Results 81 to 90 of about 5,885,991 (322)

Gated Self-supervised Learning for Improving Supervised Learning

2024 IEEE Conference on Artificial Intelligence (CAI)
In past research on self-supervised learning for image classification, the use of rotation as an augmentation has been common. However, relying solely on rotation as a self-supervised transformation can limit the ability of the model to learn rich features from the data.
Fuadi, Erland Hilman, Ruslim, Aristo Renaldo, Wardhana, Putu Wahyu Kusuma, Yudistira, Novanto   +3 more
openaire   +2 more sources

Systematic profiling of cancer‐fibroblast interactions reveals drug combinations in ovarian cancer

Molecular Oncology, EarlyView.
Fibroblasts, cells in the tumor environment, support ovarian cancer cell growth and alter morphology and drug response. We used fibroblast and cancer cell co‐culture models to test 528 drugs and discovered new drugs for combination treatment. We showed that adding Vorinostat or Birinapant to standard chemotherapy may improve drug response, suggesting ...
Greta Gudoityte, Osheen Sharma, Laura Leuenberger, Emelie Wallin, Josefin Fernebro, Päivi Östling, Rebecka Bergström, Johan Lindberg, Ulrika Joneborg, Olli Kallioniemi, Brinton Seashore‐Ludlow   +10 more
wiley   +1 more source

Advancements in Semi-Supervised Deep Learning for Brain Tumor Segmentation in MRI: A Literature Review

AI
For automatic tumor segmentation in magnetic resonance imaging (MRI), deep learning offers very powerful technical support with significant results. However, the success of supervised learning is strongly dependent on the quantity and accuracy of labeled
Chengcheng Jin, Theam Foo Ng, Haidi Ibrahim   +2 more
doaj   +1 more source

Circulating tumor DNA monitoring and blood tumor mutational burden in patients with metastatic solid tumors treated with atezolizumab

Molecular Oncology, EarlyView.
In patients treated with atezolizumab as a part of the MyPathway (NCT02091141) trial, pre‐treatment ctDNA tumor fraction at high levels was associated with poor outcomes (radiographic response, progression‐free survival, and overall survival) but better sensitivity for blood tumor mutational burden (bTMB).
Charles Swanton, Russell W. Madison, Candice Francheska B. Tambaoan, Funda Meric‐Bernstam, Christopher J. Sweeney, Razelle Kurzrock, Howard A. Burris III, David R. Spigel, Hanna Tukachinsky, Jason Hughes, Julia Malato, Bongin Yoo, Tania Szado, Cheryl Schwab, Lincoln W. Pasquina, Amaya Gasco, Katja Schulze, Claire F. Friedman   +17 more
wiley   +1 more source

An Efficient Approach to Select Instances in Self-Training and Co-Training Semi-Supervised Methods

IEEE Access, 2022
Semi-supervised learning is a machine learning approach that integrates supervised and unsupervised learning mechanisms. In this learning, most of labels in the training set are unknown, while there is a small part of data that has known labels. The semi-
Karliane Medeiros Ovidio Vale, Arthur Costa Gorgonio, Flavius Da Luz E Gorgonio, Anne Magaly De Paula Canuto   +3 more
doaj   +1 more source

Self-supervised learning

, 2020
This talk was presented for the Machine Learning Reading Group of the Wellcome Trust EPSRC for Interventional and Surgical Sciences of University College London, 11 February 2020.I gave an overview of self-supervised learning and some applications to computer vision and medical images.
openaire   +1 more source

S4L: Self-Supervised Semi-Supervised Learning [PDF]

2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019
This work tackles the problem of semi-supervised learning of image classifiers. Our main insight is that the field of semi-supervised learning can benefit from the quickly advancing field of self-supervised visual representation learning. Unifying these two approaches, we propose the framework of self-supervised semi-supervised learning and use it to ...
Xiaohua Zhai, Alexander Kolesnikov, Lucas Beyer, Avital Oliver   +3 more
openaire   +3 more sources

Machine learning for identifying liver and pancreas cancers through comprehensive serum glycopeptide spectra analysis: a case‐control study

Molecular Oncology, EarlyView.
This study presents a novel AI‐based diagnostic approach—comprehensive serum glycopeptide spectra analysis (CSGSA)—that integrates tumor markers and enriched glycopeptides from serum. Using a neural network model, this method accurately distinguishes liver and pancreatic cancers from healthy individuals.
Motoyuki Kohjima, Yuko Takami, Ken Kawabe, Kazuhiro Tanabe, Chihiro Hayashi, Mikio Mikami, Tetsuya Kusumoto   +6 more
wiley   +1 more source

Unveiling unique protein and phosphorylation signatures in lung adenocarcinomas with and without ALK, EGFR, and KRAS genetic alterations

Molecular Oncology, EarlyView.
Proteomic and phosphoproteomic analyses were performed on lung adenocarcinoma (LUAD) tumors with EGFR, KRAS, or EML4–ALK alterations and wild‐type cases. Distinct protein expression and phosphorylation patterns were identified, especially in EGFR‐mutated tumors. Key altered pathways included vesicle transport and RNA splicing.
Fanni Bugyi, Mirjam Balbisi, Simon Sugár, Lóránd Váncza, Eszter Regős, Ilona Kovalszky, Ibolya Laczó, Tünde Harkó, Gábor Kecskeméti, Zoltán Szabó, Judit Moldvay, László Drahos, Lilla Turiák   +12 more
wiley   +1 more source

Augmenting Few-Shot Learning With Supervised Contrastive Learning

IEEE Access, 2021
Few-shot learning deals with a small amount of data which incurs insufficient performance with conventional cross-entropy loss. We propose a pretraining approach for few-shot learning scenarios.
Taemin Lee, Sungjoo Yoo
doaj   +1 more source