Medical Imaging Biomarker Discovery and Integration Towards AI-Based Personalized Radiotherapy

Intensity-modulated radiation therapy (IMRT) has been used for high-accurate physical dose distribution sculpture and employed to modulate different dose levels into Gross Tumor Volume (GTV), Clinical Target Volume (CTV) and Planning Target Volume (PTV). GTV, CTV and PTV can be prescribed at different dose levels, however, there is an emphasis that their dose distributions need to be uniform, despite the fact that most types of tumour are heterogeneous. With traditional radiomics and artificial intelligence (AI) techniques, we can identify biological target volume from functional images against conventional GTV derived from anatomical imaging. Functional imaging, such as multi parameter MRI and PET can be used to implement dose painting, which allows us to achieve dose escalation by increasing doses in certain areas that are therapy-resistant in the GTV and reducing doses in less aggressive areas. In this review, we firstly discuss several quantitative functional imaging techniques including PET-CT and multi-parameter MRI. Furthermore, theoretical and experimental comparisons for dose painting by contours (DPBC) and dose painting by numbers (DPBN), along with outcome analysis after dose painting are provided. The state-of-the-art AI-based biomarker diagnosis techniques is reviewed. Finally, we conclude major challenges and future directions in AI-based biomarkers to improve cancer diagnosis and radiotherapy treatment.

Automatic Radiotherapy Planning for Glioblastoma Radiotherapy With Sparing of the Hippocampus and nTMS-Defined Motor Cortex

BackgroundNavigated transcranial magnetic stimulation (nTMS) of the motor cortex has been successfully implemented into radiotherapy planning by a number of studies. Furthermore, the hippocampus has been identified as a radiation-sensitive structure meriting particular sparing in radiotherapy. This study assesses the joint protection of these two eloquent brain regions for the treatment of glioblastoma (GBM), with particular emphasis on the use of automatic planning.Patients and MethodsPatients with motor-eloquent brain glioblastoma who underwent surgical resection after nTMS mapping of the motor cortex and adjuvant radiotherapy were retrospectively evaluated. The radiotherapy treatment plans were retrieved, and the nTMS-defined motor cortex and hippocampus contours were added. Four additional treatment plans were created for each patient: two manual plans aimed to reduce the dose to the motor cortex and hippocampus by manual inverse planning. The second pair of re-optimized plans was created by the Auto-Planning algorithm. The optimized plans were compared with the “Original” plan regarding plan quality, planning target volume (PTV) coverage, and sparing of organs at risk (OAR).ResultsA total of 50 plans were analyzed. All plans were clinically acceptable with no differences in the PTV coverage and plan quality metrics. The OARs were preserved in all plans; however, overall the sparing was significantly improved by Auto-Planning. Motor cortex protection was feasible and significant, amounting to a reduction in the mean dose by >6 Gy. The dose to the motor cortex outside the PTV was reduced by >12 Gy (mean dose) and >5 Gy (maximum dose). The hippocampi were significantly improved (reduction in mean dose: ipsilateral >6 Gy, contralateral >4.6 Gy; reduction in maximum dose: ipsilateral >5 Gy, contralateral >5 Gy). While the dose reduction using Auto-Planning was generally better than by manual optimization, the radiated total monitor units were significantly increased.ConclusionConsiderable dose sparing of the nTMS-motor cortex and hippocampus could be achieved with no disadvantages in plan quality. Auto-Planning could further contribute to better protection of OAR. Whether the improved dosimetric protection of functional areas can translate into improved quality of life and motor or cognitive performance of the patients can only be decided by future studies.

