1,411 Hits in 7.2 sec

When machine vision meets histology: A comparative evaluation of model architecture for classification of histology sections

Cheng Zhong, Ju Han, Alexander Borowsky, Bahram Parvin, Yunfu Wang, Hang Chang
2017 Medical Image Analysis  
of model architecture and its 378 impact, in terms of performance and robustness, on the classification of histology 379 sections.  ...  , on the classification of histology sections.  ...  Here, the performance is reported as the mean and standard error of the correct classification rate, as detailed in Section 4.  ... 
doi:10.1016/ pmid:27644083 pmcid:PMC5099087 fatcat:2k364a7aazdyrbiayvzactw7ue

SHIRAZ: an automated histology image annotation system for zebrafish phenomics

Brian A. Canada, Georgia K. Thomas, Keith C. Cheng, James Z. Wang
2010 Multimedia tools and applications  
In support of this project, we present a novel content-based image retrieval system for the automated annotation of images containing histological abnormalities in the developing eye of the larval zebrafish  ...  Histological characterization is used in clinical and research contexts as a highly sensitive method for detecting the morphological features of disease and abnormal gene function.  ...  development of automated cancer diagnosis systems that make use of advances in machine vision.  ... 
doi:10.1007/s11042-010-0638-4 pmid:21461317 pmcid:PMC3066164 fatcat:7ylafkbzrbhdtptdrey6volqse

A Review of Intrinsic Optical Imaging Serial Blockface Histology (ICI-SBH) for Whole Rodent Brain Imaging

Joël Lefebvre, Patrick Delafontaine-Martel, Frédéric Lesage
2019 Photonics  
The paper concludes with a perspective of future developments, calling for a consolidation of the SBH research and development efforts around the world.  ...  Serial blockface histology (SBH) systems using ICI modalities are then reported, followed by a review of some of their applications.  ...  tissue identification with image classification networks [162] , or the use of machine learning for online automated optimization of microscopy [163] .  ... 
doi:10.3390/photonics6020066 fatcat:qyfjrhymyndrzewigjrogxbbw4

ArcticAI: A Deep Learning Platform for Rapid and Accurate Histological Assessment of Intraoperative Tumor Margins [article]

Joshua Levy, Matthew Davis, Rachael Chacko, Michael Davis, Lucy Fu, Tarushii Goel, Akash Pamal, Irfan Nafi, Abhinav Angirekula, Brock Christensen, Matthew Hayden, Louis Vaickus (+1 others)
2022 medRxiv   pre-print
Using basal cell carcinoma (BCC) as a model system, the results demonstrate that ArcticAI can provide effective grossing recommendations, accurately identify tumor on histological sections, map tumor back  ...  Mohs Micrographic Surgery (MMS) is used for the removal of basal cell and squamous cell carcinoma utilizing frozen sections for real-time margin assessment while assessing 100% of the peripheral and deep  ...  Acknowledgements We would like to thank John Kim, Adnan Murtaza, Sagar Gupta, Sachin Satishkumar and Aryan Kumawat from the EDIT Machine Learning Summer program for initial explorations of 3D modeling  ... 
doi:10.1101/2022.05.06.22274781 fatcat:7lj74vmwhze75nllbanxxllfym

Evaluating reproducibility of AI algorithms in digital pathology with DAPPER [article]

Andrea Bizzego, Nicole Bussola, Marco Chierici, Marco Cristoforetti, Margherita Francescatto, Valerio Maggio, Giuseppe Jurman, Cesare Furlanello
2018 bioRxiv   pre-print
In this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility.  ...  Further, we use the deep features from the VGG model from GTEx on the KIMIA24 dataset for identification of slide of origin (24 classes) to train a classifier on 1060 annotated tiles and validated on 265  ...  first section of tools in the DAPPER framework, as a benchmark 327 dataset for validating machine learning models in digital pathology.  ... 
doi:10.1101/340646 fatcat:a7f7o5qhybcg3pvbuf6p6zzxwe

