Fully automated deep learning based auto-contouring of liver segments and spleen on contrast-enhanced CT images

Manual delineation of liver segments on computed tomography (CT) images for primary/secondary liver cancer (LC) patients is time-intensive and prone to inter/intra-observer variability. Therefore, we developed a deep-learning-based model to auto-contour liver segments and spleen on contrast-enhanced CT (CECT) images. We trained two models using 3d patch-based attention U-Net ([Formula: see text] and 3d full resolution of nnU-Net ([Formula: see text] to determine the best architecture ([Formula: see text]. BA was used with vessels ([Formula: see text] and spleen ([Formula: see text] to assess the impact on segment contouring. Models were trained, validated, and tested on 160 ([Formula: see text]), 40 ([Formula: see text]), 33 ([Formula: see text]), 25 (CCH) and 20 (CPVE) CECT of LC patients. [Formula: see text] outperformed [Formula: see text] across all segments with median differences in Dice similarity coefficients (DSC) ranging 0.03-0.05 (p < 0.05). [Formula: see text], and [Formula: see text] were not statistically different (p > 0.05), however, both were slightly better than [Formula: see text] by DSC up to 0.02. The final model, [Formula: see text], showed a mean DSC of 0.89, 0.82, 0.88, 0.87, 0.96, and 0.95 for segments 1, 2, 3, 4, 5-8, and spleen, respectively on entire test sets. Qualitatively, more than 85% of cases showed a Likert score [Formula: see text] 3 on test sets. Our final model provides clinically acceptable contours of liver segments and spleen which are usable in treatment planning.

Quantifying the Effect of 4-Dimensional Computed Tomography-Based Deformable Dose Accumulation on Representing Radiation Damage for Patients with Locally Advanced Non-Small Cell Lung Cancer Treated with Standard-Fractionated Intensity-Modulated Radiation Therapy

PURPOSE

The aim of this study was to investigate the dosimetric and clinical effects of 4-dimensional computed tomography (4DCT)-based longitudinal dose accumulation in patients with locally advanced non-small cell lung cancer treated with standard-fractionated intensity-modulated radiation therapy (IMRT).

METHODS AND MATERIALS

Sixty-seven patients were retrospectively selected from a randomized clinical trial. Their original IMRT plan, planning and verification 4DCTs, and ∼4-month posttreatment follow-up CTs were imported into a commercial treatment planning system. Two deformable image registration algorithms were implemented for dose accumulation, and their accuracies were assessed. The planned and accumulated doses computed using average-intensity images or phase images were compared. At the organ level, mean lung dose and normal-tissue complication probability (NTCP) for grade ≥2 radiation pneumonitis were compared. At the region level, mean dose in lung subsections and the volumetric overlap between isodose intervals were compared. At the voxel level, the accuracy in estimating the delivered dose was compared by evaluating the fit of a dose versus radiographic image density change (IDC) model. The dose-IDC model fit was also compared for subcohorts based on the magnitude of NTCP difference (|ΔNTCP|) between planned and accumulated doses.

RESULTS

Deformable image registration accuracy was quantified, and the uncertainty was considered for the voxel-level analysis. Compared with planned doses, accumulated doses on average resulted in <1-Gy lung dose increase and <2% NTCP increase (up to 8.2 Gy and 18.8% for a patient, respectively). Volumetric overlap of isodose intervals between the planned and accumulated dose distributions ranged from 0.01 to 0.93. Voxel-level dose-IDC models demonstrated a fit improvement from planned dose to accumulated dose (pseudo-R2 increased 0.0023) and a further improvement for patients with ≥2% |ΔNTCP| versus for patients with <2% |ΔNTCP|.

CONCLUSIONS

With a relatively large cohort, robust image registrations, multilevel metric comparisons, and radiographic image-based evidence, we demonstrated that dose accumulation more accurately represents the delivered dose and can be especially beneficial for patients with greater longitudinal response.

Feasibility of quantitative diffusion-weighted imaging during intra-procedural MRI-guided brachytherapy of locally advanced cervical and vaginal cancers

PURPOSE

To determine the feasibility of quantitative apparent diffusion coefficient (ADC) acquisition during magnetic resonance imaging-guided brachytherapy (MRgBT) using reduced field-of-view (rFOV) diffusion-weighted imaging (DWI).

METHODS AND MATERIALS

T2-weighted (T2w) MR and full-FOV single-shot echo planar (ssEPI) DWI were acquired in 7 patients with cervical or vaginal malignancy at baseline and prior to brachytherapy, while rFOV-DWI was acquired during MRgBT following brachytherapy applicator placement. The gross target volume (GTV) was contoured on the T2w images and registered to the ADC map. Voxels at the GTV's maximum Maurer distance comprised a central sub-volume (GTVcenter). Contour ADC mean and standard deviation were compared between timepoints using repeated measures ANOVA.

RESULTS

ssEPI-DWI mean ADC increased between baseline and prebrachytherapy from 1.03 ± 0.18 10-3 mm2/s to 1.34 ± 0.28 10-3 mm2/s for the GTV (p = 0.06) and from 0.84 ± 0.13 10-3 mm2/s to 1.26 ± 0.25 10-3 mm2/s at the level of the GTVcenter (p = 0.03), consistent with early treatment response. rFOV-DWI during MRgBT demonstrated mean ADC values of 1.28 ± 0.14 10-3 mm2/s and 1.28 ± 0.19 10-3 mm2/s for the GTV and GTVcenter, respectively (p = 0.02 and p = 0.03 relative to baseline). No significant differences were observed between ssEPI-DWI and rFOV-DWI ADC measurements.

CONCLUSIONS

Quantitative ADC measurement in the setting of MRI guided brachytherapy implant placement for cervical and vaginal cancers is feasible using rFOV-DWI, with comparable mean ADC comparable to prebrachytherapy ssEPI-DWI, and may enable MRI-guided radiotherapy targeting of low ADC, radiation resistant sub-volumes of tumor.

Contour-guided deep learning based deformable image registration for dose monitoring during CBCT-guided radiotherapy of prostate cancer

PURPOSE

To evaluate deep learning (DL)-based deformable image registration (DIR) for dose accumulation during radiotherapy of prostate cancer patients.

