Artificial-intelligence-driven measurements of brain metastases' response to SRS compare favorably with current manual standards of assessment

Background

Evaluation of treatment response for brain metastases (BMs) following stereotactic radiosurgery (SRS) becomes complex as the number of treated BMs increases. This study uses artificial intelligence (AI) to track BMs after SRS and validates its output compared with manual measurements.

Methods

Patients with BMs who received at least one course of SRS and followed up with MRI scans were retrospectively identified. A tool for automated detection, segmentation, and tracking of intracranial metastases on longitudinal imaging, MEtastasis Tracking with Repeated Observations (METRO), was applied to the dataset. The longest three-dimensional (3D) diameter identified with METRO was compared with manual measurements of maximum axial BM diameter, and their correlation was analyzed. Change in size of the measured BM identified with METRO after SRS treatment was used to classify BMs as responding, or not responding, to treatment, and its accuracy was determined relative to manual measurements.

Results

From 71 patients, 176 BMs were identified and measured with METRO and manual methods. Based on a one-to-one correlation analysis, the correlation coefficient was R2 = 0.76 (P = .0001). Using modified BM response classifications of BM change in size, the longest 3D diameter data identified with METRO had a sensitivity of 0.72 and a specificity of 0.95 in identifying lesions that responded to SRS, when using manual axial diameter measurements as the ground truth.

Conclusions

Using AI to automatically measure and track BM volumes following SRS treatment, this study showed a strong correlation between AI-driven measurements and the current clinically used method: manual axial diameter measurements.

Automatically tracking brain metastases after stereotactic radiosurgery

Background and purpose

Patients with brain metastases (BMs) are surviving longer and returning for multiple courses of stereotactic radiosurgery. BMs are monitored after radiation with follow-up magnetic resonance (MR) imaging every 2-3 months. This study investigated whether it is possible to automatically track BMs on longitudinal imaging and quantify the tumor response after radiotherapy.

Methods

The METRO process (MEtastasis Tracking with Repeated Observations was developed to automatically process patient data and track BMs. A longitudinal intrapatient registration method for T1 MR post-Gd was conceived and validated on 20 patients. Detections and volumetric measurements of BMs were obtained from a deep learning model. BM tracking was validated on 32 separate patients by comparing results with manual measurements of BM response and radiologists' assessments of new BMs. Linear regression and residual analysis were used to assess accuracy in determining tumor response and size change.

Results

A total of 123 irradiated BMs and 38 new BMs were successfully tracked. 66 irradiated BMs were visible on follow-up imaging 3-9 months after radiotherapy. Comparing their longest diameter changes measured manually vs. METRO, the Pearson correlation coefficient was 0.88 (p < 0.001); the mean residual error was -8 ± 17%. The mean registration error was 1.5 ± 0.2 mm.

Conclusions

Automatic, longitudinal tracking of BMs using deep learning methods is feasible. In particular, the software system METRO fulfills a need to automatically track and quantify volumetric changes of BMs prior to, and in response to, radiation therapy.

Automatic segmentation of brain metastases using T1 magnetic resonance and computed tomography images

An increasing number of patients with multiple brain metastases are being treated with stereotactic radiosurgery (SRS). Manually identifying and contouring all metastatic lesions is difficult and time-consuming, and a potential source of variability. Hence, we developed a 3D deep learning approach for segmenting brain metastases on MR and CT images. Five-hundred eleven patients treated with SRS were retrospectively identified for this study. Prior to radiotherapy, the patients were imaged with 3D T1 spoiled-gradient MR post-Gd (T1 + C) and contrast-enhanced CT (CECT), which were co-registered by a treatment planner. The gross tumor volume contours, authored by the attending radiation oncologist, were taken as the ground truth. There were 3 ± 4 metastases per patient, with volume up to 57 ml. We produced a multi-stage model that automatically performs brain extraction, followed by detection and segmentation of brain metastases using co-registered T1 + C and CECT. Augmented data from 80% of these patients were used to train modified 3D V-Net convolutional neural networks for this task. We combined a normalized boundary loss function with soft Dice loss to improve the model optimization, and employed gradient accumulation to stabilize the training. The average Dice similarity coefficient (DSC) for brain extraction was 0.975 ± 0.002 (95% CI). The detection sensitivity per metastasis was 90% (329/367), with moderate dependence on metastasis size. Averaged across 102 test patients, our approach had metastasis detection sensitivity 95 ± 3%, 2.4 ± 0.5 false positives, DSC of 0.76 ± 0.03, and 95th-percentile Hausdorff distance of 2.5 ± 0.3 mm (95% CIs). The volumes of automatic and manual segmentations were strongly correlated for metastases of volume up to 20 ml (r=0.97,p<0.001). This work expounds a fully 3D deep learning approach capable of automatically detecting and segmenting brain metastases using co-registered T1 + C and CECT.

