Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950548
Ling Zhang, M. Sonka, Le Lu, R. Summers, Jianhua Yao
Cervical nuclei carry substantial diagnostic information for cervical cancer. Therefore, in automation-assisted reading of cervical cytology, automated and accurate segmentation of nuclei is essential. This paper proposes a novel approach for segmentation of cervical nuclei that combines fully convolutional networks (FCN) and graph-based approach (FCNG). FCN is trained to learn the nucleus high-level features to generate a nucleus label mask and a nucleus probabilistic map. The mask is used to construct a graph by image transforming. The map is formulated into the graph cost function in addition to the properties of the nucleus border and nucleus region. The prior constraints regarding the context of nucleus-cytoplasm position are also utilized to modify the local cost functions. The globally optimal path in the constructed graph is identified by dynamic programming. Validation of our method was performed on cell nuclei from Herlev Pap smear dataset. Our method shows a Zijdenbos similarity index (ZSI) of 0.92 ± 0.09, compared to the best state-of-the-art approach of 0.89 ± 0.15. The nucleus areas measured by our method correlated strongly with the independent standard (r2 = 0.91).
{"title":"Combining fully convolutional networks and graph-based approach for automated segmentation of cervical cell nuclei","authors":"Ling Zhang, M. Sonka, Le Lu, R. Summers, Jianhua Yao","doi":"10.1109/ISBI.2017.7950548","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950548","url":null,"abstract":"Cervical nuclei carry substantial diagnostic information for cervical cancer. Therefore, in automation-assisted reading of cervical cytology, automated and accurate segmentation of nuclei is essential. This paper proposes a novel approach for segmentation of cervical nuclei that combines fully convolutional networks (FCN) and graph-based approach (FCNG). FCN is trained to learn the nucleus high-level features to generate a nucleus label mask and a nucleus probabilistic map. The mask is used to construct a graph by image transforming. The map is formulated into the graph cost function in addition to the properties of the nucleus border and nucleus region. The prior constraints regarding the context of nucleus-cytoplasm position are also utilized to modify the local cost functions. The globally optimal path in the constructed graph is identified by dynamic programming. Validation of our method was performed on cell nuclei from Herlev Pap smear dataset. Our method shows a Zijdenbos similarity index (ZSI) of 0.92 ± 0.09, compared to the best state-of-the-art approach of 0.89 ± 0.15. The nucleus areas measured by our method correlated strongly with the independent standard (r2 = 0.91).","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"3 1","pages":"406-409"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90448848","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950524
Zhen Yu, Dong Ni, Siping Chen, Jin Qin, Shengli Li, Tianfu Wang, B. Lei
Dermoscopy image is usually used in early diagnosis of malignant melanoma. The diagnosis accuracy by visual inspection is highly relied on the dermatologist's clinical experience. Due to the inaccuracy, subjectivity, and poor reproducibility of human judgement, an automatic recognition algorithm of dermoscopy image is highly desired. In this work, we present a hybrid classification framework for dermoscopy image assessment by combining deep convolutional neural network (CNN), Fisher vector (FV) and support vector machine (SVM). Specifically, the deep representations of subimages at various locations of a rescaled dermoscopy image are first extracted via a natural image dataset pre-trained on CNN. Then we adopt an orderless visual statistics based FV encoding methods to aggregate these features to build more invariant representations. Finally, the FV encoded representations are classified for diagnosis using a linear SVM. Compared with traditional low-level visual features based recognition approaches, our scheme is simpler and requires no complex preprocessing. Furthermore, the orderless representations are less sensitive to geometric deformation. We evaluate our proposed method on the ISBI 2016 Skin lesion challenge dataset and promising results are obtained. Also, we achieve consistent improvement in accuracy even without fine-tuning the CNN.