METHODS AND MATERIALS

Data including 341 CBCTs (209 daily, 132 weekly) and 23 planning CTs from 23 patients was retrospectively analyzed. Anatomical deformation during treatment was estimated using free-form deformation (FFD) method from Elastix and DL-based VoxelMorph approaches. The VoxelMorph method was investigated using anatomical scans (VMorph_Sc) or label images (VMorph_Msk), or the combination of both (VMorph_Sc_Msk). Accumulated doses were compared with the planning dose.

RESULTS

The DSC ranges, averaged for prostate, rectum and bladder, were 0.60-0.71, 0.67-0.79, 0.93-0.98, and 0.89-0.96 for the FFD, VMorph_Sc, VMorph_Msk, and VMorph_Sc_Msk methods, respectively. When including both anatomical and label images, VoxelMorph estimated more complex deformations resulting in heterogeneous determinant of Jacobian and higher percentage of deformation vector field (DVF) folding (up to a mean value of 1.90% in the prostate). Large differences were observed between DL-based methods regarding estimation of the accumulated dose, showing systematic overdosage and underdosage of the bladder and rectum, respectively. The difference between planned mean dose and accumulated mean dose with VMorph_Sc_Msk reached a median value of +6.3 Gy for the bladder and -5.1 Gy for the rectum.

CONCLUSION

The estimation of the deformations using DL-based approach is feasible for male pelvic anatomy but requires the inclusion of anatomical contours to improve organ correspondence. High variability in the estimation of the accumulated dose depending on the deformable strategy suggests further investigation of DL-based techniques before clinical deployment.

Ablative Margins of Colorectal Liver Metastases Using Deformable CT Image Registration and Autosegmentation

Background Confirming ablation completeness with sufficient ablative margin is critical for local tumor control following colorectal liver metastasis (CLM) ablation. An image-based confirmation method considering patient- and ablation-related biomechanical deformation is an unmet need. Purpose To evaluate a biomechanical deformable image registration (DIR) method for three-dimensional (3D) minimal ablative margin (MAM) quantification and the association with local disease progression following CT-guided CLM ablation. Materials and Methods This single-institution retrospective study included patients with CLM treated with CT-guided microwave or radiofrequency ablation from October 2015 to March 2020. A biomechanical DIR method with AI-based autosegmentation of liver, tumors, and ablation zones on CT images was applied for MAM quantification retrospectively. The per-tumor incidence of local disease progression was defined as residual tumor or local tumor progression. Factors associated with local disease progression were evaluated using the multivariable Fine-Gray subdistribution hazard model. Local disease progression sites were spatially localized with the tissue at risk for tumor progression (<5 mm) using a 3D ray-tracing method. Results Overall, 213 ablated CLMs (mean diameter, 1.4 cm) in 124 consecutive patients (mean age, 57 years ± 12 [SD]; 69 women) were evaluated, with a median follow-up interval of 25.8 months. In ablated CLMs, an MAM of 0 mm was depicted in 14.6% (31 of 213), from greater than 0 to less than 5 mm in 40.4% (86 of 213), and greater than or equal to 5 mm in 45.1% (96 of 213). The 2-year cumulative incidence of local disease progression was 72% for 0 mm and 12% for greater than 0 to less than 5 mm. No local disease progression was observed for an MAM greater than or equal to 5 mm. Among 117 tumors with an MAM less than 5 mm, 36 had local disease progression and 30 were spatially localized within the tissue at risk for tumor progression. On multivariable analysis, an MAM of 0 mm (subdistribution hazard ratio, 23.3; 95% CI: 10.8, 50.5; P < .001) was independently associated with local disease progression. Conclusion Biomechanical deformable image registration and autosegmentation on CT images enabled identification and spatial localization of colorectal liver metastases at risk for local disease progression following ablation, with a minimal ablative margin greater than or equal to 5 mm as the optimal end point. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Sofocleous in this issue.

Optimization of mesh generation for geometric accuracy, robustness, and efficiency of biomechanical-model-based deformable image registration

BACKGROUND

Successful generation of biomechanical-model-based deformable image registration (BM-DIR) relies on user-defined parameters that dictate surface mesh quality. The trial-and-error process to determine the optimal parameters can be labor-intensive and hinder DIR efficiency and clinical workflow.

PURPOSE

To identify optimal parameters in surface mesh generation as boundary conditions for a BM-DIR in longitudinal liver and lung CT images to facilitate streamlined image registration processes.

METHODS

Contrast-enhanced CT images of 29 colorectal liver cancer patients and end-exhale four-dimensional CT images of 26 locally advanced non-small cell lung cancer patients were collected. Different combinations of parameters that determine the triangle mesh quality (voxel side length and triangle edge length) were investigated. The quality of DIRs generated using these parameters was evaluated with metrics for geometric accuracy, robustness, and efficiency. Metrics for geometric accuracy included target registration error (TRE) of internal vessel bifurcations, dice similar coefficient (DSC), mean distance to agreement (MDA), Hausdorff distance (HD) for organ contours, and number of vertices in the triangle mesh. American Association of Physicists in Medicine Task Group 132 was used to ensure parameters met TRE, DSC, MDA recommendations before the comparison among the parameters. Robustness was evaluated as the success rate of DIR generation, and efficiency was evaluated as the total time to generate boundary conditions and compute finite element analysis.

RESULTS

Voxel side length of 0.2 cm and triangle edge length of 3 were found to be the optimal parameters for both liver and lung, with success rate of 1.00 and 0.98 and average DIR computation time of 100 and 143 s, respectively. For this combination, the average TRE, DSC, MDA, and HD were 0.38-0.40, 0.96-0.97, 0.09-0.12, and 0.87-1.17 mm, respectively.

CONCLUSION

The optimal parameters were found for the analyzed patients. The decision-making process described in this study serves as a recommendation for BM-DIR algorithms to be used for liver and lung. These parameters can facilitate consistence in the evaluation of published studies and more widespread utilization of BM-DIR in clinical practice.

