Deep Learning for Per-Fraction Automatic Segmentation of Gross Tumor Volume (GTV) and Organs at Risk (OARs) in Adaptive Radiotherapy of Cervical Cancer

Automatic segmentation of tumour and organs at risk in 3D MRI for cervical cancer radiation therapy with anatomical variations

Cervical cancer is a common cancer in women globally, with treatment usually involving radiation therapy (RT). Accurate segmentation for the tumour site and organ-at-risks (OARs) could assist in the reduction of treatment side effects and improve treatment planning efficiency. Cervical cancer Magnetic Resonance Imaging (MRI) segmentation is challenging due to a limited amount of training data available and large inter- and intra- patient shape variation for OARs. The proposed Masked-Net consists of a masked encoder within the 3D U-Net to account for the large shape variation within the dataset, with additional dilated layers added to improve segmentation performance. A new loss function was introduced to consider the bounding box loss during training with the proposed Masked-Net. Transfer learning from a male pelvis MRI data with a similar field of view was included. The approaches were compared to the 3D U-Net which was widely used in MRI image segmentation. The data used consisted of 52 volumes obtained from 23 patients with stage IB to IVB cervical cancer across a maximum of 7 weeks of RT with manually contoured labels including the bladder, cervix, gross tumour volume, uterus and rectum. The model was trained and tested with a 5-fold cross validation. Outcomes were evaluated based on the Dice Similarity Coefficients (DSC), the Hausdorff Distance (HD) and the Mean Surface Distance (MSD). The proposed method accounted for the small dataset, large variations in OAR shape and tumour sizes with an average DSC, HD and MSD for all anatomical structures of 0.790, 30.19mm and 3.15mm respectively.

Automatic gross tumor volume segmentation with failure detection for safe implementation in locally advanced cervical cancer

Background and Purpose

Automatic segmentation methods have greatly changed the RadioTherapy (RT) workflow, but still need to be extended to target volumes. In this paper, Deep Learning (DL) models were compared for Gross Tumor Volume (GTV) segmentation in locally advanced cervical cancer, and a novel investigation into failure detection was introduced by utilizing radiomic features.

Methods and materials

We trained eight DL models (UNet, VNet, SegResNet, SegResNetVAE) for 2D and 3D segmentation. Ensembling individually trained models during cross-validation generated the final segmentation. To detect failures, binary classifiers were trained using radiomic features extracted from segmented GTVs as inputs, aiming to classify contours based on whether their Dice Similarity Coefficient ( DSC ) < T and DSC ⩾ T . Two distinct cohorts of T2-Weighted (T2W) pre-RT MR images captured in 2D sequences were used: one retrospective cohort consisting of 115 LACC patients from 30 scanners, and the other prospective cohort, comprising 51 patients from 7 scanners, used for testing.

Results

Segmentation by 2D-SegResNet achieved the best DSC, Surface DSC (SDSC 3 mm ), and 95th Hausdorff Distance (95HD): DSC = 0.72 ± 0.16,SDSC 3 mm =0.66 ± 0.17, and 95HD = 14.6 ± 9.0 mm without missing segmentation ( M =0) on the test cohort. Failure detection could generate precision ( P = 0.88 ), recall ( R = 0.75 ), F1-score ( F = 0.81 ), and accuracy ( A = 0.86 ) using Logistic Regression (LR) classifier on the test cohort with a threshold T = 0.67 on DSC values.

Conclusions

Our study revealed that segmentation accuracy varies slightly among different DL methods, with 2D networks outperforming 3D networks in 2D MRI sequences. Doctors found the time-saving aspect advantageous. The proposed failure detection could guide doctors in sensitive cases.

Uncovering prostate cancer aggressiveness signal in T2-weighted MRI through a three-reference tissues normalization technique

Quantitative T2-weighted MRI (T2W) interpretation is impeded by the variability of acquisition-related features, such as field strength, coil type, signal amplification, and pulse sequence parameters. The main purpose of this work is to develop an automated method for prostate T2W intensity normalization. The procedure includes the following: (i) a deep learning-based network utilizing MASK R-CNN for automatic segmentation of three reference tissues: gluteus maximus muscle, femur, and bladder; (ii) fitting a spline function between average intensities in these structures and reference values; and (iii) using the function to transform all T2W intensities. The T2W distributions in the prostate cancer regions of interest (ROIs) and normal appearing prostate tissue (NAT) were compared before and after normalization using Student's t-test. The ROIs' T2W associations with the Gleason Score (GS), Decipher genomic score, and a three-tier prostate cancer risk were evaluated with Spearman's correlation coefficient (rS ). T2W differences in indolent and aggressive prostate cancer lesions were also assessed. The MASK R-CNN was trained with manual contours from 32 patients. The normalization procedure was applied to an independent MRI dataset from 83 patients. T2W differences between ROIs and NAT significantly increased after normalization. T2W intensities in 231 biopsy ROIs were significantly negatively correlated with GS (rS  = -0.21, p = 0.001), Decipher (rS  = -0.193, p = 0.003), and three-tier risk (rS  = -0.235, p < 0.001). The average T2W intensities in the aggressive ROIs were significantly lower than in the indolent ROIs after normalization. In conclusion, the automated triple-reference tissue normalization method significantly improved the discrimination between prostate cancer and normal prostate tissue. In addition, the normalized T2W intensities of cancer exhibited a significant association with tumor aggressiveness. By improving the quantitative utilization of the T2W in the assessment of prostate cancer on MRI, the new normalization method represents an important advance over clinical protocols that do not include sequences for the measurement of T2 relaxation times.