A phantom study to evaluate three different registration platform of 3D/3D, 2D/3D, and 3D surface match with 6D alignment for precise image-guided radiotherapy

Purpose

To evaluate two three‐dimensional (3D)/3D registration platforms, one two‐dimensional (2D)/3D registration method, and one 3D surface registration method (3DS). These three technologies are available to perform six‐dimensional (6D) registrations for image‐guided radiotherapy treatment.

Methods

Fiducial markers were asymmetrically placed on the surfaces of an anthropomorphic head phantom (n = 13) and a body phantom (n = 8), respectively. The point match (PM) solution to the six‐dimensional (6D) transformation between the two image sets [planning computed tomography (CT) and cone beam CT (CBCT)] was determined through least‐square fitting of the fiducial positions using singular value decomposition (SVD). The transformation result from SVD was verified and was used as the gold standard to evaluate the 6D accuracy of 3D/3D registration in Varian’s platform (3D3DV), 3D/3D and 2D/3D registration in the BrainLab ExacTrac system (3D3DE and 2D3D), as well as 3DS in the AlignRT system. Image registration accuracy from each method was quantitatively evaluated by root mean square of target registration error (rmsTRE) on fiducial markers and by isocenter registration error (IRE). The Wilcoxon signed‐rank test was utilized to compare the difference of each registration method with PM. A P < 0.05 was considered significant.

Results

rmsTRE was in the range of 0.4 mm/0.7 mm (cranial/body), 0.5 mm/1 mm, 1.0 mm/1.5 mm, and 1.0 mm/1.2 mm for PM, 3D3D, 2D3D, and 3DS, respectively. Comparing to PM, the mean errors of IRE were 0.3 mm/1 mm for 3D3D, 0.5 mm/1.4 mm for 2D3D, and 1.6 mm/1.35 mm for 3DS for the cranial and body phantoms respectively. Both of 3D3D and 2D3D methods differed significantly in the roll direction as compared to the PM method for the cranial phantom. The 3DS method was significantly different from the PM method in all three translation dimensions for both the cranial (P = 0.003–P = 0.03) and body (P < 0.001–P = 0.008) phantoms.

Conclusion

3D3D using CBCT had the best image registration accuracy among all the tested methods. 2D3D method was slightly inferior to the 3D3D method but was still acceptable as a treatment position verification device. 3DS is comparable to 2D3D technique and could be a substitute for X‐ray or CBCT for pretreatment verification for treatment of anatomical sites that are rigid.

Frequency of Large Intrafractional Target Motions During Spine Stereotactic Body Radiation Therapy

Spine stereotactic body radiation therapy frequently involves the delivery of high doses to targets in proximity to the spinal cord; thus, the radiation must be delivered with great spatial accuracy. Monitoring for large shifts in target and cord position that might occur during dose delivery is a challenge for clinics equipped with a conventional C-arm Linac. Treatment must be halted, then imaging and registration must be done to determine whether a significant shift has occurred. In this retrospective study of 1019 spine SBRT treatments, we investigated the number of target shifts >2 mm in any direction that occurred in carefully immobilized patients. Orthogonal kV images were acquired 3 to 5 times during each session using in an in-room imaging system. Although the likelihood of large intrafractional shifts was found to be very low, they did occur in 6 treatment sessions. Intrafractional monitoring was found to be an important safety component of treatment delivery.

