Applicator reconstruction in cervical cancer brachytherapy: A systematic review of current methods, challenges, and AI-driven future directions.

Introduction: Magnetic resonance imaging (MRI) is the most common tool to examine glioblastoma. Preoperative MRI can be used to initial diagnosis, and surgery planning, while follow-up MRIs can be used to evaluate treatment responses, identify recurrency, and detect side effects. The follow-up MRIs are usually taken after the first-line therapy, such as maximal safe resection. In the past, radiologists manually segment the tumor regions from normal brain tissue on follow-up MRIs, which is time-consuming, error-prone, and challenging. Several deep-learning (DL) models have been developed utilizing preoperative images, but their performance has yet to be evaluated on follow-up MRIs. In this research, we built the largest follow-up MRI cohort (311 patients) to assess these DL models and their generalizability and performance on independent preoperative and follow-up images. We also made the first follow-up-based deep learning models for this specific task. Methods: All evaluation deep learning models (10 models) were trained by the Brain Tumor Segmentation challenge 2020 (BraTS’20) and evaluated by fifty pairs of preoperative and follow-up scans from our institution. The segmentation form our institution is evaluated by board certified radiologist. MRIs in the BraTS’20 dataset were all preoperative scans. After the evaluation, we randomly assigned 264 patients’ scans from our institution to the training dataset and 47 patients’ scans to the testing dataset. We compared three types of models in our follow-up deep learning model, including 1) UNet-3D, 2) UNet-3D+transfer-learning, and 3) UNet-3D+transfer-learning+baysian-learning. The benchmark for all models was the Dice similarity coefficient (DSC). DSC can measure the spatial overlap between model prediction and ground truth. The value of DSC is between zero to one. Zero means no overlap and one indicates complete overlap. Results: Our study demonstrates that the BraTS'20 trained models' performance decreased by 13.05% in independent preoperative MRI scans and 19.04% in follow-up MRI scans. The most significant mismatch regions were FLAIR hyperintense regions (3.68% drop in independent preoperative scans and 10.61% drop in independent follow-up scans) and Non-enhancing core (5.20% drop in independent preoperative scans and 11.99% drop in independent follow-up scans). Our best model can achieve the best DSC among three tumor regions compared to all evaluation models (FLAIR hyperintense regions: DSC 0.77 V.S. DSC 0.58; Enhancing tumor region: DSC 0.87 V.S. DSC 0.68; Non-enhancing tumor region: DSC 0.92 V.S. DSC 0.55). Conclusion: Maximal safe resection induced brain structure change, decreasing the performance of the preoperative-based DL model. Implementing a follow-up MRI-based segmentation model is essential to make accurate and generalizable results to address structural changes after maximal safe resection. Our follow-up DL model demonstrates the DSC score can be recovered. We commit to further developing the tool to assist radiologists in handling follow-up MRIs for glioblastoma patients. Citation Format: Kang Lin Hsieh, Tanjida Kabir, Luis Nunez-Rubiano, Yu-Chun Hsu, Yu Cai, Juan Rodriguez Quintero, Octavio Arevalo, Kangyi Zhao, Jackie Zhang, Jiguang Zhu Zhu, Roy Riascos, Xioaqian Jiang, Shayan Shams. A confident and operator-independent deep segmentation model to measure residual tumor volume in the follow-up MRIs for glioblastoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr LB067.

Can We Avoid Ureters as Organs at Risk With MRI-Based Brachytherapy for Cervical Cancer? A Dosimetric Feasibility Study

Metal artefacts in PET/CT images hamper diagnostic accuracy in head and neck cancer (HNC). The aim of this study is to characterise the clinical effects of metal artefacts on PET/CT in HNC and to inform decision-making concerning implementation of MAR techniques. We study a combined dual energy CT and inpainting-based metal artefact reduction (DECT-I-MAR) technique for PET/CT in three settings: (A) A dental phantom with a removable amalgam-filled tooth to evaluate the PET error in comparison to a known reference. (B) PET-positive patients with metallic implants to demonstrate the relationship between CT metal artefacts and PET error. (C) Metabolic tumour volumes delineated in PET-positive patients with metal implants to evaluate the clinical impact. In (A) DECT-I-MAR reduced the PET error significantly. In (B) we demonstrate an increasing PET error with increasing CT artefact severity in patients. In (C) it is shown that the presence of artefacts in the same axial slices as the tumour significantly decreases biomarker stability and increase delineation variability. This work shows the practical feasibility of DECT-I-MAR-based PET/CT imaging, and indicates a positive clinical impact of using the technique routinely for HNC patients. The impact of CT artefacts on PET is considerable, especially in workflows where quantitative PET biomarkers and tumour volumes are used. In such cases, and for patients with tumours in proximity of metals, we recommend that a MAR technique for PET/CT is employed.

