Search

Accurate detection and segmentation of diffuse large B-cell lymphoma (DLBCL) from PET images has important implications for estimation of total metabolic tumor volume, radiomics analysis, surgical intervention and radiotherapy. Manual segmentation of tumors in whole-body PET images is time-consuming, labor-intensive and operator-dependent. In this work, we develop and validate a fast and efficient three-step cascaded deep learning model for automated detection and segmentation of DLBCL tumors from PET images. As compared to a single end-to-end network for segmentation of tumors in whole-body PET images, our three-step model is more effective (improves 3D Dice score from 58.9% to 78.1%) since each of its specialized modules, namely the slice classifier, the tumor detector and the tumor segmentor, can be trained independently to a high degree of skill to carry out a specific task, rather than a single network with suboptimal performance on overall segmentation., Comment: 8 pages, 3 figures, 3 tables

This study performs comprehensive evaluation of four neural network architectures (UNet, SegResNet, DynUNet, and SwinUNETR) for lymphoma lesion segmentation from PET/CT images. These networks were trained, validated, and tested on a diverse, multi-institutional dataset of 611 cases. Internal testing (88 cases; total metabolic tumor volume (TMTV) range [0.52, 2300] ml) showed SegResNet as the top performer with a median Dice similarity coefficient (DSC) of 0.76 and median false positive volume (FPV) of 4.55 ml; all networks had a median false negative volume (FNV) of 0 ml. On the unseen external test set (145 cases with TMTV range: [0.10, 2480] ml), SegResNet achieved the best median DSC of 0.68 and FPV of 21.46 ml, while UNet had the best FNV of 0.41 ml. We assessed reproducibility of six lesion measures, calculated their prediction errors, and examined DSC performance in relation to these lesion measures, offering insights into segmentation accuracy and clinical relevance. Additionally, we introduced three lesion detection criteria, addressing the clinical need for identifying lesions, counting them, and segmenting based on metabolic characteristics. We also performed expert intra-observer variability analysis revealing the challenges in segmenting ``easy'' vs. ``hard'' cases, to assist in the development of more resilient segmentation algorithms. Finally, we performed inter-observer agreement assessment underscoring the importance of a standardized ground truth segmentation protocol involving multiple expert annotators. Code is available at: https://github.com/microsoft/lymphoma-segmentation-dnn, Comment: 12 pages, 10 figures, 2 tables

The time-consuming task of manual segmentation challenges routine systematic quantification of disease burden. Convolutional neural networks (CNNs) hold significant promise to reliably identify locations and boundaries of tumors from PET scans. We aimed to leverage the need for annotated data via semi-supervised approaches, with application to PET images of diffuse large B-cell lymphoma (DLBCL) and primary mediastinal large B-cell lymphoma (PMBCL). We analyzed 18F-FDG PET images of 292 patients with PMBCL (n=104) and DLBCL (n=188) (n=232 for training and validation, and n=60 for external testing). We employed FCM and MS losses for training a 3D U-Net with different levels of supervision: i) fully supervised methods with labeled FCM (LFCM) as well as Unified focal and Dice loss functions, ii) unsupervised methods with Robust FCM (RFCM) and Mumford-Shah (MS) loss functions, and iii) Semi-supervised methods based on FCM (RFCM+LFCM), as well as MS loss in combination with supervised Dice loss (MS+Dice). Unified loss function yielded higher Dice score (mean +/- standard deviation (SD)) (0.73 +/- 0.03; 95% CI, 0.67-0.8) compared to Dice loss (p-value<0.01). Semi-supervised (RFCM+alpha*LFCM) with alpha=0.3 showed the best performance, with a Dice score of 0.69 +/- 0.03 (95% CI, 0.45-0.77) outperforming (MS+alpha*Dice) for any supervision level (any alpha) (p<0.01). The best performer among (MS+alpha*Dice) semi-supervised approaches with alpha=0.2 showed a Dice score of 0.60 +/- 0.08 (95% CI, 0.44-0.76) compared to another supervision level in this semi-supervised approach (p<0.01). Semi-supervised learning via FCM loss (RFCM+alpha*LFCM) showed improved performance compared to supervised approaches. Considering the time-consuming nature of expert manual delineations and intra-observer variabilities, semi-supervised approaches have significant potential for automated segmentation workflows.

