Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT

Andrearczyk, Vincent; Oreiller, Valentin; Abobakr, Moamen; Akhavanallaf, Azadeh; Balermpas, Panagiotis; Boughdad, Sarah; Capriotti, Leo; Castelli, J.; Rest, Catherine Cheze Le; Decazes, Pierre; Correia, Ricardo A.; El-Habashy, Dina; Elhalawani, Hesham; Fuller, C.D.; Jreige, Mario; Khamis, Yomna; Greca, Agustina La; Mohamed, Abdallah S.R.; Naser, Mohamed A.; Prior, John O.; Ruan, Su; Tanadini‐Lang, Stephanie; Tankyevych, Olena; Salimi, Yazdan; Vallières, Martin; Véra, Pierre; Visvikis, Dimitris; Wahid, Kareem A.; Zaidi, Habib; Hatt, Mathieu; Depeursinge, Adrien

doi:10.1007/978-3-031-27420-6_1

Cited by 13 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ability to predict the period of the disease and the impact of interventions is essential to effective medical practice and healthcare management. Hence, accurately predicting a disease diagnosis can help physicians make more informed clinical decisions on treatment approaches in clinical practice [45,46]. The prediction of outcomes using quantitative image biomarkers from medical images (i.e., handcrafted RFs and DFs) has shown tremendous potential to personalize patient care in the context of H&N tumors [47].…”

Section: Discussionmentioning

confidence: 99%

“…The head and neck tumor segmentation and outcome prediction from CT/PET images (HECKTOR) challenge in 2021 [45] aimed at identifying the best approaches to leverage the rich bi-modal information in the context of H&N tumors for the segmentation and outcome prediction so that task 2 of the challenge was defined to predict the progression-free survival. Our previous study [35] investigated the prediction of survival through handcrafted RFs applied to multiple HMLSs, including multiple dimensionality reduction algorithms linked with eight survival prediction algorithms.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques

Salmanpour¹,

Rezaeijo

Hosseinzadeh

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Background: Although handcrafted radiomics features (RF) are commonly extracted via radiomics software, employing deep features (DF) extracted from deep learning (DL) algorithms merits significant investigation. Moreover, a “tensor’’ radiomics paradigm where various flavours of a given feature are generated and explored can provide added value. We aimed to employ conventional and tensor DFs, and compare their outcome prediction performance to conventional and tensor RFs. Methods: 408 patients with head and neck cancer were selected from TCIA. PET images were first registered to CT, enhanced, normalized, and cropped. We employed 15 image-level fusion techniques (e.g., dual tree complex wavelet transform (DTCWT)) to combine PET and CT images. Subsequently, 215 RFs were extracted from each tumor in 17 images (or flavours) including CT only, PET only, and 15 fused PET-CT images through the standardized-SERA radiomics software. Furthermore, a 3 dimensional autoencoder was used to extract DFs. To predict the binary progression-free-survival-outcome, first, an end-to-end CNN algorithm was employed. Subsequently, we applied conventional and tensor DFs vs. RFs as extracted from each image to three sole classifiers, namely multilayer perceptron (MLP), random-forest, and logistic regression (LR), linked with dimension reduction algorithms. Results: DTCWT fusion linked with CNN resulted in accuracies of 75.6 ± 7.0% and 63.4 ± 6.7% in five-fold cross-validation and external-nested-testing, respectively. For the tensor RF-framework, polynomial transform algorithms + analysis of variance feature selector (ANOVA) + LR enabled 76.67 ± 3.3% and 70.6 ± 6.7% in the mentioned tests. For the tensor DF framework, PCA + ANOVA + MLP arrived at 87.0 ± 3.5% and 85.3 ± 5.2% in both tests. Conclusions: This study showed that tensor DF combined with proper machine learning approaches enhanced survival prediction performance compared to conventional DF, tensor and conventional RF, and end-to-end CNN frameworks.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques

Salmanpour¹,

Rezaeijo

Hosseinzadeh

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…12,13 However, the segmentation task remains challenging due to the complexity of PET/CT imaging and the high cost of processing 3D data. 14 Convolutional neural networks (CNNs)-based automated tumor segmentation methods have been presented as a possible solution. 15,16 Although missing small lesions, some approaches have demonstrated excellent results despite requiring the development of significant computational resources.…”

Section: Introductionmentioning

confidence: 99%

Information fusion for fully automated segmentation of head and neck tumors from PET and CT images