Evaluating reproducibility of AI algorithms in digital pathology with DAPPER

Andrea Bizzego, Nicole Bussola, Marco Chierici, Valerio Maggio, Margherita Francescatto, Luca Cima, Marco Cristoforetti, Giuseppe Jurman, Cesare Furlanello, Gustavo Rohde
2019 PLoS Computational Biology  
In this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility.  ...  Further, we use the deep features from the VGG model from GTEx on the KIMIA24 dataset for identification of slide of origin (24 classes) to train a classifier on 1, 060 annotated tiles and validated on  ...  Coviello for his help in the networks' optimization and G. Franch for the realization of the striking image.  ... 
doi:10.1371/journal.pcbi.1006269 fatcat:j2np2va2q5cg5o6qec3cwhkkoq

A review of machine learning approaches, challenges and prospects for computational tumor pathology [article]

Liangrui Pan, Zhichao Feng, Shaoliang Peng
2022 arXiv   pre-print
This review investigates image preprocessing methods in computational pathology from a pathological and technical perspective, machine learning-based methods, and applications of computational pathology  ...  Finally, the challenges and prospects of machine learning in computational pathology applications are discussed.  ...  Deep learning models and seven machine learning methods were compared for Gleason score changes and classification performance in the pT2 phase.  ... 
arXiv:2206.01728v1 fatcat:g7r7fsw2bzafpkkyg6hpzjyt5e

Deep Learning on Histopathological Images for Colorectal Cancer Diagnosis: A Systematic Review

Athena Davri, Effrosyni Birbas, Theofilos Kanavos, Georgios Ntritsos, Nikolaos Giannakeas, Alexandros T. Tzallas, Anna Batistatou
2022 Diagnostics  
The increased diagnostic load in the pathology laboratory, combined with the reported intra- and inter-variability in the assessment of biomarkers, has prompted the quest for reliable machine-based methods  ...  features related to prognosis and correlated to metastasis, and assess the specific components of the tumor microenvironment.  ...  Several studies have shown that many DL-based models' predictions did not differ in terms of statistical significance when compared to pathologists' predictions [45, 104] .  ... 
doi:10.3390/diagnostics12040837 pmid:35453885 pmcid:PMC9028395 fatcat:kl6elydxbnc7xcrlwsj2ptvzxu

Viable and necrotic tumor assessment from whole slide images of osteosarcoma using machine-learning and deep-learning models

Harish Babu Arunachalam, Rashika Mishra, Ovidiu Daescu, Kevin Cederberg, Dinesh Rakheja, Anita Sengupta, David Leonard, Rami Hallac, Patrick Leavey, Kaiming Li
2019 PLoS ONE  
With the goal of labeling the diverse regions of the digitized tissue into viable tumor, necrotic tumor, and non-tumor, we trained 13 machine-learning models and selected the top performing one (a Support  ...  Thus, we lay the foundation for a complete tumor assessment pipeline from original histology images to tumor-prediction map generation.  ...  Bogdan Armaselu for helpful discussions. We also would like to thank John-Paul Bach, Molly Ni'Suilleabhain and Sammy Glick from UT Southwestern Medical Center for their help with the datasets.  ... 
doi:10.1371/journal.pone.0210706 pmid:30995247 pmcid:PMC6469748 fatcat:mz7k6yy6encwlfur35wdqca564

Survival Associations Using Perfusion and Diffusion Magnetic Resonance Imaging in Patients With Histologic and Genetic Defined Diffuse Glioma World Health Organization Grades II and III

Anna Latysheva, Kyrre Eeg Emblem, Andrés Server, Petter Brandal, Torstein R. Meling, Jens Pahnke, John K. Hald
2018 Journal of computer assisted tomography  
A specification of the medical diagnostic task is necessary before evaluation of machine-learning models for appropriate model training.  ...  These differences were much larger when a high b-value was used (all P < 0.0001) compared to the use of a standard b-value.  ...  The quality of all corrected output data was evaluated by visual inspection.  ... 
doi:10.1097/rct.0000000000000742 pmid:29901512 fatcat:l73mkua575b6lecog5uzzrfhkq

