Lumbar and Thoracic Vertebrae Segmentation in CT Scans Using a 3D Multi-Object Localization and Segmentation CNN.

Radiation treatment of cancers like prostate or cervix cancer requires considering nearby bone structures like vertebrae. In this work, we present and validate a novel automated method for the 3D segmentation of individual lumbar and thoracic vertebra in computed tomography (CT) scans. It is based on a single, low-complexity convolutional neural network (CNN) architecture which works well even if little application-specific training data are available. It is based on volume patch-based processing, enabling the handling of arbitrary scan sizes. For each patch, it performs segmentation and an estimation of up to three vertebrae center locations in one step, which enables utilizing an advanced post-processing scheme to achieve high segmentation accuracy, as required for clinical use. Overall, 1763 vertebrae were used for the performance assessment. On 26 CT scans acquired for standard radiation treatment planning, a Dice coefficient of 0.921 ± 0.047 (mean ± standard deviation) and a signed distance error of 0.271 ± 0.748 mm was achieved. On the large-sized publicly available VerSe2020 data set with 129 CT scans depicting lumbar and thoracic vertebrae, the overall Dice coefficient was 0.940 ± 0.065 and the signed distance error was 0.109 ± 0.301 mm. A comparison to other methods that have been validated on VerSe data showed that our approach achieved a better overall segmentation performance.

Initial clinical applications treating pediatric and adolescent patients using MR-guided radiotherapy.

Purpose: To demonstrate the clinical applications and feasibility of online adaptive magnetic resonance image guided radiotherapy (MRgRT) in the pediatric, adolescent and young adult (AYA) population. Methods: This is a retrospective case series of patients enrolled onto a prospective study. All pediatric (age < 18) and AYA patients (age< 30), treated on the Elekta Unity MR linear accelerator (MRL) from 2019 to 2021 were enrolled onto a prospective registry. Rationale for MRgRT included improved visualization of and alignment to the primary tumor, re-irradiation in a critical area, ability to use smaller margins, and need for daily adaptive replanning to minimize dose to adjacent critical structures. Step-and-shoot intensity-modulated radiation treatment (IMRT) plans were generated for all Unity patients with a dose grid of 3 mm and a statistical uncertainty of < 1% per plan. Results: A total of 15 pediatric and AYA patients have been treated with median age of 13 years (range: 6 mos - 27 yrs). Seven patients were <10 yo. The clinical applications of MRgRT included Wilms tumor with unresectable IVC thrombus (n=1), Ewing sarcoma (primary and metastatic, n=3), recurrent diffuse intrinsic pontine glioma (DIPG, n=2), nasopharyngeal carcinoma (n=1), clival chordoma (n=1), primitive neuroectodermal tumor of the pancreas (n=1), recurrent gluteo-sacral germ cell tumor (n=1), C-spine ependymoma (n=1), and posterior fossa ependymoma (n=1). Two children required general anesthesia. One AYA patient could not complete the MRgRT course due to tumor-related pain exacerbated by longer treatment times. Two AYA patients experienced anxiety related to treatment on the MRL, one of which required daily Ativan. No patient experienced treatment interruptions or unexpected toxicity. Conclusion: MRgRT was well-tolerated by pediatric and AYA patients. There was no increased use of anesthesia outside of our usual practice. Dosimetric advantages were seen for patients with tumors in critical locations such as adjacent to or involving optic structures, stomach, kidney, bowel, and heart.

Quantification of uptake in pelvis F-18 FLT PET-CT images using a 3D localization and segmentation CNN.

PURPOSE: The purpose of this work was to develop and validate a deep convolutional neural network (CNN) approach for the automated pelvis segmentation in computed tomography (CT) scans to enable the quantification of active pelvic bone marrow by means of Fluorothymidine F-18 (FLT) tracer uptake measurement in positron emission tomography (PET) scans. This quantification is a critical step in calculating bone marrow dose for radiopharmaceutical therapy clinical applications as well as external beam radiation doses. METHODS: An approach for the combined localization and segmentation of the pelvis in CT volumes of varying sizes, ranging from full-body to pelvis CT scans, was developed that utilizes a novel CNN architecture in combination with a random sampling strategy. The method was validated on 34 planning CT scans and 106 full-body FLT PET-CT scans using a cross-validation strategy. Specifically, two different training and CNN application options were studied, quantitatively assessed, and statistically compared. RESULTS: The proposed method was able to successfully locate and segment the pelvis in all test cases. On all data sets, an average Dice coefficient of 0.9396 ± $\pm$ 0.0182 or better was achieved. The relative tracer uptake measurement error ranged between 0.065% and 0.204%. The proposed approach is time-efficient and shows a reduction in runtime of up to 95% compared to a standard U-Net-based approach without a localization component. CONCLUSIONS: The proposed method enables the efficient calculation of FLT uptake in the pelvis. Thus, it represents a valuable tool to facilitate bone marrow preserving adaptive radiation therapy and radiopharmaceutical dose calculation. Furthermore, the method can be adapted to process other bone structures as well as organs.

