Segmentation and Risk Score Prediction of Head and Neck Cancers in PET/CT Volumes with 3D U-Net and Cox Proportional Hazard Neural Networks

Yousefirizi, Fereshteh; Janzen, Ian; Dubljevic, Natalia; Liu, Yueh-En; Hill, Chloe; MacAulay, Calum E.; Rahmim, Arman

doi:10.1007/978-3-030-98253-9_22

Cited by 9 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [65], Yousefirizi et al (team "BCIOqurit") used a 3D nnU-Net with SE normalization [28] trained on a leave-one-center-out with a combination of a "unified" focal and Mumford-Shah losses taking the advantage of distribution, region, and boundary-based loss functions.…”

Section: Results: Reporting Of Segmentation Task Outcomementioning

confidence: 99%

“…In this section, we present the algorithms and results of participants who submitted a paper [45,33,39,65,46,17,51,48,9,16,67,6,37,43,32,21,62,53,12,59,52,1,60]. An exhaustive list of the results can be seen on the leaderboard 9 .…”

Section: Results: Reporting Of Segmentation Task Outcomementioning

confidence: 99%

“…In [65], Yousefirizi et al (team "BCIOqurit") proposed training a proportional hazard Cox model with a multilayer perceptron neural net backbone to predict the score for each patient. This Cox model was trained on a number of PET and CT radiomics features extracted from the segmented lesions, patient demographics, and encoder features provided from the penultimate layer of a multi-input 2D PET/CT convolutional neural network tasked with predicting time-to-event for each lesion.…”

Section: Results: Reporting Of Challenge Outcomementioning

confidence: 99%

“…Individual participants' papers reporting their methods and results were submitted to the challenge organizers. Reviews were organized by the organizers and the papers of the participants are published in the LNCS challenges proceedings [60,1,52,56,59,12,53,62,21,32,43,37,54,6,67,16,9,48,49,58,40,51,17,46,65,39,33,45,27]. When participating in multiple tasks, participants could submit one or multiple papers.…”

Section: Introduction: Research Contextmentioning

confidence: 99%

See 3 more Smart Citations

Overview of the HECKTOR Challenge at MICCAI 2020: Automatic Head and Neck Tumor Segmentation in PET/CT

Andrearczyk

Oreiller

Jreige

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper presents an overview of the second edition of the HEad and neCK TumOR (HECKTOR) challenge, organized as a satellite event of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2021. The challenge is composed of three tasks related to the automatic analysis of PET/CT images for patients with Head and Neck cancer (H&N), focusing on the oropharynx region. Task 1 is the automatic segmentation of H&N primary Gross Tumor Volume (GTVt) in FDG-PET/CT images. Task 2 is the automatic prediction of Progression Free Survival (PFS) from the same FDG-PET/CT. Finally, Task 3 is the same as Task 2 with ground truth GTVt annotations provided to the participants. The data were collected from six centers for a total of 325 images, split into 224 training and 101 testing cases. The interest in the challenge was highlighted by the important participation with 103 registered teams and 448 result submissions. The best methods obtained a Dice Similarity Coefficient (DSC) of 0.7591 in the first task, and a Concordance index (C-index) of 0.7196 and 0.6978 in Tasks 2 and 3, respectively. In all tasks, simplicity of the approach was found to be key to ensure generalization performance. The comparison of the PFS prediction performance in Tasks 2 and 3 suggests that providing the GTVt contour was not crucial to achieve best results, which indicates that fully automatic methods can be used. This potentially obviates the need for GTVt contouring, opening avenues for reproducible and large scale radiomics studies including thousands potential subjects. equal contribution equal contribution

show abstract

Section: Results: Reporting Of Segmentation Task Outcomementioning

confidence: 99%

Section: Results: Reporting Of Segmentation Task Outcomementioning

confidence: 99%

Section: Results: Reporting Of Challenge Outcomementioning

confidence: 99%

Section: Introduction: Research Contextmentioning

confidence: 99%

See 2 more Smart Citations

Overview of the HECKTOR Challenge at MICCAI 2020: Automatic Head and Neck Tumor Segmentation in PET/CT

