Pub Date : 2022-11-30DOI: 10.48550/arXiv.2211.16834
Vajira Lasantha Thambawita, A. Storaas, S. Hicks, P. Halvorsen, M. Riegler
Head and neck cancers are the fifth most common cancer worldwide, and recently, analysis of Positron Emission Tomography (PET) and Computed Tomography (CT) images has been proposed to identify patients with a prognosis. Even though the results look promising, more research is needed to further validate and improve the results. This paper presents the work done by team MLC for the 2022 version of the HECKTOR grand challenge held at MICCAI 2022. For Task 1, the automatic segmentation task, our approach was, in contrast to earlier solutions using 3D segmentation, to keep it as simple as possible using a 2D model, analyzing every slice as a standalone image. In addition, we were interested in understanding how different modalities influence the results. We proposed two approaches; one using only the CT scans to make predictions and another using a combination of the CT and PET scans. For Task 2, the prediction of recurrence-free survival, we first proposed two approaches, one where we only use patient data and one where we combined the patient data with segmentations from the image model. For the prediction of the first two approaches, we used Random Forest. In our third approach, we combined patient data and image data using XGBoost. Low kidney function might worsen cancer prognosis. In this approach, we therefore estimated the kidney function of the patients and included it as a feature. Overall, we conclude that our simple methods were not able to compete with the highest-ranking submissions, but we still obtained reasonably good scores. We also got interesting insights into how the combination of different modalities can influence the segmentation and predictions.
{"title":"MLC at HECKTOR 2022: The Effect and Importance of Training Data when Analyzing Cases of Head and Neck Tumors using Machine Learning","authors":"Vajira Lasantha Thambawita, A. Storaas, S. Hicks, P. Halvorsen, M. Riegler","doi":"10.48550/arXiv.2211.16834","DOIUrl":"https://doi.org/10.48550/arXiv.2211.16834","url":null,"abstract":"Head and neck cancers are the fifth most common cancer worldwide, and recently, analysis of Positron Emission Tomography (PET) and Computed Tomography (CT) images has been proposed to identify patients with a prognosis. Even though the results look promising, more research is needed to further validate and improve the results. This paper presents the work done by team MLC for the 2022 version of the HECKTOR grand challenge held at MICCAI 2022. For Task 1, the automatic segmentation task, our approach was, in contrast to earlier solutions using 3D segmentation, to keep it as simple as possible using a 2D model, analyzing every slice as a standalone image. In addition, we were interested in understanding how different modalities influence the results. We proposed two approaches; one using only the CT scans to make predictions and another using a combination of the CT and PET scans. For Task 2, the prediction of recurrence-free survival, we first proposed two approaches, one where we only use patient data and one where we combined the patient data with segmentations from the image model. For the prediction of the first two approaches, we used Random Forest. In our third approach, we combined patient data and image data using XGBoost. Low kidney function might worsen cancer prognosis. In this approach, we therefore estimated the kidney function of the patients and included it as a feature. Overall, we conclude that our simple methods were not able to compete with the highest-ranking submissions, but we still obtained reasonably good scores. We also got interesting insights into how the combination of different modalities can influence the segmentation and predictions.","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127956818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-18DOI: 10.48550/arXiv.2211.10138
Hui Xu, Yi-hong Li, Wei Zhao, G. Quellec, Lijun Lu, M. Hatt
Automatic segmentation of head and neck cancer (HNC) tumors and lymph nodes plays a crucial role in the optimization treatment strategy and prognosis analysis. This study aims to employ nnU-Net for automatic segmentation and radiomics for recurrence-free survival (RFS) prediction using pretreatment PET/CT images in multi-center HNC cohort. A multi-center HNC dataset with 883 patients (524 patients for training, 359 for testing) was provided in HECKTOR 2022. A bounding box of the extended oropharyngeal region was retrieved for each patient with fixed size of 224 x 224 x 224 $mm^{3}$. Then 3D nnU-Net architecture was adopted to automatic segmentation of primary tumor and lymph nodes synchronously.Based on predicted segmentation, ten conventional features and 346 standardized radiomics features were extracted for each patient. Three prognostic models were constructed containing conventional and radiomics features alone, and their combinations by multivariate CoxPH modelling. The statistical harmonization method, ComBat, was explored towards reducing multicenter variations. Dice score and C-index were used as evaluation metrics for segmentation and prognosis task, respectively. For segmentation task, we achieved mean dice score around 0.701 for primary tumor and lymph nodes by 3D nnU-Net. For prognostic task, conventional and radiomics models obtained the C-index of 0.658 and 0.645 in the test set, respectively, while the combined model did not improve the prognostic performance with the C-index of 0.648.
