Pub Date : 2021-04-13DOI: 10.1109/ISBI48211.2021.9434067
F. Danckaers, Jeroen Van Houtte, Brian G. Booth, F. Verstreken, Jan Sijbers
Custom splint design is becoming more common. However, poor 3D scan quality can negatively impact the design accuracy. This paper describes a method to build a 3D statistical shape and pose model of the forearm from 3dMD scans. The model is used to assist the registration of previously unseen forearms in a wide range of poses. We show that this model-based surface registration results in a good geometric fit, with accurate anatomical correspondences. This method could be used to upgrade low-resolution scans using a high-resolution model.
{"title":"Statistical Shape and Pose Model of the Forearm for Custom Splint Design","authors":"F. Danckaers, Jeroen Van Houtte, Brian G. Booth, F. Verstreken, Jan Sijbers","doi":"10.1109/ISBI48211.2021.9434067","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9434067","url":null,"abstract":"Custom splint design is becoming more common. However, poor 3D scan quality can negatively impact the design accuracy. This paper describes a method to build a 3D statistical shape and pose model of the forearm from 3dMD scans. The model is used to assist the registration of previously unseen forearms in a wide range of poses. We show that this model-based surface registration results in a good geometric fit, with accurate anatomical correspondences. This method could be used to upgrade low-resolution scans using a high-resolution model.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"329 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133678508","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 : 2021-04-13DOI: 10.1109/ISBI48211.2021.9433858
Olivia Mariani, François Marelli, C. Jaques, Alexander Ernst, M. Liebling
In vivo microscopy is an important tool to study developing organs such as the heart of the zebrafish embryo but is often limited by slow image frame acquisition speed. While collections of still images of the beating heart at arbitrary phases can be sorted to obtain a virtual heartbeat, the presence of identical heart configurations at two or more heartbeat phases can derail this approach. Here, we propose a dual illumination method to encode movement in alternate frames to disambiguate heartbeat phases in the still frames. We propose to alternately acquire images with a ramp and pulse illumination then sort all successive image pairs based on the ramp-illuminated data but use the pulse-illuminated images for display and analysis. We characterized our method on synthetic data, and show its applicability on experimental data and found that an exposure time of about 7% of the heartbeat or more is necessary to encode the movement reliably in a single heartbeat with a single redundant node. Our method opens the possibility to use sorting algorithms without prior information on the phase, even when the movement presents redundant frames.
{"title":"Unequivocal Cardiac Phase Sorting From Alternating Ramp-And Pulse-Illuminated Microscopy Image Sequences","authors":"Olivia Mariani, François Marelli, C. Jaques, Alexander Ernst, M. Liebling","doi":"10.1109/ISBI48211.2021.9433858","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9433858","url":null,"abstract":"In vivo microscopy is an important tool to study developing organs such as the heart of the zebrafish embryo but is often limited by slow image frame acquisition speed. While collections of still images of the beating heart at arbitrary phases can be sorted to obtain a virtual heartbeat, the presence of identical heart configurations at two or more heartbeat phases can derail this approach. Here, we propose a dual illumination method to encode movement in alternate frames to disambiguate heartbeat phases in the still frames. We propose to alternately acquire images with a ramp and pulse illumination then sort all successive image pairs based on the ramp-illuminated data but use the pulse-illuminated images for display and analysis. We characterized our method on synthetic data, and show its applicability on experimental data and found that an exposure time of about 7% of the heartbeat or more is necessary to encode the movement reliably in a single heartbeat with a single redundant node. Our method opens the possibility to use sorting algorithms without prior information on the phase, even when the movement presents redundant frames.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114597675","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 : 2021-04-13DOI: 10.1109/ISBI48211.2021.9433903
Andrew Zhen, Minjeong Kim, Guorong Wu
Alzheimer’s disease (AD) is clinically heterogeneous in presentation and progression, demonstrating variable topographic distributions of clinical phenotypes, progression rate, and underlying neuro-degeneration mechanisms. Although striking efforts have been made to disentangle the massive heterogeneity in AD by identifying latent clusters with similar imaging or phenotype patterns, such unsupervised clustering techniques often yield sub-optimal stratification results that do not agree with clinical manifestations. To address this limitation, we present a novel deep predictive stratification network (DPS-Net) to learn the best feature representations from neuroimages, which allows us to identify latent fine-grained clusters (aka subtypes) with greater neuroscientific insight. The driving force of DPS-Net is a series of clinical outcomes from different cognitive domains (such as language and memory), which we consider as the benchmark to alleviate the heterogeneity issue of neurodegeneration pathways in the AD population. Since subject-specific longitudinal change is more relevant to disease progression, we propose to identify the latent subtypes from longitudinal neuroimaging data. Because AD manifests disconnection syndrome, we have applied our datadriven subtyping approach to longitudinal structural connectivity networks from the ADNI database. Our deep neural network identified more separated and clinically backed subtypes than conventional unsupervised methods used to solve the subtyping task– indicating its great applicability in future neuroimaging studies.
