603 Hits in 7.0 sec

Weakly-supervised learning for lung carcinoma classification using deep learning

Fahdi Kanavati, Gouji Toyokawa, Seiya Momosaki, Michael Rambeau, Yuka Kozuma, Fumihiro Shoji, Koji Yamazaki, Sadanori Takeo, Osamu Iizuka, Masayuki Tsuneki
2020 Scientific Reports  
We trained a Convolution Neural Network (CNN) based on the EfficientNet-B3 architecture, using transfer learning and weakly-supervised learning, to predict carcinoma in Whole Slide Images (WSIs) using  ...  Recently, Artificial Intelligence (AI) deep learning models have been widely shown to be useful in various medical fields, particularly image and pathological diagnoses; however, AI models for the pathological  ...  Leona Shinkai, and Imaging Center staffs at Medmain Inc. We thank the pathologists from around the world who have been engaged in the annotation work for this study.  ... 
doi:10.1038/s41598-020-66333-x pmid:32518413 fatcat:of7yl3ebpvhcng5kwybdmsbs4y

WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma [article]

Chu Han, Xipeng Pan, Lixu Yan, Huan Lin, Bingbing Li, Su Yao, Shanshan Lv, Zhenwei Shi, Jinhai Mai, Jiatai Lin, Bingchao Zhao, Zeyan Xu (+31 others)
2022 arXiv   pre-print
Lung cancer is the leading cause of cancer death worldwide, and adenocarcinoma (LUAD) is the most common subtype.  ...  for histopathology images of LUAD.  ...  Lung Cancer -Histopathology Image Analysis Histopathology slides are the golden standard for lung cancer diagnosis [12] .  ... 
arXiv:2204.06455v2 fatcat:o75sroudm5dr3mxyjgxkxvo54q

Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images [article]

Ming Y. Lu, Drew F. K. Williamson, Tiffany Y. Chen, Richard J. Chen, Matteo Barbieri, Faisal Mahmood
2020 arXiv   pre-print
However, deep learning-based computational pathology approaches either require manual annotation of gigapixel whole slide images (WSIs) in fully-supervised settings or thousands of WSIs with slide-level  ...  CLAM is a deep-learning-based weakly-supervised method that uses attention-based learning to automatically identify sub-regions of high diagnostic value in order to accurately classify the whole slide,  ...  Acknowledgements The authors would like to thank Alexander Bruce for scanning internal cohorts of patient histology slides at Competing Interests The authors declare that they have no competing financial  ... 
arXiv:2004.09666v2 fatcat:a7rdk6ttwvcf5oiprybaxgc2wa

Comparative analysis of machine learning approaches to classify tumor mutation burden in lung adenocarcinoma using histopathology images

Apaar Sadhwani, Huang-Wei Chang, Ali Behrooz, Trissia Brown, Isabelle Auvigne-Flament, Hardik Patel, Robert Findlater, Vanessa Velez, Fraser Tan, Kamilla Tekiela, Ellery Wulczyn, Eunhee S. Yi (+7 others)
2021 Scientific Reports  
Here we developed a deep learning system to both classify histologic patterns in lung adenocarcinoma and predict TMB status using de-identified Hematoxylin and Eosin (H&E) stained whole slide images.  ...  We first trained a convolutional neural network to map histologic features across whole slide images of lung cancer resection specimens.  ...  We would also like to thank Gary Zeger, Lindsey Clark, and Graziella Solinas for additional image review and adjudication of challenging annotations.  ... 
doi:10.1038/s41598-021-95747-4 pmid:34400666 pmcid:PMC8368039 fatcat:4whqisqfmfgwtmihsnzr72nd6q

Pan-cancer computational histopathology reveals tumor mutational burden status through weakly-supervised deep learning [article]

Siteng Chen, Jinxi Xiang, Xiyue Wang, Jun Zhang, Sen Yang, Junzhou Huang, Wei Yang, Junhua Zheng, Xiao Han
2022 arXiv   pre-print
We included whole slide images (WSIs) of 3228 diagnostic slides from the Cancer Genome Atlas and 531 WSIs from the Clinical Proteomic Tumor Analysis Consortium for the development and verification of a  ...  We proposed a multiscale weakly-supervised deep learning framework for predicting TMB of seven types of tumors based only on routinely used hematoxylin-eosin (H&E)-stained WSIs.  ...  Weakly-supervised deep learning strategy was carried out for our prediction pipeline.  ... 
arXiv:2204.03257v1 fatcat:m5eutw5ue5cxjkh2xat5rxs524

Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images [article]

Masayuki Tsuneki, Fahdi Kanavati
2022 medRxiv   pre-print
In this paper, we trained multi-organ deep learning models to classify adenocarcinoma in biopsy and radical lymph node dissection specimens whole slide images (WSIs).  ...  ., endoscopic biopsy, transbronchial lung biopsy, and needle biopsy) of possible primary organs (e.g., stomach, colon, lung, and breast) and radical lymph node dissection specimen is very useful and should  ...  Makoto Abe at Department of Pathology, Tochigi Cancer Center (Tochigi, Japan); Dr.  ... 
doi:10.1101/2022.03.28.22273054 fatcat:gjjvz2kd3zdj3edcshqgcapt7m

Deep Interactive Learning-based ovarian cancer segmentation of H E-stained whole slide images to study morphological patterns of BRCA mutation [article]

David Joon Ho, M. Herman Chui, Chad M. Vanderbilt, Jiwon Jung, Mark E. Robson, Chan-Sik Park, Jin Roh, Thomas J. Fuchs
2022 arXiv   pre-print
Deep learning has been widely used to analyze digitized hematoxylin and eosin (H&E)-stained histopathology whole slide images.  ...  Instead of annotating all pixels from cancer and non-cancer regions on giga-pixel whole slide images, an iterative process of annotating mislabeled regions from a segmentation model and training/finetuning  ...  Acknowledgments This work was supported by the Warren Alpert Foundation Center for Digital and Computational Pathology at Memorial Sloan Kettering Cancer Center and the NIH/NCI Cancer Center Support Grant  ... 
arXiv:2203.15015v1 fatcat:7k72zbzfbfemxmj73txemt4sxa

Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning [article]

Bin Li, Yin Li, Kevin W. Eliceiri
2021 arXiv   pre-print
We address the challenging problem of whole slide image (WSI) classification. WSIs have very high resolutions and usually lack localized annotations.  ...  Second, since WSIs can produce large or unbalanced bags that hinder the training of MIL models, we propose to use self-supervised contrastive learning to extract good representations for MIL and alleviate  ...  Acknowledgment: The work was supported by NIH P41-GM135019, the Semiconductor Research Corporation (SRC), and the Morgridge Institute for Research.  ... 
arXiv:2011.08939v3 fatcat:igrzeve6ergnlk6bn35peh4kcy

Beyond Classification: Whole Slide Tissue Histopathology Analysis By End-To-End Part Learning

Chensu Xie, Hassan Muhammad, Chad M. Vanderbilt, Raul Caso, Dig Vijay Kumar Yarlagadda, Gabriele Campanella, Thomas J. Fuchs
2020 International Conference on Medical Imaging with Deep Learning  
An emerging technology in cancer care and research is the use of histopathology whole slide images (WSI). Leveraging computation methods to aid in WSI assessment poses unique challenges.  ...  For this reason, state-of-the-art methods for WSI analysis adopt a two-stage approach where the training of a tile encoder is decoupled from the tile aggregation.  ...  Acknowlegements This work was supported by the Warren Alpert Foundation Center for Digital and Computational Pathology at Memorial Sloan Kettering Cancer Center, the NIH/NCI Cancer Center Support Grant  ... 
dblp:conf/midl/XieMVCYCF20 fatcat:cpawx67uyre5fowibxlwtrtnpi

Weakly-Supervised Tumor Purity Prediction From Frozen H&E Stained Slides [article]

Matthew Brendel, Vanesa Getseva, Majd Al Assaad, Michael Sigouros, Alexandros Sigaras, Troy Kane, Pegah Khosravi, Juan Miguel Mosquera, Olivier Elemento, Iman Hajirasouliha
2021 bioRxiv   pre-print
This approach allows for a flexible analysis of tumors from whole slide imaging (WSI) of histology hematoxylin and eosin (H&E) slides.  ...  Here we propose an approach, weakly-supervised purity (wsPurity), which can accurately quantify tumor purity within a slide, using multiple and different types of cancer.  ...  The results shown here are in whole or part based upon data generated by the TCGA Research Network:  ... 
doi:10.1101/2021.11.09.467901 fatcat:35zhnb5gtjcophxwpmeefeqc5e

