Mohammad Amin Izadi, Nafiseh Alemohammad, Parham Geramifar, Ali Salimi, Zeinab Paymani, Roya Eisazadeh, Rezvan Samimi, Babak Nikkholgh, Zaynab Sabouri
{"title":"利用三维密集 U-Net 在霍奇金淋巴瘤患者的 18F-FDG PET/CT 成像中自动检测和分割病灶。","authors":"Mohammad Amin Izadi, Nafiseh Alemohammad, Parham Geramifar, Ali Salimi, Zeinab Paymani, Roya Eisazadeh, Rezvan Samimi, Babak Nikkholgh, Zaynab Sabouri","doi":"10.1097/MNM.0000000000001892","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>The accuracy of automatic tumor segmentation in PET/computed tomography (PET/CT) images is crucial for the effective treatment and monitoring of Hodgkin lymphoma. This study aims to address the challenges faced by certain segmentation algorithms in accurately differentiating lymphoma from normal organ uptakes due to PET image resolution and tumor heterogeneity.</p><p><strong>Materials and methods: </strong>Variants of the encoder-decoder architectures are state-of-the-art models for image segmentation. Among these kinds of architectures, U-Net is one of the most famous and predominant for medical image segmentation. In this study, we propose a fully automatic approach for Hodgkin lymphoma segmentation that combines U-Net and DenseNet architectures to reduce network loss for very small lesions, which is trained using the Tversky loss function. The hypothesis is that the fusion of these two deep learning models can improve the accuracy and robustness of Hodgkin lymphoma segmentation. A dataset with 141 samples was used to train our proposed network. Also, to test and evaluate the proposed network, we allocated two separate datasets of 20 samples.</p><p><strong>Results: </strong>We achieved 0.759 as the mean Dice similarity coefficient with a median value of 0.767, and interquartile range (0.647-0.837). A good agreement was observed between the ground truth of test images against the predicted volume with precision and recall scores of 0.798 and 0.763, respectively.</p><p><strong>Conclusion: </strong>This study demonstrates that the integration of U-Net and DenseNet architectures, along with the Tversky loss function, can significantly enhance the accuracy of Hodgkin lymphoma segmentation in PET/CT images compared to similar studies.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automatic detection and segmentation of lesions in 18 F-FDG PET/CT imaging of patients with Hodgkin lymphoma using 3D dense U-Net.\",\"authors\":\"Mohammad Amin Izadi, Nafiseh Alemohammad, Parham Geramifar, Ali Salimi, Zeinab Paymani, Roya Eisazadeh, Rezvan Samimi, Babak Nikkholgh, Zaynab Sabouri\",\"doi\":\"10.1097/MNM.0000000000001892\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>The accuracy of automatic tumor segmentation in PET/computed tomography (PET/CT) images is crucial for the effective treatment and monitoring of Hodgkin lymphoma. This study aims to address the challenges faced by certain segmentation algorithms in accurately differentiating lymphoma from normal organ uptakes due to PET image resolution and tumor heterogeneity.</p><p><strong>Materials and methods: </strong>Variants of the encoder-decoder architectures are state-of-the-art models for image segmentation. Among these kinds of architectures, U-Net is one of the most famous and predominant for medical image segmentation. In this study, we propose a fully automatic approach for Hodgkin lymphoma segmentation that combines U-Net and DenseNet architectures to reduce network loss for very small lesions, which is trained using the Tversky loss function. The hypothesis is that the fusion of these two deep learning models can improve the accuracy and robustness of Hodgkin lymphoma segmentation. A dataset with 141 samples was used to train our proposed network. Also, to test and evaluate the proposed network, we allocated two separate datasets of 20 samples.</p><p><strong>Results: </strong>We achieved 0.759 as the mean Dice similarity coefficient with a median value of 0.767, and interquartile range (0.647-0.837). A good agreement was observed between the ground truth of test images against the predicted volume with precision and recall scores of 0.798 and 0.763, respectively.</p><p><strong>Conclusion: </strong>This study demonstrates that the integration of U-Net and DenseNet architectures, along with the Tversky loss function, can significantly enhance the accuracy of Hodgkin lymphoma segmentation in PET/CT images compared to similar studies.</p>\",\"PeriodicalId\":19708,\"journal\":{\"name\":\"Nuclear Medicine Communications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2024-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nuclear Medicine Communications\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/MNM.0000000000001892\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/10/8 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nuclear Medicine Communications","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/MNM.0000000000001892","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/8 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
Automatic detection and segmentation of lesions in 18 F-FDG PET/CT imaging of patients with Hodgkin lymphoma using 3D dense U-Net.
Objective: The accuracy of automatic tumor segmentation in PET/computed tomography (PET/CT) images is crucial for the effective treatment and monitoring of Hodgkin lymphoma. This study aims to address the challenges faced by certain segmentation algorithms in accurately differentiating lymphoma from normal organ uptakes due to PET image resolution and tumor heterogeneity.
Materials and methods: Variants of the encoder-decoder architectures are state-of-the-art models for image segmentation. Among these kinds of architectures, U-Net is one of the most famous and predominant for medical image segmentation. In this study, we propose a fully automatic approach for Hodgkin lymphoma segmentation that combines U-Net and DenseNet architectures to reduce network loss for very small lesions, which is trained using the Tversky loss function. The hypothesis is that the fusion of these two deep learning models can improve the accuracy and robustness of Hodgkin lymphoma segmentation. A dataset with 141 samples was used to train our proposed network. Also, to test and evaluate the proposed network, we allocated two separate datasets of 20 samples.
Results: We achieved 0.759 as the mean Dice similarity coefficient with a median value of 0.767, and interquartile range (0.647-0.837). A good agreement was observed between the ground truth of test images against the predicted volume with precision and recall scores of 0.798 and 0.763, respectively.
Conclusion: This study demonstrates that the integration of U-Net and DenseNet architectures, along with the Tversky loss function, can significantly enhance the accuracy of Hodgkin lymphoma segmentation in PET/CT images compared to similar studies.
期刊介绍:
Nuclear Medicine Communications, the official journal of the British Nuclear Medicine Society, is a rapid communications journal covering nuclear medicine and molecular imaging with radionuclides, and the basic supporting sciences. As well as clinical research and commentary, manuscripts describing research on preclinical and basic sciences (radiochemistry, radiopharmacy, radiobiology, radiopharmacology, medical physics, computing and engineering, and technical and nursing professions involved in delivering nuclear medicine services) are welcomed, as the journal is intended to be of interest internationally to all members of the many medical and non-medical disciplines involved in nuclear medicine. In addition to papers reporting original studies, frankly written editorials and topical reviews are a regular feature of the journal.