{"title":"Disentangling The Spatio-Temporal Heterogeneity of Alzheimer’s Disease Using A Deep Predictive Stratification Network","authors":"Andrew Zhen, Minjeong Kim, Guorong Wu","doi":"10.1109/ISBI48211.2021.9433903","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9433903","url":null,"abstract":"Alzheimer’s disease (AD) is clinically heterogeneous in presentation and progression, demonstrating variable topographic distributions of clinical phenotypes, progression rate, and underlying neuro-degeneration mechanisms. Although striking efforts have been made to disentangle the massive heterogeneity in AD by identifying latent clusters with similar imaging or phenotype patterns, such unsupervised clustering techniques often yield sub-optimal stratification results that do not agree with clinical manifestations. To address this limitation, we present a novel deep predictive stratification network (DPS-Net) to learn the best feature representations from neuroimages, which allows us to identify latent fine-grained clusters (aka subtypes) with greater neuroscientific insight. The driving force of DPS-Net is a series of clinical outcomes from different cognitive domains (such as language and memory), which we consider as the benchmark to alleviate the heterogeneity issue of neurodegeneration pathways in the AD population. Since subject-specific longitudinal change is more relevant to disease progression, we propose to identify the latent subtypes from longitudinal neuroimaging data. Because AD manifests disconnection syndrome, we have applied our datadriven subtyping approach to longitudinal structural connectivity networks from the ADNI database. Our deep neural network identified more separated and clinically backed subtypes than conventional unsupervised methods used to solve the subtyping task– indicating its great applicability in future neuroimaging studies.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115356495","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 : 2021-04-13DOI: 10.1109/ISBI48211.2021.9433998
Thanh-an Michel Pham, Emmanuel Soubies, F. Soulez, M. Unser
Single-molecule localization microscopy (SMLM) is a fluorescence microscopy technique that achieves super-resolution imaging by sequentially activating and localizing random sparse subsets of fluorophores. Each activated fluorophore emits light that then scatters through the sample, thus acting as a source of illumination from inside the sample. Hence, the sequence of SMLM frames carries information on the distribution of the refractive index of the sample. In this proof-of-concept work, we explore the possibility of exploiting this information to recover the refractive index of the imaged sample, given the localized molecules. Our results with simulated data suggest that it is possible to exploit the phase information that underlies the SMLM data.
