Garazi Serna
YOU?
Author Swipe
View article: Histology-informed microstructural diffusion simulations for MRI cancer characterisation—the Histo-μSim framework
Histology-informed microstructural diffusion simulations for MRI cancer characterisation—the Histo-μSim framework Open
Diffusion Magnetic Resonance Imaging (dMRI) simulations in geometries mimicking the microscopic complexity of human tissues enable the development of innovative biomarkers with unprecedented fidelity to histology. Simulation-informed dMRI …
View article: Clinically feasible liver tumour cell size measurement through histology-informed in vivo diffusion MRI
Clinically feasible liver tumour cell size measurement through histology-informed in vivo diffusion MRI Open
Our biologically meaningful approach may complement standard-of-care radiology, and become a new tool for enhanced cancer characterisation in precision oncology.
View article: Radiomics signature for dynamic monitoring of tumor inflamed microenvironment and immunotherapy response prediction
Radiomics signature for dynamic monitoring of tumor inflamed microenvironment and immunotherapy response prediction Open
Background The efficacy of immune checkpoint inhibitors (ICIs) depends on the tumor immune microenvironment (TIME), with a preference for a T cell-inflamed TIME. However, challenges in tissue-based assessments via biopsies have triggered t…
View article: SpinFlowSim: a blood flow simulation framework for histology-informed diffusion MRI microvasculature mapping in cancer
SpinFlowSim: a blood flow simulation framework for histology-informed diffusion MRI microvasculature mapping in cancer Open
Diffusion Magnetic Resonance Imaging (dMRI) sensitises the MRI signal to spin motion. This includes Brownian diffusion, but also flow across intricate networks of capillaries. This effect, the intra-voxel incoherent motion (IVIM), enables …
View article: Histology-informed microstructural diffusion simulations for MRI cancer characterisation — the Histo-μSim framework
Histology-informed microstructural diffusion simulations for MRI cancer characterisation — the Histo-μSim framework Open
Diffusion Magnetic Resonance Imaging (dMRI) simulations in geometries mimicking the complexity of human tissues at the microscopic scale enable the development of innovative biomarkers with unprecedented fidelity to histology. To date, app…
View article: Enhancing Tumor Microstructural Quantification With Machine Learning and Diffusion‐Relaxation <scp>MRI</scp>
Enhancing Tumor Microstructural Quantification With Machine Learning and Diffusion‐Relaxation <span>MRI</span> Open
Diffusion MRI (dMRI) enables tumor characterization, providing metrics of cellular properties that could become powerful biomarkers.1-3 However, the number and type of properties that can be resolved depends on the number of images encompa…
View article: Clinically feasible liver tumour cell size measurement through histology-informed<i>in vivo</i>diffusion MRI
Clinically feasible liver tumour cell size measurement through histology-informed<i>in vivo</i>diffusion MRI Open
Innovative diffusion Magnetic Resonance Imaging (dMRI) models enable the non-invasive measurement of cancer biological properties in vivo . However, while cancers frequently spread to the liver, models tailored for liver application and ea…
View article: Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer
Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer Open
Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retr…
View article: TABLE 1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
TABLE 1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Clinical population characteristics for NSCLC-MSK and pan-cancer-VHIO cohort
View article: FIGURE 3 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
FIGURE 3 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Visualization of high and low PD-L1 score patients from the NSCLC-MSK and pan-cancer-VHIO cohort. Magnification of tumor areas with the highest attention scores for both high PD-L1 (TPS ≥ 1%) and low PD-L1 (TPS < 1%) samples from the train…
View article: FIGURE 4 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
FIGURE 4 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Explainability for model performance in the pan-cancer-VHIO validation cohort. Overall performance of the model in the validation cohort (A). Distribution of true negative ratio (TNR), true positive ratio (TPR), false negative ratio (FNR),…
View article: FIGURE 4 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
FIGURE 4 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Explainability for model performance in the pan-cancer-VHIO validation cohort. Overall performance of the model in the validation cohort (A). Distribution of true negative ratio (TNR), true positive ratio (TPR), false negative ratio (FNR),…
View article: FIGURE 2 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
FIGURE 2 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Performance overview of the model for predicting PD-L1 status and response to immunotherapy in NSCLC-MSK and pan-cancer-VHIO cohort. AUC curves for the model to predict PD-L1 status (TPS ≥ 1%) in the training (NSCLC-MSK cohort; A) and in t…