Automatic segmentation for plan-of-the-day selection in CBCT-guided adaptive radiation therapy of cervical cancer

Objective.Plan-of-the-day (PoD) adaptive radiation therapy (ART) is based on a library of treatment plans, among which, at each treatment fraction, the PoD is selected using daily images. However, this strategy is limited by PoD selection uncertainties. This work aimed to propose and evaluate a workflow to automatically and quantitatively identify the PoD for cervix cancer ART based on daily CBCT images.Approach.The quantification was based on the segmentation of the main structures of interest in the CBCT images (clinical target volume [CTV], rectum, bladder, and bowel bag) using a deep learning model. Then, the PoD was selected from the treatment plan library according to the geometrical coverage of the CTV. For the evaluation, the resulting PoD was compared to the one obtained considering reference CBCT delineations.Main results.In experiments on a database of 23 patients with 272 CBCT images, the proposed method obtained an agreement between the reference PoD and the automatically identified PoD for 91.5% of treatment fractions (99.6% when considering a 5% margin on CTV coverage).Significance.The proposed automatic workflow automatically selected PoD for ART using deep-learning methods. The results showed the ability of the proposed process to identify the optimal PoD in a treatment plan library.

Study Protocol COVER-ALL: Clinical Impact of a Volumetric Image Method for Confirming Tumour Coverage with Ablation on Patients with Malignant Liver Lesions

PURPOSE

This study aims to evaluate the intra-procedural use of a novel ablation confirmation (AC) method, consisting of biomechanical deformable image registration incorporating AI-based auto-segmentation, and its impact on tumor coverage by quantitative three-dimensional minimal ablative margin (MAM) CT-generated assessment.

MATERIALS AND METHODS

This single-center, randomized, phase II, intent-to-treat trial is enrolling 100 subjects with primary and secondary liver tumors (≤ 3 tumors, 1-5 cm in diameter) undergoing microwave or radiofrequency ablation with a goal of achieving ≥ 5 mm MAM. For the experimental arm, the proposed novel AC method is utilized for ablation applicator(s) placement verification and MAM assessment. For the control arm, the same variables are assessed by visual inspection and anatomical landmarks-based quantitative measurements aided by co-registration of pre- and post-ablation contrast-enhanced CT images. The primary objective is to evaluate the impact of the proposed AC method on the MAM. Secondary objectives are 2-year LTP-free survival, complication rates, quality of life, liver function, other oncological outcomes, and impact of AC method on procedure workflow.

DISCUSSION

The COVER-ALL trial will provide information on the role of a biomechanical deformable image registration-based ablation confirmation method incorporating AI-based auto-segmentation for improving MAM, which might translate in improvements of liver ablation efficacy.

CONCLUSION

The COVER-ALL trial aims to provide information on the role of a novel intra-procedural AC method for improving MAM, which might translate in improvements of liver ablation efficacy.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT04083378.

Leveraging deep learning-based segmentation and contours-driven deformable registration for dose accumulation in abdominal structures

PURPOSE

Discrepancies between planned and delivered dose to GI structures during radiation therapy (RT) of liver cancer may hamper the prediction of treatment outcomes. The purpose of this study is to develop a streamlined workflow for dose accumulation in a treatment planning system (TPS) during liver image-guided RT and to assess its accuracy when using different deformable image registration (DIR) algorithms.

MATERIALS AND METHODS

Fifty-six patients with primary and metastatic liver cancer treated with external beam radiotherapy guided by daily CT-on-rails (CTOR) were retrospectively analyzed. The liver, stomach and duodenum contours were auto-segmented on all planning CTs and daily CTORs using deep-learning methods. Dose accumulation was performed for each patient using scripting functionalities of the TPS and considering three available DIR algorithms based on: (i) image intensities only; (ii) intensities + contours; (iii) a biomechanical model (contours only). Planned and accumulated doses were converted to equivalent dose in 2Gy (EQD2) and normal tissue complication probabilities (NTCP) were calculated for the stomach and duodenum. Dosimetric indexes for the normal liver, GTV, stomach and duodenum and the NTCP values were exported from the TPS for analysis of the discrepancies between planned and the different accumulated doses.

RESULTS

Deep learning segmentation of the stomach and duodenum enabled considerable acceleration of the dose accumulation process for the 56 patients. Differences between accumulated and planned doses were analyzed considering the 3 DIR methods. For the normal liver, stomach and duodenum, the distribution of the 56 differences in maximum doses (D2%) presented a significantly higher variance when a contour-driven DIR method was used instead of the intensity only-based method. Comparing the two contour-driven DIR methods, differences in accumulated minimum doses (D98%) in the GTV were >2Gy for 15 (27%) of the patients. Considering accumulated dose instead of planned dose in standard NTCP models of the duodenum demonstrated a high sensitivity of the duodenum toxicity risk to these dose discrepancies, whereas smaller variations were observed for the stomach.

CONCLUSION

This study demonstrated a successful implementation of an automatic workflow for dose accumulation during liver cancer RT in a commercial TPS. The use of contour-driven DIR methods led to larger discrepancies between planned and accumulated doses in comparison to using an intensity only based DIR method, suggesting a better capability of these approaches in estimating complex deformations of the GI organs.

Development and validation of a population-based anatomical colorectal model for radiation dosimetry in late effects studies of survivors of childhood cancer

PURPOSE

The purposes of this study were to develop and integrate a colorectal model that incorporates anatomical variations of pediatric patients into the age-scalable MD Anderson Late Effects (MDA-LE) computational phantom, and validate the model for pediatric radiation therapy (RT) dose reconstructions.

METHODS

Colorectal contours were manually derived from whole-body non-contrast computed tomography (CT) scans of 114 pediatric patients (age range: 2.1-21.6 years, 74 males, 40 females). One contour was used for an anatomical template, 103 for training and 10 for testing. Training contours were used to create a colorectal principal component analysis (PCA)-based statistical shape model (SSM) to extract the population's dominant deformations. The SSM was integrated into the MDA-LE phantom. Geometric accuracy was assessed between patient-specific and SSM contours using several overlap metrics. Two alternative colorectal shapes were generated using the first 17 dominant modes of the PCA-based SSM. Dosimetric accuracy was assessed by comparing colorectal doses from test patients' CT-based RT plans (ground truth) with reconstructed doses for the mean and two alternative models in age-matched MDA-LE phantoms.

RESULTS

When using all 103 PCA modes, the mean (min-max) Dice similarity coefficient, distance-to-agreement and Hausdorff distance between the patient-specific and reconstructed contours for the test patients were 0.89 (0.85-0.91), 2.1 mm (1.7-3.0), and 8.6 mm (5.7-14.3), respectively. The average percent difference between reconstructed and ground truth mean and maximum colorectal doses for the mean (alternative 1, 2) model were 6.3% (8.1%, 6.1%) and 4.4% (4.3%, 4.7%), respectively.