Deep Learning Framework with Multi-Head Dilated Encoders for Enhanced Segmentation of Cervical Cancer on Multiparametric Magnetic Resonance Imaging

T2-weighted magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) are essential components of cervical cancer diagnosis. However, combining these channels for the training of deep learning models is challenging due to image misalignment. Here, we propose a novel multi-head framework that uses dilated convolutions and shared residual connections for the separate encoding of multiparametric MRI images. We employ a residual U-Net model as a baseline, and perform a series of architectural experiments to evaluate the tumor segmentation performance based on multiparametric input channels and different feature encoding configurations. All experiments were performed on a cohort of 207 patients with locally advanced cervical cancer. Our proposed multi-head model using separate dilated encoding for T2W MRI and combined b1000 DWI and apparent diffusion coefficient (ADC) maps achieved the best median Dice similarity coefficient (DSC) score, 0.823 (confidence interval (CI), 0.595-0.797), outperforming the conventional multi-channel model, DSC 0.788 (95% CI, 0.568-0.776), although the difference was not statistically significant (p > 0.05). We investigated channel sensitivity using 3D GRAD-CAM and channel dropout, and highlighted the critical importance of T2W and ADC channels for accurate tumor segmentation. However, our results showed that b1000 DWI had a minor impact on the overall segmentation performance. We demonstrated that the use of separate dilated feature extractors and independent contextual learning improved the model's ability to reduce the boundary effects and distortion of DWI, leading to improved segmentation performance. Our findings could have significant implications for the development of robust and generalizable models that can extend to other multi-modal segmentation applications.

A new architecture combining convolutional and transformer-based networks for automatic 3D multi-organ segmentation on CT images

PURPOSE

Deep learning-based networks have become increasingly popular in the field of medical image segmentation. The purpose of this research was to develop and optimize a new architecture for automatic segmentation of the prostate gland and normal organs in the pelvic, thoracic, and upper gastro-intestinal (GI) regions.

METHODS

We developed an architecture which combines a shifted-window (Swin) transformer with a convolutional U-Net. The network includes a parallel encoder, a cross-fusion block, and a CNN-based decoder to extract local and global information and merge related features on the same scale. A skip connection is applied between the cross-fusion block and decoder to integrate low-level semantic features. Attention gates (AGs) are integrated within the CNN to suppress features in image background regions. Our network is termed "SwinAttUNet." We optimized the architecture for automatic image segmentation. Training datasets consisted of planning-CT datasets from 300 prostate cancer patients from an institutional database and 100 CT datasets from a publicly available dataset (CT-ORG). Images were linearly interpolated and resampled to a spatial resolution of (1.0 × 1.0× 1.5) mm3 . A volume patch (192 × 192 × 96) was used for training and inference, and the dataset was split into training (75%), validation (10%), and test (15%) cohorts. Data augmentation transforms were applied consisting of random flip, rotation, and intensity scaling. The loss function comprised Dice and cross-entropy equally weighted and summed. We evaluated Dice coefficients (DSC), 95th percentile Hausdorff Distances (HD95), and Average Surface Distances (ASD) between results of our network and ground truth data.

RESULTS

SwinAttUNet, DSC values were 86.54 ± 1.21, 94.15 ± 1.17, and 87.15 ± 1.68% and HD95 values were 5.06 ± 1.42, 3.16 ± 0.93, and 5.54 ± 1.63 mm for the prostate, bladder, and rectum, respectively. Respective ASD values were 1.45 ± 0.57, 0.82 ± 0.12, and 1.42 ± 0.38 mm. For the lung, liver, kidneys and pelvic bones, respective DSC values were: 97.90 ± 0.80, 96.16 ± 0.76, 93.74 ± 2.25, and 89.31 ± 3.87%. Respective HD95 values were: 5.13 ± 4.11, 2.73 ± 1.19, 2.29 ± 1.47, and 5.31 ± 1.25 mm. Respective ASD values were: 1.88 ± 1.45, 1.78 ± 1.21, 0.71 ± 0.43, and 1.21 ± 1.11 mm. Our network outperformed several existing deep learning approaches using only attention-based convolutional or Transformer-based feature strategies, as detailed in the results section.