Breast cancer outcome prediction with tumour tissue images and machine learning

Riku Turkki, Dmitrii Byckhov, Mikael Lundin, Jorma Isola, Stig Nordling, Panu E. Kovanen, Clare Verrill, Karl von Smitten, Heikki Joensuu, Johan Lundin, Nina Linder
2019 Breast Cancer Research and Treatment  
The outcome classifier is trained using sample images of 868 patients and evaluated and compared with human expert classification in a test set of 431 patients.  ...  The DRS classification remained as an independent predictor of breast cancer-specific survival in a multivariate Cox model with a hazard ratio of 2.04 (95% CI 1.20-3.44, p = 0.007).  ...  We thank the Digital Microscopy and Molecular Pathology unit at FIMM, supported by the Helsinki Institute of Life Science and Biocenter Finland for providing slide scanning services.  ... 
doi:10.1007/s10549-019-05281-1 pmid:31119567 pmcid:PMC6647903 fatcat:3guvw4nfjnggtnuas3o4nj2ady

Deep Learning for Prostate Pathology [article]

Okyaz Eminaga, Yuri Tolkach, Christian Kunder, Mahmood Abbas, Ryan Han, Rosalie Nolley, Axel Semjonow, Martin Boegemann, Sebastian Huss, Andreas Loening, Robert West, Geoffrey Sonn (+4 others)
2019 arXiv   pre-print
The current study detects different morphologies related to prostate pathology using deep learning models; these models were evaluated on 2,121 hematoxylin and eosin (H&E) stain histology images captured  ...  The true positive rate (TPR) for slides with prostate cancer was 99.7% by a false positive rate of 0.785%.  ...  Acknowledgment PlexusNet and the derivate digital markers for survival and genomic alteration are patented.  ... 
arXiv:1910.04918v3 fatcat:svjtmndhdzdshhuxi32dqnccqe

Computer-aided diagnosis of lung carcinoma using deep learning - a pilot study [article]

Zhang Li, Zheyu Hu, Jiaolong Xu, Tao Tan, Hui Chen, Zhi Duan, Ping Liu, Jun Tang, Guoping Cai, Quchang Ouyang, Yuling Tang, Geert Litjens (+1 others)
2018 arXiv   pre-print
Conclusion: The deep learning analysis could help to speed up the detection process for the whole-slide image (WSI) and keep the comparable detection rate with human observer.  ...  Aim: Early detection and correct diagnosis of lung cancer are the most important steps in improving patient outcome.  ...  Acknowledgments The authors would like to thank Tao Xu, Jun XU, Shanshan Wan, Ke Lou, Hui Li, Keyu Li and Yusheng Yan for collecting all the images.  ... 
arXiv:1803.05471v1 fatcat:iywr6rujnja7thxgtdipnvoy44

3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images

Zakaria Senousy, Mohammed M. Abdelsamea, Mona Mostafa Mohamed, Mohamed Medhat Gaber
2021 Entropy  
In digital breast pathology, it is vital to measure how confident a DCNN is in grading using a machine-confidence metric, especially with the presence of major computer vision challenging problems such  ...  models in the ensemble architecture.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/e23050620 pmid:34065765 pmcid:PMC8156865 fatcat:sivkrzunr5esrhyado4fhipr2a

Quantification of Liver Fibrosis—A Comparative Study

Alexandros Arjmand, Markos G. Tsipouras, Alexandros T. Tzallas, Roberta Forlano, Pinelopi Manousou, Nikolaos Giannakeas
2020 Applied Sciences  
In this paper, early and recent studies on this topic have been reviewed according to these research aims: the datasets used for the analysis, the employed image processing techniques, the obtained results  ...  In the last three decades, several publications focused on the quantification of liver fibrosis by means of the estimation of the collagen proportional area (CPA) in liver biopsies obtained from digital  ...  On the contrary, CNN deep architectures require a large amount of data samples compared to conventional machine learning algorithms.  ... 
doi:10.3390/app10020447 fatcat:laisu5u5onb65iiwzlfvewtenm
« Previous Showing results 1 — 15 out of 1,411 results