CONCLUSIONS

We developed, validated and integrated a colorectal PCA-based SSM into the MDA-LE phantom and demonstrated its dosimetric performance for accurate pediatric RT dose reconstruction.

Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images

Objectives

Colorectal cancer (CRC), the third most common cancer in the USA, is a leading cause of cancer-related death worldwide. Up to 60% of patients develop liver metastasis (CRLM). Treatments like radiation and ablation therapies require disease segmentation for planning and therapy delivery. For ablation, ablation-zone segmentation is required to evaluate disease coverage. We hypothesize that fully convolutional (FC) neural networks, trained using novel methods, will provide rapid and accurate identification and segmentation of CRLM and ablation zones.

Methods

Four FC model styles were investigated: Standard 3D-UNet, Residual 3D-UNet, Dense 3D-UNet, and Hybrid-WNet. Models were trained on 92 patients from the liver tumor segmentation (LiTS) challenge. For the evaluation, we acquired 15 patients from the 3D-IRCADb database, 18 patients from our institution (CRLM = 24, ablation-zone = 19), and those submitted to the LiTS challenge (n = 70). Qualitative evaluations of our institutional data were performed by two board-certified radiologists (interventional and diagnostic) and a radiology-trained physician fellow, using a Likert scale of 1–5.

Results

The most accurate model was the Hybrid-WNet. On a patient-by-patient basis in the 3D-IRCADb dataset, the median (min–max) Dice similarity coefficient (DSC) was 0.73 (0.41–0.88), the median surface distance was 1.75 mm (0.57–7.63 mm), and the number of false positives was 1 (0–4). In the LiTS challenge (n = 70), the global DSC was 0.810. The model sensitivity was 98% (47/48) for sites ≥15 mm in diameter. Qualitatively, 100% (24/24; minority vote) of the CRLM and 84% (16/19; majority vote) of the ablation zones had Likert scores ≥4.

Conclusion

The Hybrid-WNet model provided fast (<30 s) and accurate segmentations of CRLM and ablation zones on contrast-enhanced CT scans, with positive physician reviews.

Automatic contouring QA method using a deep learning-based autocontouring system

Purpose

To determine the most accurate similarity metric when using an independent system to verify automatically generated contours.

Methods

A reference autocontouring system (primary system to create clinical contours) and a verification autocontouring system (secondary system to test the primary contours) were used to generate a pair of 6 female pelvic structures (UteroCervix [uterus + cervix], CTVn [nodal clinical target volume (CTV)], PAN [para‐aortic lymph nodes], bladder, rectum, and kidneys) on 49 CT scans from our institution and 38 from other institutions. Additionally, clinically acceptable and unacceptable contours were manually generated using the 49 internal CT scans. Eleven similarity metrics (volumetric Dice similarity coefficient (DSC), Hausdorff distance, 95% Hausdorff distance, mean surface distance, and surface DSC with tolerances from 1 to 10 mm) were calculated between the reference and the verification autocontours, and between the manually generated and the verification autocontours. A support vector machine (SVM) was used to determine the threshold that separates clinically acceptable and unacceptable contours for each structure. The 11 metrics were investigated individually and in certain combinations. Linear, radial basis function, sigmoid, and polynomial kernels were tested using the combinations of metrics as inputs for the SVM.

Results

The highest contouring error detection accuracies were 0.91 for the UteroCervix, 0.90 for the CTVn, 0.89 for the PAN, 0.92 for the bladder, 0.95 for the rectum, and 0.97 for the kidneys and were achieved using surface DSCs with a thickness of 1, 2, or 3 mm. The linear kernel was the most accurate and consistent when a combination of metrics was used as an input for the SVM. However, the best model accuracy from the combinations of metrics was not better than the best model accuracy from a surface DSC as an input.

Conclusions

We distinguished clinically acceptable contours from clinically unacceptable contours with an accuracy higher than 0.9 for the targets and critical structures in patients with cervical cancer; the most accurate similarity metric was surface DSC with a thickness of 1, 2, or 3 mm.

Detection of vessel bifurcations in CT scans for automatic objective assessment of deformable image registration accuracy

PURPOSE

Objective assessment of deformable image registration (DIR) accuracy often relies on the identification of anatomical landmarks in image pairs, a manual process known to be extremely time-expensive. The goal of this study is to propose a method to automatically detect vessel bifurcations in images and assess their use for the computation of target registration errors (TREs).

MATERIALS AND METHODS

Three image datasets were retrospectively analyzed. The first dataset included 10 pairs of inhale/exhale phases from lung 4DCTs and full inhale and exhale breath-hold CT scans from 10 patients presenting with chronic obstructive pulmonary disease, with 300 corresponding landmarks available for each case (DIR-Lab). The second dataset included six pairs of inhale/exhale phases from lung 4DCTs (POPI dataset), with 100 pairs of landmarks for each case. The third dataset included 28 pairs of pre/post-radiotherapy liver contrast-enhanced CT scans, each with five manually picked vessel bifurcation correspondences. For all images, the vasculature was autosegmented by computing and thresholding a vesselness image. Images of the vasculature centerline were computed, and bifurcations were detected based on centerline voxel neighbors' count. The vasculature segmentations were independently registered using a Demons algorithm between representations of their surface with distance maps. Detected bifurcations were considered as corresponding when distant by less than 5 mm after vasculature DIR. The selected pairs of bifurcations were used to calculate TRE after registration of the images considering three algorithms: rigid registration, Anaconda, and a Demons algorithm. For comparison with the ground truth, TRE values calculated using the automatically detected correspondences were interpolated in the whole organs to generate TRE maps. The performance of the method in automatically calculating TRE after image registration was quantified by measuring the correlation with the TRE obtained when using the ground truth landmarks.

RESULTS

The median Pearson correlation coefficients between ground truth TRE and corresponding values in the generated TRE maps were r = 0.81 and r = 0.67 for the lung and liver cases, respectively. The correlation coefficients between mean TRE for each case were r = 0.99 and r = 0.64 for the lung and liver cases, respectively.

CONCLUSION

For lungs or liver CT scans DIR, a strong correlation was obtained between TRE calculated using manually picked or landmarks automatically detected with the proposed method. This tool should be particularly useful in studies requiring assessing the reliability of a high number of DIRs.

