinence (LFI) is one of the most quality-of-life impairing symptoms in prostate cancer. We aimed to assess the impact of radiotherapy (RT) technique and dose-volume effects on LFI using a robust score. We identified 409 patients who underwent curative intent using standard fractionated radiation therapy, 190 of them were finally included and analyzed. The severity of LFI was assessed using the Jorge & Wexner score. With a median follow-up of 55 months (range 15-96) months, LFI crude rate was 11.5%. In the multivariate analyses, image-guided radiotherapy (IGRT), rectal maximum dose (Dmax) and anal canal minimum dose (Dmin) were significantly associated with LFI risk. The use of IGRT was associated with lower risk of LFI (p = 0.02); higher rectum Dmax (≥ 68.4 Gy; p = 0.02) and anal canal Dmin (≥ 6.4 Gy; p = 0.04) were associated with increased risk. Our results suggest a significant impact of the total dose delivered to the anorectal volumes and the use of IGRT to spare organs at risk during radiation delivery.

Prostate motion in magnetic resonance imaging-guided radiotherapy and its impact on margins.

This study focused on reducing the margin for prostate cancer treatment using magnetic resonance imaging-guided radiotherapy by investigating the intrafractional motion of the prostate and different motion-mitigation strategies. We retrospectively analyzed intrafractional prostate motion in 77patients with low- to intermediate-risk prostate cancer treated with five fractions of 7.25 Gy on a1.5 T magnetic resonance linear accelerator. Systematic drift motion was observed and described by an intrafractional motion model. The planning target volume (PTV) margin was calculated in acohort of 77patients and prospectively evaluated for geometric coverage in aseparate cohort of 24patients. The intrafractional model showed that the prostate position starts out of equilibrium for the anterior-posterior (-1.8 ± 3.1mm) and superior-inferior (1.7 ± 2.6mm) directions, with relaxation times of12 and 15min, respectively. Position verification scans are acquired at 30min on average. At that time, the transient drift motion becomes indistinguishable from the residual random intrafractional motion. PTV margins can be reduced to 1.8 mm (left-right), 3.2 mm (anterior-posterior), and 2.9 mm (superior-inferior). Evaluation of the overlap with the clinical target volume (CTV) was performed for atotal of 120 fractions of 24patients. The overlap range between the CTV and the PTV was 93-100% and the applied 3‑mm PTV margin for the CTV had a99.5% averaged geometric overlap for all patients. APTV margin reduction to 3 mm is feasible. Apatient-specific approach could reduce the margins further.

The Role of Image-Guided Superficial Radiation Therapy in the Treatment of Nonmelanoma Skin Cancer

Background: Basal cell carcinoma (BCC) and squamous cell carcinoma, collectively referred to as nonmelanoma skin cancer (NMSC) are the most common type of skin cancer and can lead to significant morbidity and mortality. There are several treatment options available for NMSC including superficial radiation therapy (SRT), which has improved in recent years with the addition of image guidance (IGSRT). In some cases, patients are not offered IGSRT as a treatment option and additional guidance on its benefits may be beneficial. Objective: For a panel of expert dermatologists to review published studies on IGSRT for the treatment NMSC and create consensus recommendations on its use. Methods: A comprehensive literature search of PubMed, EMBASE, Scopus, and Google Scholar was completed for English-language original research articles on the use of IGSRT to treat NMSC. A panel of six dermatologists with significant expertise in treating NMSC convened to review the articles and create consensus statements based on the available data. A modified Delphi process was used to approve each statement for adoption and a strength of recommendation was assigned using Strength of Recommendation Taxonomy (SORT) criteria. Results: After screening the articles that met the initial search criteria, 12 articles were distributed to the panelists for review prior to the roundtable discussion. The panel unanimously voted to adopt eight statements with an additional two statements receiving five out six votes for adoption. Eight of the statements received a strength of recommendation of “A” while two of the statements were given a strength of recommendation of “B” based on SORT criteria. Conclusion: IGSRT is a safe and effective treatment for NMSC that often results in highly favorable cosmetic outcomes. It can be considered a first-line treatment option for appropriately selected cases of NMSC.

