365 Hits in 3.9 sec

Cross-Modal Self-Attention Distillation for Prostate Cancer Segmentation [article]

Guokai Zhang, Xiaoang Shen, Ye Luo, Jihao Luo, Zeju Wang, Weigang Wang, Binghui Zhao, Jianwei Lu
2020 arXiv   pre-print
In this paper, we develop a cross-modal self-attention distillation network by fully exploiting the encoded information of the intermediate layers from different modalities, and the extracted attention  ...  Automatic segmentation of the prostate cancer from the multi-modal magnetic resonance images is of critical importance for the initial staging and prognosis of patients.  ...  CONCLUSION In this paper, we present a novel cross-modal self-attention distillation network for prostate cancer segmentation from a whole MRI.  ... 
arXiv:2011.03908v1 fatcat:arn5w6kqhnf57btymeq4tciat4

Transformers in Medical Image Analysis: A Review [article]

Kelei He, Chen Gan, Zhuoyuan Li, Islem Rekik, Zihao Yin, Wen Ji, Yang Gao, Qian Wang, Junfeng Zhang, Dinggang Shen
2022 arXiv   pre-print
Second, we review various Transformer architectures tailored for medical image applications and discuss their limitations.  ...  Specifically, we first overview the core concepts of the attention mechanism built into Transformers and other basic components.  ...  Colorectal Kather [58] colorectal cancer histology dataset GIM and LIM modules; parallel structure 93.3 94.8 Ikromjanov et al. [59] Prostate Cancer Prostate Kaggle PANDA challenge dataset Classify according  ... 
arXiv:2202.12165v3 fatcat:a2bur66wxrbvtjy7wswzhohglm

Accurate Prostate Cancer Detection and Segmentation on Biparametric MRI using Non-local Mask R-CNN with Histopathological Ground Truth [article]

Zhenzhen Dai, Ivan Jambor, Pekka Taimen, Milan Pantelic, Mohamed Elshaikh, Craig Rogers, Otto Ettala, Peter Boström, Hannu Aronen, Harri Merisaari, Ning Wen
2020 arXiv   pre-print
Conclusion: DL models can achieve high prostate cancer detection and segmentation accuracy on bp-MRI based on annotations from histologic images.  ...  Two label selection strategies were investigated in self-training.  ...  Introduction Prostate cancer (PCa) accounts for more than 20% of new cancer diagnoses in men, with an estimated 191,930 new cases and 33,330 deaths expected in 2020 (1) .  ... 
arXiv:2010.15233v1 fatcat:cxb25g4nh5bnjig53yaxpu56ui

Front Matter: Volume 11596

Bennett A. Landman, Ivana Išgum
2021 Medical Imaging 2021: Image Processing  
The publisher is not responsible for the validity of the information or for any outcomes resulting from reliance thereon.  ...  Please use the following format to cite material from these proceedings: Publication of record for individual papers is online in the SPIE Digital Library.  ...  11596 0Z Improving T1w MRI-based brain tumor segmentation using cross-modal distillation 11596 11 Use of a convolutional neural network to identify infarct core using computed tomography perfusion parameters  ... 
doi:10.1117/12.2595437 fatcat:7x4u3yicqvev5n3gmo54gqr2am

Pathomic Fusion: An Integrated Framework for Fusing Histopathology and Genomic Features for Cancer Diagnosis and Prognosis [article]

Richard J. Chen, Ming Y. Lu, Jingwen Wang, Drew F. K. Williamson, Scott J. Rodig, Neal I. Lindeman, Faisal Mahmood
2020 arXiv   pre-print
attention mechanism.  ...  In this work, we propose Pathomic Fusion, an interpretable strategy for end-to-end multimodal fusion of histology image and genomic (mutations, CNV, RNA-Seq) features for survival outcome prediction.  ...  [16] have used graph convolutional networks for breast, colon and prostate cancer histology classification respectively.  ... 
arXiv:1912.08937v3 fatcat:uruvdqhve5fu3e3amoce5pykmy

A Survey on Deep Learning of Small Sample in Biomedical Image Analysis [article]

Pengyi Zhang, Yunxin Zhong, Yulin Deng, Xiaoying Tang, Xiaoqiong Li
2019 arXiv   pre-print
learning techniques, (3) transfer learning techniques, (4) active learning techniques, and (5) miscellaneous techniques involving data augmentation, domain knowledge, traditional shallow methods and attention  ...  The success of deep learning has been witnessed as a promising technique for computer-aided biomedical image analysis, due to end-to-end learning framework and availability of large-scale labelled samples  ...  Acknowledgements The authors would like to thank members of the Medical Image Analysis for discussions and suggestions.  ... 
arXiv:1908.00473v1 fatcat:atotvdxp6janve2mz3swyf47xa

Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models [article]

Jialin Peng, Ye Wang
2021 arXiv   pre-print
The labeling costs for medical images are very high, especially in medical image segmentation, which typically requires intensive pixel/voxel-wise labeling.  ...  application of deep learning models in medical image segmentation.  ...  To improve cross-modal segmentation with limited training samples, Cai et al.  ... 
arXiv:2103.00429v1 fatcat:p44a5e34sre4nasea5kjvva55e

Computer-Assisted Analysis of Biomedical Images [article]