Institutional experience with SRS VMAT planning for multiple cranial metastases

Background and Purpose

This study summarizes the cranial stereotactic radiosurgery (SRS) volumetric modulated arc therapy (VMAT) procedure at our institution.

Materials and Methods

Volumetric modulated arc therapy plans were generated for 40 patients with 188 lesions (range 2–8, median 5) in Eclipse and treated on a TrueBeam STx. Limitations of the custom beam model outside the central 2.5 mm leaves necessitated more than one isocenter pending the spatial distribution of lesions. Two to nine arcs were used per isocenter. Conformity index (CI), gradient index (GI) and target dose heterogeneity index (HI) were determined for each lesion. Dose to critical structures and treatment times are reported.

Results

Lesion size ranged 0.05–17.74 cm³ (median 0.77 cm³), and total tumor volume per case ranged 1.09–26.95 cm³ (median 7.11 cm³). For each lesion, HI ranged 1.2–1.5 (median 1.3), CI ranged 1.0–2.9 (median 1.2), and GI ranged 2.5–8.4 (median 4.4). By correlating GI to PTV volume a predicted GI = 4/PTV^0.2 was determined and implemented in a script in Eclipse and used for plan evaluation. Brain volume receiving 7 Gy (V_7 Gy) ranged 10–136 cm³ (median 42 cm³). Total treatment time ranged 24–138 min (median 61 min).

Conclusions

Volumetric modulated arc therapy provide plans with steep dose gradients around the targets and low dose to critical structures, and VMAT treatment is delivered in a shorter time than conventional methods using one isocenter per lesion. To further improve VMAT planning for multiple cranial metastases, better tools to shorten planning time are needed. The most significant improvement would come from better dose modeling in Eclipse, possibly by allowing for customizing the dynamic leaf gap (DLG) for a special SRS model and not limit to one DLG per energy per treatment machine and thereby remove the limitation on the Y‐jaw and allow planning with a single isocenter.

Melanoma brain metastases treated with stereotactic radiosurgery and concurrent pembrolizumab display marked regression; efficacy and safety of combined treatment

Background

Brain metastases are common in patients with metastatic melanoma. With increasing numbers of melanoma patients on anti-PD-1 therapy, we sought to evaluate the safety and initial response of brain metastases treated with concurrent pembrolizumab and radiation therapy.

Methods

From an institutional database, we retrospectively identified patients with melanoma brain metastases treated with radiation therapy (RT) who received concurrent pembrolizumab. Concurrent treatment was defined as RT during pembrolizumab administration period and up to 4 months after most recent pembrolizumab treatment. Response was categorized by change in maximum diameter on first scheduled follow-up MRI. Lesion and patient specific outcomes including response, lesion control, brain control and overall survival were recorded and descriptively compared to contemporary treatments with RT and concurrent ipilimumab or RT without immunotherapy.

Results

From January 2014 through December 2015, we identified 21 patients who received concurrent radiation therapy and pembrolizumab for brain metastases or resection cavities that had at least one scheduled follow-up MRI. Eleven underwent stereotactic radiosurgery (SRS), 7 received hypofractionated radiation and 3 had whole brain treatment (WBRT). All treatments were well tolerated with no observed Grade 4 or 5 toxicities; Grade 3 edema and confusion occurred in 1 patient treated with WBRT after prior SRS. For metastases treated with SRS, at first scheduled follow-up MRI (median 57 days post SRS), 70% (16/23) exhibited complete (CR, n = 8) or partial response (PR, n = 8). The intracranial response rates (CR/PR) for patients treated with SRS and concurrent ipilimumab and SRS without concurrent immunotherapy was 32% and 22%, respectively.

Conclusions

Concurrent pembrolizumab with brain RT appears safe in patients with metastatic melanoma, and SRS in particular is effective in markedly reducing the size of brain metastases at the time of first follow-up MRI. These results compare favorably to SRS in combination with ipilimumab and SRS without concurrent immunotherapy.