MP43-02 LESSONS LEARNED IN APPLYING DEEP LEARNING TO FACILITATE PROSTATE MR-US FUSION BIOPSY WORKFLOW

Factors predicting MRI glioma segmentation accuracy in deep learning models: a systematic review and meta-analysis.

Background: This study aims to develop an automatic segmentation model based on U-Net architecture. The model will delineate the high-risk clinical target volume (HR-CTV) and pelvic organs at risk (OARs) in brachytherapy for cervical cancer. The goal is to improve the consistency and clinical efficiency of segmentation results. Methods: The automatic segmentation model was developed by U-Net architecture, and the Computed Tomography (CT) images of 102 cervical cancer patients receiving Three-Dimensional image-guided brachytherapy (3D IGBT) were used for network training (63 cases in training set, 20 cases in test set, and 19 cases in validation set). The segmentation objects included HR-CTV, sigmoid colon, rectum, bladder and small intestine. The accuracy of the automatic segmentation model was evaluated by Dice similarity coefficient (DSC) and Hausdorff distance (HD). In addition, the time efficiency was evaluated by comparing the time of manual delineation and the time of artificial intelligence (AI) assisted automatic delineation. Results: The auto-segmentation performance of HR-CTV and OARs was good, with an average DSC of 0.90 ± 0.03 and 0.85 ± 0.04, respectively. The DSC values of the rectum, sigmoid colon and bladder were 0.91 ± 0.04, 0.88 ± 0.06 and 0.86 ± 0.04, respectively. Among the organs at risk, the small intestine had the lowest segmentation data, with a DSC of only 0.77 ± 0.20 and a HD of 25.06 ± 16.24 mm. The automatic delineation took only 1.53 ± 0.03 minutes, while the manual delineation took the longest time. AI assisted manual delineation shortened the delineation time of HR-CTV and OARs by 5 minutes and 10 minutes, respectively. Conclusions: U-Net meets clinical expectations in the delineation of HR-CTV and OARs in brachytherapy for cervical cancer, and performs better than the traditional model in HR-CTV. However, the delineation results of small intestine and sigmoid colon need to be further verified by a larger sample size.

1. To develop a deep-learning segmentation model for automated measurement of maximal aortic diameter (Dmax) and volumes of aortic dissection components: true-lumen (TL), circulating false-lumen (CFL), and thrombus (Th) on CT angiography (CTA). 2. To assess the predictive value of these measures for adverse aortic remodeling in residual aortic dissection (RAD). This retrospective study included 322 patients from two centers. The segmentation model was trained on 120 patients (Center 1) and tested on an internal dataset (30 patients, Center 1) and an external dataset (10 patients, Center 2) in terms of Dice Similarity Coefficient (DSC). The model extracted Dmax, global false-lumen volume (FLGlo = CFL + Th), and local false-lumen volume (FLLoc, measured 3 cm around the largest diameter). Clinical validation was performed on 83 patients from Center1 (internal validation, 2-year follow-up) and 79 patients from Center2 (external validation, 4.5-year follow-up). The segmentation model achieved high accuracy (Center 1, DSC: 0.93 TL, 0.93 CFL, 0.87 Th; Center 2, DSC: 0.92 TL, 0.93 CFL, 0.84 Th) with strong agreement between automated and manual measurements. Aortic remodeling occurred in 39/83 patients (46.9%) from Center1 and 33/79 patients (41.7%) from Center2. Aortic remodeling occurred in 39/83 patients (47%) from Center1 and 33/80 (42%) from Center2. FLLoc outperformed Dmax and FLGlo (Center 1: AUC = 0.83, 0.73, and 0.76; Center 2: AUC = 0.77, 0.64, and 0.70). At optimal thresholds, FLLoc showed good predictive performance (Center 1: Sensitivity = 0.87, Specificity = 0.68). Deep-learning segmentation provides accurate aortic measurements. Local false-lumen volumes predict adverse aortic remodeling in RAD better than diameter and global false-lumen volumes. Question In residual aortic dissection (RAD) after type-A dissection, early identification of high-risk patients on initial CT angiography is crucial for endovascular treatment decisions. Findings False-lumen local volumes (3 cm around aortic dissection maximal diameters), obtained with an automatic deep-learning method, predict adverse remodeling better than diameter or global false-lumen volumes. Clinical relevance A deep-learning segmentation method of aortic dissection components on CTA, enabling automatic measurements of diameters and volumes is feasible. It provides local false-lumen volumes, a better predictive marker of adverse aortic remodeling than the currently used diameters and global volumes.