Leonardo Rundo
2021 arXiv   pre-print
In reference to biomedical image analysis, the advances in image acquisition modalities and high-throughput imaging experiments are creating new challenges.  ...  As a matter of fact, the proposed computer-assisted bioimage analysis methods can be beneficial for the definition of imaging biomarkers, as well as for quantitative medicine and biology.  ...  represents the gold-standard for diagnosis of prostate cancer [259] .  ... 
arXiv:2106.04381v1 fatcat:osqiyd3sbja3zgrby7bf4eljfm

Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models

Jialin Peng, Ye Wang
2021 IEEE Access  
The labeling costs for medical images are very high, especially in medical image segmentation, which typically requires intensive pixel/voxel-wise labeling.  ...  INDEX TERMS Medical image segmentation, semi-supervised segmentation, partially-supervised segmentation, noisy label, sparse annotation. 36828  ...  To improve cross-modal segmentation with limited training samples, Cai et al.  ... 
doi:10.1109/access.2021.3062380 fatcat:r5vsec2yfzcy5nk7wusiftyayu

Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond

Guang Yang, Qinghao Ye, Jun Xia
2021 Information Fusion  
We then introduced our solutions for XAI leveraging multi-modal and multi-centre data fusion, and subsequently validated in two showcases following real clinical scenarios.  ...  The XAI becomes more and more crucial for deep learning powered applications, especially for medical and healthcare studies, although in general these deep neural networks can return an arresting dividend  ...  prostate cancer Singh et al. [121] DeepLIFT and others Post-hoc Global, Local Model-agnostic Ophthalmic diagnosis Attention Mechanism Kwon et al. [130] Attention Intrinsic Global, Local  ... 
doi:10.1016/j.inffus.2021.07.016 pmid:34980946 pmcid:PMC8459787 fatcat:3rmzvn72dbgglcddgolce2xsfe

Deep Neural Architectures for Medical Image Semantic Segmentation: Review

Muhammad Zubair Khan, Mohan Kumar Gajendran, Yugyung Lee, Muazzam A. Khan
2021 IEEE Access  
The proposed network is simulated over 3D MRI volumes for prostate segmentation; a critical diagnostic task for assessing the prostate condition.  ...  The Attention U-Net is used for lesion and pancreas segmentation.  ... 
doi:10.1109/access.2021.3086530 fatcat:hacpqwdxybh63j5ygebqszm7qq

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation [article]

Nima Tajbakhsh, Laura Jeyaseelan, Qian Li, Jeffrey Chiang, Zhihao Wu, Xiaowei Ding
2020 arXiv   pre-print
data is available for training, and weak annotations where the training data has only sparse annotations, noisy annotations, or image-level annotations.  ...  The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks.  ...  Manifold mixup has recently proved effective for prostate cancer segmentation on MR image Jung et al. (2019) , improving Dice by two to four points depending on the neural architecture used for segmentation  ... 
arXiv:1908.10454v2 fatcat:mjvfbhx75bdkbheysq3r7wmhdi

Recent advances in multifunctional magnetic nanoparticles and applications to biomedical diagnosis and treatment

Kai Yan, Penghui Li, Haie Zhu, Yingjie Zhou, Jingde Ding, Jie Shen, Zheng Li, Zushun Xu, Paul K. Chu
2013 RSC Advances  
In addition, targeted drug and gene delivery, hyperthermia treatment for cancer, and other biomedical diagnosis rendered possible by MNPs are described.  ...  This review summarizes recent developments pertaining to the synthesis of MNPs with focus on the various surface modification strategies such as chemical synthesis, self-assembly, and ligand exchange.  ...  multiple types of cancer, including recurrent malignant astrocytic brain tumors, breast and prostate cancer, malignant melanoma, lymph node metastasis, glioblastoma, cervical carcinoma, and head and neck  ... 
doi:10.1039/c3ra40348c fatcat:xgh5ofbuy5bu7oqmdrmkq32chi

Adversary-Aware Multimodal Neural Networks for Cancer Susceptibility Prediction From Multiomics Data

Md. Rezaul Karim, Tanhim Islam, Christoph Lange-Bever, Dietrich Rebholz-Schuhmann, Stefan Josef Decker
2022 IEEE access 10  
A critical and challenging usage scenario for AI is aiding the treatment of cancerous conditions. Providing accurate diagnosis for cancer is a challenging problem in precision oncology.  ...  Overall, our study suggests that a well-fitted and adversarially robust model can provide consistent and reliable diagnosis for cancer.  ...  via attention-gated tensor fusion.  ... 
doi:10.18154/rwth-2022-06375 fatcat:kugca7gol5fbrmwb34m33lpfve

Efficient High-Resolution Deep Learning: A Survey [article]

Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis
2022 arXiv   pre-print
Such high-resolution data often need to be processed by deep learning models for cancer detection, automated road navigation, weather prediction, surveillance, optimizing agricultural processes and many  ...  Using high-resolution images and videos as direct inputs for deep learning models creates many challenges due to their high number of parameters, computation cost, inference latency and GPU memory consumption  ...  Cross-shaped self-attention, shown in Figure 15 , splits the K Fig. 14 : HRFormer block. Multi-head self-attention (MHSA) is applied only within each patch.  ... 
arXiv:2207.13050v1 fatcat:bcmi2kcf55gzve44w6cpez5dvm
« Previous Showing results 1 — 15 out of 365 results