Few-Shot Breast Cancer Metastases Classification via Unsupervised Cell Ranking

A pathologist-AI collaboration framework for enhancing diagnostic accuracies and efficiencies

In pathology, the deployment of artificial intelligence (AI) in clinical settings is constrained by limitations in data collection and in model transparency and interpretability. Here we describe a digital pathology framework, nuclei.io, that incorporates active learning and human-in-the-loop real-time feedback for the rapid creation of diverse datasets and models. We validate the effectiveness of the framework via two crossover user studies that leveraged collaboration between the AI and the pathologist, including the identification of plasma cells in endometrial biopsies and the detection of colorectal cancer metastasis in lymph nodes. In both studies, nuclei.io yielded considerable diagnostic performance improvements. Collaboration between clinicians and AI will aid digital pathology by enhancing accuracies and efficiencies.

Publicly available datasets of breast histopathology H&E whole-slide images: A scoping review

Advancements in digital pathology and computing resources have made a significant impact in the field of computational pathology for breast cancer diagnosis and treatment. However, access to high-quality labeled histopathological images of breast cancer is a big challenge that limits the development of accurate and robust deep learning models. In this scoping review, we identified the publicly available datasets of breast H&E-stained whole-slide images (WSIs) that can be used to develop deep learning algorithms. We systematically searched 9 scientific literature databases and 9 research data repositories and found 17 publicly available datasets containing 10 385 H&E WSIs of breast cancer. Moreover, we reported image metadata and characteristics for each dataset to assist researchers in selecting proper datasets for specific tasks in breast cancer computational pathology. In addition, we compiled 2 lists of breast H&E patches and private datasets as supplementary resources for researchers. Notably, only 28% of the included articles utilized multiple datasets, and only 14% used an external validation set, suggesting that the performance of other developed models may be susceptible to overestimation. The TCGA-BRCA was used in 52% of the selected studies. This dataset has a considerable selection bias that can impact the robustness and generalizability of the trained algorithms. There is also a lack of consistent metadata reporting of breast WSI datasets that can be an issue in developing accurate deep learning models, indicating the necessity of establishing explicit guidelines for documenting breast WSI dataset characteristics and metadata.

Incremental RPN: Hierarchical Region Proposal Network for Apple Leaf Disease Detection in Natural Environments

Apple leaf diseases can seriously affect apple production and quality, and accurately detecting them can improve the efficiency of disease monitoring. Owing to the complex natural growth environment, apple leaf lesions may be easily confused with background noise, leading to poor performance. In this study, a cascaded Incremental Region Proposal Network (Inc-RPN) is proposed to accurately detect apple leaf diseases in natural environments. The proposed Inc-RPN has a two-layer RPN architecture, where the precursor RPN is leveraged to generate diseased leaf proposals, and the successor RPN focuses on extracting target disease spots based on diseased leaf proposals. In the successor RPN, a low-level feature aggregation module is designed to fully utilize the bridged features and preserve the semantic information of the target disease spots. An incremental module is also leveraged to extract aggregated diseased leaf features and target disease spot features. Finally, a novel position anchor generator is designed to generate anchors based on diseased leaf proposals. The experimental results show that the proposed Inc-RPN performs very well on the FALD_CED and Apple Leaf Disease datasets, showing that it can accurately perform apple leaf disease detection tasks.

Unsupervised few shot learning architecture for diagnosis of periodontal disease in dental panoramic radiographs

In the domain of medical imaging, the advent of deep learning has marked a significant progression, particularly in the nuanced area of periodontal disease diagnosis. This study specifically targets the prevalent issue of scarce labeled data in medical imaging. We introduce a novel unsupervised few-shot learning algorithm, meticulously crafted for classifying periodontal diseases using a limited collection of dental panoramic radiographs. Our method leverages UNet architecture for generating regions of interest (RoI) from radiographs, which are then processed through a Convolutional Variational Autoencoder (CVAE). This approach is pivotal in extracting critical latent features, subsequently clustered using an advanced algorithm. This clustering is key in our methodology, enabling the assignment of labels to images indicative of periodontal diseases, thus circumventing the challenges posed by limited datasets. Our validation process, involving a comparative analysis with traditional supervised learning and standard autoencoder-based clustering, demonstrates a marked improvement in both diagnostic accuracy and efficiency. For three real-world validation datasets, our UNet-CVAE architecture achieved up to average 14% higher accuracy compared to state-of-the-art supervised models including the vision transformer model when trained with 100 labeled images. This study not only highlights the capability of unsupervised learning in overcoming data limitations but also sets a new benchmark for diagnostic methodologies in medical AI, potentially transforming practices in data-constrained scenarios.

A systematic review of few-shot learning in medical imaging

The lack of annotated medical images limits the performance of deep learning models, which usually need large-scale labelled datasets. Few-shot learning techniques can reduce data scarcity issues and enhance medical image analysis speed and robustness. This systematic review gives a comprehensive overview of few-shot learning methods for medical image analysis, aiming to establish a standard methodological pipeline for future research reference. With a particular emphasis on the role of meta-learning, we analysed 80 relevant articles published from 2018 to 2023, conducting a risk of bias assessment and extracting relevant information, especially regarding the employed learning techniques. From this, we delineated a comprehensive methodological pipeline shared among all studies. In addition, we performed a statistical analysis of the studies' results concerning the clinical task and the meta-learning method employed while also presenting supplemental information such as imaging modalities and model robustness evaluation techniques. We discussed the findings of our analysis, providing a deep insight into the limitations of the state-of-the-art methods and the most promising approaches. Drawing on our investigation, we yielded recommendations on potential future research directions aiming to bridge the gap between research and clinical practice.