头颈癌(HNC)肿瘤和淋巴结的自动分割在优化治疗策略和预后分析中具有至关重要的作用。本研究旨在利用nnU-Net对HNC多中心队列进行自动分割，并利用预处理PET/CT图像进行无复发生存(RFS)预测。HECKTOR 2022提供了一个包含883例患者的多中心HNC数据集(524例用于培训，359例用于测试)。为每个患者检索扩展口咽区域的边界框，固定大小为224 x 224 x 224 $mm^{3}$。然后采用三维nnU-Net结构对原发肿瘤和淋巴结进行同步自动分割。基于预测分割，为每位患者提取10个常规特征和346个标准化放射组学特征。构建了三个预后模型，分别包含常规和放射组学特征，并通过多变量CoxPH模型将它们组合起来。研究了减少多中心变化的统计协调方法ComBat。分别以Dice评分和C-index作为分割和预后任务的评价指标。对于分割任务，我们使用3D nnU-Net实现了原发肿瘤和淋巴结的平均骰子得分在0.701左右。对于预后任务，常规模型和放射组学模型在测试集中的C-index分别为0.658和0.645，而联合模型的C-index为0.648，没有提高预后性能。
{"title":"Joint nnU-Net and Radiomics Approaches for Segmentation and Prognosis of Head and Neck Cancers with PET/CT images","authors":"Hui Xu, Yi-hong Li, Wei Zhao, G. Quellec, Lijun Lu, M. Hatt","doi":"10.48550/arXiv.2211.10138","DOIUrl":"https://doi.org/10.48550/arXiv.2211.10138","url":null,"abstract":"Automatic segmentation of head and neck cancer (HNC) tumors and lymph nodes plays a crucial role in the optimization treatment strategy and prognosis analysis. This study aims to employ nnU-Net for automatic segmentation and radiomics for recurrence-free survival (RFS) prediction using pretreatment PET/CT images in multi-center HNC cohort. A multi-center HNC dataset with 883 patients (524 patients for training, 359 for testing) was provided in HECKTOR 2022. A bounding box of the extended oropharyngeal region was retrieved for each patient with fixed size of 224 x 224 x 224 $mm^{3}$. Then 3D nnU-Net architecture was adopted to automatic segmentation of primary tumor and lymph nodes synchronously.Based on predicted segmentation, ten conventional features and 346 standardized radiomics features were extracted for each patient. Three prognostic models were constructed containing conventional and radiomics features alone, and their combinations by multivariate CoxPH modelling. The statistical harmonization method, ComBat, was explored towards reducing multicenter variations. Dice score and C-index were used as evaluation metrics for segmentation and prognosis task, respectively. For segmentation task, we achieved mean dice score around 0.701 for primary tumor and lymph nodes by 3D nnU-Net. For prognostic task, conventional and radiomics models obtained the C-index of 0.658 and 0.645 in the test set, respectively, while the combined model did not improve the prognostic performance with the C-index of 0.648.","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132987881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-10DOI: 10.1007/978-3-031-27420-6_14
Mingyuan Meng, Lei Bi, D. Feng, Jinman Kim
{"title":"Radiomics-enhanced Deep Multi-task Learning for Outcome Prediction in Head and Neck Cancer","authors":"Mingyuan Meng, Lei Bi, D. Feng, Jinman Kim","doi":"10.1007/978-3-031-27420-6_14","DOIUrl":"https://doi.org/10.1007/978-3-031-27420-6_14","url":null,"abstract":"","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123862968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-29DOI: 10.48550/arXiv.2210.16704
Abhishek Srivastava, Debesh Jha, B. Aydogan, Mohamed E.Abazeed, Ulas Bagci
Head and Neck (H&N) organ-at-risk (OAR) and tumor segmentations are essential components of radiation therapy planning. The varying anatomic locations and dimensions of H&N nodal Gross Tumor Volumes (GTVn) and H&N primary gross tumor volume (GTVp) are difficult to obtain due to lack of accurate and reliable delineation methods. The downstream effect of incorrect segmentation can result in unnecessary irradiation of normal organs. Towards a fully automated radiation therapy planning algorithm, we explore the efficacy of multi-scale fusion based deep learning architectures for accurately segmenting H&N tumors from medical scans.