Image-guided brachytherapy for cervical cancer: A Canadian Brachytherapy Group survey

Enhanced histopathology of the immune system uses a precise, compartment-specific, and semi-quantitative evaluation of lymphoid organs in toxicology studies. The assessment of lymphocyte populations in tissues is subject to sampling variability and limited distinctive cytologic features of lymphocyte subpopulations as seen with hematoxylin and eosin (H&E) staining. Although immunohistochemistry is necessary for definitive characterization of T- and B-cell compartments, routine toxicologic assessments are based solely on H&E slides. Here, a deep learning (DL) model was developed using normal rats to quantify relevant compartments of the spleen, including periarteriolar lymphoid sheaths, follicles, germinal centers, and marginal zones from H&E slides. Slides were scanned, destained, dual labeled with CD3 and CD79a chromogenic immunohistochemistry, and rescanned to generate exact co-registered images that served as the ground truth for training and validation. The DL model identified individual splenic compartments with high accuracy (97.8% Dice similarity coefficient) directly from H&E-stained tissue. The DL model was utilized to study the normal range of lymphoid compartment area and cellularity. Future implementation of our DL model and expanding this approach to other lymphoid tissues have the potential to improve accuracy and precision in enhanced histopathology evaluation of the immune system with concurrent gains in time efficiency for the pathologist.

Aim To develop an optimal method for automated segmentation of atherosclerotic plaque structural components in optical coherence tomography (OCT) images using an ensemble of deep learning neural network models based on a comparison of nine artificial neural network architectures.Material and methods This study utilized a multidisciplinary OCT dataset obtained from examinations of 103 patients. Each OCT session was annotated as a set of two-dimensional binary masks corresponding to the pixel boundaries of four key morphological features of plaques: vascular lumen, fibrous cap, lipid core, and microvessels. Nine deep learning models, including U-Net, DeepLabV3, and others, were used to segment the anatomical structures. Model hyperparameters were tuned using Bayesian optimization, and the performance was assessed using the Dice Similarity Coefficient (DSC) metric.Results The models demonstrated high segmentation accuracy for the vascular lumen (DSC: 0.987) and moderate accuracy for the fibrous cap (DSC: 0.736) and lipid core (DSC: 0.751). Microvessel segmentation proved more challenging, with a final DSC accuracy of 61%. A weighted ensemble of models, accounting for the uneven representation of different morphological structures and model confidence, achieved an average DSC of 88.2%, which significantly improved the overall accuracy compared to individual models. This accuracy value exceeds those of all individual models, including the highest DSC values of 0.784 (for microvessels) and 0.751 (for lipid core), indicating a consistent improvement in the segmentation accuracy by integrating the models.Conclusion The study confirms the effectiveness of the proposed strategy for segmentation of atherosclerotic plaques in OCT images. This strategy is based on using specialized models for various morphological features and a weighted ensemble adapted to the uneven representation of different morphological structures and morphological complexity. This approach provided a high segmentation accuracy despite the pronounced inequality in the representation of classes. The study results can contribute to the development of decision support methods in cardiology aimed at improving diagnostic accuracy and treatment of cardiovascular diseases.