View article: FIGURE 1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
FIGURE 1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Overview of the study design. A, Population description of the NSCLC-MSK (training) and pan-cancer-VHIO (test) cohorts. B, Workflow of the attention-based MIL pipeline to classify PD-L1 status on IHC slides. The predicted PD-L1 status was …
View article: Data from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Data from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Programmed death-ligand 1 (PD-L1) IHC is the most commonly used biomarker for immunotherapy response. However, quantification of PD-L1 status in pathology slides is challenging. Neither manual quantification nor a computer-based mimicking …
View article: FIGURE 3 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
FIGURE 3 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Visualization of high and low PD-L1 score patients from the NSCLC-MSK and pan-cancer-VHIO cohort. Magnification of tumor areas with the highest attention scores for both high PD-L1 (TPS ≥ 1%) and low PD-L1 (TPS < 1%) samples from the train…
View article: Figure S2 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Figure S2 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Visualization of PanCytokeratin IHC staining, PD-L1 IHC staining and model attention heatmaps of a high (top) and low (bottom) PD-L1 score patients pan-cancer-VHIO cohort. PanCytokeratin IHC stained images differentiate tumor tissue (A, D)…
View article: Table S1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Table S1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Model classification performance for the training (NSCLC-MSK) and test (pan-cancer-VHIO) cohorts: Accuracy, Sensitivity, Specificity, Positive Predictive Value (PPV) and Negative Predictive Value (NPV). For the Pan-cancer cohort, the perfo…
View article: TABLE 1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
TABLE 1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Clinical population characteristics for NSCLC-MSK and pan-cancer-VHIO cohort
View article: FIGURE 2 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
FIGURE 2 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Performance overview of the model for predicting PD-L1 status and response to immunotherapy in NSCLC-MSK and pan-cancer-VHIO cohort. AUC curves for the model to predict PD-L1 status (TPS ≥ 1%) in the training (NSCLC-MSK cohort; A) and in t…
View article: Figure S1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Figure S1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Performance overview of the model for predicting PD-L1 status and response to immunotherapy when trained on pan-cancer-VHIO cohort and validated in NSCLC-MSK. Area under the receiver operating characteristic (ROC) curves for the model to p…
View article: Figure S1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Figure S1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Performance overview of the model for predicting PD-L1 status and response to immunotherapy when trained on pan-cancer-VHIO cohort and validated in NSCLC-MSK. Area under the receiver operating characteristic (ROC) curves for the model to p…
View article: Figure S2 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Figure S2 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Visualization of PanCytokeratin IHC staining, PD-L1 IHC staining and model attention heatmaps of a high (top) and low (bottom) PD-L1 score patients pan-cancer-VHIO cohort. PanCytokeratin IHC stained images differentiate tumor tissue (A, D)…
View article: FIGURE 1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
FIGURE 1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Overview of the study design. A, Population description of the NSCLC-MSK (training) and pan-cancer-VHIO (test) cohorts. B, Workflow of the attention-based MIL pipeline to classify PD-L1 status on IHC slides. The predicted PD-L1 status was …
View article: Table S1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Table S1 from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Model classification performance for the training (NSCLC-MSK) and test (pan-cancer-VHIO) cohorts: Accuracy, Sensitivity, Specificity, Positive Predictive Value (PPV) and Negative Predictive Value (NPV). For the Pan-cancer cohort, the perfo…
View article: Data from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Data from Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Programmed death-ligand 1 (PD-L1) IHC is the most commonly used biomarker for immunotherapy response. However, quantification of PD-L1 status in pathology slides is challenging. Neither manual quantification nor a computer-based mimicking …
View article: Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression
Weakly Supervised Deep Learning Predicts Immunotherapy Response in Solid Tumors Based on PD-L1 Expression Open
Programmed death-ligand 1 (PD-L1) IHC is the most commonly used biomarker for immunotherapy response. However, quantification of PD-L1 status in pathology slides is challenging. Neither manual quantification nor a computer-based mimicking …