Journal of Pathology Informatics最新文献

In this paper, we consider the current and potential role of the latest generation of Large Language Models (LLMs) in medical informatics, particularly within the realms of clinical and anatomic pathology. We aim to provide a thorough understanding of the considerations that arise when employing LLMs in healthcare settings, such as determining appropriate use cases and evaluating the advantages and limitations of these models.

Furthermore, this paper will consider the infrastructural and organizational requirements necessary for the successful implementation and utilization of LLMs in healthcare environments. We will discuss the importance of addressing education, security, bias, and privacy concerns associated with LLMs in clinical informatics, as well as the need for a robust framework to overcome regulatory, compliance, and legal challenges.

Our objective was to develop an automated deep-learning-based method to evaluate cellularity in rat bone marrow hematoxylin and eosin whole slide images for preclinical safety assessment. We trained a shallow CNN for segmenting marrow, 2 Mask R-CNN models for segmenting megakaryocytes (MKCs), and small hematopoietic cells (SHCs), and a SegNet model for segmenting red blood cells. We incorporated the models into a pipeline that identifies and counts MKCs and SHCs in rat bone marrow. We compared cell segmentation and counts that our method generated to those that pathologists generated on 10 slides with a range of cell depletion levels from 10 studies. For SHCs, we compared cell counts that our method generated to counts generated by Cellpose and Stardist. The median Dice and object Dice scores for MKCs using our method vs pathologist consensus and the inter- and intra-pathologist variation were comparable, with overlapping first-third quartile ranges. For SHCs, the median scores were close, with first-third quartile ranges partially overlapping intra-pathologist variation. For SHCs, in comparison to Cellpose and Stardist, counts from our method were closer to pathologist counts, with a smaller 95% limits of agreement range. The performance of the bone marrow analysis pipeline supports its incorporation into routine use as an aid for hematotoxicity assessment by pathologists. The pipeline could help expedite hematotoxicity assessment in preclinical studies and consequently could expedite drug development. The method may enable meta-analysis of rat bone marrow characteristics from future and historical whole slide images and may generate new biological insights from cross-study comparisons.

Whole slide imaging is revolutionizing the field of pathology and is currently being used for clinical, educational, and research initiatives by an increasing number of institutions. Pathology departments have distinct needs for digital pathology systems, yet the cost of digital workflows is cited as a major barrier for widespread adoption by many organizations. Memorial Sloan Kettering Cancer Center (MSK) is an early adopter of whole slide imaging with incremental investments in resources that started more than 15 years ago. This experience and the large-scale scan operations led to the identification of required framework components of digital pathology operations. The cost of these components for the 2021 digital pathology operations at MSK were studied and calculated to enable an understanding of the operation and benchmark the accompanying costs.

This paper describes the unique infrastructure cost and the costs associated with the digital pathology clinical operation use cases in a large, tertiary cancer center. These calculations can serve as a blueprint for other institutions to provide the necessary concepts and offer insights towards the financial requirements for digital pathology adoption by other institutions.

AI Chat Bots such as ChatGPT are revolutionizing our AI capabilities, especially in text generation, to help expedite many tasks, but they introduce new dilemmas. The detection of AI-generated text has become a subject of great debate considering the AI text detector’s known and unexpected limitations. Thus far, much research in this area has focused on the detection of AI-generated text; however, the goal of this study was to evaluate the opposite scenario, an AI-text detection tool's ability to discriminate human-generated text. Thousands of abstracts from several of the most well-known scientific journals were used to test the predictive capabilities of these detection tools, assessing abstracts from 1980 to 2023. We found that the AI text detector erroneously identified up to 8% of the known real abstracts as AI-generated text. This further highlights the current limitations of such detection tools and argues for novel detectors or combined approaches that can address this shortcoming and minimize its unanticipated consequences as we navigate this new AI landscape.

Lung cancer has been the leading cause of cancer-related deaths worldwide. Early detection and diagnosis of lung cancer can greatly improve the chances of survival for patients. Machine learning has been increasingly used in the medical sector for the detection of lung cancer, but the lack of interpretability of these models remains a significant challenge. Explainable machine learning (XML) is a new approach that aims to provide transparency and interpretability for machine learning models. The entire experiment has been performed in the lung cancer dataset obtained from Kaggle. The outcome of the predictive model with ROS (Random Oversampling) class balancing technique is used to comprehend the most relevant clinical features that contributed to the prediction of lung cancer using a machine learning explainable technique termed SHAP (SHapley Additive exPlanation). The results show the robustness of GBM's capacity to detect lung cancer, with 98.76% accuracy, 98.79% precision, 98.76% recall, 98.76% F-Measure, and 0.16% error rate, respectively. Finally, a mobile app is developed incorporating the best model to show the efficacy of our approach.