Three-dimensional (3D) prostate image segmentation is useful for cancer diagnosis and therapy guidance, but can be time-consuming to perform manually and involves varying levels of difficulty and interoperator variability within the prostatic base, midgland (MG), and apex. In this study, the authors measured accuracy and interobserver variability in the segmentation of the prostate on T2-weighted endorectal magnetic resonance (MR) imaging within the whole gland (WG), and separately within the apex, midgland, and base regions. The authors collected MR images from 42 prostate cancer patients. Prostate border delineation was performed manually by one observer on all images and by two other observers on a subset of ten images. The authors used complementary boundary-, region-, and volume-based metrics [mean absolute distance (MAD), Dice similarity coefficient (DSC), recall rate, precision rate, and volume difference (ΔV)] to elucidate the different types of segmentation errors that they observed. Evaluation for expert manual and semiautomatic segmentation approaches was carried out. Compared to manual segmentation, the authors' semiautomatic approach reduces the necessary user interaction by only requiring an indication of the anteroposterior orientation of the prostate and the selection of prostate center points on the apex, base, and midgland slices. Based on these inputs, the algorithm identifies candidate prostate boundary points using learned boundary appearance characteristics and performs regularization based on learned prostate shape information. The semiautomated algorithm required an average of 30 s of user interaction time (measured for nine operators) for each 3D prostate segmentation. The authors compared the segmentations from this method to manual segmentations in a single-operator (mean whole gland MAD = 2.0 mm, DSC = 82%, recall = 77%, precision = 88%, and ΔV = - 4.6 cm(3)) and multioperator study (mean whole gland MAD = 2.2 mm, DSC = 77%, recall = 72%, precision = 86%, and ΔV = - 4.0 cm(3)). These results compared favorably with observed differences between manual segmentations and a simultaneous truth and performance level estimation reference for this data set (whole gland differences as high as MAD = 3.1 mm, DSC = 78%, recall = 66%, precision = 77%, and ΔV = 15.5 cm(3)). The authors found that overall, midgland segmentation was more accurate and repeatable than the segmentation of the apex and base, with the base posing the greatest challenge. The main conclusions of this study were that (1) the semiautomated approach reduced interobserver segmentation variability; (2) the segmentation accuracy of the semiautomated approach, as well as the accuracies of recently published methods from other groups, were within the range of observed expert variability in manual prostate segmentation; and (3) further efforts in the development of computer-assisted segmentation would be most productive if focused on improvement of segmentation accuracy and reduction of variability within the prostatic apex and base.

BackgroundNasopharyngeal carcinoma (NPC), an endemic malignancy in Southeast Asia and southern China, necessitates precise delineation of the gross tumor volume (GTV) for radiotherapy to optimize patient prognosis. Positron emission tomography (PET) imaging offers valuable metabolic insights to guide radiotherapy planning but is hampered by manual GTV segmentation, which is labor-intensive and prone to inter- and intra-observer variability. Conventional segmentation methods are inherently limited, and comparative evaluations of deep learning (DL) frameworks for PET-based primary NPC lesion segmentation remain scarce. Thus, this study aimed to optimize the delineation of primary NPC radiotherapy target volumes by leveraging PET-image-based DL segmentation technology, with the goal of enhancing both the precision and efficiency of lesion delineation.MethodsResearchers retrospectively collected PET imaging data from 212 NPC patients at the Affiliated Hospital of Guangdong Medical University. The patients were randomly divided into training (170 patients) and testing (42 patients) datasets. A radiation oncologist and a nuclear medicine physician collaboratively delineated the cancer lesion boundaries through consensus. After data preprocessing, three DL models (Res-Unet, Nn-Unet, and Nn-Former) were used to automatically segment the lesions. Training was based on the training dataset. During evaluation, the models’ segmentation performance was comprehensively assessed using Dice similarity coefficient (DSC) and Hausdorff distance (HD). A visual analysis of the results was also conducted to intuitively understand the models’ segmentation capabilities.ResultsIn the training set, Nn-Unet achieved the highest DSC of 0.869, whereas in the testing set, its DSC was 0.833. The DSC for Nn-Former hovered around 0.8 in both the training and testing sets. In contrast, Res-Unet demonstrated the lowest DSC values among the three models, particularly in the testing set (DSC =0.794). Statistical analysis revealed that the DSC of Nn-Unet was significantly higher than that of both Res-Unet and Nn-Former in the training set (P<0.01 for both comparisons). Regarding the 95% HD and average surface distance (ASD) values, Nn-Unet outperformed the other two models in both the training and testing sets. However, Res-Unet exhibited a much higher HD value in the testing set compared to the training set. The Loss curves for all models gradually decreased as training progressed, indicating that the models were learning relevant features of NPC lesions. The final Loss value for Res-Unet was approximately 0.7, whereas Nn-Unet and Nn-Former had final Loss values below 0.8.ConclusionsThe PET-image-based automatic segmentation model for the primary tumor of NPC established in this study demonstrates the clinical potential of Nn-Unet in primary lesion of NPC segmentation tasks.

