Original paper "Weakly-supervised segmentation using inherently-explainable classification models and their application to brain tumour classiciation)
Soumick Chatterjee
soumickmj
AI & ML interests
Representation learning, computer vision, image reconstruction, LLM
Recent Activity
updated
a collection
about 1 month ago
GP-Models
updated
a collection
about 1 month ago
GP-Models
updated
a collection
about 1 month ago
GP-Models
Organizations
ReconResNet (part of the NCC1701 pipeline) for undersampled MRI reconstruction. This collection contains weights from the original paper, and more.
-
soumickmj/NCC1701_ReconResNet2D_DS6MRA_Varden2D10
17.3M • Updated • 3 -
soumickmj/NCC1701_ReconResNet2D_DS6MRA_Varden2D05
17.3M • Updated • 5 -
soumickmj/NCC1701_ReconResNet2D_IXIT1Guys_s60to90_Varden1D15
17.3M • Updated • 6 -
soumickmj/NCC1701_ReconResNet2D_IXIT1Guys_s60to90_Varden1D10
17.3M • Updated • 3
Models from "DS6, Deformation-Aware Semi-Supervised Learning" paper, and the models trained also on the SMILE-UHURA challenge dataset
-
DS6, Deformation-aware Semi-supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data
Paper • 2006.10802 • Published -
soumickmj/DS6_UNet3D_woDeform
Image Segmentation • 0.1B • Updated • 12 • 2 -
soumickmj/DS6_UNetMSS3D_wDeform
Image Segmentation • 0.1B • Updated • 9 -
soumickmj/DS6_UNetMSS3D_woDeform
Image Segmentation • 0.1B • Updated • 10
ProbUNets from the paper "PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation"
-
PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation
Paper • 2312.15686 • Published -
soumickmj/PULASki_ProbUNet2D_Hausdorff_VSeg
Image Segmentation • 10.2M • Updated • 6 -
soumickmj/PULASki_ProbUNet2D_Sinkhorn_VSeg
Image Segmentation • 10.2M • Updated • 33 -
soumickmj/PULASki_ProbUNet2D_FID_VSeg
Image Segmentation • 10.2M • Updated • 10
The trained model weights from the paper "Unsupervised cardiac MRI phenotyping with 3D diffusion autoencoders reveals novel genetic insights"
-
GlastonburyGroup/UKBBLatent_Cardiac_20208_DiffAE3D_L128_S1701
Image Feature Extraction • 45M • Updated • 8 -
GlastonburyGroup/UKBBLatent_Cardiac_20208_DiffAE3D_L128_S1993
Image Feature Extraction • 45M • Updated • 11 -
GlastonburyGroup/UKBBLatent_Cardiac_20208_DiffAE3D_L128_S1994
Image Feature Extraction • 45M • Updated • 9 -
GlastonburyGroup/UKBBLatent_Cardiac_20208_DiffAE3D_L128_S42
Image Feature Extraction • 45M • Updated • 12
Models from the "StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational Autoencoder" manuscript and more
-
SPOCKMIP: Segmentation of Vessels in MRAs with Enhanced Continuity using Maximum Intensity Projection as Loss
Paper • 2407.08655 • Published • 1 -
soumickmj/SMILEUHURA_neuRoSliCCe_SPOCKMIP_UNetMSS3D_mMIP
0.1B • Updated • 10 -
soumickmj/SMILEUHURA_neuRoSliCCe_SPOCKMIP_UNetMSS3D_MIP
0.1B • Updated • 7 -
soumickmj/SMILEUHURA_neuRoSliCCe_SPOCKMIP_UNetMSS3D_DS6MIP
0.1B • Updated • 7
Original paper "Weakly-supervised segmentation using inherently-explainable classification models and their application to brain tumour classiciation)
The trained model weights from the paper "Unsupervised cardiac MRI phenotyping with 3D diffusion autoencoders reveals novel genetic insights"
-
GlastonburyGroup/UKBBLatent_Cardiac_20208_DiffAE3D_L128_S1701
Image Feature Extraction • 45M • Updated • 8 -
GlastonburyGroup/UKBBLatent_Cardiac_20208_DiffAE3D_L128_S1993
Image Feature Extraction • 45M • Updated • 11 -
GlastonburyGroup/UKBBLatent_Cardiac_20208_DiffAE3D_L128_S1994
Image Feature Extraction • 45M • Updated • 9 -
GlastonburyGroup/UKBBLatent_Cardiac_20208_DiffAE3D_L128_S42
Image Feature Extraction • 45M • Updated • 12
ReconResNet (part of the NCC1701 pipeline) for undersampled MRI reconstruction. This collection contains weights from the original paper, and more.
-
soumickmj/NCC1701_ReconResNet2D_DS6MRA_Varden2D10
17.3M • Updated • 3 -
soumickmj/NCC1701_ReconResNet2D_DS6MRA_Varden2D05
17.3M • Updated • 5 -
soumickmj/NCC1701_ReconResNet2D_IXIT1Guys_s60to90_Varden1D15
17.3M • Updated • 6 -
soumickmj/NCC1701_ReconResNet2D_IXIT1Guys_s60to90_Varden1D10
17.3M • Updated • 3
Models from the "StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational Autoencoder" manuscript and more
Models from "DS6, Deformation-Aware Semi-Supervised Learning" paper, and the models trained also on the SMILE-UHURA challenge dataset
-
DS6, Deformation-aware Semi-supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data
Paper • 2006.10802 • Published -
soumickmj/DS6_UNet3D_woDeform
Image Segmentation • 0.1B • Updated • 12 • 2 -
soumickmj/DS6_UNetMSS3D_wDeform
Image Segmentation • 0.1B • Updated • 9 -
soumickmj/DS6_UNetMSS3D_woDeform
Image Segmentation • 0.1B • Updated • 10
-
SPOCKMIP: Segmentation of Vessels in MRAs with Enhanced Continuity using Maximum Intensity Projection as Loss
Paper • 2407.08655 • Published • 1 -
soumickmj/SMILEUHURA_neuRoSliCCe_SPOCKMIP_UNetMSS3D_mMIP
0.1B • Updated • 10 -
soumickmj/SMILEUHURA_neuRoSliCCe_SPOCKMIP_UNetMSS3D_MIP
0.1B • Updated • 7 -
soumickmj/SMILEUHURA_neuRoSliCCe_SPOCKMIP_UNetMSS3D_DS6MIP
0.1B • Updated • 7
ProbUNets from the paper "PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation"
-
PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation
Paper • 2312.15686 • Published -
soumickmj/PULASki_ProbUNet2D_Hausdorff_VSeg
Image Segmentation • 10.2M • Updated • 6 -
soumickmj/PULASki_ProbUNet2D_Sinkhorn_VSeg
Image Segmentation • 10.2M • Updated • 33 -
soumickmj/PULASki_ProbUNet2D_FID_VSeg
Image Segmentation • 10.2M • Updated • 10