Automatic contouring system for cervical cancer using convolutional neural networks

PURPOSE

To develop a tool for the automatic contouring of clinical treatment volumes (CTVs) and normal tissues for radiotherapy treatment planning in cervical cancer patients.

METHODS

An auto-contouring tool based on convolutional neural networks (CNN) was developed to delineate three cervical CTVs and 11 normal structures (seven OARs, four bony structures) in cervical cancer treatment for use with the Radiation Planning Assistant, a web-based automatic plan generation system. A total of 2254 retrospective clinical computed tomography (CT) scans from a single cancer center and 210 CT scans from a segmentation challenge were used to train and validate the CNN-based auto-contouring tool. The accuracy of the tool was evaluated by calculating the Sørensen-dice similarity coefficient (DSC) and mean surface and Hausdorff distances between the automatically generated contours and physician-drawn contours on 140 internal CT scans. A radiation oncologist scored the automatically generated contours on 30 external CT scans from three South African hospitals.

RESULTS

The average DSC, mean surface distance, and Hausdorff distance of our CNN-based tool were 0.86/0.19 cm/2.02 cm for the primary CTV, 0.81/0.21 cm/2.09 cm for the nodal CTV, 0.76/0.27 cm/2.00 cm for the PAN CTV, 0.89/0.11 cm/1.07 cm for the bladder, 0.81/0.18 cm/1.66 cm for the rectum, 0.90/0.06 cm/0.65 cm for the spinal cord, 0.94/0.06 cm/0.60 cm for the left femur, 0.93/0.07 cm/0.66 cm for the right femur, 0.94/0.08 cm/0.76 cm for the left kidney, 0.95/0.07 cm/0.84 cm for the right kidney, 0.93/0.05 cm/1.06 cm for the pelvic bone, 0.91/0.07 cm/1.25 cm for the sacrum, 0.91/0.07 cm/0.53 cm for the L4 vertebral body, and 0.90/0.08 cm/0.68 cm for the L5 vertebral bodies. On average, 80% of the CTVs, 97% of the organ at risk, and 98% of the bony structure contours in the external test dataset were clinically acceptable based on physician review.

CONCLUSIONS

Our CNN-based auto-contouring tool performed well on both internal and external datasets and had a high rate of clinical acceptability.

Modeling Complex Deformations of the Sigmoid Colon Between External Beam Radiation Therapy and Brachytherapy Images of Cervical Cancer

PURPOSE

In this study, we investigated registration methods for estimating the large interfractional sigmoid deformations that occur between external beam radiation therapy (EBRT) and brachytherapy (BT) for cervical cancer.

METHODS AND MATERIALS

Sixty-three patients were retrospectively analyzed. The sigmoid colon was delineated on 2 computed tomography images acquired during EBRT (without applicator) and BT (with applicator) for each patient. Five registration approaches were compared to propagate the contour of the sigmoid from BT to EBRT anatomies: rigid registration, commercial hybrid (ANAtomically CONstrained Deformation Algorithm), controlling ROI surface projection of RayStation, and the classical and constrained symmetrical thin-plate spline robust point matching (sTPS-RPM) methods. Deformation of the sigmoid due to insertion of the BT applicator was reported. Registration performance was compared by using the Dice similarity coefficient (DSC), distance to agreement, and Hausdorff distance. The 2 sTPS-RPM methods were compared by using surface triangle quality criteria between deformed surfaces. Using the deformable approaches, the BT dose of the sigmoid was deformed toward the EBRT anatomy. The displacement and discrepancy between the deformable methods to propagate the planned D1cm³ and D2cm³ of the sigmoid from BT to EBRT anatomies were reported for 55 patients.

RESULTS

Large and complex deformations of the sigmoid were observed for each patient. Rigid registration resulted in poor sigmoid alignment with a mean DSC of 0.26. Using the contour to drive the deformation, ANAtomically CONstrained Deformation Algorithm was able to slightly improve the alignment of the sigmoid with a mean DSC of 0.57. Using only the sigmoid surface as controlling ROI, the mean DSC was improved to 0.79. The classical and constrained sTPS-RPM methods provided mean DSCs of 0.95 and 0.96, respectively, with an average inverse consistency error <1 mm. The constrained sTPS-RPM provided more realistic deformations and better surface topology of the deformed sigmoids. The planned mean (range) D1cm³ and D2cm³ of the sigmoid were 13.4 Gy (1-24.1) and 12.2 Gy (1-21.5) on the BT anatomy, respectively. Using the constrained sTPS-RPM to deform the sigmoid from BT to EBRT anatomies, these hotspots had a mean (range) displacement of 27.1 mm (6.8-81).

CONCLUSIONS

Large deformations of the sigmoid were observed between the EBRT and BT anatomies, suggesting that the D1cm³ and D2cm³ of the sigmoid would unlikely to be at the same position throughout treatment. The proposed constrained sTPS-RPM seems to be the preferred approach to manage the large deformation due to BT applicator insertion. Such an approach could be used to map the EBRT dose to the BT anatomy for personalized BT planning optimization.

Biomechanical modeling of neck flexion for deformable alignment of the salivary glands in head and neck cancer images

During head and neck (HN) cancer radiation therapy, analysis of the dose-response relationship for the parotid glands (PG) relies on the ability to accurately align soft tissue organs between longitudinal images. In order to isolate the response of the salivary glands to delivered dose, from deformation due to patient position, it is important to resolve the patient postural changes, mainly due to neck flexion. In this study we evaluate the use of a biomechanical model-based deformable image registration (DIR) algorithm to estimate the displacements and deformations of the salivary glands due to postural changes. A total of 82 pairs of CT images of HN cancer patients with varying angles of neck flexion were retrospectively obtained. The pairs of CTs of each patient were aligned using bone-based rigid registration. The images were then deformed using biomechanical model-based DIR method that focused on the mandible, C1 vertebrae, C3 vertebrae, and external contour. For comparison, an intensity-based DIR was also performed. The accuracy of the biomechanical model-based DIR was assessed using Dice similarity coefficient (DSC) for all images and for the subset of images where the PGs had a volume change within 20%. The accuracy was compared to the intensity-based DIR. The PG mean  ±  STD DSC were 0.63  ±  0.18, 0.80  ±  0.08, and 0.82  ±  0.15 for the rigid registration, biomechanical model-based DIR, and intensity based DIR, respectively, for patients with a PG volume change up to 20%. For the entire cohort of patients, where the PG volume change was up to 57%, the PG mean  ±  STD DSC were 0.60  ±  0.18, 0.78  ±  0.09, and 0.81  ±  0.14 for the rigid registration, biomechanical model-based DIR, and intensity based DIR, respectively. The difference in DSC of the intensity and biomechanical model-based DIR methods was not statistically significant when the volume change was less than 20% (two-sided paired t-test, p   =  0.12). When all volume changes were considered, there was a significant difference between the two registration approaches, although the magnitude was small. These results demonstrate that the proposed biomechanical model with boundary conditions on the bony anatomy can serve to describe the varying angles of neck flexion appearing in images during radiation treatment and to align the salivary glands for proper analysis of dose-response relationships. It also motivates the need for dose response modeling following neck flexion for cases where parotid gland response is noted.