Stereotactic radiotherapy of appropriately selected meningiomas and metastatic brain tumor beds with gamma knife icon versus volumetric modulated arc therapy.

PURPOSE: To determine if the gamma knife icon (GKI) can provide superior stereotactic radiotherapy (SRT) dose distributions for appropriately selected meningioma and post-resection brain tumor bed treatments to volumetric modulated arc therapy (VMAT). MATERIALS AND METHODS: Appropriately selected targets were not proximal to great vessels, did not have sensitive soft tissue including organs-at-risk (OARs) within the planning target volume (PTV), and did not have concave tumors containing excessive normal brain tissue. Four of fourteen candidate meningioma patients and six of six candidate patients with brain tumor cavities were considered for this treatment planning comparison study. PTVs were generated for GKI and VMAT by adding 1 mm and 3 mm margins, respectively, to the GTVs. Identical PTV V100% -values were obtained for the GKI and VMAT plans for each patient. Meningioma and tumor bed prescription doses were 52.7-54.0 in 1.7-1.8 Gy fractions and 25 Gy in 5 Gy fractions, respectively. GKI dose rate was 3.735 Gy/min for 16 mm collimators. RESULTS: PTV radical dose homogeneity index was 3.03 ± 0.35 for GKI and 1.27 ± 0.19 for VMAT. Normal brain D1% , D5% , and D10% were lower for GKI than VMAT by 45.8 ± 10.9%, 38.9 ± 11.5%, and 35.4 ± 16.5% respectively. All OARs considered received lower maximum doses for GKI than VMAT. GKI and VMAT treatment times for meningioma plans were 12.1 ± 4.13 min and 6.2 ± 0.32 min, respectively, and, for tumor cavities, were 18.1 ± 5.1 min and 11.0 ± 0.56 min, respectively. CONCLUSIONS: Appropriately selected meningioma and brain tumor bed patients may benefit from GKI-based SRT due to the decreased normal brain and OAR doses relative to VMAT enabled by smaller margins. Care must be taken in meningioma patient selection for SRT with the GKI, even if they are clinically appropriate for VMAT.

The Dosimetric and Temporal Effects of Respiratory-Gated, High-Dose-Rate Radiation Therapy in Patients With Lung Cancer.

PURPOSE: To evaluate the dosimetric and temporal effects of high-dose-rate respiratory-gated radiation therapy in patients with lung cancer. METHODS: Treatment plans from 5 patients with lung cancer (3 nongated and 2 gated at 80EX-80IN) were retrospectively evaluated. Prescription dose for these patients varied from 8 to 18 Gy/fraction with 3 to 5 treatment fractions. Using the same treatment planning criteria, 4 new treatment plans, corresponding to 4 gating windows (20EX-20IN, 40EX-40IN, 60EX-60IN, and 80EX-80IN), were generated for each patient. Mean tumor dose, mean lung dose, and lung V20 were used to assess the dosimetric effects. A MATLAB algorithm was developed to compute treatment time. RESULTS: Mean lung dose and lung V20 were on average reduced between -16.1% to -6.0% and -20.0% to -7.2%, respectively, for gated plans when compared to the corresponding nongated plans, and between -5.8% to -4.2% and -7.0% to -5.4%, respectively, for plans with smaller gating windows when compared to the corresponding plans gated at 80EX-80IN. Treatment delivery times of gated plans using high-dose rate were reduced on average between -19.7% (-0.10 min/100 MU) and -27.2% (-0.13 min/100 MU) for original nongated plans and -15.6% (-0.15 min/100 MU) and -20.3% (-0.19 min/100 MU) for original 80EX-80IN-gated plans. CONCLUSION: Respiratory-gated radiation therapy in patients with lung cancer can reduce lung dose while maintaining tumor dose. Because treatment delivery during gated therapy is discontinuous, total treatment time may be prolonged. However, this increase in treatment time can be offset by increasing the dose delivery rate. Estimation of treatment time may be helpful in selecting patients for respiratory gating and choosing appropriate gating windows.