{"title":"Multi-Scale Fusion Methodologies for Head and Neck Tumor Segmentation","authors":"Abhishek Srivastava, Debesh Jha, B. Aydogan, Mohamed E.Abazeed, Ulas Bagci","doi":"10.48550/arXiv.2210.16704","DOIUrl":"https://doi.org/10.48550/arXiv.2210.16704","url":null,"abstract":"Head and Neck (H&N) organ-at-risk (OAR) and tumor segmentations are essential components of radiation therapy planning. The varying anatomic locations and dimensions of H&N nodal Gross Tumor Volumes (GTVn) and H&N primary gross tumor volume (GTVp) are difficult to obtain due to lack of accurate and reliable delineation methods. The downstream effect of incorrect segmentation can result in unnecessary irradiation of normal organs. Towards a fully automated radiation therapy planning algorithm, we explore the efficacy of multi-scale fusion based deep learning architectures for accurately segmenting H&N tumors from medical scans.","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"603 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123221568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-22DOI: 10.48550/arXiv.2209.11268
Kai Wang, Yunxiang Li, M. Dohopolski, Tao Peng, W. Lu, You Zhang, Jing Wang
For Head and Neck Cancers (HNC) patient management, automatic gross tumor volume (GTV) segmentation and accurate pre-treatment cancer recurrence prediction are of great importance to assist physicians in designing personalized management plans, which have the potential to improve the treatment outcome and quality of life for HNC patients. In this paper, we developed an automated primary tumor (GTVp) and lymph nodes (GTVn) segmentation method based on combined pre-treatment positron emission tomography/computed tomography (PET/CT) scans of HNC patients. We extracted radiomics features from the segmented tumor volume and constructed a multi-modality tumor recurrence-free survival (RFS) prediction model, which fused the prediction results from separate CT radiomics, PET radiomics, and clinical models. We performed 5-fold cross-validation to train and evaluate our methods on the MICCAI 2022 HEad and neCK TumOR segmentation and outcome prediction challenge (HECKTOR) dataset. The ensemble prediction results on the testing cohort achieved Dice scores of 0.77 and 0.73 for GTVp and GTVn segmentation, respectively, and a C-index value of 0.67 for RFS prediction. The code is publicly available (https://github.com/wangkaiwan/HECKTOR-2022-AIRT). Our team's name is AIRT.
{"title":"Recurrence-free Survival Prediction under the Guidance of Automatic Gross Tumor Volume Segmentation for Head and Neck Cancers","authors":"Kai Wang, Yunxiang Li, M. Dohopolski, Tao Peng, W. Lu, You Zhang, Jing Wang","doi":"10.48550/arXiv.2209.11268","DOIUrl":"https://doi.org/10.48550/arXiv.2209.11268","url":null,"abstract":"For Head and Neck Cancers (HNC) patient management, automatic gross tumor volume (GTV) segmentation and accurate pre-treatment cancer recurrence prediction are of great importance to assist physicians in designing personalized management plans, which have the potential to improve the treatment outcome and quality of life for HNC patients. In this paper, we developed an automated primary tumor (GTVp) and lymph nodes (GTVn) segmentation method based on combined pre-treatment positron emission tomography/computed tomography (PET/CT) scans of HNC patients. We extracted radiomics features from the segmented tumor volume and constructed a multi-modality tumor recurrence-free survival (RFS) prediction model, which fused the prediction results from separate CT radiomics, PET radiomics, and clinical models. We performed 5-fold cross-validation to train and evaluate our methods on the MICCAI 2022 HEad and neCK TumOR segmentation and outcome prediction challenge (HECKTOR) dataset. The ensemble prediction results on the testing cohort achieved Dice scores of 0.77 and 0.73 for GTVp and GTVn segmentation, respectively, and a C-index value of 0.67 for RFS prediction. The code is publicly available (https://github.com/wangkaiwan/HECKTOR-2022-AIRT). Our team's name is AIRT.","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"127 16","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113939775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-22DOI: 10.48550/arXiv.2209.10809
A. Myronenko, M. R. Siddiquee, Dong Yang, Yufan He, Daguang Xu
Head and neck tumor segmentation challenge (HECKTOR) 2022 offers a platform for researchers to compare their solutions to segmentation of tumors and lymph nodes from 3D CT and PET images. In this work, we describe our solution to HECKTOR 2022 segmentation task. We re-sample all images to a common resolution, crop around head and neck region, and train SegResNet semantic segmentation network from MONAI. We use 5-fold cross validation to select best model checkpoints. The final submission is an ensemble of 15 models from 3 runs. Our solution (team name NVAUTO) achieves the 1st place on the HECKTOR22 challenge leaderboard with an aggregated dice score of 0.78802.