{"title":"Hybrid dermoscopy image classification framework based on deep convolutional neural network and Fisher vector","authors":"Zhen Yu, Dong Ni, Siping Chen, Jin Qin, Shengli Li, Tianfu Wang, B. Lei","doi":"10.1109/ISBI.2017.7950524","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950524","url":null,"abstract":"Dermoscopy image is usually used in early diagnosis of malignant melanoma. The diagnosis accuracy by visual inspection is highly relied on the dermatologist's clinical experience. Due to the inaccuracy, subjectivity, and poor reproducibility of human judgement, an automatic recognition algorithm of dermoscopy image is highly desired. In this work, we present a hybrid classification framework for dermoscopy image assessment by combining deep convolutional neural network (CNN), Fisher vector (FV) and support vector machine (SVM). Specifically, the deep representations of subimages at various locations of a rescaled dermoscopy image are first extracted via a natural image dataset pre-trained on CNN. Then we adopt an orderless visual statistics based FV encoding methods to aggregate these features to build more invariant representations. Finally, the FV encoded representations are classified for diagnosis using a linear SVM. Compared with traditional low-level visual features based recognition approaches, our scheme is simpler and requires no complex preprocessing. Furthermore, the orderless representations are less sensitive to geometric deformation. We evaluate our proposed method on the ISBI 2016 Skin lesion challenge dataset and promising results are obtained. Also, we achieve consistent improvement in accuracy even without fine-tuning the CNN.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"45 1","pages":"301-304"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78723173","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950521
S. Demyanov, R. Chakravorty, ZongYuan Ge, SeyedBehzad Bozorgtabar, M. Pablo, Adrian Bowling, R. Garnavi
Neural networks are powerful tools for medical image classification and segmentation. However, existing network structures and training procedures assume that the output classes are mutually exclusive and equally important. Many datasets of medical images do not satisfy these conditions. For example, some skin disease datasets have images labelled as coarse-grained class (such as Benign) in addition to images with fine-grained labels (such as a Benign subclass called Blue Nevus), and conventional neural network can not leverage such additional data for training. Also, in the clinical decision making, some classes (such as skin cancer or Melanoma) often carry more importance than other lesion types. We propose a novel Tree-Loss function for training and fine-tuning a neural network classifier using all available labelled images. The key step is the definition of the class taxonomy tree, which is used to describe the relations between labels. The tree can be also adjusted to reflect the desired importance of each class. These steps can be performed by a domain expert without detailed knowledge of machine learning techniques. The experiments demonstrate the improved performance compared with the conventional approach even without using additional data.
{"title":"Tree-loss function for training neural networks on weakly-labelled datasets","authors":"S. Demyanov, R. Chakravorty, ZongYuan Ge, SeyedBehzad Bozorgtabar, M. Pablo, Adrian Bowling, R. Garnavi","doi":"10.1109/ISBI.2017.7950521","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950521","url":null,"abstract":"Neural networks are powerful tools for medical image classification and segmentation. However, existing network structures and training procedures assume that the output classes are mutually exclusive and equally important. Many datasets of medical images do not satisfy these conditions. For example, some skin disease datasets have images labelled as coarse-grained class (such as Benign) in addition to images with fine-grained labels (such as a Benign subclass called Blue Nevus), and conventional neural network can not leverage such additional data for training. Also, in the clinical decision making, some classes (such as skin cancer or Melanoma) often carry more importance than other lesion types. We propose a novel Tree-Loss function for training and fine-tuning a neural network classifier using all available labelled images. The key step is the definition of the class taxonomy tree, which is used to describe the relations between labels. The tree can be also adjusted to reflect the desired importance of each class. These steps can be performed by a domain expert without detailed knowledge of machine learning techniques. The experiments demonstrate the improved performance compared with the conventional approach even without using additional data.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"13 1","pages":"287-291"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75228452","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950467
Boliang Yu, L. Weber, A. Pacureanu, M. Langer, C. Olivier, P. Cloetens, F. Peyrin
X-ray phase computed tomography (CT) offers higher sensitivity than conventional X-ray CT. A new phase-CT instrument producing a nano-focused beam has been developed at the ESRF (European Synchrotron Radiation Facility) for nano-imaging. In order to obtain final images, a suited phase retrieval algorithm is necessary, which is attracting broader interest recently. In this paper, we explicit the 3D phase CT image reconstruction problem, including the stage of phase retrieval prior to 3D CT reconstruction. The phase retrieval problem is solved by extending the single distance Paganin method to multi-distance acquisitions, followed by an iterative non-linear conjugate gradient descent optimization method. The method is evaluated on bone tissue samples imaged at voxel sizes of 120 nm. The results obtained from acquisition at 1 and 4 distances, with and without the iterative refinement are compared. The results show that this method yields improved images compared to other methods.