Deformable image registration for radiation therapy: principle, methods, applications and evaluation

Background: Deformable image registration (DIR) is increasingly used in the field of radiation therapy (RT) to account for anatomical deformations. The aims of this paper are to describe the main applications of DIR in RT and discuss current DIR evaluation methods. Methods: Articles on DIR published from January 2000 to October 2018 were extracted from PubMed and Science Direct. Our search was restricted to articles that report data obtained from humans, were written in English, and address DIR methods for RT. A total of 207 articles were selected from among 2506 identified in the search process. Results: At planning, DIR is used for organ delineation using atlas-based segmentation, deformation-based planning target volume definition, functional planning and magnetic resonance imaging-based dose calculation. In image-guided RT, DIR is used for contour propagation and dose calculation on per-treatment imaging. DIR is also used to determine the accumulated dose from fraction to fraction in external beam RT and brachytherapy, both for dose reporting and adaptive RT. In the case of re-irradiation, DIR can be used to estimate the cumulated dose of the two irradiations. Finally, DIR can be used to predict toxicity in voxel-wise population analysis. However, the evaluation of DIR remains an open issue, especially when dealing with complex cases such as the disappearance of matter. To quantify DIR uncertainties, most evaluation methods are limited to geometry-based metrics. Software companies have now integrated DIR tools into treatment planning systems for clinical use, such as contour propagation and fraction dose accumulation. Conclusions: DIR is increasingly important in RT applications, from planning to toxicity prediction. DIR is routinely used to reduce the workload of contour propagation. However, its use for complex dosimetric applications must be carefully evaluated by combining quantitative and qualitative analyses.

Deformable image registration for dose mapping between external beam radiotherapy and brachytherapy images of cervical cancer

For locally advanced cervical cancer (LACC), anatomy correspondence with and without BT applicator needs to be quantified to merge the delivered doses of external beam radiation therapy (EBRT) and brachytherapy (BT). This study proposed and evaluated different deformable image registration (DIR) methods for this application. Twenty patients who underwent EBRT and BT for LACC were retrospectively analyzed. Each patient had a pre-BT CT at EBRT boost (without applicator) and a CT and MRI at BT (with applicator). The evaluated DIR methods were the diffeomorphic Demons, commercial intensity and hybrid methods, and three different biomechanical models. The biomechanical models considered different boundary conditions (BCs). The impact of the BT devices insertion on the anatomy was quantified. DIR method performances were quantified using geometric criteria between the original and deformed contours. The BT dose was deformed toward the pre-CT BT by each DIR method. The impact of boundary conditions to drive the biomechanical model was evaluated based on the deformation vector field and dose differences. The GEC-ESTRO guideline dose indices were reported. Large organ displacements, deformations, and volume variations were observed between the pre-BT and BT anatomies. Rigid registration and intensity-based DIR resulted in poor geometric accuracy with mean Dice similarity coefficient (DSC) inferior to 0.57, 0.63, 0.42, 0.32, and 0.43 for the rectum, bladder, vagina, cervix and uterus, respectively. Biomechanical models provided a mean DSC of 0.96 for all the organs. By considering the cervix-uterus as one single structure, biomechanical models provided a mean DSC of 0.88 and 0.94 for the cervix and uterus, respectively. The deformed doses were represented for each DIR method. Caution should be used when performing DIR for this application as standard techniques may have unacceptable results. The biomechanical model with the cervix-uterus as one structure provided the most realistic deformations to propagate the BT dose toward the EBRT boost anatomy.

Statistical Shape Model to Generate a Planning Library for Cervical Adaptive Radiotherapy

External beam radiotherapy is extensively used to treat cervical carcinomas. A single planning CT scan enables the calculation of the dose distribution. The treatment is delivered over five weeks. Large per-treatment anatomical variations may hamper the dose delivery, with the potential of an organ-at-risk (OAR) overdose and a tumor underdose. To anticipate these deformations, a recent approach proposed three planning CTs with variable bladder volumes, which had the limitation of not covering all per-treatment anatomical variations. An original patient-specific population-based library has been proposed. It consisted of generating two representative anatomies, in addition to the standard planning CT anatomy. First, the cervix and bladder meshes of a population of 20 patients (314 images) were registered to an anatomical template, using a deformable mesh registration. An iterative point-matching algorithm was developed based on local shape context (histogram of polar or cylindrical coordinates and geodesic distance to the base) and on a topology constraint filter. Second, a standard principal component analysis (PCA) model of the cervix and bladder was generated to extract the dominant deformation modes. Finally, specific deformations were obtained using posterior PCA models, with a constraint representing the top of the uterus deformation. For a new patient, the cervix-uterus and bladder were registered to the template, and the patient's modeled planning library was built according to the model deformations. This method was applied following a leave-one-patient-out cross-validation. The performances of the modeled library were compared to those of the three-CT-based library, showing an improvement in both target coverage and OAR sparing.

Adaptive radiotherapy for head and neck cancer

INTRODUCTION

Large anatomical variations can be observed during the treatment course intensity-modulated radiotherapy (IMRT) for head and neck cancer (HNC), leading to potential dose variations. Adaptive radiotherapy (ART) uses one or several replanning sessions to correct these variations and thus optimize the delivered dose distribution to the daily anatomy of the patient. This review, which is focused on ART in the HNC, aims to identify the various strategies of ART and to estimate the dosimetric and clinical benefits of these strategies.