Heterogeneity of computational pathomic signature predicts drug resistance and intra-tumor heterogeneity of ovarian cancer

BACKGROUND

Chemotherapy resistance is the main cause of ovarian cancer progression and even death. However, there are no clear indicators for predicting the risk of drug resistance in patients. Intra-tumor heterogeneity (ITH) is one of the characteristics of malignant tumors, which is associated with the treatment and prognosis of tumors. Accordingly, our study aims to investigate the correlation between the image features of intra-tumor heterogeneity and drug resistance of ovarian cancer based on artificial intelligence.

METHODS

We obtained hematoxylin and eosin staining frozen histopathological images of ovarian cancer and paracarcinoma tissues from the Cancer Genome Atlas. We extracted quantitative image features of whole-slide images based on the automatic image nuclear segmentation processing technology. After that, we used bioinformatics analysis to find the relationship between image features of intra-tumor heterogeneity and drug resistance.

RESULTS

Our results show that our automatic image processing process based on computer artificial intelligence can extract image features effectively, and the key image features extracted are closely related to ITH. Among them, the Perimeter.sd image feature with the most prominent ITH feature can accurately predict the risk of platinum-based chemotherapy drug resistance in ovarian cancer patients.

CONCLUSION

Automatic image processing and feature extraction based on artificial intelligence have excellent results. Perimeter.sd can be used as a useful image feature indicator for evaluating ITH. ITH is associated with drug resistance of ovarian cancer, so ITH characteristics can be used as an effective indicator to evaluate drug resistance in patients with ovarian cancer.

A visual-language foundation model for pathology image analysis using medical Twitter

The lack of annotated publicly available medical images is a major barrier for computational research and education innovations. At the same time, many de-identified images and much knowledge are shared by clinicians on public forums such as medical Twitter. Here we harness these crowd platforms to curate OpenPath, a large dataset of 208,414 pathology images paired with natural language descriptions. We demonstrate the value of this resource by developing pathology language-image pretraining (PLIP), a multimodal artificial intelligence with both image and text understanding, which is trained on OpenPath. PLIP achieves state-of-the-art performances for classifying new pathology images across four external datasets: for zero-shot classification, PLIP achieves F1 scores of 0.565-0.832 compared to F1 scores of 0.030-0.481 for previous contrastive language-image pretrained model. Training a simple supervised classifier on top of PLIP embeddings also achieves 2.5% improvement in F1 scores compared to using other supervised model embeddings. Moreover, PLIP enables users to retrieve similar cases by either image or natural language search, greatly facilitating knowledge sharing. Our approach demonstrates that publicly shared medical information is a tremendous resource that can be harnessed to develop medical artificial intelligence for enhancing diagnosis, knowledge sharing and education.

Construction of VGG16 Convolution Neural Network (VGG16_CNN) Classifier with NestNet-Based Segmentation Paradigm for Brain Metastasis Classification

Brain metastases (BMs) happen often in patients with metastatic cancer (MC), requiring initial and precise diagnosis of BMs, which remains important for medical care preparation and radiotherapy prognostication. Nevertheless, the susceptibility of automated BM (ABMS) diagnosis is unfairly great for minute BMs, and integrating into medical exercises to distinguish true metastases (MtS) from false positives remains difficult. For enhancing BM classification execution, MtS localization is performed through the NestNet framework. Subsequent to segmentation, classification is performed by employing the VGG16 convolution neural network. A novel loss function is computed by employing the weighted softmax function (WSF) for enhancing minute MtS diagnosis and for calibrating susceptibility and particularity. The aim of this study was to merge temporal prior data for ABMS detection. The proffered VGG16_CNN is capable of differentiating positive MtS among MtS candidates with high confidence, which typically needs distinct specialist analysis or additional investigation, remaining specifically apt for specialist reinforcement in actual medical practice. The proffered VGG16_CNN framework can be correlated with three advanced methodologies (moU-Net, DSNet, and U-Net) concerning diverse criteria. It was observed that the proffered VGG16_CNN attained 93.74% accuracy, 92% precision, 92.1% recall, and 67.08% F1-score.

RWSF-BLP: a novel lncRNA-disease association prediction model using random walk-based multi-similarity fusion and bidirectional label propagation

An increasing number of studies and experiments have demonstrated that long noncoding RNAs (lncRNAs) have a massive impact on various biological processes. Predicting potential associations between lncRNAs and diseases not only can improve our understanding of the molecular mechanisms of human diseases but also can facilitate the identification of biomarkers for disease diagnosis, treatment, and prevention. However, identifying such associations through experiments is costly and demanding, thereby prompting researchers to develop computational methods to complement these experiments. In this paper, we constructed a novel model called RWSF-BLP (a novel lncRNA-disease association prediction model using Random Walk-based multi-Similarity Fusion and Bidirectional Label Propagation), which applies an efficient random walk-based multi-similarity fusion (RWSF) method to fuse different similarity matrices and utilizes bidirectional label propagation to predict potential lncRNA-disease associations. Leave-one-out cross-validation (LOOCV) and 5-fold cross-validation (5-fold-CV) were implemented in the evaluation RWSF-BLP performance. Results showed that, RWSF-BLP has reliable AUCs of 0.9086 and 0.9115 ± 0.0044 under the framework of LOOCV and 5-fold-CV and outperformed other four canonical methods. Case studies on lung cancer and leukemia demonstrated that potential lncRNA-disease associations can be predicted through our method. Therefore, our method can accurately infer potential lncRNA-disease associations and may be a good choice in future biomedical research.