{"title":"Automated head and neck tumor segmentation from 3D PET/CT","authors":"A. Myronenko, M. R. Siddiquee, Dong Yang, Yufan He, Daguang Xu","doi":"10.48550/arXiv.2209.10809","DOIUrl":"https://doi.org/10.48550/arXiv.2209.10809","url":null,"abstract":"Head and neck tumor segmentation challenge (HECKTOR) 2022 offers a platform for researchers to compare their solutions to segmentation of tumors and lymph nodes from 3D CT and PET images. In this work, we describe our solution to HECKTOR 2022 segmentation task. We re-sample all images to a common resolution, crop around head and neck region, and train SegResNet semantic segmentation network from MONAI. We use 5-fold cross validation to select best model checkpoints. The final submission is an ensemble of 15 models from 3 runs. Our solution (team name NVAUTO) achieves the 1st place on the HECKTOR22 challenge leaderboard with an aggregated dice score of 0.78802.","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114670347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-16DOI: 10.1007/978-3-030-98253-9_22
F. Yousefirizi, I. Janzen, Natalia Dubljevic, Yueh-En Liu, Chloe Hill, Calum MacAulay, A. Rahmim
{"title":"Segmentation and Risk Score Prediction of Head and Neck Cancers in PET/CT Volumes with 3D U-Net and Cox Proportional Hazard Neural Networks","authors":"F. Yousefirizi, I. Janzen, Natalia Dubljevic, Yueh-En Liu, Chloe Hill, Calum MacAulay, A. Rahmim","doi":"10.1007/978-3-030-98253-9_22","DOIUrl":"https://doi.org/10.1007/978-3-030-98253-9_22","url":null,"abstract":"","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125136389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-11DOI: 10.1007/978-3-030-98253-9_1
V. Andrearczyk, Valentin Oreiller, S. Boughdad, C. Rest, H. Elhalawani, Mario Jreige, John O. Prior, M. Vallières, D. Visvikis, M. Hatt, A. Depeursinge
{"title":"Overview of the HECKTOR Challenge at MICCAI 2021: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT Images","authors":"V. Andrearczyk, Valentin Oreiller, S. Boughdad, C. Rest, H. Elhalawani, Mario Jreige, John O. Prior, M. Vallières, D. Visvikis, M. Hatt, A. Depeursinge","doi":"10.1007/978-3-030-98253-9_1","DOIUrl":"https://doi.org/10.1007/978-3-030-98253-9_1","url":null,"abstract":"","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121859382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-06DOI: 10.1007/978-3-030-98253-9_18
Emmanuelle Bourigault, D. McGowan, A. Mehranian, Bartlomiej W. Papie.z
{"title":"Multimodal PET/CT Tumour Segmentation and Prediction of Progression-Free Survival using a Full-Scale UNet with Attention","authors":"Emmanuelle Bourigault, D. McGowan, A. Mehranian, Bartlomiej W. Papie.z","doi":"10.1007/978-3-030-98253-9_18","DOIUrl":"https://doi.org/10.1007/978-3-030-98253-9_18","url":null,"abstract":"","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128916203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-20DOI: 10.1007/978-3-030-67194-5_4
Andrei Iantsen, D. Visvikis, M. Hatt
{"title":"Squeeze-and-Excitation Normalization for Automated Delineation of Head and Neck Primary Tumors in Combined PET and CT Images","authors":"Andrei Iantsen, D. Visvikis, M. Hatt","doi":"10.1007/978-3-030-67194-5_4","DOIUrl":"https://doi.org/10.1007/978-3-030-67194-5_4","url":null,"abstract":"","PeriodicalId":305210,"journal":{"name":"HECKTOR@MICCAI","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121338073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：