MATERIAL AND METHODS

We performed an electronic search of articles published in PubMed/MEDLINE and Science Direct from January 2005 to December 2016. Among a total of 134 articles assessed for eligibility, 29 articles were ultimately retained for the review. Eighteen studies evaluated dosimetric variations without ART, and 11 studies reported the benefits of ART.

RESULTS

Eight in silico studies tested a number of replanning sessions, ranging from 1 to 6, aiming primarily to reduce the dose to the parotid glands. The optimal timing for replanning appears to be early during the first two weeks of treatment. Compared to standard IMRT, ART decreases the mean dose to the parotid gland from 0.6 to 6 Gy and the maximum dose to the spinal cord from 0.1 to 4 Gy while improving target coverage and homogeneity in most studies. Only five studies reported the clinical results of ART, and three of those studies included a non-randomized comparison with standard IMRT. These studies suggest a benefit of ART in regard to decreasing xerostomia, increasing quality of life, and increasing local control. Patients with the largest early anatomical and dose variations are the best candidates for ART.

CONCLUSION

ART may decrease toxicity and improve local control for locally advanced HNC. However, randomized trials are necessary to demonstrate the benefit of ART before using the technique in routine practice.

Multi-atlas-based segmentation of prostatic urethra from planning CT imaging to quantify dose distribution in prostate cancer radiotherapy

BACKGROUND AND PURPOSE

Segmentation of intra-prostatic urethra for dose assessment from planning CT may help explaining urinary toxicity in prostate cancer radiotherapy. This work sought to: i) propose an automatic method for urethra segmentation in CT, ii) compare it with previously proposed surrogate models and iii) quantify the dose received by the urethra in patients treated with IMRT.

MATERIALS AND METHODS

A weighted multi-atlas-based urethra segmentation method was devised from a training data set of 55 CT scans of patients receiving brachytherapy with visible urinary catheters. Leave-one-out cross validation was performed to quantify the error between the urethra segmentation and the catheter ground truth with two scores: the centerlines distance (CLD) and the percentage of centerline within a certain distance from the catheter (PWR). The segmentation method was then applied to a second test data set of 95 prostate cancer patients having received 78Gy IMRT to quantify dose to the urethra.

RESULTS

Mean CLD was 3.25±1.2mm for the whole urethra and 3.7±1.7mm, 2.52±1.5mm, and 3.01±1.7mm for the top, middle, and bottom thirds, respectively. In average, 53% of the segmented centerlines were within a radius<3.5mm from the centerline ground truth and 83% in a radius<5mm. The proposed method outperformed existing surrogate models. In IMRT, urethra DVH was significantly higher than prostate DVH from V74Gy to V79Gy.

CONCLUSION

A multi-atlas-based segmentation method was proposed enabling assessment of the dose within the prostatic urethra.

Roles of Deformable Image Registration in adaptive RT: From contour propagation to dose monitoring

Adaptive radiation therapy (ART) is based on the optimization of the treatment plan during the treatment delivery to compensate for anatomical deformations. Deformable Image Registration (DIR) then constitutes a key step in order to analyze the huge amount of daily or weekly images to provide clinically usefull information. Two main applications of DIR have been developped in ART: delineation propagation and dose accumulation. If delineation propagation is well validated and transfered in the clinic, some challenges remain to address for dose accumulation. In this paper, we review the recent developments of DIR in ART, particularly in prostate and head-and-neck (H&N), with a focus on their evaluation.

Optimal adaptive IMRT strategy to spare the parotid glands in oropharyngeal cancer

PURPOSE

In oropharyngeal cancer adaptive radiation therapy (ART), this study aimed to quantify the dosimetric benefit of numerous replanning strategies, defined by various numbers and timings of replannings, with regard to parotid gland (PG) sparing.

MATERIAL AND METHODS

Thirteen oropharyngeal cancer patients had one planning and then six weekly CT scans during the seven weeks of IMRT. Weekly doses were recalculated without replanning or with replanning to spare the PG. Sixty-three ART scenarios were simulated by considering all the combinations of numbers and timings of replanning. The PG cumulated doses corresponding to "standard" IMRT and ART scenarios were estimated and compared, either by calculating the average of weekly doses or using deformable image registration (DIR).

RESULTS

Considering average weekly doses, the mean PG overdose using standard IMRT, compared to the planned dose, was 4.1Gy. The mean dosimetric benefit of 6 replannings was 3.3Gy. Replanning at weeks 1, 1-5, 1-2-5, 1-2-4-5 and 1-2-4-5-6 produced the lowest PG mean doses, 94% of the maximum benefit being obtained with 3 replannings. The percentage of patients who had a benefit superior to 5Gy for the contralateral PG was 31% for the three-replannings strategy. The same conclusions were found using DIR.

CONCLUSION

Early replannings proved the most beneficial for PG sparing, three replannings (weeks 1-2-5), representing an attractive combination for ART in oropharyngeal cancer.

A Nomogram to predict parotid gland overdose in head and neck IMRT

Purposes

To generate a nomogram to predict parotid gland (PG) overdose and to quantify the dosimetric benefit of weekly replanning based on its findings, in the context of intensity-modulated radiotherapy (IMRT) for locally-advanced head and neck carcinoma (LAHNC).

Material and methods

Twenty LAHNC patients treated with radical IMRT underwent weekly computed tomography (CT) scans during IMRT. The cumulated PG dose was estimated by elastic registration. Early predictors of PG overdose (cumulated minus planned doses) were identified, enabling a nomogram to be generated from a linear regression model. Its performance was evaluated using a leave-one-out method. The benefit of weekly replanning was then estimated for the nomogram-identified PG overdose patients.

Results

Clinical target volume 70 (CTV70) and the mean PG dose calculated from the planning and first weekly CTs were early predictors of PG overdose, enabling a nomogram to be generated. A mean PG overdose of 2.5Gy was calculated for 16 patients, 14 identified by the nomogram. All patients with PG overdoses >1.5Gy were identified. Compared to the cumulated delivered dose, weekly replanning of these 14 targeted patients enabled a 3.3Gy decrease in the mean PG dose.

Conclusion

Based on the planning and first week CTs, our nomogram allowed the identification of all patients with PG overdoses >2.5Gy to be identified, who then benefitted from a final 4Gy decrease in mean PG overdose by means of weekly replanning.