Gamma Knife Radiosurgery for Tuberculum Sellae Meningiomas: A Series of 78 Consecutive Patients

Background: Outcomes of Gamma Knife Radiosurgery (GKRS) for tuberculum sellae meningiomas (TSMs) have not been reported explicitly within any meningioma series. We present the first and largest TSM series with clinical, radiosurgical, and outcome features for 78 consecutive patients managed with GKRS. Methods: Patients who underwent GKRS for TSMs between 2005 and 2021 and had a minimum of 6 months of follow-up were included. Medical records, imaging studies, and follow-up examinations were evaluated retrospectively.Results: A total of 78 patients with a median age of 50.5 years were included. SRS was conducted as an upfront treatment for 38 patients (48.7%). The median target volume was 1.7 cm3 (range, 0.1-14.6). During a median follow-up of 78.5 months, the cumulative PFS rates of the whole cohort at 1, 5, and 10 years by Kaplan-Meier analysis were 100%, 97.9%, and 94.5%, respectively. Of 47 patients with impaired vision, improvement and/or preservation of visual acuity and visual field were achieved in 55.3% and 42.6%, respectively. No new-onset hormonal deficits were observed.Conclusions: Based on our data, SRS represents an effective and safe modality for unresected or recurrent/residual TSMs. SRS should be offered to patients who are not willing or not ideal candidates for surgery.

Deep Learning-Aided Automatic Contouring of Clinical Target Volumes for Radiotherapy in Breast Cancer After Modified Radical Mastectomy

Purpose: The aim of this study is to develop a practicable automatic clinical target volume (CTV) delineation method for radiotherapy of breast cancer after modified radical mastectomy.Methods: Unlike breast conserving surgery, the radiotherapy CTV for modified radical mastectomy involves several regions, including CTV in the chest wall (CTVcw), supra- and infra-clavicular region (CTVsc), and internal mammary lymphatic region (CTVim). For accurate and efficient segmentation of the CTVs in radiotherapy of breast cancer after modified radical mastectomy, a multi-scale convolutional neural network with an orientation attention mechanism is proposed to capture the corresponding features in different perception fields. A channel-specific local Dice loss, alongside several data augmentation methods, is also designed specifically to stabilize the model training and improve the generalization performance of the model. The segmentation performance is quantitatively evaluated by statistical metrics and qualitatively evaluated by clinicians in terms of consistency and time efficiency.Results: The proposed method is trained and evaluated on the self-collected dataset, which contains 110 computed tomography scans from patients with breast cancer who underwent modified mastectomy. The experimental results show that the proposed segmentation method achieved superior performance in terms of Dice similarity coefficient (DSC), Hausdorff distance (HD) and Average symmetric surface distance (ASSD) compared with baseline approaches.Conclusion: Both quantitative and qualitative evaluation results demonstrated that the specifically designed method is practical and effective in automatic contouring of CTVs for radiotherapy of breast cancer after modified radical mastectomy. Clinicians can significantly save time on manual delineation while obtaining contouring results with high consistency by employing this method.

Effect of inaccurate small field output factors on brain SRS plans

External beam radiotherapy often includes the use of field sizes 3 × 3 cm2 or less, which can be defined as small fields. Dosimetry is a difficult, yet important part of the radiotherapy process. The dosimetry of small fields has additional challenges, which can lead to treatment inconsistencies if not done properly. Most important is the use of an appropriate detector, as well as the application of the necessary corrections. The International Atomic Energy Agency and the American Association of Physicists in Medicine provide the International Code of Practice (CoP) TRS-483 for the dosimetry of small static fields used in external MV photon beams. It gives guidelines on how to apply small-field correction factors for small field dosimetry. The purpose of this study was to evaluate the impact of inaccurate small-field output factors on clinical brain stereotactic radiosurgery plans with and without applying the small-field correction factors as suggested in the CoP. Small-field correction factors for a Varian TrueBeam linear accelerator were applied to uncorrected relative dose factors. Uncorrected and corrected clinical plans were created with two different beam configurations, 6 MV with a flattening filter (6 WFF) and 6 MV without a flattening filter (6 FFF). For the corrected plans, the planning target volume mean dose was 1.6 ± 0.9% lower with p < 0.001 for 6 WFF and 1.8 ± 1.5% lower with p < 0.001 for 6 FFF. For brainstem, a major organ at risk, the corrected plans had a dose that was 1.6 ± 0.9% lower with p = 0.03 for 6 WFF and 1.8 ± 1.5% lower with p = 0.10 for 6 FFF. This represents a systematic error that should and can be corrected.

