Lymphoma Segmentation in PET Images Based on Multi-view and Conv3D Fusion Strategy

Hu, Haigen; Shen, Leizhao; Zhou, Tongxue; Decazes, Pierre; Véra, Pierre; Ruan, Su

doi:10.1109/isbi45749.2020.9098595

Cited by 9 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table II lists integrative information of studies about some subtypes and in single modality or multimodality. Hu et al 14 trained two subnetworks in 2D multiview and 3D, and then captured features in different-axis observations for lymphoma segmentation in PET samples. They divided 109 samples into 80 for training and 29 for test, and achieved the DSC of 66.64%.…”

Section: As For the Comparison With Four Fusion Baselines Tablementioning

confidence: 99%

“…utilized a domain transferred CNN to identify normal physiological FDG uptake from the input PET images for a whole‐body PET‐CT lymphoma study. Recently, Hu et al 14 . trained two subnetworks in 2D multiview and 3D, and then captured features in different‐axis observations for lymphoma segmentation in PET images.…”

Section: Introductionmentioning

confidence: 99%

“…Another research proposed a coarse‐to‐fine adversarial network to achieve natural killer/T‐cell lymphoma segmentation in PET/CT images 4 . Until recently, the most of researches still focus on extracting feature representations from single modality without an in‐depth consideration on complementary information 13,14 …”

Section: Introductionmentioning

confidence: 99%

“…With the development of transfer learning, Bi et al 13 utilized a domain transferred CNN to identify normal physiological FDG uptake from the input PET images for a whole-body PET-CT lymphoma study. Recently, Hu et al 14 trained two subnetworks in 2D multiview and 3D, and then captured features in differentaxis observations for lymphoma segmentation in PET images. Another research proposed a coarse-to-fine adversarial network to achieve natural killer/T-cell lymphoma segmentation in PET/CT images.…”

Section: Introductionmentioning

confidence: 99%

“…4 Until recently, the most of researches still focus on extracting feature representations from single modality without an in-depth consideration on complementary information. 13,14 Specially, the diffuse subtype like DLBCL can spread throughout the whole body, and thus multi-modality segmentation may further enhance the disease analysis. In addition, making full advantage of various imaging techniques, such as PET and CT, requires fusion methods of complementary information, which may enable much better monitoring of heterogeneous tumors as well as better investigation of tumor invasion of adjacent tissues and clearer interpretation of disease prognosis.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Diffuse large B‐cell lymphoma segmentation in PET‐CT images via hybrid learning for feature fusion

et al. 2021

View full text Add to dashboard Cite

Purpose: Diffuse large B-cell lymphoma (DLBCL) is an aggressive type of lymphoma with high mortality and poor prognosis that especially has a high incidence in Asia. Accurate segmentation of DLBCL lesions is crucial for clinical radiation therapy. However, manual delineation of DLBCL lesions is tedious and time-consuming. Automatic segmentation provides an alternative solution but is difficult for diffuse lesions without the sufficient utilization of multimodality information. Our work is the first study focusing on positron emission tomography and computed tomography (PET-CT) feature fusion for the DLBCL segmentation issue. We aim to improve the fusion performance of complementary information contained in PET-CT imaging with a hybrid learning module in the supervised convolutional neural network. Methods: First, two encoder branches extract single-modality features, respectively. Next, the hybrid learning component utilizes them to generate spatial fusion maps which can quantify the contribution of complementary information. Such feature fusion maps are then concatenated with specific-modality (i.e., PET and CT) feature maps to obtain a representation of the final fused feature maps in different scales. Finally, the reconstruction part of our network creates a prediction map of DLBCL lesions by integrating and up-sampling the final fused feature maps from encoder blocks in different scales. Results: The ability of our method was evaluated to detect foreground and segment lesions in three independent body regions (nasopharynx, chest, and abdomen) of a set of 45 PET-CT scans. Extensive ablation experiments compared our method to four baseline techniques for multimodality fusion (input-level (IL) fusion, multichannel (MC) strategy, multibranch (MB) strategy, and quantitative weighting (QW) fusion). The results showed that our method achieved a high detection accuracy (99.63% in the nasopharynx, 99.51% in the chest, and 99.21% in the abdomen) and had the superiority in segmentation performance with the mean dice similarity coefficient (DSC) of 73.03% and the modified Hausdorff distance (MHD) of 4.39 mm, when compared with the baselines (DSC: IL:

show abstract

Section: As For the Comparison With Four Fusion Baselines Tablementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Diffuse large B‐cell lymphoma segmentation in PET‐CT images via hybrid learning for feature fusion

et al. 2021

View full text Add to dashboard Cite

show abstract

Deep PET/CT Fusion with Dempster-Shafer Theory for Lymphoma Segmentation

Ling¹,

Denœux²,

Tonnelet³

et al. 2021

Machine Learning in Medical Imaging

View full text Add to dashboard Cite

Multimodal deep learning model on interim [18F]FDG PET/CT for predicting primary treatment failure in diffuse large B-cell lymphoma

Cheng

Shi²,

Huang³

et al. 2022

Eur Radiol

View full text Add to dashboard Cite

Purpose: Prediction of primary treatment failure (PTF) is necessary for patients suffering from diffuse large B-cell lymphoma (DLBCL), since it serves as a prominent means for enhancing front-line outcomes. Utilizing interim 18 F-Fluorodeoxyglucose (FDG) positron emission tomography and computed tomography (PET/CT) image data, we aimed to construct multimodal deep learning (MDL) models to predict possible PTF of low-risk DLBCL, which could enable individualized treatment decision-making in clinical practice.Methods: From June 2016 to November 2020, 205 DLBCL patients undergoing interim 18 F-FDG PET-CT scans and the front-line standard-of-care were enrolled. We also collected other 44 patients for the external validation. We built a powerful backbone by redesigning the famous visual recognition network named Conv-LSTM in aspects of network architecture and learning strategy. On top of our improved backbone, multiple MDL models using different feature fusion strategies were developed and compared, including pixel intermixing model, separate channel model, separate branch model, quantitative weighting model, and hybrid learning model. Moreover, we proposed to use a contrastive training objective in the above best model to enhance the modal correlation of semantic embeddings for further improving prediction performance. For visualization, the region of interest was instructed using an activation map.Results: The MDL model using the hybrid learning strategy provided the best performance in predicting possible PTF with the accuracy of 89.76% (95% con dence interval [CI]: 84.85%-93.20%) in the test cohort. After further optimized by contrastive objective training, the accuracy was improved to 91.22% (95% CI: 86.55%-94.37%). The AUCs of contrastive hybrid learning achieved 0.926 and 0.925 in the test cohort and external validation cohort, respectively. Conclusion: Our model showed outstanding performance for predicting PTF of low-risk DLBCL and hold promise of improving clinical individualized treatment strategies.

show abstract

Lymphoma Segmentation in PET Images Based on Multi-view and Conv3D Fusion Strategy

Cited by 9 publications

References 11 publications

Diffuse large B‐cell lymphoma segmentation in PET‐CT images via hybrid learning for feature fusion

Diffuse large B‐cell lymphoma segmentation in PET‐CT images via hybrid learning for feature fusion

Deep PET/CT Fusion with Dempster-Shafer Theory for Lymphoma Segmentation

Multimodal deep learning model on interim [18F]FDG PET/CT for predicting primary treatment failure in diffuse large B-cell lymphoma

Contact Info

Product

Resources

About