Using [(18)F]Fluorothymidine Imaged With Positron Emission Tomography to Quantify and Reduce Hematologic Toxicity Due to Chemoradiation Therapy for Pelvic Cancer Patients.

PURPOSE: The purpose of the present prospective clinical trial was to determine the efficacy of [(18)F]fluorothymidine (FLT)-identified active bone marrow sparing for pelvic cancer patients by correlating the FLT uptake change during and after chemoradiation therapy with hematologic toxicity. METHODS AND MATERIALS: Simulation FLT positron emission tomography (PET) images were used to spare pelvic bone marrow using intensity modulated radiation therapy (IMRT BMS) for 32 patients with pelvic cancer. FLT PET scans taken during chemoradiation therapy after 1 and 2 weeks and 30 days and 1 year after completion of chemoradiation therapy were used to evaluate the acute and chronic dose response of pelvic bone marrow. Complete blood counts were recorded at each imaging point to correlate the FLT uptake change with systemic hematologic toxicity. RESULTS: IMRT BMS plans significantly reduced the dose to the pelvic regions identified with FLT uptake compared with control IMRT plans (P<.001, paired t test). Radiation doses of 4 Gy caused an ∼50% decrease in FLT uptake in the pelvic bone marrow after either 1 or 2 weeks of chemoradiation therapy. Additionally, subjects with more FLT-identified bone marrow exposed to ≥4 Gy after 1 week developed grade 2 leukopenia sooner than subjects with less marrow exposed to ≥4 Gy (P<.05, Cox regression analysis). Apparent bone marrow recovery at 30 days after therapy was not maintained 1 year after chemotherapy. The FLT uptake in the pelvic bone marrow regions that received >35 Gy was 18.8% ± 1.8% greater at 30 days after therapy than at 1 year after therapy. The white blood cell, platelet, lymphocyte, and neutrophil counts at 1 year after therapy were all lower than the pretherapy levels (P<.05, paired t test). CONCLUSIONS: IMRT BMS plans reduced the dose to FLT-identified pelvic bone marrow for pelvic cancer patients. However, reducing hematologic toxicity is challenging owing to the acute radiation sensitivity (∼4 Gy) and chronic suppression of activity in bone marrow receiving radiation doses >35 Gy, as measured by the FLT uptake change correlated with the complete blood cell counts.

Bone marrow sparing in intensity modulated proton therapy for cervical cancer: Efficacy and robustness under range and setup uncertainties.

BACKGROUND AND PURPOSE: This study evaluates the potential efficacy and robustness of functional bone marrow sparing (BMS) using intensity-modulated proton therapy (IMPT) for cervical cancer, with the goal of reducing hematologic toxicity. MATERIAL AND METHODS: IMPT plans with prescription dose of 45 Gy were generated for ten patients who have received BMS intensity-modulated X-ray therapy (IMRT). Functional bone marrow was identified by (18)F-flourothymidine positron emission tomography. IMPT plans were designed to minimize the volume of functional bone marrow receiving 5-40 Gy while maintaining similar target coverage and healthy organ sparing as IMRT. IMPT robustness was analyzed with ±3% range uncertainty errors and/or ±3 mm translational setup errors in all three principal dimensions. RESULTS: In the static scenario, the median dose volume reductions for functional bone marrow by IMPT were: 32% for V(5Gy), 47% for V(10Gy), 54% for V(20Gy), and 57% for V(40Gy), all with p<0.01 compared to IMRT. With assumed errors, even the worst-case reductions by IMPT were: 23% for V(5Gy), 37% for V(10Gy), 41% for V(20Gy), and 39% for V(40Gy), all with p<0.01. CONCLUSIONS: The potential sparing of functional bone marrow by IMPT for cervical cancer is significant and robust under realistic systematic range uncertainties and clinically relevant setup errors.

Spatial mapping of functional pelvic bone marrow using FLT PET.

