AI in cancer detection

The paper introduces MIISS, a framework for similarity search in multiplexed immunofluorescence images, showing domain-specific models outperform others.

The paper proposes deep learning methods to reconstruct 3D CyCIF images and select optimal ROIs from histology and MTI data for tumor representation.

This paper develops a deep learning method to generate compact whole slide image representations for bone marrow cytology, achieving improved diagnostic prediction and image retrieval.

This paper introduces SEQUOIA, a transformer model that predicts cancer transcriptomes from histology images, achieving high accuracy in predicting gene expression and recurrence risk in breast cancer.

SAMPLER provides a statistical method to generate efficient whole slide image representations, achieving comparable or better accuracy than attention models while being significantly faster.

This paper introduces RNA-GAN, a deep generative model that creates synthetic whole-slide image tiles using gene expression profiles, outperforming traditional GANs and showing imputation capabilities.

This paper develops a deep-learning model to assess kidney biopsy images, predicting graft loss and guiding organ utilization by improving upon traditional scoring methods.

This study evaluates the reproducibility of human histology scoring for ARDS in a porcine model and demonstrates that CNNs can automate the process with acceptable performance.

This paper uses weakly supervised contrastive learning to infer molecular subtypes and recurrence risk in breast cancer from unannotated pathology images, achieving strong cross-cohort performance and alignment with pathologist annotations.

This paper compares single and ensemble CNN models for detecting invasive breast cancer in histological images, finding ensembles improve accuracy across internal and external datasets.

This paper introduces wsi2rppa, a weakly supervised contrastive learning framework that infers protein levels and drug response in breast cancer from whole slide images, achieving 0.79 AUC for trastuzumab response prediction.

This study uses attention-based multiple instance learning to predict HRD status from H&E images across ten tumor types, achieving moderate to high AUROC values.

The paper introduces a weakly supervised deep learning framework to identify cancer-related optical signatures in normal-appearing breast tissue using SLAM imaging.

This study develops an R-based method to accurately measure DAB staining on immunohistochemical slides, achieving a mean absolute error of 0.76% compared to manual measurements.

This paper introduces CycGANRegNet, a deep learning method for registering serial WSIs in different stains, achieving better performance than existing methods on breast cancer patient data.

This study develops a deep learning model to classify head and neck squamous lesions with confidence scores to identify uncertain predictions.

This paper introduces PGDIPS, a physics-guided deep learning method for stain deconvolution in histopathology images, achieving better generalization and interpretability without training data.

HAPPY quantifies cell and tissue variability in placenta histology images, providing metrics that align with clinical experts and reveal deviations in placental infarction.

The paper presents a web/cloud-based digital pathology framework for AI development and deployment, supporting collaborative annotation and remote slide access.

This paper develops a deep learning model to segment portal tract regions in liver biopsy images, showing strong correlation with fibrosis staging.

The paper presents a pan-cancer PDX histology image repository with genomic and pathological annotations for deep learning analysis of tumor regions and xenograft-transplant lymphoproliferative disorder prediction.

This paper applies a convolutional neural network to dynamic optical contrast imaging for tumor classification in head and neck cancers, achieving high accuracy in non-tumor tissue classification.

This study uses deep learning to segment tumor microenvironments in lung cancer images, predicting patient survival and gene mutations with moderate to high accuracy.

The paper introduces DPLab, a web-based platform for analyzing whole-slide pathology images, enabling 3D tissue reconstruction and sharing of analysis results.

This paper develops a deep learning system to predict pathological complete response in TNBC patients using histopathology images and biomarkers, achieving 93% accuracy.

This paper introduces a weakly-supervised method to predict tumor purity from H&E stained slides, achieving high accuracy and enabling clinical applications.

stainlib provides a Python library for augmenting and normalizing H&E histopathology images to improve model robustness across clinical settings.

This paper develops a CNN-based method to predict HER2 status in esophageal cancer tissue microarrays with high accuracy, outperforming manual assessment and reducing the need for costly follow-up tests.

This paper develops a deep learning approach for classifying lung adenocarcinoma patterns and non-small cell lung cancer types using histopathological images, achieving high accuracy in classification tasks.