Evolving Trends and Patterns of Utilization of Magnetic Resonance-Guided Radiotherapy at a Single Institution, 2018-2024.

Background/Objectives: Over the past decade, significant advances have been made in image-guided radiotherapy (RT) particularly with the introduction of magnetic resonance (MR)-guided radiotherapy (MRgRT). However, the optimal clinical applications of MRgRT are still evolving. The intent of this analysis was to describe our institutional MRgRT utilization patterns and evolution therein, specifically as an early adopter within a center endowed with multiple other technology platforms. Materials/Methods: We retrospectively evaluated patterns of MRgRT utilization for patients treated with a 0.35-Tesla MR-Linac at our institution from April 2018 to April 2024. We analyzed changes in utilization across six annualized periods: Period 1 (April 2018-April 2019) through Period 6 (April 2023-April 2024). We defined ultra-hypofractionation (UHfx) as 5 or fewer fractions with a minimum fractional dose of 5 Gy. Electronic health records were reviewed, and data were extracted related to patient, tumor, and treatment characteristics. Results: A total of 823 treatment courses were delivered to 712 patients treated for 854 lesions. The most commonly treated sites were the pancreas (242 [29.4%]), thorax (172; 20.9%), abdominopelvic lymph nodes (107; 13.0%), liver (72; 8.7%), and adrenal glands (68; 8.3%). The median total prescribed dose of 50 Gy in five fractions (fxs) was typically delivered in consecutive days with automatic beam gating in inspiration breath hold. The median biologically effective dose (α/β = 10, BED10) was 94.4 Gy with nearly half (404, 49.1%) of all courses at a prescribed BED10 ≥ 100 Gy, which is widely regarded as a highly effective ablative dose. Courses in Period 6 vs. Period 1 more often had a prescribed BED10 ≥ 100 Gy (60.2% vs. 41.6%; p = 0.004). Of the 6036 total delivered fxs, nearly half (2643, 43.8%) required at least one fx of on-table adaptive radiotherapy (oART), most commonly for pancreatic tumors (1081, 17.9%). UHfx was used in over three quarters of all courses (630, 76.5%) with 472 (57.4%) of these requiring oART for at least one fraction. The relative utilization of oART increased significantly from Period 1 to Period 6 (37.6% to 85.0%; p < 0.001); a similar increase in the use of UHfx (66.3% to 89.5%; p < 0.001) was also observed. The median total in-room time for oART decreased from 81 min in Period 1 to 45 min in Period 6, while for non-oART, it remained stable around 40 min across all periods. Conclusions: Our institution implemented MRgRT with a priority for targeting mobile extracranial tumors in challenging anatomic locations that are frequently treated with dose escalation, require enhanced soft-tissue visualization, and could benefit from an ablative radiotherapy approach. Over the period under evaluation, the use of high-dose ablative doses (BED10 ≥ 100 Gy), oART and UHfx (including single-fraction ablation) increased significantly, underscoring both a swift learning curve and ability to optimize processes to maximize throughput and efficiency.

Preliminary application of EPID three-dimensional dose reconstruction in in vivo dose verification of breast cancer intensity-modulated radiation therapy.

A preliminary study was conducted using electronic portal imaging device (EPID) based dose verification in pre-treatment and in vivo dose reconstruction modes for breast cancer intensity-modulated radiation therapy (IMRT) technique with known repositioning set-up errors. For 43 IMRT plans, the set-up errors were determined from 43 sets of EPID images and 258 sets of cone beam computed tomography images. In-house developed Edose software was used to reconstruct the dose distribution using the pre-treatment and on-treatment (in vivo) EPID acquired fluence maps. The maximum setup error was<3.5mm. For 43 pre-treatment cases, the γ pass rate (3%/3 mm) is 98.49% ± 1.15%. The chest wall target ΔV98%P, ΔV95%P, andΔV90%P are all<5%, while the majority of the ipsilateral lung ΔV5Gy, ΔV20Gy, and ΔV30Gy are also<5%. For 258 in vivo cases, the γ pass rate is 90.98% ± 6.53%, with the chest wall target ΔV90%P and ipsilateral lung ΔV30Gy both<5%, while the other volume differences all exceed 5%. The γ pass rate for in vivo verification is significantly lower than pre-treatment values. Although the in vivo γ verification satisfies the medical physics requirements, the reconstructed coverage of the chest wall target is far below the clinical dosimetry requirements. In vivo 3D dose reconstruction directly predicts changes in the planning target volume to aid clinicians better understand the actual dose received by patients with intra-fractional motion and anatomical changes.