The purpose of this study was to determine the ability of regions identified with bony landmarks on CT imaging to accurately represent active bone marrow when compared to FLT PET imaging. These surrogate regions could then be used to create a bone marrow sparing radiation therapy plan when FLT PET imaging is not available. Whole body (WB) FLT PET images were obtained of 18 subjects prior to chemoradiation therapy. The FLT image of each subject was registered to a CT image acquired for that subject to obtain anatomic information of the pelvis. Seventeen regions were identified based on features of the pelvic bones, sacrum, and femoral heads. The probability of FLT uptake being located in each of 17 different CT-based regions of the bony pelvis was calculated using Tukey's multiple comparison test. Statistical analysis of FLT uptake in the pelvis indicated four distinct groups within the 17 regions that had similar levels of activity. Regions located in the central part of the pelvis, including the superior part of the sacrum, the inner halves of the iliac crests, and the L5 vertebral body, had greater FLT uptake than those in the peripheral regions (p-value < 0.05). We have developed a method to use CT-defined pelvic bone regions to represent FLT PET-identified functional bone marrow. Individual regions that have a statistically significant probability of containing functional bone marrow can be used as avoidance regions to reduce radiation dose to functional bone marrow in radiation therapy planning. However, because likely active bone marrow regions and pelvic targets typically overlap, patient-specific spatial detail may be advantageous in IMRT planning scenarios and may best be provided using FLT PET imaging.

A methodology for incorporating functional bone marrow sparing in IMRT planning for pelvic radiation therapy.

BACKGROUND AND PURPOSE: The purpose of this study was to design a radiation therapy treatment planning approach that would spare hematopoietically active bone marrow using [(18)F]FLT PET imaging. MATERIALS AND METHODS: We have developed an IMRT planning methodology to incorporate functional PET imaging using [(18)F]FLT scans. Plans were generated for two simulated cervical cancer patients, where pelvic active bone marrow regions were incorporated as avoidance regions based on the ranges: SUV4 ≥ 4; 4>SUV3 ≥ 3; and 3 > SUV2 ≥ 2. Dose objectives were set to reduce bone marrow volume that received 10 (V(10)) and 20 (V(20))Gy. RESULTS: Active bone marrow regions identified by [(18)F]FLT with an SUV ≥ 2, SUV ≥ 3, and SUV ≥ 4 represented an average of 43.0%, 15.3%, and 5.8%, respectively of the total osseous pelvis for the two cases studied. Improved dose-volume histograms for all identified bone marrow SUV volumes and decreases in V(10), and V(20) were achieved without clinically significant changes to PTV or OAR doses. CONCLUSIONS: Incorporation of [(18)F]FLT PET in IMRT planning provides a methodology to reduce radiation dose to active bone marrow without compromising PTV or OAR dose objectives in pelvic malignancies.

3'-deoxy-3'-[¹8F]fluorothymidine PET quantification of bone marrow response to radiation dose.

PURPOSE: The purpose of this study was to quantify the relationship of bone marrow response to radiation dose, using 3'-deoxy-3'-[(18)F]fluorothymidine ([(18)F]FLT)-labeled uptake quantified in positron-emission tomography (PET) scans. METHODS AND MATERIALS: Pre- and post-Week 1 treatment [(18)F]FLT PET images were registered to the CT images used to create the radiation treatment plan. Changes in [(18)F]FLT uptake values were measured using profile data of standardized uptake values (SUVs) and doses along the vertebral bodies located at a field border where a range of radiation doses were present for 10 patients. Data from the profile measurements were grouped into 1 Gy dose bins from 1 to 9 Gy to compare SUV changes for all patients. Additionally, the maximum pretreatment, the post-Week 1 treatment, and the dose values located within the C6-T7 vertebrae that straddled the field edge were measured for all patients. RESULTS: Both the profile and the individual vertebral data showed a strong correlation between SUV change and radiation dose. Relative differences in SUVs between bins >1 Gy and <7 Gy were statistically significant (p < 0.01, two-sample t test). The reduction in SUV was approximately linear until it reached a reduction threshold of 75%-80% in SUV for doses greater than 6 Gy/week for both the dose-binned data and the vertebral maximum SUVs. CONCLUSIONS: The change in SUV observed in head and neck cancer patients treated with chemoradiation shows the potential for using [(18)F]FLT PET images for identifying active bone marrow and monitoring changes due to radiation dose. Additionally, the change in [(18)F]FLT uptake observed in bone marrow for different weekly doses suggests potential dose thresholds for reducing bone marrow toxicity.