Pub Date : 2023-10-05DOI: 10.1007/978-3-031-44689-4_8
Menghan Yu, Sourabh Kulhare, C. Mehanian, Charles B Delahunt, Daniel E Shea, Zohreh Laverriere, Ishan Shah, M. Horning
{"title":"How Good Are Synthetic Medical Images? An Empirical Study with Lung Ultrasound","authors":"Menghan Yu, Sourabh Kulhare, C. Mehanian, Charles B Delahunt, Daniel E Shea, Zohreh Laverriere, Ishan Shah, M. Horning","doi":"10.1007/978-3-031-44689-4_8","DOIUrl":"https://doi.org/10.1007/978-3-031-44689-4_8","url":null,"abstract":"","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"8 1","pages":"75-85"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139322953","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 : 2022-09-07DOI: 10.1007/978-3-031-16980-9_7
Petru-Daniel Tudosiu, W. H. Pinaya, M. Graham, Pedro Borges, Virginia Fernandez, Dai-gang Yang, J. Appleyard, G. Novati, Disha Mehra, M. Vella, P. Nachev, S. Ourselin, M. Cardoso
{"title":"Morphology-Preserving Autoregressive 3D Generative Modelling of the Brain","authors":"Petru-Daniel Tudosiu, W. H. Pinaya, M. Graham, Pedro Borges, Virginia Fernandez, Dai-gang Yang, J. Appleyard, G. Novati, Disha Mehra, M. Vella, P. Nachev, S. Ourselin, M. Cardoso","doi":"10.1007/978-3-031-16980-9_7","DOIUrl":"https://doi.org/10.1007/978-3-031-16980-9_7","url":null,"abstract":"","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126553920","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 : 2022-09-05DOI: 10.1007/978-3-031-16980-9_5
M. R. Siddiquee, Jay Shah, Teresa Wu, C. Chong, T. Schwedt, Baoxin Li
{"title":"HealthyGAN: Learning from Unannotated Medical Images to Detect Anomalies Associated with Human Disease","authors":"M. R. Siddiquee, Jay Shah, Teresa Wu, C. Chong, T. Schwedt, Baoxin Li","doi":"10.1007/978-3-031-16980-9_5","DOIUrl":"https://doi.org/10.1007/978-3-031-16980-9_5","url":null,"abstract":"","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114308251","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 : 2022-08-05DOI: 10.48550/arXiv.2208.03203
Jiayu Huo, V. Vakharia, Chengyuan Wu, A. Sharan, A. Ko, S. Ourselin, R. Sparks
, Abstract. Laser interstitial thermal therapy (LITT) is a novel minimally invasive treatment that is used to ablate intracranial structures to treat mesial temporal lobe epilepsy (MTLE). Region of interest (ROI) segmentation before and after LITT would enable automated lesion quantification to objectively assess treatment efficacy. Deep learning tech-niques, such as convolutional neural networks (CNNs) are state-of-the-art solutions for ROI segmentation, but require large amounts of anno-tated data during the training. However, collecting large datasets from emerging treatments such as LITT is impractical. In this paper, we propose a progressive brain lesion synthesis framework (PAVAE) to expand both the quantity and diversity of the training dataset. Concretely, our framework consists of two sequential networks: a mask synthesis network and a mask-guided lesion synthesis network. To better employ extrinsic information to provide additional supervision during network training, we design a condition embedding block (CEB) and a mask embedding block (MEB) to encode inherent conditions of masks to the feature space. Finally, a segmentation network is trained using raw and synthetic lesion images to evaluate the effectiveness of the proposed framework. Experimental results show that our method can achieve realistic synthetic results and boost the performance of down-stream segmentation tasks above traditional
{"title":"Brain Lesion Synthesis via Progressive Adversarial Variational Auto-Encoder","authors":"Jiayu Huo, V. Vakharia, Chengyuan Wu, A. Sharan, A. Ko, S. Ourselin, R. Sparks","doi":"10.48550/arXiv.2208.03203","DOIUrl":"https://doi.org/10.48550/arXiv.2208.03203","url":null,"abstract":", Abstract. Laser interstitial thermal therapy (LITT) is a novel minimally invasive treatment that is used to ablate intracranial structures to treat mesial temporal lobe epilepsy (MTLE). Region of interest (ROI) segmentation before and after LITT would enable automated lesion quantification to objectively assess treatment efficacy. Deep learning tech-niques, such as convolutional neural networks (CNNs) are state-of-the-art solutions for ROI segmentation, but require large amounts of anno-tated data during the training. However, collecting large datasets from emerging treatments such as LITT is impractical. In this paper, we propose a progressive brain lesion synthesis framework (PAVAE) to expand both the quantity and diversity of the training dataset. Concretely, our framework consists of two sequential networks: a mask synthesis network and a mask-guided lesion synthesis network. To better employ extrinsic information to provide additional supervision during network training, we design a condition embedding block (CEB) and a mask embedding block (MEB) to encode inherent conditions of masks to the feature space. Finally, a segmentation network is trained using raw and synthetic lesion images to evaluate the effectiveness of the proposed framework. Experimental results show that our method can achieve realistic synthetic results and boost the performance of down-stream segmentation tasks above traditional","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122805204","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 : 2022-08-03DOI: 10.48550/arXiv.2208.02135
Berke Doga Basaran, Mengyun Qiao, P. Matthews, Wenjia Bai
Understanding the intensity characteristics of brain lesions is key for defining image-based biomarkers in neurological studies and for predicting disease burden and outcome. In this work, we present a novel foreground-based generative method for modelling the local lesion characteristics that can both generate synthetic lesions on healthy images and synthesize subject-specific pseudo-healthy images from pathological images. Furthermore, the proposed method can be used as a data augmentation module to generate synthetic images for training brain image segmentation networks. Experiments on multiple sclerosis (MS) brain images acquired on magnetic resonance imaging (MRI) demonstrate that the proposed method can generate highly realistic pseudo-healthy and pseudo-pathological brain images. Data augmentation using the synthetic images improves the brain image segmentation performance compared to traditional data augmentation methods as well as a recent lesion-aware data augmentation technique, CarveMix. The code will be released at https://github.com/dogabasaran/lesion-synthesis.