{"title":"Phase retrieval in 3D X-ray magnified phase nano CT: Imaging bone tissue at the nanoscale","authors":"Boliang Yu, L. Weber, A. Pacureanu, M. Langer, C. Olivier, P. Cloetens, F. Peyrin","doi":"10.1109/ISBI.2017.7950467","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950467","url":null,"abstract":"X-ray phase computed tomography (CT) offers higher sensitivity than conventional X-ray CT. A new phase-CT instrument producing a nano-focused beam has been developed at the ESRF (European Synchrotron Radiation Facility) for nano-imaging. In order to obtain final images, a suited phase retrieval algorithm is necessary, which is attracting broader interest recently. In this paper, we explicit the 3D phase CT image reconstruction problem, including the stage of phase retrieval prior to 3D CT reconstruction. The phase retrieval problem is solved by extending the single distance Paganin method to multi-distance acquisitions, followed by an iterative non-linear conjugate gradient descent optimization method. The method is evaluated on bone tissue samples imaged at voxel sizes of 120 nm. The results obtained from acquisition at 1 and 4 distances, with and without the iterative refinement are compared. The results show that this method yields improved images compared to other methods.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"83 1","pages":"56-59"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76299639","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950643
V. Aubert, O. Acosta, N. Rioux-Leclercq, R. Mathieu, F. Commandeur, R. Crevoisier
Objectives: Using in silico simulations from histopathological cancer prostate specimen, the objectives were to identify the total dose corresponding to various fractionations necessary to destroy the tumor cells (50% to 99.9%) and to assess the impact of the Gleason score on those doses.
{"title":"In silico model to simulate the radiation response at various fractionation from histopathological images of prostate tumors","authors":"V. Aubert, O. Acosta, N. Rioux-Leclercq, R. Mathieu, F. Commandeur, R. Crevoisier","doi":"10.1109/ISBI.2017.7950643","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950643","url":null,"abstract":"Objectives: Using in silico simulations from histopathological cancer prostate specimen, the objectives were to identify the total dose corresponding to various fractionations necessary to destroy the tumor cells (50% to 99.9%) and to assess the impact of the Gleason score on those doses.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"61 1","pages":"818-821"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76908413","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950564
Jian Li, R. Leahy
Non-local means (NLM) filtering of fMRI can reduce noise while preserving spatial structure. We have developed a variant called temporal-NLM (tNLM) which uses similarity in time-series between voxels as the basis for computing the weights in the filter. Using tNLM, dynamic fMRI data can be denoised while spatial boundaries between functionally distinct areas in the brain tend to be preserved. The degree of smoothing in tNLM is determined by a parameter h. Here we describe a procedure for selection of h to optimize our ability to differentiate functionally discrete brain regions. We demonstrate the method in application to optimized filtering of task fMRI data.