Adaptive MR-Guided Stereotactic Radiotherapy is Beneficial for Ablative Treatment of Lung Tumors in High-Risk Locations

PurposeTo explore the benefit of adaptive magnetic resonance-guided stereotactic body radiotherapy (MRgSBRT) for treatment of lung tumors in different locations with a focus on ultracentral lung tumors (ULT).Patients &amp; MethodsA prospective cohort of 21 patients with 23 primary and secondary lung tumors was analyzed. Tumors were located peripherally (N = 10), centrally (N = 2) and ultracentrally (N = 11, planning target volume (PTV) overlap with proximal bronchi, esophagus and/or pulmonary artery). All patients received MRgSBRT with gated dose delivery and risk-adapted fractionation. Before each fraction, the baseline plan was recalculated on the anatomy of the day (predicted plan). Plan adaptation was performed in 154/165 fractions (93.3%). Comparison of dose characteristics between predicted and adapted plans employed descriptive statistics and Bayesian linear multilevel models. The posterior distributions resulting from the Bayesian models are presented by the mean together with the corresponding 95% compatibility interval (CI).ResultsPlan adaptation decreased the proportion of fractions with violated planning objectives from 94% (predicted plans) to 17% (adapted plans). In most cases, inadequate PTV coverage was remedied (predicted: 86%, adapted: 13%), corresponding to a moderate increase of PTV coverage (mean +6.3%, 95% CI: [5.3–7.4%]) and biologically effective PTV doses (BED10) (BEDmin: +9.0 Gy [6.7–11.3 Gy], BEDmean: +1.4 Gy [0.8–2.1 Gy]). This benefit was smaller in larger tumors (−0.1%/10 cm³ PTV [−0.2 to −0.02%/10 cm³ PTV]) and ULT (−2.0% [−3.1 to −0.9%]). Occurrence of exceeded maximum doses inside the PTV (predicted: 21%, adapted: 4%) and violations of OAR constraints (predicted: 12%, adapted: 1%, OR: 0.14 [0.04–0.44]) was effectively reduced. OAR constraint violations almost exclusively occurred if the PTV had touched the corresponding OAR in the baseline plan (18/19, 95%).ConclusionAdaptive MRgSBRT is highly recommendable for ablative treatment of lung tumors whose PTV initially contacts a sensitive OAR, such as ULT. Here, plan adaptation protects the OAR while maintaining best-possible PTV coverage.

Usefulness of 99mTc–pertechnetate SPECT-CT in thyroid tissue volumetry: phantom studies and a clinical case series

Background: An accurate measurement of the target volume is of primary importance in theragnostics of hyperthyroidism Objective: Our purpose was to evaluate the accuracy of a threshold–based isocontour extraction procedure for thyroid tissue volumetry from SPECT-CT. Methods: Cylindrical vials with a fixed volume of 99mTcO4 at different activities were inserted into a neck phantom in two different thickness settings. Images were acquired by orienting the phantom in different positions, i.e., 40 planar images and 40 SPECT-CT. The fixed values of the iso-contouring threshold for SPECT and SPECT-CT were calculated by means of linear and spline regression models. Mean, Median, Standard Deviation, Standard Error, Mean Absolute Percentage Error and Root Mean-Square Error were computed. Any difference between the planar method, SPECT and SPECT-CT and the effective volume was evaluated by means of ANOVA and post-hoc tests. Moreover, planar and SPECT-CT acquisitions were performed in 8 patients with hyperthyroidism, considering relevant percentage differences greater than > 20 % from CT gold standard. Results: Concerning phantom studies, the planar method shows higher values of each parameter than the other two methods. SPECT-CT shows lower variability. However, no significant differences were observed between SPECT and SPECT-CT measurements. In patients, relevant differences were found in 7 out of 9 lesions with the planar method, in 6 lesions with SPECT, but in only one with SPECT-CT. Conclution: Our study confirms the superiority of SPECT in volume measurement if compared with the planar method. A more accurate measurement can be obtained from SPECT-CT.