A novel optimization of cone beam CT frequency for lung radiation therapy based on an image-guided radiation therapy protocol and patient classification method

A novel optimization of cone beam CT frequency for lung radiation therapy based on an image-guided radiation therapy protocol and patient classification method

Fluorescence molecular imaging-guided photodynamic therapy for early breast cancer in the prone position: feasibility evaluation with Monte Carlo simulations.

The successful diagnosis and treatment of early-stage breast cancer enhances the quality of life of patients. As a promising alternative to recently developed magnetic resonance imaging-guided radiotherapy, we proposed fluorescence molecular imaging-guided photodynamic therapy (FMI-guided PDT), which requires no expensive equipment. In the FMI simulations, ICG-C11 which has emission peaks at near-infrared wavelengths was used as the FMI agent. In the PDT simulation, Upconversion nanoparticles-Quantum dots-Rose bengal (UCQR) which was a PDT agent with upconversion capabilities was used. The feasibility of breast cancer diagnosis and treatment using our proposed method is evaluated through Monte Carlo simulations of exact light transport through a realistic breast model in the prone position. Monte Carlo modeling in voxelized media was performed. Fluorescence propagation from the tumor and the amount of singlet oxygen produced within the tumor were estimated from the calculated fluence. Next, the effects of tumor diameter and depth from the skin surface on the simulation results were evaluated. The simulation results showed successful detection of tumors with diameters of 5-9 mm in the 15-25 mm depth region, where tumors are commonly found. Furthermore, simulations have estimated that those tumors can be completely treated by PDT with less than ten light irradiations. This study suggests that fluorescent molecular imaging-guided photodynamic therapy may be a potential treatment for early-stage breast cancer. Our method would be more suitable than the conventional method for young women who are at higher risk of radiation exposure effects.

Teratocarcinosarcoma of the nasal cavity: challenges in the clinico-pathologic perspectives.

Clinicopathologic illustration of sinonasal teratocarcinosarcoma (SNTCS) in a middle-aged man, highlighting the difficulties and challenges encountered during surgical intervention, histopathologic diagnosis, and its overall management. Case report and literature review. A 40-year-old man having recurrent epistaxis for three months presented with a dark-colored protruding polypoid nasal mass. Magnetic resonance imaging revealed a large, heterogeneous gadolinium-enhanced infiltrative lesion in the left nasal cavity with a T2-hypointense trans-septal zone. The mass abutted the cribriform plate, lamina papyracea, and septum, involved the inferior and middle turbinates, and blocked the choanae through the nasopharynx. There was profuse hemorrhage when an endoscope-assisted biopsy was attempted. Histopathology from the debulked specimen suggested SNTCS. The diagnosis was confirmed on immunohistochemistry. A metastatic search turned negative. However, at three weeks, the patient returned with a recurrence. A repeat debulking was done, and he was thereafter put on adjuvant chemotherapy. A second recurrence/residual lesion was noted midway through the chemotherapy regimen. However, it resolved after completion of the chemotherapy and subsequent image-guided radiotherapy, and the patient continued to be disease-free till the last follow-up at six weeks postradiotherapy. SNTCS is an extremely aggressive malignancy that is seldom encountered in routine otolaryngology and pathology practice, with only a few reports of SNTCS documented. It is histologically composed of epithelial, mesenchymal, and primitive neuroectodermal elements with areas of undifferentiation. They are notorious for troublesome intra-operative bleeding, making complete surgical excision difficult, and the absence of a tumor-free margin often results in recurrence. Owing to their variegated and heterogeneous tissue composition, histopathologic diagnosis is enormously challenging without a representative tissue sample and immunohistochemistry. In spite of prompt and energetic multimodality treatment, survival rate is dismal.

