binary classification model of supervised cnn deep learning with multiple hidden layers Search Results


multi-resolution cnn architecture  (Panoptes Pharma GmbH)
90
Panoptes Pharma GmbH multi-resolution cnn architecture
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Multi Resolution Cnn Architecture, supplied by Panoptes Pharma GmbH, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/multi-resolution cnn architecture/product/Panoptes Pharma GmbH
Average 90 stars, based on 1 article reviews
multi-resolution cnn architecture - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier
resnet18-softmax  (SoftMax Inc)
90
SoftMax Inc resnet18-softmax
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Resnet18 Softmax, supplied by SoftMax Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/resnet18-softmax/product/SoftMax Inc
Average 90 stars, based on 1 article reviews
resnet18-softmax - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier
msa multiple sequence alignment bmi body mass index nb naïve bayes cnn convolutional neural network ncbi national centre  (Biotechnology Information)
86
Biotechnology Information msa multiple sequence alignment bmi body mass index nb naïve bayes cnn convolutional neural network ncbi national centre
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Msa Multiple Sequence Alignment Bmi Body Mass Index Nb Naïve Bayes Cnn Convolutional Neural Network Ncbi National Centre, supplied by Biotechnology Information, used in various techniques. Bioz Stars score: 86/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/msa multiple sequence alignment bmi body mass index nb naïve bayes cnn convolutional neural network ncbi national centre/product/Biotechnology Information
Average 86 stars, based on 1 article reviews
msa multiple sequence alignment bmi body mass index nb naïve bayes cnn convolutional neural network ncbi national centre - by Bioz Stars, 2026-06
86/100 stars
  Buy from Supplier
panoptes-based multi-resolution cnn models  (Panoptes Pharma GmbH)
90
Panoptes Pharma GmbH panoptes-based multi-resolution cnn models
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Panoptes Based Multi Resolution Cnn Models, supplied by Panoptes Pharma GmbH, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/panoptes-based multi-resolution cnn models/product/Panoptes Pharma GmbH
Average 90 stars, based on 1 article reviews
panoptes-based multi-resolution cnn models - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier
paired multi-scale 3d cnn  (Optics and Photonics)
90
Optics and Photonics paired multi-scale 3d cnn
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Paired Multi Scale 3d Cnn, supplied by Optics and Photonics, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/paired multi-scale 3d cnn/product/Optics and Photonics
Average 90 stars, based on 1 article reviews
paired multi-scale 3d cnn - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier
deep multiple instance cnn  (IEEE Access)
90
IEEE Access deep multiple instance cnn
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Deep Multiple Instance Cnn, supplied by IEEE Access, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/deep multiple instance cnn/product/IEEE Access
Average 90 stars, based on 1 article reviews
deep multiple instance cnn - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier
multi-column cnn  (SoftMax Inc)
90
SoftMax Inc multi-column cnn
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Multi Column Cnn, supplied by SoftMax Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/multi-column cnn/product/SoftMax Inc
Average 90 stars, based on 1 article reviews
multi-column cnn - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier
multi branch residual cnn  (Kaggle Inc)
86
Kaggle Inc multi branch residual cnn
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Multi Branch Residual Cnn, supplied by Kaggle Inc, used in various techniques. Bioz Stars score: 86/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/multi branch residual cnn/product/Kaggle Inc
Average 86 stars, based on 1 article reviews
multi branch residual cnn - by Bioz Stars, 2026-06
86/100 stars
  Buy from Supplier
fundus imaging  (EyePACS LLC)
90
EyePACS LLC fundus imaging
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Fundus Imaging, supplied by EyePACS LLC, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/fundus imaging/product/EyePACS LLC
Average 90 stars, based on 1 article reviews
fundus imaging - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier
multi-resolution cnn models  (Panoptes Pharma GmbH)
90
Panoptes Pharma GmbH multi-resolution cnn models
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Multi Resolution Cnn Models, supplied by Panoptes Pharma GmbH, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/multi-resolution cnn models/product/Panoptes Pharma GmbH
Average 90 stars, based on 1 article reviews
multi-resolution cnn models - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier
multiple cnn models  (Kaggle Inc)
86
Kaggle Inc multiple cnn models
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Multiple Cnn Models, supplied by Kaggle Inc, used in various techniques. Bioz Stars score: 86/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/multiple cnn models/product/Kaggle Inc
Average 86 stars, based on 1 article reviews
multiple cnn models - by Bioz Stars, 2026-06
86/100 stars
  Buy from Supplier
mnist handwritten digit database  (National Institute of Standards and Technology)
90
National Institute of Standards and Technology mnist handwritten digit database
Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.
Mnist Handwritten Digit Database, supplied by National Institute of Standards and Technology, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/mnist handwritten digit database/product/National Institute of Standards and Technology
Average 90 stars, based on 1 article reviews
mnist handwritten digit database - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier

Image Search Results


Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.

Journal: Cell Reports Medicine

Article Title: Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models

doi: 10.1016/j.xcrm.2021.100400

Figure Lengend Snippet: Workflow and Panoptes architecture (A) A total of 456 patients in the cohorts from CPTAC and TCGA with feature annotations. (B) Overall workflow. I, H&E slide images of endometrial cancers were downloaded from databases; II, slides were separated at the per-patient level into a training, validation, and test set; III, slides were cut into 299 × 299-pixel tiles excluding background, and contaminants and qualified tiles were packaged into TFrecord files for each set; IV, training and validation sets were used to train the convolutional neural networks, and the testing set was used to evaluate trained models; V, activation maps of test set tiles were extracted and dimensionally reduced by tSNE to visualize features, while the per-tile predictions were aggregated back into intact slides; VI, an independent test set with samples from NYU hospitals was used to test the generalizability of selected best-performing models. (C) Slides were cut into paired tile sets at 2.5×, 5×, and 10× equivalent resolution of the same region to prepare for Panoptes. (D) Panoptes architecture with optional 1 × 1 convolutional layer and clinical features branch.

Article Snippet: Overall, we demonstrated that our multi-resolution CNN architecture, Panoptes, can be developed into a practical tool to assist pathologists’ classifying endometrial cancer histological subtypes and, more important, to provide additional information about patients’ molecular subtypes and mutation status in a much more rapid fashion and without the need for sequencing.

Techniques: Biomarker Discovery, Activation Assay