Deep Learning for Whole-Slide Tissue Histopathology Classification: A Comparative Study in the Identification of Dysplastic and Non-Dysplastic Barrett's Esophagus

Rasoul Sali, Nazanin Moradinasab, Shan Guleria, Lubaina Ehsan, Philip Fernandes, Tilak U Shah, Sana Syed, Donald E Brown
2020 Journal of Personalized Medicine  
Deep learning-based approaches have shown promising results in the analysis of whole-slide tissue histopathology images (WSIs).  ...  of esophageal cancer compared to weakly supervised and fully supervised approaches.  ...  Weakly supervised learning for whole slide lung cancer image classification. IEEE Trans. Cybern. 2018, 50, 3950–3962. [CrossRef] 19.  ... 
doi:10.3390/jpm10040141 pmid:32977465 pmcid:PMC7711456 fatcat:j73keotvufgq7nja26vtlbqq7e

CELNet: Evidence Localization for Pathology Images using Weakly Supervised Learning [article]

Yongxiang Huang, Albert C. S. Chung
2019 arXiv   pre-print
To overcome this problem, we propose a weakly supervised learning-based approach that can effectively learn to localize the discriminative evidence for a diagnostic label from weakly labeled training data  ...  Despite deep convolutional neural networks boost the performance of image classification and segmentation in digital pathology analysis, they are usually weak in interpretability for clinical applications  ...  In this paper, we propose a weakly supervised learning (WSL) method that can learn to localize the discriminative evidence for the class-of-interest on pathology images from weakly labeled (i.e. image-level  ... 
arXiv:1909.07097v1 fatcat:jlkdftmq4ndqbiqgglbhsq2lxa

Deep Learning of Histopathology Images at the Single Cell Level

Kyubum Lee, John H. Lockhart, Mengyu Xie, Ritu Chaudhary, Robbert J. C. Slebos, Elsa R. Flores, Christine H. Chung, Aik Choon Tan
2021 Frontiers in Artificial Intelligence  
Recently, deep learning approaches have been widely used for digital histopathology images for cancer diagnoses and prognoses.  ...  In this review we focus on machine learning-based digital histopathology image analysis methods for characterizing tumor ecosystem.  ...  RJCS, RC, and JHL obtained and processed the image data. ACT, CHC, and ERF supervised the project. All the authors revised and approved the final manuscript.  ... 
doi:10.3389/frai.2021.754641 pmid:34568816 pmcid:PMC8461055 fatcat:utnyq2nvmzbitkipjo6tpiuioq

Pan-cancer image-based detection of clinically actionable genetic alterations [article]

Jakob Nikolas Kather, Lara R Heij, Heike I Grabsch, Loes FS Kooreman, Chiara Loeffler, Amelie Echle, Jeremias Krause, Hannah Sophie Muti, Jan M Niehues, Kai AJ Sommer, Peter Bankhead, Jefree J Schulte (+11 others)
2019 biorxiv/medrxiv   pre-print
Here, we show that deep learning can predict point mutations, molecular tumor subtypes and immune-related gene expression signatures directly from routine histological images of tumor tissue.  ...  Together, our findings show that a single deep learning algorithm can predict clinically actionable alterations from routine histology data.  ...  Only those images containing at least 1 mm 2 contiguous tumor tissue were used for 133 downstream analysis. 6% of whole slide images, corresponding to 5% of patients were excluded 134 due to technical  ... 
doi:10.1101/833756 fatcat:7xwb3ovndjcbti52zgp4szc3qu

Weakly supervised multiple instance learning histopathological tumor segmentation [article]

Marvin Lerousseau, Maria Vakalopoulou, Marion Classe, Julien Adam, Enzo Battistella, Alexandre Carré, Théo Estienne, Théophraste Henry, Eric Deutsch, Nikos Paragios
2021 arXiv   pre-print
In this paper, we propose a weakly supervised framework for whole slide imaging segmentation that relies on standard clinical annotations, available in most medical systems.  ...  In particular, we exploit a multiple instance learning scheme for training models.  ...  Weakly supervised learning for tissue-type segmentation in histopathological images Contextually, we consider a set S = {S i } of training whole slide images, where each slide S i is associated with a  ... 
arXiv:2004.05024v4 fatcat:3wdvmquq4rhzji7yep6guozeue
« Previous Showing results 1 — 15 out of 603 results