Prior-FOVNet: A Multimodal Deep Learning Framework for Megavoltage Computed Tomography Truncation Artifact Correction and Field-of-View Extension.

Megavoltage computed tomography (MVCT) plays a crucial role in patient positioning and dose reconstruction during tomotherapy. However, due to the limited scan field of view (sFOV), the entire cross-section of certain patients may not be fully covered, resulting in projection data truncation. Truncation artifacts in MVCT can compromise registration accuracy with the planned kilovoltage computed tomography (KVCT) and hinder subsequent MVCT-based adaptive planning. To address this issue, we propose a Prior-FOVNet to correct the truncation artifacts and extend the field of view (eFOV) by leveraging material and shape priors learned from the KVCT of the same patient. Specifically, to address the intensity discrepancies between different imaging modalities, we employ a contrastive learning-based GAN, named TransNet, to transform KVCT images into synthesized MVCT (sMVCT) images. The sMVCT images, along with pre-corrected MVCT images obtained via sinogram extrapolation, are then input into a Swin Transformer-based image inpainting network for artifact correction and FOV extension. Experimental results using both simulated and real patient data demonstrate that our method outperforms existing truncation correction techniques in reducing truncation artifacts and reconstructing anatomical structures beyond the sFOV. It achieves the lowest MAE of 23.8 ± 5.6 HU and the highest SSIM of 97.8 ± 0.6 across the test dataset, thereby enhancing the reliability and clinical applicability of MVCT in adaptive radiotherapy.

Complex Large-Deformation Multimodality Image Registration Network for Image-Guided Radiotherapy of Cervical Cancer.

In recent years, image-guided brachytherapy for cervical cancer has become an important treatment method for patients with locally advanced cervical cancer, and multi-modality image registration technology is a key step in this system. However, due to the patient's own movement and other factors, the deformation between the different modalities of images is discontinuous, which brings great difficulties to the registration of pelvic computed tomography (CT/) and magnetic resonance (MR) images. In this paper, we propose a multimodality image registration network based on multistage transformation enhancement features (MTEF) to maintain the continuity of the deformation field. The model uses wavelet transform to extract different components of the image and performs fusion and enhancement processing as the input to the model. The model performs multiple registrations from local to global regions. Then, we propose a novel shared pyramid registration network that can accurately extract features from different modalities, optimizing the predicted deformation field through progressive refinement. In order to improve the registration performance, we also propose a deep learning similarity measurement method combined with bistructural morphology. On the basis of deep learning, bistructural morphology is added to the model to train the pelvic area registration evaluator, and the model can obtain parameters covering large deformation for loss function. The model was verified by the actual clinical data of cervical cancer patients. After a large number of experiments, our proposed model achieved the highest dice similarity coefficient (DSC) metric compared with the state-of-the-art registration methods. The DSC index of the MTEF algorithm is 5.64% higher than that of the TransMorph algorithm. It will effectively integrate multi-modal image information, improve the accuracy of tumor localization, and benefit more cervical cancer patients.