{"title":"Diffraction Tomography From Single-Molecule Localization Microscopy: Numerical Feasibility","authors":"Thanh-an Michel Pham, Emmanuel Soubies, F. Soulez, M. Unser","doi":"10.1109/ISBI48211.2021.9433998","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9433998","url":null,"abstract":"Single-molecule localization microscopy (SMLM) is a fluorescence microscopy technique that achieves super-resolution imaging by sequentially activating and localizing random sparse subsets of fluorophores. Each activated fluorophore emits light that then scatters through the sample, thus acting as a source of illumination from inside the sample. Hence, the sequence of SMLM frames carries information on the distribution of the refractive index of the sample. In this proof-of-concept work, we explore the possibility of exploiting this information to recover the refractive index of the imaged sample, given the localized molecules. Our results with simulated data suggest that it is possible to exploit the phase information that underlies the SMLM data.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116894487","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}
Automatic segmentation of knee bone structures is an important task in orthopedics diagnosis of knee disease based on MRI images. Inspired by doctors’ diagnosis of knee in sagittal plane of MR image, we propose to first calculate the sagittal maximum intensity projection (MIP) of MR image, then construct a high precision 2D-3D hierarchical feature fusion network for automatic segmentation of knee based on convolutional encoding and decoding architecture. It includes: 1) A 2D bypass network extracting global features based on MIP; 2) A 3D backbone network calculating local details based on MR volume; 3) A feature fusion module integrating 2D global context and 3D local details hierarchically. Particularly, the global features as anchor points will be fused with the local details at each level of the encoding path to enrich the context of local details and improve the segmentation accuracy. Our method is verified on SKI10 dataset. The average dice coefficients of femur, femoral cartilage, tibia and tibia cartilage are 0.978, 0.848, 0.979 and 0.848, respectively, and the segmentation performance is far better than the state-of-the-art methods.
{"title":"2d-3d Hierarchical Feature Fusion Network For Segmentation Of Bone Structure In Knee Mr Image","authors":"Hui Wang, Demin Yao, Jiayi Chen, Yanjing Liu, Wensheng Li, Yonghong Shi","doi":"10.1109/ISBI48211.2021.9433777","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9433777","url":null,"abstract":"Automatic segmentation of knee bone structures is an important task in orthopedics diagnosis of knee disease based on MRI images. Inspired by doctors’ diagnosis of knee in sagittal plane of MR image, we propose to first calculate the sagittal maximum intensity projection (MIP) of MR image, then construct a high precision 2D-3D hierarchical feature fusion network for automatic segmentation of knee based on convolutional encoding and decoding architecture. It includes: 1) A 2D bypass network extracting global features based on MIP; 2) A 3D backbone network calculating local details based on MR volume; 3) A feature fusion module integrating 2D global context and 3D local details hierarchically. Particularly, the global features as anchor points will be fused with the local details at each level of the encoding path to enrich the context of local details and improve the segmentation accuracy. Our method is verified on SKI10 dataset. The average dice coefficients of femur, femoral cartilage, tibia and tibia cartilage are 0.978, 0.848, 0.979 and 0.848, respectively, and the segmentation performance is far better than the state-of-the-art methods.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116451874","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 : 2021-04-13DOI: 10.1109/ISBI48211.2021.9434117
Aurélie Leborgne, F. Ber, Laetitia Degiorgis, L. Harsan, Stella Marc-Zwecker, V. Noblet
Functional Magnetic Resonance Imaging (fMRI) is an imaging technique that allows to explore brain function in vivo. Many methods dedicated to analyzing these data are based on graph modeling, each node corresponding to a brain region and the edges representing their functional link. The objective of this work is to investigate the interest of methods for extracting frequent pattern in graphs to compare these data between two populations. Results are presented in the context of the characterization of a mouse model of Alzheimer’s disease in comparison with a group of control mice.
