Results 121 to 130 of about 5,782,720 (331)

Spatial heterogeneity of hotspot mutations and clonal relatedness in ovarian endometrioid carcinoma

Molecular Oncology, EarlyView.
Spatially resolved analysis revealed heterogeneous distributions of selected cancer‐associated mutations within ovarian endometrioid carcinomas. Shared mutations between paired endometrial and ovarian tumors supported clonal relatedness. These findings highlight the value of sampling multiple tumor regions when interpreting molecular profiles ...
Takahito Ashihara, Kosuke Murakami, Shiro Takamatsu, Akiko Kanto, Seiichi Mori, Tomoyuki Otani, Kazuko Sakai, Yasushi Kotani, Kazuto Nishio, Kaoru Abiko, Noriomi Matsumura   +10 more
wiley   +1 more source

Comparison of spatial classification rules with different conditional distributions of class label

Nonlinear Analysis, 2014
In this paper spatial classification rules based on Bayes discriminant functions are considered. The novelty of this work is that the statistical supervised classification method is improved by extending the influence of spatial correlation between ...
Giedrius Stabingis, Kęstutis Dučinskas, Lijana Stabingienė   +2 more
doaj   +1 more source

Tumour‐proximal deep serum proteomics identifies biomarkers associated with ovarian cancer

Molecular Oncology, EarlyView.
New biomarkers are needed for early ovarian cancer detection. Ovarian (tumour‐proximal) and peripheral vein serum from healthy women and patients with benign or malignant tumours underwent nanoparticle‐enriched deep proteomics. Ovarian serum yielded more protein identifications and revealed tumour‐reflective signatures.
Darren Lau, Daniel Pincher, Clifford Young, Nicholas Chappell, Noor A. Lokman, Parul Mittal, Leigh Donnellan, Martin K. Oehler, Doug A. Brooks, Peter Hoffmann   +9 more
wiley   +1 more source

A self-supervised classification model for endometrial diseases. [PDF]

J Cancer Res Clin Oncol, 2023
Fang Y, Wei Y, Liu X, Qin L, Gao Y, Yu Z, Xu X, Cha G, Zhu X, Wang X, Xu L, Cao L, Chen X, Jiang H, Zhang C, Zhou Y, Zhu J.   +16 more
europepmc   +1 more source

Analysis of supervised classification techniques

, 2017
As the number of digital documents and data are being increased rapidly, it is important to classify them in to respective categories. This process of classifying the data is called classification.
D. Rajeswara Rao, P. Lakhmi Prasanna, K. Maithri, T. Dhinesh, Y. Meghana   +4 more
core   +1 more source

Attitudes of cancer patients toward ctDNA‐based liquid biopsy for follow‐up

Molecular Oncology, EarlyView.
This mixed‐methods study explored cancer patients' experiences, knowledge, and preferences regarding ctDNA‐based liquid biopsy for follow‐up. Awareness of ctDNA was low and recall of previous liquid biopsy was imperfect, yet acceptance was high.
Siddharth Chhajlani, Laura Mariën, Caro De Weerdt, Sanne Wouters, Laure‐Anne Teuwen, Hans Prenen, Katleen Janssens, Timon Vandamme   +7 more
wiley   +1 more source

Training set edition using Rough Set Theory for Semi-supervised Classification

, 2017
Semi-supervised Classification (SSC) is becoming an attractive research filed due to the emergence of real-world problems on which the number of unlabeled examples exceeds the labeled ones.
Nápoles, G., Nowe, A., García Lorenzo, M.M., Sengupta, D., Grau, I.   +4 more
core   +2 more sources

Application of spatial classification rules for remotely sensed images

Lietuvos Matematikos Rinkinys, 2014
In this paper the remote sensed image classification example using spacial classification rule with distance (SCRD) is examined. This supervised classification method was first presented in paper [11].
Giedrius Stabingis, Lijana Stabingienė
doaj   +1 more source

A novel two stage scheme utilizing the test set for model selection in text classification [PDF]

, 2005
Text classification is a natural application domain for semi-supervised learning, as labeling documents is expensive, but on the other hand usually an abundance of unlabeled documents is available.
Pfahringer, Bernhard, Mayo, Michael, Reutemann, Peter   +2 more
core  

Automated FRAP microscopy for high‐throughput analysis of protein dynamics in chromatin organization and transcription

FEBS Open Bio, EarlyView.
RoboMic is an automated confocal microscopy pipeline for high‐throughput functional imaging in living cells. Demonstrated with fluorescence recovery after photobleaching (FRAP), it integrates AI‐driven nuclear segmentation, ROI selection, bleaching, and analysis.
Selçuk Yavuz, Bart Geverts, Johan A. Slotman, Andrea Sacchetti, Stefan Prekovic, Martin E. van Royen, Adriaan B. Houtsmuller   +6 more
wiley   +1 more source