Research aims to make AI decisions in digital pathology more understandable to pathologists.
problem Making AI decisions in digital pathology more understandable and interpretable.
method Combining machine learning with human intelligence to balance AI and human capabilities.
result Combining AI and human intelligence to improve diagnostic accuracy and understanding.
Deep learning models outperform human pathologists in detecting mitotically active tumor regions.
problem Manual selection of tumor regions with highest mitotic activity can lead to significant inter-rater variability.
method Evaluated three deep learning methods for predicting mitotic density in canine mast cell tumors.
result Two-stage object detection model outperformed human pathologists in predicting mitotic density.
Study uses deep learning to detect BCCs in high-res histopathological images.
problem Detecting BCCs in high-resolution, weakly labeled histopathological images.
method Attention-based deep learning models to process ultra-high resolution images with weak labels.
result Attention-based models achieve almost perfect classification performance (AUC of 0.99).
Accurate and robust cell nuclei classification is the cornerstone for a wider range of tasks in digital and Computational Pathology. However, most machine learning systems require extensive labeling from expert pathologists for each individual problem at hand, with no or limited abilities for knowledge transfer between…
Paper develops a BERT-based classifier to reduce pathology report annotation workload.
problem Manual annotation of pathology reports is labor-intensive and time-consuming.
method Developed an automatic text classifier using BERT and introduced a human-centric metric to identify low-confidence cases.
result The model reduces manual annotation workload by 80% to 98%.
New strategies help CNNs recognize tissue features across different stains.
problem Training deep learning models for images with multiple stains is challenging and expensive.
method Presented unsupervised training strategies that leverage one staining modality to improve performance on images with multiple stains.
result CNNs trained with these strategies outperform standard training methods on images with multiple stains.
Deep feature fusion improves mitosis counting accuracy.
problem Manual mitosis counting by pathologists is time-consuming and inconsistent.
method Combines Faster R-CNN for object detection with UNet segmentation features and RGB image features.
result Achieved an F-score of 0.508 on mitosis counting challenge dataset, outperforming state-of-the-art methods.
Algorithm segments glandular structures in colon histology images for cancer grading.
problem Manual gland segmentation is time-consuming and risky for patients.
method Local intensity and texture features, Random Forest classifier, multilevel approach.
result Fast, accurate automatic gland segmentation for clinical use.
A new deep learning framework for histopathology classification using patches and permutation-invariant operators.
problem Small n, large p problem and pixel-level annotation limitations in medical imaging.
method Single shared neural network processing patches, combining patch scores with permutation-invariant operator.
result Improves accuracy and applicability of deep learning in medical image analysis.
This paper proposes a novel selective autoencoder approach within the framework of deep convolutional networks. The crux of the idea is to train a deep convolutional autoencoder to suppress undesired parts of an image frame while allowing the desired parts resulting in efficient object detection. The efficacy of the fr…
TACOMA improves cancer biomarker validation by incorporating deep features.
problem Improving accuracy and repeatability in TMA image scoring.
method Incorporating deep learning representations learned through unsupervised clustering and recursive space partitioning.
result Reduced error rate by about 6% on breast cancer TMA images.
Study uses image analysis to predict MSI status in tumors.
problem Challenges in distinguishing MSI from its counterpart.
method Interpretable pathological image analysis strategies using Haematoxylin and eosin-stained images.
result Strategies achieve decent performance in MSI prediction.
Deep Learning model diagnoses four lymphoma categories with high accuracy.
problem Automated detection of lymphoma categories using digital pathology images.
method Convolutional neural network algorithm trained on 128 cases of lymph node images.
result Excellent diagnostic accuracy (95% image-by-image, 10% set-by-set).
Weakly supervised learning for histopathology disease localization.
problem Locating abnormal cells or single cells in histopathology slides.
method Pre-trained deep convolutional networks, feature embedding, top instances and negative evidence.
result Comparable performance to strong annotations on lymph node metastases detection challenge.
CNN-based prostate cancer grading improves accuracy and efficiency.
problem Manual Gleason grading by pathologists is time-consuming and prone to errors.
method Patch-Based Image Reconstruction (PBIR), Distribution Correction (DC), Quadratic Weighted Mean Square Error (QWMSE).
result Achieved superior expert-level performance (0.8885 quadratic-weighted kappa coefficient).
Paper proposes clustering model for ICC based on histologic patterns.
problem Challenges in grading rare cancers like ICC due to small sample sizes and difficulty in extracting patterns.
method Unsupervised deep convolutional autoencoder clustering model trained on 246 ICC digitized slides.
result Three clusters significantly associated with recurrence-free survival in Cox-proportional hazard models.
Method predicts ODX scores for breast cancer patients based on clinical data.
problem Predicting ODX scores for breast cancer patients to aid decision-making.
method Distributional random forest approach using 9 clinico-pathological characteristics.
result Correctly predicted 92% of low risk and 40.2% of high risk patients.
PathologyGAN learns deep representations of cancer tissue images.
problem Limited high-quality labels for cancer tissue images.
method Developed a GAN framework for unsupervised learning of cancer tissue phenotypes.
result Generated high-quality images with interpretable latent space.