Shiri

Amini

Yousefirizi³

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundPET/CT images combining anatomic and metabolic data provide complementary information that can improve clinical task performance. PET image segmentation algorithms exploiting the multi‐modal information available are still lacking.PurposeOur study aimed to assess the performance of PET and CT image fusion for gross tumor volume (GTV) segmentations of head and neck cancers (HNCs) utilizing conventional, deep learning (DL), and output‐level voting‐based fusions.MethodsThe current study is based on a total of 328 histologically confirmed HNCs from six different centers. The images were automatically cropped to a 200 × 200 head and neck region box, and CT and PET images were normalized for further processing. Eighteen conventional image‐level fusions were implemented. In addition, a modified U2‐Net architecture as DL fusion model baseline was used. Three different input, layer, and decision‐level information fusions were used. Simultaneous truth and performance level estimation (STAPLE) and majority voting to merge different segmentation outputs (from PET and image‐level and network‐level fusions), that is, output‐level information fusion (voting‐based fusions) were employed. Different networks were trained in a 2D manner with a batch size of 64. Twenty percent of the dataset with stratification concerning the centers (20% in each center) were used for final result reporting. Different standard segmentation metrics and conventional PET metrics, such as SUV, were calculated.ResultsIn single modalities, PET had a reasonable performance with a Dice score of 0.77 ± 0.09, while CT did not perform acceptably and reached a Dice score of only 0.38 ± 0.22. Conventional fusion algorithms obtained a Dice score range of [0.76–0.81] with guided‐filter‐based context enhancement (GFCE) at the low‐end, and anisotropic diffusion and Karhunen–Loeve transform fusion (ADF), multi‐resolution singular value decomposition (MSVD), and multi‐level image decomposition based on latent low‐rank representation (MDLatLRR) at the high‐end. All DL fusion models achieved Dice scores of 0.80. Output‐level voting‐based models outperformed all other models, achieving superior results with a Dice score of 0.84 for Majority_ImgFus, Majority_All, and Majority_Fast. A mean error of almost zero was achieved for all fusions using SUVpeak, SUVmean and SUVmedian.ConclusionPET/CT information fusion adds significant value to segmentation tasks, considerably outperforming PET‐only and CT‐only methods. In addition, both conventional image‐level and DL fusions achieve competitive results. Meanwhile, output‐level voting‐based fusion using majority voting of several algorithms results in statistically significant improvements in the segmentation of HNC.

show abstract

Multi‐modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers

Zhao,

Wang,

Phan

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundHead and neck (HN) gross tumor volume (GTV) auto‐segmentation is challenging due to the morphological complexity and low image contrast of targets. Multi‐modality images, including computed tomography (CT) and positron emission tomography (PET), are used in the routine clinic to assist radiation oncologists for accurate GTV delineation. However, the availability of PET imaging may not always be guaranteed.PurposeTo develop a deep learning segmentation framework for automated GTV delineation of HN cancers using a combination of PET/CT images, while addressing the challenge of missing PET data.MethodsTwo datasets were included for this study: Dataset I: 524 (training) and 359 (testing) oropharyngeal cancer patients from different institutions with their PET/CT pairs provided by the HECKTOR Challenge; Dataset II: 90 HN patients(testing) from a local institution with their planning CT, PET/CT pairs. To handle potentially missing PET images, a model training strategy named the “Blank Channel” method was implemented. To simulate the absence of a PET image, a blank array with the same dimensions as the CT image was generated to meet the dual‐channel input requirement of the deep learning model. During the model training process, the model was randomly presented with either a real PET/CT pair or a blank/CT pair. This allowed the model to learn the relationship between the CT image and the corresponding GTV delineation based on available modalities. As a result, our model had the ability to handle flexible inputs during prediction, making it suitable for cases where PET images are missing.To evaluate the performance of our proposed model, we trained it using training patients from Dataset I and tested it with Dataset II. We compared our model (Model 1) with two other models which were trained for specific modality segmentations: Model 2 trained with only CT images, and Model 3 trained with real PET/CT pairs. The performance of the models was evaluated using quantitative metrics, including Dice similarity coefficient (DSC), mean surface distance (MSD), and 95% Hausdorff Distance (HD95). In addition, we evaluated our Model 1 and Model 3 using the 359 test cases in Dataset I.ResultsOur proposed model(Model 1) achieved promising results for GTV auto‐segmentation using PET/CT images, with the flexibility of missing PET images. Specifically, when assessed with only CT images in Dataset II, Model 1 achieved DSC of 0.56 ± 0.16, MSD of 3.4 ± 2.1 mm, and HD95 of 13.9 ± 7.6 mm. When the PET images were included, the performance of our model was improved to DSC of 0.62 ± 0.14, MSD of 2.8 ± 1.7 mm, and HD95 of 10.5 ± 6.5 mm. These results are comparable to those achieved by Model 2 and Model 3, illustrating Model 1′s effectiveness in utilizing flexible input modalities. Further analysis using the test dataset from Dataset I showed that Model 1 achieved an average DSC of 0.77, surpassing the overall average DSC of 0.72 among all participants in the HECKTOR Challenge.ConclusionsWe successfully refined a multi‐modal segmentation tool for accurate GTV delineation for HN cancer. Our method addressed the issue of missing PET images by allowing flexible data input, thereby providing a practical solution for clinical settings where access to PET imaging may be limited.

show abstract

Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT

Cited by 13 publications

References 45 publications

Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques

Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques

Information fusion for fully automated segmentation of head and neck tumors from PET and CT images

Multi‐modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers

Contact Info

Product

Resources

About