no code implementations • 24 Jan 2024 • Shuchang Ye, Mingyuan Meng, Mingjian Li, Dagan Feng, Jinman Kim
Recent generative representation learning methods have demonstrated the benefits of dual-modal learning from both image and text modalities.
no code implementations • 19 Jan 2024 • Mingjian Li, Mingyuan Meng, Michael Fulham, David Dagan Feng, Lei Bi, Jinman Kim
These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation.
1 code implementation • 28 Nov 2023 • Mingyuan Meng, Yuxin Xue, Dagan Feng, Lei Bi, Jinman Kim
This textural information is crucial for medical dense prediction as it can differentiate the subtle human anatomy in medical images.
1 code implementation • 28 Oct 2023 • Hao Wang, Euijoon Ahn, Lei Bi, Jinman Kim
The clinical diagnosis of skin lesion involves the analysis of dermoscopic and clinical modalities.
no code implementations • 24 Oct 2023 • Yuxin Xue, Lei Bi, Yige Peng, Michael Fulham, David Dagan Feng, Jinman Kim
We introduce (1) An adaptive residual estimation mapping mechanism, AE-Net, designed to dynamically rectify the preliminary synthesized PET images by taking the residual map between the low-dose PET and synthesized output as the input, and (2) A self-supervised pre-training strategy to enhance the feature representation of the coarse generator.
1 code implementation • 11 Sep 2023 • Mingyuan Meng, Michael Fulham, Dagan Feng, Lei Bi, Jinman Kim
However, DNN-based registration needs to explore the spatial information of each image and fuse this information to characterize spatial correspondence.
1 code implementation • 7 Jul 2023 • Mingyuan Meng, Lei Bi, Michael Fulham, Dagan Feng, Jinman Kim
In view of this, we propose a merging-diverging learning framework for survival prediction from multi-modality images.
1 code implementation • 7 Jul 2023 • Mingyuan Meng, Lei Bi, Michael Fulham, Dagan Feng, Jinman Kim
Recently, Non-Iterative Coarse-to-finE (NICE) registration methods have been proposed to perform coarse-to-fine registration in a single network and showed advantages in both registration accuracy and runtime.
2 code implementations • 17 May 2023 • Mingyuan Meng, Bingxin Gu, Michael Fulham, Shaoli Song, Dagan Feng, Lei Bi, Jinman Kim
Instead of adopting MTL, we propose a novel Segmentation-to-Survival Learning (SSL) strategy, where our AdaMSS is trained for tumor segmentation and survival prediction sequentially in two stages.
no code implementations • 3 Apr 2023 • Yuxin Xue, Yige Peng, Lei Bi, Dagan Feng, Jinman Kim
We compared our method to the state-of-the-art methods on whole-body PET with different dose reduction factors (DRFs).
no code implementations • 20 Mar 2023 • Hao Wang, Euijoon Ahn, Jinman Kim
These SSL approaches, however, are not designed for handling multi-resolution WSIs, which limits their performance in learning discriminative image features.
no code implementations • 10 Feb 2023 • Wei-Chien Wang, Euijoon Ahn, Dagan Feng, Jinman Kim
Over the last decade, supervised deep learning on manually annotated big data has been progressing significantly on computer vision tasks.
no code implementations • 4 Jan 2023 • Yusheng Zhou, Hao Li, Jianan Liu, Zhengmin Kong, Tao Huang, Euijoon Ahn, Zhihan Lv, Jinman Kim, David Dagan Feng
Our results substantiate the potential of UNAEN as a promising solution applicable in real-world clinical environments, with the capability to enhance diagnostic accuracy and facilitate image-guided therapies.
no code implementations • 12 Dec 2022 • Yuan Yuan, Euijoon Ahn, Dagan Feng, Mohamad Khadra, Jinman Kim
However, existing state of the art AI algorithms which are based on deep learning technology are often limited to 2D images that fails to capture inter-slice correlations in 3D volumetric images.