CONCLUSIONS

We have demonstrated that our new architecture combining Transformer- and convolution-based features is able to better learn the local and global context for automatic segmentation of multi-organ, CT-based anatomy.

A Deep Learning Approach for Automatic Segmentation during Daily MRI-Linac Radiotherapy of Glioblastoma

Glioblastoma changes during chemoradiotherapy are inferred from high-field MRI before and after treatment but are rarely investigated during radiotherapy. The purpose of this study was to develop a deep learning network to automatically segment glioblastoma tumors on daily treatment set-up scans from the first glioblastoma patients treated on MRI-linac. Glioblastoma patients were prospectively imaged daily during chemoradiotherapy on 0.35T MRI-linac. Tumor and edema (tumor lesion) and resection cavity kinetics throughout the treatment were manually segmented on these daily MRI. Utilizing a convolutional neural network, an automatic segmentation deep learning network was built. A nine-fold cross-validation schema was used to train the network using 80:10:10 for training, validation, and testing. Thirty-six glioblastoma patients were imaged pre-treatment and 30 times during radiotherapy (n = 31 volumes, total of 930 MRIs). The average tumor lesion and resection cavity volumes were 94.56 ± 64.68 cc and 72.44 ± 35.08 cc, respectively. The average Dice similarity coefficient between manual and auto-segmentation for tumor lesion and resection cavity across all patients was 0.67 and 0.84, respectively. This is the first brain lesion segmentation network developed for MRI-linac. The network performed comparably to the only other published network for auto-segmentation of post-operative glioblastoma lesions. Segmented volumes can be utilized for adaptive radiotherapy and propagated across multiple MRI contrasts to create a prognostic model for glioblastoma based on multiparametric MRI.

Clinical evaluation on automatic segmentation results of convolutional neural networks in rectal cancer radiotherapy

Purpose

Image segmentation can be time-consuming and lacks consistency between different oncologists, which is essential in conformal radiotherapy techniques. We aimed to evaluate automatic delineation results generated by convolutional neural networks (CNNs) from geometry and dosimetry perspectives and explore the reliability of these segmentation tools in rectal cancer.

Methods

Forty-seven rectal cancer cases treated from February 2018 to April 2019 were randomly collected retrospectively in our cancer center. The oncologists delineated regions of interest (ROIs) on planning CT images as the ground truth, including clinical target volume (CTV), bladder, small intestine, and femoral heads. The corresponding automatic segmentation results were generated by DeepLabv3+ and ResUNet, and we also used Atlas-Based Autosegmentation (ABAS) software for comparison. The geometry evaluation was carried out using the volumetric Dice similarity coefficient (DSC) and surface DSC, and critical dose parameters were assessed based on replanning optimized by clinically approved or automatically generated CTVs and organs at risk (OARs), i.e., the Planref and Plantest. Pearson test was used to explore the correlation between geometric metrics and dose parameters.

Results

In geometric evaluation, DeepLabv3+ performed better in DCS metrics for the CTV (volumetric DSC, mean = 0.96, P< 0.01; surface DSC, mean = 0.78, P< 0.01) and small intestine (volumetric DSC, mean = 0.91, P< 0.01; surface DSC, mean = 0.62, P< 0.01), ResUNet had advantages in volumetric DSC of the bladder (mean = 0.97, P< 0.05). For critical dose parameters analysis between Planref and Plantest, there was a significant difference for target volumes (P< 0.01), and no significant difference was found for the ResUNet-generated small intestine (P > 0.05). For the correlation test, a negative correlation was found between DSC metrics (volumetric, surface DSC) and dosimetric parameters (δD95, δD95, HI, CI) for target volumes (P< 0.05), and no significant correlation was found for most tests of OARs (P > 0.05).

Conclusions

CNNs show remarkable repeatability and time-saving in automatic segmentation, and their accuracy also has a certain potential in clinical practice. Meanwhile, clinical aspects, such as dose distribution, may need to be considered when comparing the performance of auto-segmentation methods.

Deep Learning in MRI-guided Radiation Therapy: A Systematic Review

MRI-guided radiation therapy (MRgRT) offers a precise and adaptive approach to treatment planning. Deep learning applications which augment the capabilities of MRgRT are systematically reviewed. MRI-guided radiation therapy offers a precise, adaptive approach to treatment planning. Deep learning applications which augment the capabilities of MRgRT are systematically reviewed with emphasis placed on underlying methods. Studies are further categorized into the areas of segmentation, synthesis, radiomics, and real time MRI. Finally, clinical implications, current challenges, and future directions are discussed.