Segmentation of lymphoma lesions is challenging due to their varied sizes and locations in whole-body PET scans. This work presents a fully-automated segmentation technique using a multi-center dataset of diffuse large B-cell lymphoma (DLBCL) with heterogeneous characteristics. We utilized a dataset of [18F]FDG-PET scans (n=194) from two different imaging centers, including cases with primary mediastinal large B-cell lymphoma (PMBCL) (n=104). Automated brain and bladder removal approaches were utilized as preprocessing steps to tackle false positives caused by normal hypermetabolic uptake in these organs. Our segmentation model is a convolutional neural network (CNN) based on a 3D U-Net architecture that includes squeeze and excitation (SE) modules. Hybrid distribution, region, and boundary-based losses (Unified Focal and Mumford-Shah (MS)) were utilized that showed the best performance compared to other combinations (p<0.05). Cross-validation between different centers, DLBCL and PMBCL cases, and three random splits were applied on train/validation data. The ensemble of these six models achieved a Dice similarity coefficient (DSC) of 0.77 +- 0.08 and Hausdorff distance (HD) of 16.5 +-12.5. Our 3D U-net model with SE modules for segmentation with hybrid loss performed significantly better (p<0.05) as compared to the 3D U-Net (without SE modules) using the same loss function (Unified Focal and MS loss) (DSC= 0.64 +-0.21 and HD= 26.3 +- 18.7). Our model can facilitate a fully automated quantification pipeline in a multi-center context that opens the possibility for routine reporting of total metabolic tumor volume (TMTV) and other metrics shown useful for the management of lymphoma.

Purpose: The XCAT phantom allows for highly sophisticated multimodality imaging research. It includes a complete set of organs, muscle, bone, soft tissue, while also accounting for age, sex, and body mass index (BMI), which allows phantom studies to be performed at a population scale. At the same time, the XCAT phantom does not currently include the lymphatic system, critical for evaluating bulky nodal malignancies in lymphoma. We aimed to incorporate a full lymphatic system into the XCAT phantom and to generate realistic simulated images via guidance from lymphoma patient studies. Methods: A template lymphatic system was extended based on known anatomy was used to define 276 lymph nodes and corresponding vessels using non-uniform rational basis spline (NURBS) surfaces. Lymph node properties were modified using the Rhinoceros 3D viewing software. The XCAT general parameter script was used to input organ concentrations and generate binary files with uptake and attenuation information. Results: Lymph nodes can be scaled, stretched, and translated within the intuitive Rhinoceros interface, to allow for realistic simulation of different lymph node pathologies. Bulky, heterogeneous PMBCL tumours were generated in the mediastinum using expanded lymph nodes. Our results suggest that optimized thresholding provides better accuracy for determining total metabolic tumour volume (TMTV) of PMBCL tumours, while the gradient method was most accurate for total lesion glycolysis (TLG). Conclusions: An upgraded XCAT phantom with a fully simulated lymphatic system was created. Distributed to the research community, the XCAT phantom with the new lymphatic system has the potential of enabling studies to optimize image quality and quantitation, towards improved assessment of lymphoma including predictive modeling (e.g. improved TMTV and radiomics research)., Comment: 27 pages, 9 figures, 2 tables, 4 supplemental figures

String gas cosmology is rewritten in the Einstein frame. In an effective theory in which a gas of closed strings is coupled to a dilaton gravity background without any potential for the dilaton, the Hagedorn phase which is quasi-static in the string frame corresponds to an expanding, non-accelerating phase from the point of view of the Einstein frame. The Einstein frame curvature singularity which appears in this toy model is related to the blowing up of the dilaton in the string frame. However, for large values of the dilaton, the toy model clearly is inapplicable. Thus, there must be a new string phase which is likely to be static with frozen dilaton. With such a phase, the horizon problem can be successfully addressed in string gas cosmology. The generation of cosmological perturbations in the Hagedorn phase seeded by a gas of long strings in thermal equilibrium is reconsidered, both from the point of view of the string frame (in which it is easier to understand the generation of fluctuations) and the Einstein frame (in which the evolution equations are well known). It is shown that fixing the dilaton at some early stage is important in order to obtain a scale-invariant spectrum of cosmological fluctuations in string gas cosmology., Comment: 11 pages, 3 figures