1 code implementation • 15 Nov 2022 • Mingyuan Meng, Lei Bi, Dagan Feng, Jinman Kim
In this study, we focus on brain tumor sequence registration between pre-operative and follow-up Magnetic Resonance Imaging (MRI) scans of brain glioma patients, in the context of Brain Tumor Sequence Registration challenge (BraTS-Reg 2022).
2 code implementations • 10 Nov 2022 • Mingyuan Meng, Lei Bi, Dagan Feng, Jinman Kim
Recently, deep learning methods have been proposed to perform end-to-end outcome prediction so as to remove the reliance on manual segmentation.
no code implementations • 28 Oct 2022 • Lei Bi, Michael Fulham, Shaoli Song, David Dagan Feng, Jinman Kim
We also introduced a hyper connected fusion to fuse the contextual and complementary image features across multiple transformers in an iterative manner.
1 code implementation • 16 Sep 2022 • Yige Peng, Jinman Kim, Dagan Feng, Lei Bi
In this study, we introduce a false positive reduction network to overcome this limitation.
1 code implementation • 25 Jun 2022 • Mingyuan Meng, Lei Bi, Dagan Feng, Jinman Kim
Recently, iterative deep registration methods have been used to alleviate this limitation, where the transformations are iteratively learned in a coarse-to-fine manner.
no code implementations • 13 May 2022 • Jianan Liu, Hao Li, Tao Huang, Euijoon Ahn, Kang Han, Adeel Razi, Wei Xiang, Jinman Kim, David Dagan Feng
However, the difference in degradation representations between synthetic and authentic LR images suppresses the quality of SR images reconstructed from authentic LR images.
no code implementations • nlppower (ACL) 2022 • Usman Naseem, Byoung Chan Lee, Matloob Khushi, Jinman Kim, Adam G. Dunn
We present and release PHS-BERT, a transformer-based PLM, to identify tasks related to public health surveillance on social media.
no code implementations • 13 Dec 2021 • Bhakti Baheti, Satrajit Chakrabarty, Hamed Akbari, Michel Bilello, Benedikt Wiestler, Julian Schwarting, Evan Calabrese, Jeffrey Rudie, Syed Abidi, Mina Mousa, Javier Villanueva-Meyer, Brandon K. K. Fields, Florian Kofler, Russell Takeshi Shinohara, Juan Eugenio Iglesias, Tony C. W. Mok, Albert C. S. Chung, Marek Wodzinski, Artur Jurgas, Niccolo Marini, Manfredo Atzori, Henning Muller, Christoph Grobroehmer, Hanna Siebert, Lasse Hansen, Mattias P. Heinrich, Luca Canalini, Jan Klein, Annika Gerken, Stefan Heldmann, Alessa Hering, Horst K. Hahn, Mingyuan Meng, Lei Bi, Dagan Feng, Jinman Kim, Ramy A. Zeineldin, Mohamed E. Karar, Franziska Mathis-Ullrich, Oliver Burgert, Javid Abderezaei, Aymeric Pionteck, Agamdeep Chopra, Mehmet Kurt, Kewei Yan, Yonghong Yan, Zhe Tang, Jianqiang Ma, Sahar Almahfouz Nasser, Nikhil Cherian Kurian, Mohit Meena, Saqib Shamsi, Amit Sethi, Nicholas J. Tustison, Brian B. Avants, Philip Cook, James C. Gee, Lin Tian, Hastings Greer, Marc Niethammer, Andrew Hoopes, Malte Hoffmann, Adrian V. Dalca, Stergios Christodoulidis, Theo Estiene, Maria Vakalopoulou, Nikos Paragios, Daniel S. Marcus, Christos Davatzikos, Aristeidis Sotiras, Bjoern Menze, Spyridon Bakas, Diana Waldmannstetter
Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance.
2 code implementations • 30 Sep 2021 • Yuyu Guo, Lei Bi, Dongming Wei, Liyun Chen, Zhengbin Zhu, Dagan Feng, Ruiyan Zhang, Qian Wang, Jinman Kim
In the first stage, we process the raw dense image to extract sparse landmarks to represent the target organ anatomical topology and discard the redundant information that is unnecessary for motion estimation.