{"title":"Parameter selection for optimized non-local means filtering of task fMRI","authors":"Jian Li, R. Leahy","doi":"10.1109/ISBI.2017.7950564","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950564","url":null,"abstract":"Non-local means (NLM) filtering of fMRI can reduce noise while preserving spatial structure. We have developed a variant called temporal-NLM (tNLM) which uses similarity in time-series between voxels as the basis for computing the weights in the filter. Using tNLM, dynamic fMRI data can be denoised while spatial boundaries between functionally distinct areas in the brain tend to be preserved. The degree of smoothing in tNLM is determined by a parameter h. Here we describe a procedure for selection of h to optimize our ability to differentiate functionally discrete brain regions. We demonstrate the method in application to optimized filtering of task fMRI data.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"1 1","pages":"476-480"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85939960","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950710
B. Lokesh, A. Thittai
In this paper, a new method inspired by the synthetic aperture approach is proposed that aims at reducing the system's complexity (only 8 or 16 active elements) without compromising the image quality, and at frame rates comparable to or higher than conventional focused linear array technique. The novel method has been investigated in simulations using Field II software and experiments performed on a wire phantom using an ultrasound scanner. Results show that the proposed method provides better Lateral Resolution (LR) to that obtained when conventional focused linear array technique is used. The estimated LR at the focal point was 1.09 mm and 0.29 mm for conventional and the proposed method, respectively, in simulations. These were estimated to be 1.03 mm and 0.38 mm, respectively, in experiments. The image quality is shown to improve further when sign coherence factor weighting is incorporated during beamforming.
{"title":"Design of a low cost ultrasound system using diverging beams and synthetic aperture approach: Preliminary study","authors":"B. Lokesh, A. Thittai","doi":"10.1109/ISBI.2017.7950710","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950710","url":null,"abstract":"In this paper, a new method inspired by the synthetic aperture approach is proposed that aims at reducing the system's complexity (only 8 or 16 active elements) without compromising the image quality, and at frame rates comparable to or higher than conventional focused linear array technique. The novel method has been investigated in simulations using Field II software and experiments performed on a wire phantom using an ultrasound scanner. Results show that the proposed method provides better Lateral Resolution (LR) to that obtained when conventional focused linear array technique is used. The estimated LR at the focal point was 1.09 mm and 0.29 mm for conventional and the proposed method, respectively, in simulations. These were estimated to be 1.03 mm and 0.38 mm, respectively, in experiments. The image quality is shown to improve further when sign coherence factor weighting is incorporated during beamforming.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"39 1","pages":"1108-1111"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87391488","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950695
E. Ribeiro, M. Häfner, Georg Wimmer, Toru Tamaki, J. Tischendorf, S. Yoshida, Shinji Tanaka, A. Uhl
This work addresses Transfer Learning via Convolutional Neural Networks (CNN's) for the automated classification of colonic polyps in eight HD-endoscopic image databases acquired using different modalities. For this purpose, we explore if the architecture, the training approach, the number of classes, the number of images as well as the nature of the images in the training phase can influence the results. The experiments show that when the number of classes and the nature of the images are similar to the target database, the results are improved. Also, the better results obtained by the transfer learning compared to the most used features in the literature suggest that features learned by CNN's can be highly relevant for automated classification of colonic polyps.
{"title":"Exploring texture Transfer Learning for Colonic Polyp Classification via Convolutional Neural Networks","authors":"E. Ribeiro, M. Häfner, Georg Wimmer, Toru Tamaki, J. Tischendorf, S. Yoshida, Shinji Tanaka, A. Uhl","doi":"10.1109/ISBI.2017.7950695","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950695","url":null,"abstract":"This work addresses Transfer Learning via Convolutional Neural Networks (CNN's) for the automated classification of colonic polyps in eight HD-endoscopic image databases acquired using different modalities. For this purpose, we explore if the architecture, the training approach, the number of classes, the number of images as well as the nature of the images in the training phase can influence the results. The experiments show that when the number of classes and the nature of the images are similar to the target database, the results are improved. Also, the better results obtained by the transfer learning compared to the most used features in the literature suggest that features learned by CNN's can be highly relevant for automated classification of colonic polyps.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"14 1","pages":"1044-1048"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83125575","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950633
Fan Zhang, Pegah Kahali, Yannick Suter, I. Norton, Laura Rigolo, P. Savadjiev, Yang Song, Y. Rathi, Weidong (Tom) Cai, W. Wells, A. Golby, L. O’Donnell
This work presents an initial exploration of joint cortical surface and diffusion MRI analysis for neurosurgical patient data. We propose a groupwise cortical modeling strategy that performs an embedding of cortical points from a healthy population and a method for transferring the embedding (with associated information of anatomical label) to patient datasets for cortical parcellation prediction. Our proposed method correlates cortical surfaces based on groupwise white matter connectivity characteristics via a fiber clustering scheme. Unlike other parcellation methods, correspondence of cortical surface vertices is not required. Thus the proposed method can be applied to datasets of patients with brain tumors, using an approximate cortical surface such as a white matter/gray matter boundary derived from diffusion anisotropy. Our initial results on patient data showed good overlap of functional ground truth (subject-specific functional MRI activation areas) with predicted cortical parcels, with 10 of 13 activations overlapping an anatomically corresponding prediction.