{"title":"Analysis Of Brain Functional Connectivity By Frequent Pattern Mining In Graphs. Application To The Characterization Of Murine Models","authors":"Aurélie Leborgne, F. Ber, Laetitia Degiorgis, L. Harsan, Stella Marc-Zwecker, V. Noblet","doi":"10.1109/ISBI48211.2021.9434117","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9434117","url":null,"abstract":"Functional Magnetic Resonance Imaging (fMRI) is an imaging technique that allows to explore brain function in vivo. Many methods dedicated to analyzing these data are based on graph modeling, each node corresponding to a brain region and the edges representing their functional link. The objective of this work is to investigate the interest of methods for extracting frequent pattern in graphs to compare these data between two populations. Results are presented in the context of the characterization of a mouse model of Alzheimer’s disease in comparison with a group of control mice.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124232122","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 : 2021-04-13DOI: 10.1109/ISBI48211.2021.9433849
Ben Huyge, Jonathan G. Sanctorum, Nathanael Six, J. D. Beenhouwer, Jan Sijbers
One of the most commonly used correction methods in X-ray imaging is flat field correction, which corrects for systematic inconsistencies, such as differences in detector pixel response. In conventional X-ray imaging, flat fields are acquired by exposing the detector without any object in the X-ray beam. However, in edge illumination X-ray CT, which is an emerging phase contrast imaging technique, two masks are used to measure the refraction of the X-rays. These masks remain in place while the flat fields are acquired and thus influence the intensity of the flat fields. This influence is studied theoretically and validated experimentally using Monte Carlo simulations of an edge illumination experiment in GATE.
{"title":"Analysis Of Flat Fields In Edge Illumination Phase Contrast Imaging","authors":"Ben Huyge, Jonathan G. Sanctorum, Nathanael Six, J. D. Beenhouwer, Jan Sijbers","doi":"10.1109/ISBI48211.2021.9433849","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9433849","url":null,"abstract":"One of the most commonly used correction methods in X-ray imaging is flat field correction, which corrects for systematic inconsistencies, such as differences in detector pixel response. In conventional X-ray imaging, flat fields are acquired by exposing the detector without any object in the X-ray beam. However, in edge illumination X-ray CT, which is an emerging phase contrast imaging technique, two masks are used to measure the refraction of the X-rays. These masks remain in place while the flat fields are acquired and thus influence the intensity of the flat fields. This influence is studied theoretically and validated experimentally using Monte Carlo simulations of an edge illumination experiment in GATE.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124974531","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}
Computed tomography urography imaging is routinely performed to evaluate the kidneys. Kidney 3D segmentation and reconstruction from urographic images provides physicians with an intuitive visualization way to accurately diagnose and treat kidney diseases, particularly used in surgical planning and outcome analysis before and after kidney surgery. While 3D fully convolution networks have achieved a big success in medical image segmentation, they get trapped in clinical unseen data and cannot be adapted in deferent modalities with one training procedure. This study proposes an unsupervised domain adaptation or translation method with 2D networks to deeply learn urographic images for accurate kidney segmentation. We tested our proposed method on clinical urography data. The experimental results demonstrate our proposed method can resolve the domain shift problem of kidney segmentation and achieve the comparable or better results than supervised learning based segmentation methods.
{"title":"Accurate 3d Kidney Segmentation Using Unsupervised Domain Translation And Adversarial Networks","authors":"Wankang Zeng, Wenkang Fan, Rongzhen Chen, Zhuohui Zheng, Song Zheng, Jianhui Chen, Rong Liu, Q. Zeng, Zengqin Liu, Yinran Chen, Xióngbiao Luó","doi":"10.1109/ISBI48211.2021.9434099","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9434099","url":null,"abstract":"Computed tomography urography imaging is routinely performed to evaluate the kidneys. Kidney 3D segmentation and reconstruction from urographic images provides physicians with an intuitive visualization way to accurately diagnose and treat kidney diseases, particularly used in surgical planning and outcome analysis before and after kidney surgery. While 3D fully convolution networks have achieved a big success in medical image segmentation, they get trapped in clinical unseen data and cannot be adapted in deferent modalities with one training procedure. This study proposes an unsupervised domain adaptation or translation method with 2D networks to deeply learn urographic images for accurate kidney segmentation. We tested our proposed method on clinical urography data. The experimental results demonstrate our proposed method can resolve the domain shift problem of kidney segmentation and achieve the comparable or better results than supervised learning based segmentation methods.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125385894","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 : 2021-04-13DOI: 10.1109/ISBI48211.2021.9434011
P. Cole, A. Pyrros, Oluwasanmi Koyejo
Radiology exams require exposing a patient to a variable dosage of radiation. Importantly, the amount of radiation used during the exam directly corresponds to the level of noise in the resulting image, and increased amounts of radiation can pose health risks to patients. This results in a tradeoff, as radiologists need a high-quality image to make a diagnosis. In this work, we propose a method to recover image fidelity given a noisy, or low-dose, sample. Using a two-part criterion that consists of a pixel-wise loss and an adversarial loss, we are able to recover the structure and fine detail of the normal-dose sample. To evaluate the denoising method, we implement simulations of realistic low-dose noise for a computed tomography exam, which may be of independent interest. Quantitative and qualitative results highlight the performance of our approach as compared to existing baselines.