2 code implementations • 16 Sep 2021 • Mingyuan Meng, Bingxin Gu, Lei Bi, Shaoli Song, David Dagan Feng, Jinman Kim
However, the models using the whole target regions will also include non-relevant background information, while the models using segmented tumor regions will disregard potentially prognostic information existing out of primary tumors (e. g., local lymph node metastasis and adjacent tissue invasion).
1 code implementation • 16 Jul 2021 • Hao Wang, Euijoon Ahn, Jinman Kim
To address these problems, we present a novel self-supervised spatiotemporal learning framework for remote physiological signal representation learning, where there is a lack of labelled training data.
1 code implementation • 11 Jul 2021 • Euijoon Ahn, Dagan Feng, Jinman Kim
Hence, we propose a new spatial guided self-supervised clustering network (SGSCN) for medical image segmentation, where we introduce multiple loss functions designed to aid in grouping image pixels that are spatially connected and have similar feature representations.
1 code implementation • 9 Jul 2021 • Usman Naseem, Adam G. Dunn, Matloob Khushi, Jinman Kim
We present BioALBERT, a domain-specific adaptation of A Lite Bidirectional Encoder Representations from Transformers (ALBERT), trained on biomedical (PubMed and PubMed Central) and clinical (MIMIC-III) corpora and fine tuned for 6 different tasks across 20 benchmark datasets.
no code implementations • 17 Jun 2021 • Usman Naseem, Matloob Khushi, Jinman Kim, Adam G. Dunn
In this study, to classify vaccine sentiment tweets with limited information, we present a novel end-to-end framework consisting of interconnected components that use domain-specific LM trained on vaccine-related tweets and models commonsense knowledge into a bidirectional gated recurrent network (CK-BiGRU) with context-aware attention.
no code implementations • 9 Jun 2021 • Kai-Chieh Liang, Lei Bi, Ashnil Kumar, Michael Fulham, Jinman Kim
Our ST-DSNN learns and accumulates image features from the PET images done over time.
no code implementations • 23 Apr 2021 • Yige Peng, Lei Bi, Ashnil Kumar, Michael Fulham, Dagan Feng, Jinman Kim
Most CNNs are designed for single-modality imaging data (CT or PET alone) and do not exploit the information embedded in PET-CT where there is a combination of an anatomical and functional imaging modality.
no code implementations • 1 Apr 2021 • Xiaohang Fu, Lei Bi, Ashnil Kumar, Michael Fulham, Jinman Kim
Further, there is not a method to exploit the intercategory relationships in the 7PC.
2 code implementations • 9 Mar 2021 • Mingyuan Meng, Lei Bi, Michael Fulham, David Dagan Feng, Jinman Kim
In this study, we propose an Appearance Adjustment Network (AAN) to enhance the adaptability of DLRs to appearance variations.
no code implementations • 9 Mar 2021 • Bingxin Gu, Mingyuan Meng, Lei Bi, Jinman Kim, David Dagan Feng, Shaoli Song
Methods: A total of 257 patients (170/87 in internal/external cohorts) with advanced NPC (TNM stage III or IVa) were enrolled.
no code implementations • 5 Mar 2021 • Xiaohang Fu, Lei Bi, Ashnil Kumar, Michael Fulham, Jinman Kim
Furthermore, lung nodules are often heterogeneous in the cross-sectional image slices of a 3D volume.
no code implementations • 19 Sep 2020 • Usman Naseem, Matloob Khushi, Vinay Reddy, Sakthivel Rajendran, Imran Razzak, Jinman Kim
In recent years, with the growing amount of biomedical documents, coupled with advancement in natural language processing algorithms, the research on biomedical named entity recognition (BioNER) has increased exponentially.
no code implementations • 29 Jul 2020 • Lei Bi, Jinman Kim, Tingwei Su, Michael Fulham, David Dagan Feng, Guang Ning
The application of CNNs, to adrenal masses is challenging due to large intra-class variations, large inter-class similarities and imbalanced training data due to the size of the mass lesions.
no code implementations • 29 Jul 2020 • Xiaohang Fu, Lei Bi, Ashnil Kumar, Michael Fulham, Jinman Kim
Our MSAM can be applied to common backbone architectures and trained end-to-end.
no code implementations • 12 Jul 2020 • Yige Peng, Lei Bi, Michael Fulham, Dagan Feng, Jinman Kim
'Radiomics' is a method that extracts mineable quantitative features from radiographic images.