Resection cavity auto-contouring for patients with pediatric medulloblastoma using only CT information

PURPOSE

Target delineation for radiation therapy is a time-consuming and complex task. Autocontouring gross tumor volumes (GTVs) has been shown to increase efficiency. However, there is limited literature on post-operative target delineation, particularly for CT-based studies. To this end, we trained a CT-based autocontouring model to contour the post-operative GTV of pediatric patients with medulloblastoma.

METHODS

One hundred four retrospective pediatric CT scans were used to train a GTV auto-contouring model. Eighty patients were then preselected for contour visibility, continuity, and location to train an additional model. Each GTV was manually annotated with a visibility score based on the number of slices with a visible GTV (1 = < 25%, 2 = 25-50%, 3 = > 50-75%, and 4 = > 75-100%). Contrast and the contrast-to-noise ratio (CNR) were calculated for the GTV contour with respect to a cropped background image. Both models were tested on the original and pre-selected testing sets. The resulting surface and overlap metrics were calculated comparing the clinical and autocontoured GTVs and the corresponding clinical target volumes (CTVs).

RESULTS

Eighty patients were pre-selected to have a continuous GTV within the posterior fossa. Of these, 7, 41, 21, and 11 were visibly scored as 4, 3, 2, and 1, respectively. The contrast and CNR removed an additional 11 and 20 patients from the dataset, respectively. The Dice similarity coefficients (DSC) were 0.61 ± 0.29 and 0.67 ± 0.22 on the models without pre-selected training data and 0.55 ± 13.01 and 0.83 ± 0.17 on the models with pre-selected data, respectively. The DSC on the CTV expansions were 0.90 ± 0.13.

CONCLUSION

We successfully automatically contoured continuous GTVs within the posterior fossa on scans that had contrast > ± 10 HU. CT-Based auto-contouring algorithms have potential to positively impact centers with limited MRI access.

Comparison of Online-Onboard Adaptive Intensity-Modulated Radiation Therapy or Volumetric-Modulated Arc Radiotherapy With Image-Guided Radiotherapy for Patients With Gynecologic Tumors in Dependence on Fractionation and the Planning Target Volume Margin

Importance

Patients with newly diagnosed locally advanced cervical carcinomas or recurrences after surgery undergoing radiochemotherapy whose tumor is unsuited for a brachytherapy boost need high-dose percutaneous radiotherapy with small margins to compensate for clinical target volume deformations and set-up errors. Cone-beam computed tomography-based online adaptive radiotherapy (ART) has the potential to reduce planning target volume (PTV) margins below 5 mm for these tumors.

Objective

To compare online ART technologies with image-guided radiotherapy (IGRT) for gynecologic tumors.

Design, Setting, and Participants

This comparative effectiveness study comprised all 7 consecutive patients with gynecologic tumors who were treated with ART with artificial intelligence segmentation from January to May 2022 at the West German Cancer Center. All adapted treatment plans were reviewed for the new scenario of organs at risk and target volume. Dose distributions of adapted and scheduled plans optimized on the initial planning computed tomography scan were compared.

Exposure

Online ART for gynecologic tumors.

Main Outcomes and Measures

Target dose coverage with ART compared with IGRT for PTV margins of 5 mm or less in terms of the generalized equivalent uniform dose (gEUD) without increasing the gEUD for the organs at risk (bladder and rectum).

Results

The first 10 treatment series among 7 patients (mean [SD] age, 65.7 [16.5] years) with gynecologic tumors from a prospective observational trial performed with ART were compared with IGRT. For a clinical PTV margin of 5 mm, IGRT was associated with a median gEUD decrease in the interfractional clinical target volume of -1.5% (90% CI, -31.8% to 2.9%) for all fractions in comparison with the planned dose distribution. Online ART was associated with a decrease of -0.02% (90% CI, -3.2% to 1.5%), which was less than the decrease with IGRT (P < .001). This was not associated with an increase in the gEUD for the bladder or rectum. For a PTV margin of 0 mm, the median gEUD deviation with IGRT was -13.1% (90% CI, -47.9% to 1.6%) compared with 0.1% (90% CI, -2.3% to 6.6%) with ART (P < .001). The benefit associated with ART was larger for a PTV margin of 0 mm than of 5 mm (P = .004) due to spreading of the cold spot at the clinical target volume margin from fraction to fraction with a median SD of 2.4 cm (90% CI, 1.9-3.4 cm) for all patients.

Conclusions and Relevance

This study suggests that ART is associated with an improvement in the percentage deviation of gEUD for the interfractional clinical target volume compared with IGRT. As the gain of ART depends on fractionation and PTV margin, a strategy is proposed here to switch from IGRT to ART, if the delivered gEUD distribution becomes unfavorable in comparison with the expected distribution during the course of treatment.

Automated Contouring and Planning in Radiation Therapy: What Is 'Clinically Acceptable'?

Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is 'clinical acceptability'? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of 'clinical acceptability' and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.