A network score-based metric to optimize the quality assurance of automatic radiotherapy target segmentations

Physics and Imaging in Radiation Oncology, Год журнала: 2023, Номер 28, С. 100500 - 100500

Опубликована: Окт. 1, 2023

Язык: Английский

---

Advances in Radiation Oncology Top Downloaded Articles of 2024

Advances in Radiation Oncology, Год журнала: 2025, Номер 10(4), С. 101749 - 101749

Опубликована: Апрель 1, 2025

Язык: Английский

---

Smart contours: deep learning-driven internal gross tumor volume delineation in non-small cell lung cancer using 4D CT maximum and average intensity projections

Radiation Oncology, Год журнала: 2025, Номер 20(1)

Опубликована: Апрель 18, 2025

Delineating the internal gross tumor volume (IGTV) is crucial for treatment of non-small cell lung cancer (NSCLC). Deep learning (DL) enables automation this process; however, current studies focus mainly on multiple phases four-dimensional (4D) computed tomography (CT), which leads to indirect results. This study proposed a DL-based method automatic IGTV delineation using maximum and average intensity projections (MIP AIP, respectively) from 4D CT. We retrospectively enrolled 124 patients with NSCLC divided them into training (70%, n = 87) validation (30%, 37) cohorts. Four-dimensional CT images were acquired, corresponding MIP AIP generated. The IGTVs contoured used as ground truth (GT). or images, along (IGTVMIP-manu IGTVAIP-manu, respectively), fed DL models validation. assessed performance three segmentation models-U-net, attention U-net, V-net-using Dice similarity coefficient (DSC) 95th percentile Hausdorff distance (HD95) primary metrics. U-net model trained presented mean DSC 0.871 ± 0.048 HD95 2.958 2.266 mm, whereas achieved 0.852 0.053 3.209 2.136 mm. Among models, similar results, considerably surpassing V-net. can automate streamline contouring, enhance accuracy consistency radiotherapy planning improve patient outcomes.

Язык: Английский

---

Incorporating patient-specific information for the development of rectal tumor auto-segmentation models for online adaptive magnetic resonance Image-guided radiotherapy

Physics and Imaging in Radiation Oncology, Год журнала: 2024, Номер 32, С. 100648 - 100648

Опубликована: Сен. 16, 2024

Язык: Английский

---

Clinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies

Deleted Journal, Год журнала: 2024, Номер 1(1)

Опубликована: Янв. 1, 2024

Abstract Radiation therapy is a localized cancer treatment that relies on precise delineation of the target to be treated and healthy tissues guarantee optimal effect. This step, known as contouring or segmentation, involves identifying both volumes organs at risk imaging modalities like CT, PET, MRI guide radiation delivery. Manual however, time-consuming highly subjective, despite presence guidelines. In recent years, automated segmentation methods, particularly deep learning models, have shown promise in addressing this task. However, challenges persist their clinical use, including need for robust quality assurance (QA) processes risks associated with use models. review examines considerations adoption auto-segmentation radiotherapy, focused volume. We discuss potential (eg, over- under-segmentation, automation bias, appropriate trust), mitigation strategies human oversight, uncertainty quantification, education professionals), we highlight importance expanding QA include geometric, dose-volume, outcome-based performance monitoring. While offers significant benefits, careful attention rigorous measures are essential its successful integration practice.

Язык: Английский

---

Evaluating the dosimetric impact of deep‐learning‐based auto‐segmentation in prostate cancer radiotherapy: Insights into real‐world clinical implementation and inter‐observer variability

Journal of Applied Clinical Medical Physics, Год журнала: 2024, Номер unknown

Опубликована: Дек. 1, 2024

Abstract Purpose This study aimed to investigate the dosimetric impact of deep‐learning‐based auto‐contouring for clinical target volume (CTV) and organs at risk (OARs) delineation in prostate cancer radiotherapy planning. Additionally, we compared geometric accuracy system variability observed between human experts. Methods We evaluated 28 planning CT volumes, each with three contour sets: reference original contours (OC), auto‐segmented (AC), expert‐defined manual (EC). generated 3D‐CRT intensity‐modulated radiation therapy (IMRT) plans set their characteristics using dose‐volume histograms (DVHs), homogeneity index (HI), conformity (CI), gamma pass rate (3%/3 mm). Results The differences automated both a second manually are smaller than two contoured sets bladder, right femoral head (RFH), left (LFH) structures. Furthermore, dose distribution volumes (PTVs) derived from automatically CTVs auto‐contoured OARs demonstrated consistency based on across all cases IMRT plans. For example, plans, average D 95 PTVs was 77.71 ± 0.53 Gy EC 77.58 0.69 OC 77.62 0.38 AC Automated contouring significantly reduced time, averaging 0.08 min 24.9 4.5 delineation. Conclusion Our can reduce inter‐expert achieve comparable gold standard contours, highlighting its potential streamlining workflows. quantitative analysis revealed no consistent trend increasing or decreasing OAR doses due indicating minimal treatment outcomes. These findings support feasibility utilizing our model

Язык: Английский

---

On the trail of CBCT-guided adaptive rectal boost radiotherapy, does daily delineation require a radiation oncologist?

Technical Innovations & Patient Support in Radiation Oncology, Год журнала: 2024, Номер 32, С. 100284 - 100284

Опубликована: Окт. 22, 2024

Язык: Английский

---