{"title":"Subject-Specific Lesion Generation and Pseudo-Healthy Synthesis for Multiple Sclerosis Brain Images","authors":"Berke Doga Basaran, Mengyun Qiao, P. Matthews, Wenjia Bai","doi":"10.48550/arXiv.2208.02135","DOIUrl":"https://doi.org/10.48550/arXiv.2208.02135","url":null,"abstract":"Understanding the intensity characteristics of brain lesions is key for defining image-based biomarkers in neurological studies and for predicting disease burden and outcome. In this work, we present a novel foreground-based generative method for modelling the local lesion characteristics that can both generate synthetic lesions on healthy images and synthesize subject-specific pseudo-healthy images from pathological images. Furthermore, the proposed method can be used as a data augmentation module to generate synthetic images for training brain image segmentation networks. Experiments on multiple sclerosis (MS) brain images acquired on magnetic resonance imaging (MRI) demonstrate that the proposed method can generate highly realistic pseudo-healthy and pseudo-pathological brain images. Data augmentation using the synthetic images improves the brain image segmentation performance compared to traditional data augmentation methods as well as a recent lesion-aware data augmentation technique, CarveMix. The code will be released at https://github.com/dogabasaran/lesion-synthesis.","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122570717","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 : 2021-11-04DOI: 10.1007/978-3-030-87592-3_7
Pedro Borges, Richard Shaw, Thomas Varsavsky, Kerstin Kläser, David Thomas, I. Drobnjak, S. Ourselin, M. Cardoso
{"title":"The Role of MRI Physics in Brain Segmentation CNNs: Achieving Acquisition Invariance and Instructive Uncertainties","authors":"Pedro Borges, Richard Shaw, Thomas Varsavsky, Kerstin Kläser, David Thomas, I. Drobnjak, S. Ourselin, M. Cardoso","doi":"10.1007/978-3-030-87592-3_7","DOIUrl":"https://doi.org/10.1007/978-3-030-87592-3_7","url":null,"abstract":"","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"333 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116370310","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 : 2020-10-04DOI: 10.1007/978-3-030-59520-3_9
Jingya Liu, Yingli Tian, A. Ağıldere, K. Haberal, M. Coşkun, C. Duzgol, O. Akin
{"title":"DyeFreeNet: Deep Virtual Contrast CT Synthesis","authors":"Jingya Liu, Yingli Tian, A. Ağıldere, K. Haberal, M. Coşkun, C. Duzgol, O. Akin","doi":"10.1007/978-3-030-59520-3_9","DOIUrl":"https://doi.org/10.1007/978-3-030-59520-3_9","url":null,"abstract":"","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116906024","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 : 2020-10-04DOI: 10.1007/978-3-030-59520-3_17
Srijay Deshpande, F. Minhas, N. Rajpoot
{"title":"Train Small, Generate Big: Synthesis of Colorectal Cancer Histology Images","authors":"Srijay Deshpande, F. Minhas, N. Rajpoot","doi":"10.1007/978-3-030-59520-3_17","DOIUrl":"https://doi.org/10.1007/978-3-030-59520-3_17","url":null,"abstract":"","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"2009 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125652503","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 : 2020-10-04DOI: 10.1007/978-3-030-59520-3_6
Hongyu Wang, Jun Feng, Xiaoying Pan, Di Yang, Bao-ying Chen
{"title":"High-Quality Interpolation of Breast DCE-MRI Using Learned Transformations","authors":"Hongyu Wang, Jun Feng, Xiaoying Pan, Di Yang, Bao-ying Chen","doi":"10.1007/978-3-030-59520-3_6","DOIUrl":"https://doi.org/10.1007/978-3-030-59520-3_6","url":null,"abstract":"","PeriodicalId":150099,"journal":{"name":"SASHIMI@MICCAI","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133223785","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：