Resistor mesh model of a spherical head: Part 2: A review of applications to cortical mapping

A resistor mesh model (RMM) has been validated with reference to the analytical model by consideration of a set of four dipoles close to the cortex. The application of the RMM to scalp potential interpolation was detailed in Part 1. Using the RMM and the same four dipoles, the different methods of cortical mapping were compared and have shown the potentiality of this RMM for obtaining current and potential cortical distributions. The lead-field matrices are well-adapted tools, but the use of a square matrix of high dimension does not permit the inverse solution to be improved in the presence of noise, as a regularisation technique is necessary with noisy data. With the RMM, the transfer matrix and the cortical imaging technique proved to be easy to implement. Further development of the RMM will include application to more realistic head models with more accurate conductivities.

Resistor mesh model of a spherical head: Part 1: Applications to scalp potential interpolation

A resistor mesh model (RMM) has been implemented to describe the electrical properties of the head and the configuration of the intracerebral current sources by simulation of forward and inverse problems in electroencephalogram/event related potential (EEG/ERP) studies. For this study, the RMM representing the three basic tissues of the human head (brain, skull and scalp) was superimposed on a spherical volume mimicking the head volume: it included 43 102 resistances and 14 123 nodes. The validation was performed with reference to the analytical model by consideration of a set of four dipoles close to the cortex. Using the RMM and the chosen dipoles, four distinct families of interpolation technique (nearest neighbour, polynomial, splines and lead fields) were tested and compared so that the scalp potentials could be recovered from the electrode potentials. The 3D spline interpolation and the inverse forward technique (IFT) gave the best results. The IFT is very easy to use when the lead-field matrix between scalp electrodes and cortex nodes has been calculated. By simple application of the Moore-Penrose pseudo inverse matrix to the electrode cap potentials, a set of current sources on the cortex is obtained. Then, the forward problem using these cortex sources renders all the scalp potentials.

Ex vivo discrimination between normal and pathological tissues in human breast surgical biopsies using bioimpedance spectroscopy

Ex vivo bioimpedance data measured on normal and cancerous female breast tissues are reported. They clearly show that the electrical properties of normal tissues, surrounding tissues, and carcinoma are different. These differences lie in the conductivity, in the characteristic frequency (frequency of the maximum of the imaginary part of the bioimpedance), and also in the shape of the Bode plots. Modeling using an R-S-Zcpe model is reported as well as indexes extracted from the real and imaginary parts of the bioimpedance. Even if a classification of the different types of tissues remains a difficult task and leads to much less precise diagnosis than microscopic examination, the electrical behavior of mammary tissue could be used to develop a noninvasive technique for early breast cancer detection.

A multifrequency serial EIT system

A multifrequency (1 kHz-1 MHz) serial electrical impedance tomography (EIT) system has been developed. It is based on 16 active electrodes and can be extended up to 32. Each active electrode can be programmed for current driving and for measuring either the injected current or the voltage difference between adjacent electrodes, and includes calibration facilities. Real and imaginary parts of the impedance are obtained by applying a parametric identification method (extended Prony), but other techniques are easily adaptable. Image reconstruction is carried out using the Sheffield filtered back-projection algorithm. Characteristic frequency images are under development and should be of great interest to distinguish between normal and tumorous tissues.

Parametric modelling for electrical impedance spectroscopy system

Three parametric modelling approaches based on the Cole-Cole model are introduced. Comparison between modelling only the real part and modelling both the real and imaginary parts is carried out by simulations, in which random and systematic noise are considered, respectively. The results of modelling the in vitro data collected from sheep are given to reach the conclusions.

Bioelectrical impedance techniques in medicine. Part III: Impedance imaging. First section: general concepts and hardware

Measurement accuracy is a key point in impedance imaging and is mainly limited by factors that take place in the acquisition system. This part is a review of hardware solutions developed in acquisition systems for electrical impedance tomography (EIT). The general principles of EIT along with the changes that have taken place in the last decade, in terms of measurement strategy, and a certain number of definitions are introduced. The major hardware error sources that occur in the front end of EIT systems are presented. A review of the various alternatives published in the literature that are used to drive current, including current and voltage approaches, and the main solutions recommended in the literature to overcome the key point drawbacks of voltage measurement systems, including voltage buffers, instrumentation amplifiers, and demodulators, are provided. Some calibration procedures and approaches for the evaluation of the performance of EIT systems are also presented.

Bioelectrical impedance techniques in medicine. Part III: Impedance imaging. Third section: medical applications

In several areas of clinical medicine, electrical impedance tomography could offer significant advantages over existing methods. These advantages have been supported by preliminary studies or by validation studies, which are described. The suggested applications are reviewed in this section. They mainly concern developments in impedance variations on brain, lung (neonatal, edema, emphysema), and heart; changes in blood volume, gastrointestinal system (gastric emptying, gastroesophageal reflux, pharyngeal transit time); pelvis (pelvis congestion); and thermal mapping in hyperthermia and breast (tissue characterization). The conductivity information at one frequency in a pixel is insufficient to take into account the very complex physiological mechanisms that underlie the observed impedance changes. To gain a better understanding of these mechanisms, research is currently being carried out on imaging of the imaginary part, parametric imaging, spectroscopic imaging, and 3D imaging, which are developed at the end of this section.

Bioelectrical impedance techniques in medicine. Part I: Bioimpedance measurement. Second section: impedance spectrometry

Electrical impedance spectrometry is an important application field of bioimpedance measurements. After introducing the electrical properties of biological tissues, this part presents instrumental aspects and applications of electrical impedance spectrometry. The main instrumental constraints encountered in spectrometric electrical impedance measurements are reviewed, focusing on low-frequency applications. Examples of impedance cells and probes are presented and several instrumental setups operating in the frequency and time domain are described. Some examples of applications are presented, including in vitro characterization and modeling of normal tissues, in vitro and in vivo characterization of cancerous tissues, and assessment of tissue perfusion/ischemia levels.

In vitro tissue characterization and modelling using electrical impedance measurements in the 100 Hz-10 MHz frequency range

In vitro electrical impedance spectrometry was performed on tissue samples excised from sheep. Measured data have been processed to reduce dispersion in measurements and to provide criteria useful for tissue comparison. Two electrical models are proposed for tissues exhibiting a one-circle impedance locus and a two-circle impedance locus. Measurement results and electrical parameters of tissues and models fitted to experimental data are presented. Model sensitivity to parameter variations is discussed.