Bone matching versus tumor matching in image-guided carbon ion radiotherapy for locally advanced non-small cell lung cancer

Background and purposeThis study evaluates the dosimetric impact of tumor matching (TM) and bone matching (BM) in carbon ion radiotherapy for locally advanced non-small cell lung cancer.Materials and methodsForty patients diagnosed with locally advanced non-small cell lung cancer were included in this study. TM and BM techniques were employed for recalculation based on re-evaluation computed tomography (CT) images of the patients, resulting in the generation of dose distributions: Plan-T and Plan-B, respectively. These distributions were compared with the original dose distribution, Plan-O. The percentage of the internal gross tumor volume (iGTV) receiving a prescription dose greater than 95% (V95%) was evaluated using dose-volume parameters. Statistical analysis was performed using a paired signed-rank sum test. Additionally, the study investigated the influence of tumor displacement, volume changes, and rotational errors on target dose coverage.ResultsThe median iGTV V95% values for the Plan-O, Plan-T, and Plan-B groups were 100%, 99.93%, and 99.60%, respectively, with statistically significant differences observed. TM demonstrated improved target dose coverage compared to BM. Moreover, TM exhibited better target coverage in case of larger tumor displacement. TM’s increased adjustability in rotation directions compared to BM significantly influenced dosimetric outcomes, rendering it more tolerant to variations in tumor morphology.ConclusionTM exhibited superior target dose coverage compared to BM, particularly in cases of larger tumor displacement. TM also demonstrated better tolerance to variations in tumor morphology.

Unsupervised Bayesian generation of synthetic CT from CBCT using patient-specific score-based prior.

Cone-beam computed tomography (CBCT) scans, performed fractionally (e.g., daily or weekly), are widely utilized for patient alignment in the image-guided radiotherapy (IGRT) process, thereby making it a potential imaging modality for the implementation of adaptive radiotherapy (ART) protocols. Nonetheless, significant artifacts and incorrect Hounsfield unit (HU) values hinder their application in quantitative tasks such as target and organ segmentations and dose calculation. Therefore, acquiring CT-quality images from the CBCT scans is essential to implement online ART in clinical settings. This work aims to develop an unsupervised learning method using the patient-specific diffusion model for CBCT-based synthetic CT (sCT) generation to improve the image quality of CBCT. The proposed method is in an unsupervised framework that utilizes a patient-specific score-based model as the image prior alongside a customized total variation (TV) regularization to enforce coherence across different transverse slices. The score-based model is unconditionally trained using the same patient's planning CT (pCT) images to characterize the manifold of CT-quality images and capture the unique anatomical information of the specific patient. The efficacy of the proposed method was assessed on images from anatomical sites including head and neck (H&N) cancer, pancreatic cancer, and lung cancer. The performance of the proposed CBCT correction method was evaluated using quantitative metrics, including mean absolute error (MAE), non-uniformity (NU), and structural similarity index measure (SSIM). Additionally, the proposed algorithm was benchmarked against other unsupervised learning-based CBCT correction algorithms. The proposed method significantly reduced various kinds of CBCT artifacts in the studies of H&N, pancreatic, and lung cancer patients. In the lung stereotactic body radiation therapy (SBRT) patient study, the MAE, NU, and SSIM were improved from 47 HU, 45 HU, and 0.58 in the original CBCT images to 13 HU, 14dB, and 0.67 in the generated sCT images. Compared to other unsupervised learning-based algorithms, the proposed method demonstrated superior performance in artifact reduction. The proposed unsupervised method can generate sCT from CBCT with reduced artifacts and precise HU values, enabling CBCT-guided segmentation and replanning for online ART.

A review on functional lung avoidance radiotherapy plan for lung cancer.

Lung cancer is the most common malignant tumor in China. Its incidence and mortality rate increase year by year. In the synthesis treatment of lung cancer, radiotherapy (RT) plays a vital role, and radiation-induced lung injury(RILI) has become the major limiting factor in prescription dose escalation. Conventional RT is designed to minimize radiation exposure to healthy lungs without considering the inhomogeneity of lung function, which is significantly non-uniform in most patients. In accordance with the functional and structural heterogeneity of lung tissue, functional lung avoidance RT (FLART) can reduce radiation exposure to functional lung (FL), thus reducing RILI. Meanwhile, a dose-function histogram (DFH) was proposed to describe the dose parameters of the optimized image-guided RT plan. This paper reviews lung function imaging for lung cancer RT plans. It also reviews the clinical applications of function-guided RT plans and their current problems and research directions to provide better guidance for clinical selection.