Andrearczyk

Oreiller

Jreige

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The final ensembled prediction was generated by averaging all fourteen predictions and thresholding the resulting mask to 0.5. In, 59 Yousefirizi et al used a 3D nnU-Net with SE normalization trained on a leave-one-center-out with a combination of a "unified" focal and Mumford-Shah losses, leveraging the advantage of distribution, region, and boundary-based loss functions. Lastly, Ren et al 60 proposed a 3D nnU-Net with various PET normalization techniques, namely, PET-clip and PET-sin.…”

Section: The Current State-of-the-art Methods For Handn Tumor Segment...mentioning

confidence: 99%

SwinCross: Cross‐modal Swin transformer for head‐and‐neck tumor segmentation in PET/CT images

Li,

Chen,

Jang

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundRadiotherapy (RT) combined with cetuximab is the standard treatment for patients with inoperable head and neck cancers. Segmentation of head and neck (H&N) tumors is a prerequisite for radiotherapy planning but a time‐consuming process. In recent years, deep convolutional neural networks (DCNN) have become the de facto standard for automated image segmentation. However, due to the expensive computational cost associated with enlarging the field of view in DCNNs, their ability to model long‐range dependency is still limited, and this can result in sub‐optimal segmentation performance for objects with background context spanning over long distances. On the other hand, Transformer models have demonstrated excellent capabilities in capturing such long‐range information in several semantic segmentation tasks performed on medical images.PurposeDespite the impressive representation capacity of vision transformer models, current vision transformer‐based segmentation models still suffer from inconsistent and incorrect dense predictions when fed with multi‐modal input data. We suspect that the power of their self‐attention mechanism may be limited in extracting the complementary information that exists in multi‐modal data. To this end, we propose a novel segmentation model, debuted, Cross‐modal Swin Transformer (SwinCross), with cross‐modal attention (CMA) module to incorporate cross‐modal feature extraction at multiple resolutions.MethodsWe propose a novel architecture for cross‐modal 3D semantic segmentation with two main components: (1) a cross‐modal 3D Swin Transformer for integrating information from multiple modalities (PET and CT), and (2) a cross‐modal shifted window attention block for learning complementary information from the modalities. To evaluate the efficacy of our approach, we conducted experiments and ablation studies on the HECKTOR 2021 challenge dataset. We compared our method against nnU‐Net (the backbone of the top‐5 methods in HECKTOR 2021) and other state‐of‐the‐art transformer‐based models, including UNETR and Swin UNETR. The experiments employed a five‐fold cross‐validation setup using PET and CT images.ResultsEmpirical evidence demonstrates that our proposed method consistently outperforms the comparative techniques. This success can be attributed to the CMA module's capacity to enhance inter‐modality feature representations between PET and CT during head‐and‐neck tumor segmentation. Notably, SwinCross consistently surpasses Swin UNETR across all five folds, showcasing its proficiency in learning multi‐modal feature representations at varying resolutions through the cross‐modal attention modules.ConclusionsWe introduced a cross‐modal Swin Transformer for automating the delineation of head and neck tumors in PET and CT images. Our model incorporates a cross‐modality attention module, enabling the exchange of features between modalities at multiple resolutions. The experimental results establish the superiority of our method in capturing improved inter‐modality correlations between PET and CT for head‐and‐neck tumor segmentation. Furthermore, the proposed methodology holds applicability to other semantic segmentation tasks involving different imaging modalities like SPECT/CT or PET/MRI. Code:https://github.com/yli192/SwinCross_CrossModalSwinTransformer_for_Medical_Image_Segmentation

show abstract

Overview of the HECKTOR Challenge at MICCAI 2021: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT Images

Andrearczyk

Oreiller

Boughdad

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Segmentation and Risk Score Prediction of Head and Neck Cancers in PET/CT Volumes with 3D U-Net and Cox Proportional Hazard Neural Networks

Cited by 9 publications

References 24 publications

Overview of the HECKTOR Challenge at MICCAI 2020: Automatic Head and Neck Tumor Segmentation in PET/CT

Overview of the HECKTOR Challenge at MICCAI 2020: Automatic Head and Neck Tumor Segmentation in PET/CT

SwinCross: Cross‐modal Swin transformer for head‐and‐neck tumor segmentation in PET/CT images

Overview of the HECKTOR Challenge at MICCAI 2021: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT Images

Contact Info

Product

Resources

About