{"title":"Learning To Recover Sharp Detail From Simulated Low-Dose Ct Studies","authors":"P. Cole, A. Pyrros, Oluwasanmi Koyejo","doi":"10.1109/ISBI48211.2021.9434011","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9434011","url":null,"abstract":"Radiology exams require exposing a patient to a variable dosage of radiation. Importantly, the amount of radiation used during the exam directly corresponds to the level of noise in the resulting image, and increased amounts of radiation can pose health risks to patients. This results in a tradeoff, as radiologists need a high-quality image to make a diagnosis. In this work, we propose a method to recover image fidelity given a noisy, or low-dose, sample. Using a two-part criterion that consists of a pixel-wise loss and an adversarial loss, we are able to recover the structure and fine detail of the normal-dose sample. To evaluate the denoising method, we implement simulations of realistic low-dose noise for a computed tomography exam, which may be of independent interest. Quantitative and qualitative results highlight the performance of our approach as compared to existing baselines.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121263237","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 : 2021-04-13DOI: 10.1109/ISBI48211.2021.9434059
Angshuman Paul, Thomas C. Shen, Yifan Peng, Zhiyong Lu, R. Summers
A trained radiologist may learn the visual presentation of a new disease by looking at a few relevant image examples in research articles. However, training a machine learning model in such a manner is an arduous task not only due to the small number of labeled training images but also for the low resolution of such images. We design a few-shot learning method that can diagnose new diseases from chest x-rays utilizing only a few relevant labeled x-ray images from the published literature. Our method uses prior knowledge about other diseases for feature extraction from x-rays of new diseases. We formulate a classifier that is initially trained with a few labeled feature vectors corresponding to low-resolution images from the PubMed Central. The classifier is subsequently re-trained using unlabeled feature vectors corresponding to high-resolution x-ray images. Experiments on publicly available datasets show the superiority of the proposed method to several state-of-the-art few-shot learning techniques for chest x-ray diagnosis.
{"title":"Learning Few-Shot Chest X-Ray Diagnosis Using Images From The Published Scientific Literature","authors":"Angshuman Paul, Thomas C. Shen, Yifan Peng, Zhiyong Lu, R. Summers","doi":"10.1109/ISBI48211.2021.9434059","DOIUrl":"https://doi.org/10.1109/ISBI48211.2021.9434059","url":null,"abstract":"A trained radiologist may learn the visual presentation of a new disease by looking at a few relevant image examples in research articles. However, training a machine learning model in such a manner is an arduous task not only due to the small number of labeled training images but also for the low resolution of such images. We design a few-shot learning method that can diagnose new diseases from chest x-rays utilizing only a few relevant labeled x-ray images from the published literature. Our method uses prior knowledge about other diseases for feature extraction from x-rays of new diseases. We formulate a classifier that is initially trained with a few labeled feature vectors corresponding to low-resolution images from the PubMed Central. The classifier is subsequently re-trained using unlabeled feature vectors corresponding to high-resolution x-ray images. Experiments on publicly available datasets show the superiority of the proposed method to several state-of-the-art few-shot learning techniques for chest x-ray diagnosis.","PeriodicalId":372939,"journal":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121947765","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：