1 code implementation • CVPR 2020 • Yuyu Guo, Lei Bi, Euijoon Ahn, Dagan Feng, Qian Wang, Jinman Kim
SVIN introduces dual networks: first is the spatiotemporal motion network that leverages the 3D convolutional neural network (CNN) for unsupervised parametric volumetric registration to derive spatiotemporal motion field from two-image volumes; the second is the sequential volumetric interpolation network, which uses the derived motion field to interpolate image volumes, together with a new regression-based module to characterize the periodic motion cycles in functional organ structures.
1 code implementation • 2 Dec 2019 • Mingyuan Meng, Xingyu Yang, Lei Bi, Jinman Kim, Shanlin Xiao, Zhiyi Yu
Most STDP-based SNNs adopted a slow-learning Fully-Connected (FC) architecture and used a sub-optimal vote-based scheme for spike decoding.
no code implementations • 22 Sep 2019 • Ha Tran Hong Phan, Ashnil Kumar, David Feng, Michael Fulham, Jinman Kim
Cell event detection in cell videos is essential for monitoring of cellular behavior over extended time periods.
no code implementations • 7 Jun 2019 • Euijoon Ahn, Ashnil Kumar, Dagan Feng, Michael Fulham, Jinman Kim
Hence, we propose a new unsupervised feature learning method that learns feature representations to then differentiate dissimilar medical images using an ensemble of different convolutional neural networks (CNNs) and K-means clustering.
no code implementations • 15 Mar 2019 • Euijoon Ahn, Ashnil Kumar, Dagan Feng, Michael Fulham, Jinman Kim
The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data.
no code implementations • 13 Feb 2019 • Lei Bi, Yuyu Guo, Qian Wang, Dagan Feng, Michael Fulham, Jinman Kim
Our approach leverages deep residual architectures and FCNs and learns and infers the location of the optic cup and disk in a step-wise manner with fine-grained details.
1 code implementation • 5 Oct 2018 • Ashnil Kumar, Michael Fulham, Dagan Feng, Jinman Kim
Our aim is to improve fusion of the complementary information in multi-modality PET-CT with a new supervised convolutional neural network (CNN) that learns to fuse complementary information for multi-modality medical image analysis.
no code implementations • 23 Jul 2018 • Lei Bi, Dagan Feng, Jinman Kim
Segmentation of skin lesions is considered as an important step in computer aided diagnosis (CAD) for automated melanoma diagnosis.
no code implementations • 16 Jul 2018 • Euijoon Ahn, Jinman Kim, Ashnil Kumar, Michael Fulham, Dagan Feng
The availability of large-scale annotated image datasets and recent advances in supervised deep learning methods enable the end-to-end derivation of representative image features that can impact a variety of image analysis problems.
no code implementations • 7 Sep 2017 • Ha Tran Hong Phan, Ashnil Kumar, David Feng, Michael Fulham, Jinman Kim
We compared our method to several published supervised methods evaluated on the same dataset and to a supervised LSTM method with a similar design and configuration to our unsupervised method.
2 code implementations • 31 Jul 2017 • Lei Bi, Jinman Kim, Ashnil Kumar, Dagan Feng, Michael Fulham
Positron emission tomography (PET) image synthesis plays an important role, which can be used to boost the training data for computer aided diagnosis systems.
no code implementations • 10 Apr 2017 • Lei Bi, Jinman Kim, Ashnil Kumar, Dagan Feng
Recently, deep learning methods based on fully convolutional networks (FCNs) have been successful in many segmentation problems primarily because they leverage a large labelled dataset to hierarchically learn the features that best correspond to the shallow visual appearance as well as the deep semantics of the areas to be segmented.
no code implementations • 12 Mar 2017 • Lei Bi, Jinman Kim, Euijoon Ahn, Dagan Feng
Dermoscopy images play an important role in the non-invasive early detection of melanoma [1].