Long-term risk of radionecrosis and imaging changes after stereotactic radiosurgery for brain metastases

Radionecrosis is a well-characterized effect of stereotactic radiosurgery (SRS) and is occasionally associated with serious neurologic sequelae. Here, we investigated the incidence of and clinical variables associated with the development of radionecrosis and related radiographic changes after SRS for brain metastases in a cohort of patients with long-term follow up. 271 brain metastases treated with single-fraction linear accelerator-based SRS were analyzed. Radionecrosis was diagnosed either pathologically or radiographically. Univariate and multivariate Cox regression was performed to determine the association between radionecrosis and clinical factors available prior to treatment planning. After median follow up of 17.2 months, radionecrosis was observed in 70 (25.8%) lesions, including 47 (17.3%) symptomatic cases. 22 of 70 cases (31.4%) were diagnosed pathologically and 48 (68.6%) were diagnosed radiographically. The actuarial incidence of radionecrosis was 5.2% at 6 months, 17.2% at 12 months and 34.0% at 24 months. On univariate analysis, radionecrosis was associated with maximum tumor diameter (HR 3.55, p < 0.001), prior whole brain radiotherapy (HR 2.21, p = 0.004), prescription dose (HR 0.56, p = 0.02) and histology other than non-small cell lung, breast or melanoma (HR 1.85, p = 0.04). On multivariate analysis, only maximum tumor diameter (HR 3.10, p < 0.001) was associated with radionecrosis risk. This data demonstrates that with close imaging follow-up, radionecrosis after single-fraction SRS for brain metastases is not uncommon. Maximum tumor diameter on pre-treatment MR imaging can provide a reliable estimate of radionecrosis risk prior to treatment planning, with the greatest risk among tumors measuring >1 cm.

Clinical Assessment of 2D/3D Registration Accuracy in 4 Major Anatomic Sites Using On-Board 2D Kilovoltage Images for 6D Patient Setup

To provide a comprehensive assessment of patient setup accuracy in 6 degrees of freedom (DOFs) using 2-dimensional/3-dimensional (2D/3D) image registration with on-board 2-dimensional kilovoltage (OB-2 DkV) radiographic images, we evaluated cranial, head and neck (HN), and thoracic and abdominal sites under clinical conditions. A fast 2D/3D image registration method using graphics processing unit GPU was modified for registration between OB-2 DkV and 3D simulation computed tomography (simCT) images, with 3D/3D registration as the gold standard for 6 DOF alignment. In 2D/3D registration, body roll rotation was obtained solely by matching orthogonal OB-2 DkV images with a series of digitally reconstructed radiographs (DRRs) from simCT with a small rotational increment along the gantry rotation axis. The window/level adjustments for optimal visualization of the bone in OB-2 DkV and DRRs were performed prior to registration. Ideal patient alignment at the isocenter was calculated and used as an initial registration position. In 3D/3D registration, cone-beam CT (CBCT) was aligned to simCT on bony structures using a bone density filter in 6DOF. Included in this retrospective study were 37 patients treated in 55 fractions with frameless stereotactic radiosurgery or stereotactic body radiotherapy for cranial and paraspinal cancer. A cranial phantom was used to serve as a control. In all cases, CBCT images were acquired for patient setup with subsequent OB-2 DkV verification. It was found that the accuracy of the 2D/3D registration was 0.0 ± 0.5 mm and 0.1° ± 0.4° in phantom. In patient, it is site dependent due to deformation of the anatomy: 0.2 ± 1.6 mm and -0.4° ± 1.2° on average for each dimension for the cranial site, 0.7 ± 1.6 mm and 0.3° ± 1.3° for HN, 0.7 ± 2.0 mm and -0.7° ± 1.1° for the thorax, and 1.1 ± 2.6 mm and -0.5° ± 1.9° for the abdomen. Anatomical deformation and presence of soft tissue in 2D/3D registration affect the consistency with 3D/3D registration in 6 DOF: the discrepancy increases in superior to inferior direction.