We report a study that validates the impact of diffusion-perfusion mismatch in a deep learning (DL) model predicting the final infarction lesion from baseline magnetic resonance imaging (MRI). From 472 consecutive patients with acute ischemic stroke, we gathered baseline and follow-up MRI having intervals of 3–7 days, and initial and final infarction lesions were segmented. Four U-Net-based DL models from baseline MRI with different combinations of diffusion-weighted imaging (DWI), perfusion-weighted imaging (PWI) maps, and initial diffusion-restricted lesion prediction map (Pred <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">init</sub> map) were trained to predict the final infarction lesion. Five-fold cross-validation was used for training and testing. As an external test set, 55 patients from another institution were analyzed. Dice similarity coefficient (DSC) was compared between the models and subgroups according to the presence of lesion growth and/or diffusion-perfusion mismatch. The model using the PWI maps and Pred <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">init</sub> map showed the best mean DSC (0.422 and 0.486 for internal and external test set, respectively). This model showed better performance in predicting rapid lesion growth compared with the baseline model (mean DSC difference, 0.040; 95% confidence interval: 0.018–0.062). Using the PWI map with initial diffusion-restricted lesion prediction improved the performance of DL model in predicting the final infarction lesion from baseline MRI.

This study evaluated the performance of a multi-stage Segmentation Residual Network (SegResNet)-based deep learning (DL) model for the automatic segmentation of cone-beam computed tomography (CBCT) images of patients with stage III and IV periodontitis. Seventy pre-processed CBCT scans from patients undergoing periodontal rehabilitation were used for training and validation. The model was tested on 10 CBCT scans independent from the training dataset by comparing results with semi-automatic (SA) segmentations. Segmentation accuracy was assessed using the Dice similarity coefficient (DSC), Intersection over Union (IoU), and Hausdorff distance 95th percentile (HD95). Linear periodontal measurements were performed on four tooth surfaces to assess the validity of the DL segmentation in the periodontal region. The DL model achieved a mean DSC of 0.9650 ± 0.0097, with an IoU of 0.9340 ± 0.0180 and HD95 of 0.4820 mm ± 0.1269 mm, showing strong agreement with SA segmentation. Linear measurements revealed high statistical correlations between the mesial, distal, and lingual surfaces, with intraclass correlation coefficients (ICC) of 0.9442 (p < 0.0001), 0.9232 (p < 0.0001), and 0.9598(p < 0.0001), respectively, while buccal measurements revealed lower consistency, with an ICC of 0.7481 (p < 0.0001). The DL method reduced the segmentation time by 47 times compared to the SA method. Acquired 3D models may enable precise treatment planning in cases where conventional diagnostic modalities are insufficient. However, the robustness of the model must be increased to improve its general reliability and consistency at the buccal aspect of the periodontal region. This study presents a DL model for the CBCT-based segmentation of periodontal defects, demonstrating high accuracy and a 47-fold time reduction compared to SA methods, thus improving the feasibility of 3D diagnostics for advanced periodontitis.

Kidney volume is associated with renal function and the severity of renal diseases, thus accurate assessment of the kidney is important. Although the voxel count method is reported to be more accurate than several methods, its laborious and time-consuming process is considered as a main limitation. In need of a new technology that is fast and as accurate as the manual voxel count method, the aim of this study was to develop the first deep learning model for automatic kidney detection and volume estimation from computed tomography (CT) images of dogs. A total of 182,974 image slices from 386 CT scans of 211 dogs were used to develop this deep learning model. Owing to the variance of kidney size and location in dogs compared to humans, several processing methods and an architecture based on UNEt Transformers which is known to show promising results for various medical image segmentation tasks including this study. Combined loss function and data augmentation were applied to elevate the performance of the model. The Dice similarity coefficient (DSC) which shows the similarity between manual segmentation and automated segmentation by deep-learning model was 0.915 ± 0.054 (mean ± SD) with post-processing. Kidney volume agreement analysis assessing the similarity between the kidney volume estimated by manual voxel count method and the deep-learning model was r = 0.960 (p < 0.001), 0.95 from Lin's concordance correlation coefficient (CCC), and 0.975 from the intraclass correlation coefficient (ICC). Kidney volume was positively correlated with body weight (BW), and insignificantly correlated with body conditions score (BCS), age, and sex. The correlations between BW, BCS, and kidney volume were as follows: kidney volume = 3.701 × BW + 11.962 (R2 = 0.74, p < 0.001) and kidney volume = 19.823 × BW/BCS index + 10.705 (R2 = 0.72, p < 0.001). The deep learning model developed in this study is useful for the automatic estimation of kidney volume. Furthermore, a reference range established in this study for CT-based normal kidney volume considering BW and BCS can be helpful in assessment of kidney in dogs.