{"title":"Automated connectivity-based groupwise cortical atlas generation: Application to data of neurosurgical patients with brain tumors for cortical parcellation prediction","authors":"Fan Zhang, Pegah Kahali, Yannick Suter, I. Norton, Laura Rigolo, P. Savadjiev, Yang Song, Y. Rathi, Weidong (Tom) Cai, W. Wells, A. Golby, L. O’Donnell","doi":"10.1109/ISBI.2017.7950633","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950633","url":null,"abstract":"This work presents an initial exploration of joint cortical surface and diffusion MRI analysis for neurosurgical patient data. We propose a groupwise cortical modeling strategy that performs an embedding of cortical points from a healthy population and a method for transferring the embedding (with associated information of anatomical label) to patient datasets for cortical parcellation prediction. Our proposed method correlates cortical surfaces based on groupwise white matter connectivity characteristics via a fiber clustering scheme. Unlike other parcellation methods, correspondence of cortical surface vertices is not required. Thus the proposed method can be applied to datasets of patients with brain tumors, using an approximate cortical surface such as a white matter/gray matter boundary derived from diffusion anisotropy. Our initial results on patient data showed good overlap of functional ground truth (subject-specific functional MRI activation areas) with predicted cortical parcels, with 10 of 13 activations overlapping an anatomically corresponding prediction.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"4 1","pages":"774-777"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82004891","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950631
Rutger Fick, N. Sepasian, M. Pizzolato, A. Ianuş, R. Deriche
Axon diameter estimation has been a focus of the diffusion MRI community for the past decade. The main argument has been that while diffusion models always overestimate the true axon diameter, their estimation still correlates with changes in true value. Until now, this remains more as a discussion point. The aim of this paper is to clarify this hypothesis using a recently acquired cat spinal cord data set, where the diffusion MRI signal of both a multi-shell and Ax-Caliber acquisition have been registered with the underlying histology values. We find that the axon diameter as estimated by signal models and AxCaliber does not correlate with their true sizes for axon diameters smaller than 3 µm. On the other hand, we also train a random forest machine learning algorithm to map signal-based features to histology values of axon diameter and volume fraction. The results show that, in this dataset, this approach leads to a more reliable estimation of physically relevant axon diameters than using sophisticated diffusion models.
{"title":"Assessing the feasibility of estimating axon diameter using diffusion models and machine learning","authors":"Rutger Fick, N. Sepasian, M. Pizzolato, A. Ianuş, R. Deriche","doi":"10.1109/ISBI.2017.7950631","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950631","url":null,"abstract":"Axon diameter estimation has been a focus of the diffusion MRI community for the past decade. The main argument has been that while diffusion models always overestimate the true axon diameter, their estimation still correlates with changes in true value. Until now, this remains more as a discussion point. The aim of this paper is to clarify this hypothesis using a recently acquired cat spinal cord data set, where the diffusion MRI signal of both a multi-shell and Ax-Caliber acquisition have been registered with the underlying histology values. We find that the axon diameter as estimated by signal models and AxCaliber does not correlate with their true sizes for axon diameters smaller than 3 µm. On the other hand, we also train a random forest machine learning algorithm to map signal-based features to histology values of axon diameter and volume fraction. The results show that, in this dataset, this approach leads to a more reliable estimation of physically relevant axon diameters than using sophisticated diffusion models.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"1 1","pages":"766-769"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81507196","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}