The Pathology Informatics Bootcamp, held annually at the Pathology Informatics Summit, provides pathology trainees with essential knowledge in the rapidly evolving field of Pathology Informatics. With a focus on data analytics, data science, and data management in 2022, the bootcamp addressed the growing importance of data analysis in pathology and laboratory medicine practice. The expansion of data-related subjects in Pathology Informatics Essentials for Residents (PIER) and the Clinical Informatics fellowship examinations highlights the increasing significance of these skills in pathology practice in particular and medicine in general. The curriculum included lectures on databases, programming, analytics, machine learning basics, and specialized topics like anatomic pathology data analysis and dashboarding.

Purpose

To provide a flexible, end-to-end platform for visually distinguishing diseased from undiseased tissue in a medical image, in particular pathology slides, and classifying diseased regions by subtype. Highly accurate results are obtained using small training datasets and reduced-scale source images that can be easily shared.

Approach

An ensemble of lightweight convolutional neural networks (CNNs) is trained on different subsets of images derived from a relatively small number of annotated whole-slide histopathology images (WSIs). The WSIs are first reduced in scale in a manner that preserves anatomic features critical to analysis while also facilitating convenient handling and storage. The segmentation and subtyping tasks are performed sequentially on the reduced-scale images using the same basic workflow: generating and sifting tiles from the image, then classifying each tile with an ensemble of appropriately trained CNNs. For segmentation, the CNN predictions are combined using a function to favor a selected similarity metric, and a mask or map for a a candidate image is produced from tiles whose combined predictions exceed a decision boundary. For subtyping, the resulting mask is applied to the candidate image, and new tiles are derived from the unoccluded regions. These are classified by the subtyping CNNs to produce an overall subtype prediction.

Results and conclusion

This approach was applied successfully to two very different datasets of large WSIs, one (PAIP2020) involving multiple subtypes of colorectal cancer and the other (CAMELYON16) single-type breast cancer metastases. Scored using standard similarity metrics, the segmentations outperformed more complex models typifying the state of the art.

Introduction

A correct histopathological diagnosis is dependent on an array of technical variables. The quality and completeness of a histological section on a slide is extremely prudent for correct interpretation. However, this is mostly done manually and depends largely on the expertise of histotechnician. In this study, we analysed the application of digital image analysis for quality control of histological section as a proof-of-concept.

Material and methods

Images of 1000 histological sections and their corresponding blocks were captured. Area of the section was measured from these digital images of tissue block (Digiblock) and slide (Digislide). The data was analysed to calculate DigislideQC score, dividing the area of tissue on the slide by the tissue area on the block and it was compared with the number of recuts done for incomplete section.

Results

Digislide QC score ranged from 0.1 to 0.99. It showed an area under curve (AUC) of 98.8%. A cut-off value of 0.65 had a sensitivity of 99.6% and a specificity of 96.7%.

Conclusion

Digiblock and Digislide images can provide information about quality of sections. DigislideQC score can correctly identify the slides which require recuts before it is sent for reporting and potentially reduce histopathologists’ slide screening effort and ultimately turnaround time. These can be incorporated in routine histopathology workflows and lab information systems. This simple technology can also improve future digital pathology and telepathology workflows.

Deep learning has been widely used to analyze digitized hematoxylin and eosin (H&E)-stained histopathology whole slide images. Automated cancer segmentation using deep learning can be used to diagnose malignancy and to find novel morphological patterns to predict molecular subtypes. To train pixel-wise cancer segmentation models, manual annotation from pathologists is generally a bottleneck due to its time-consuming nature. In this paper, we propose Deep Interactive Learning with a pretrained segmentation model from a different cancer type to reduce manual annotation time. Instead of annotating all pixels from cancer and non-cancer regions on giga-pixel whole slide images, an iterative process of annotating mislabeled regions from a segmentation model and training/finetuning the model with the additional annotation can reduce the time. Especially, employing a pretrained segmentation model can further reduce the time than starting annotation from scratch. We trained an accurate ovarian cancer segmentation model with a pretrained breast segmentation model by 3.5 hours of manual annotation which achieved intersection-over-union of 0.74, recall of 0.86, and precision of 0.84. With automatically extracted high-grade serous ovarian cancer patches, we attempted to train an additional classification deep learning model to predict BRCA mutation. The segmentation model and code have been released at https://github.com/MSKCC-Computational-Pathology/DMMN-ovary.

Deep models for cell detection have demonstrated utility in bone marrow cytology, showing impressive results in terms of accuracy and computational efficiency. However, these models have yet to be implemented in the clinical diagnostic workflow. Additionally, the metrics used to evaluate cell detection models are not necessarily aligned with clinical goals and targets. In order to address these issues, we introduce novel, automatically generated visual summaries of bone marrow aspirate specimens called cell projection plots (CPPs). Encompassing relevant biological patterns such as neutrophil maturation, CPPs provide a compact summary of bone marrow aspirate cytology. To gauge clinical relevance, CPPs were inspected by 3 hematopathologists, who decided whether corresponding diagnostic synopses matched with generated CPPs. Pathologists were able to match CPPs to the correct synopsis with a matching degree of 85%. Our finding suggests CPPs can represent clinically relevant information from bone marrow aspirate specimens and may be used to efficiently summarize bone marrow cytology to pathologists. CPPs could be a step toward human-centered implementation of artificial intelligence (AI) in hematopathology, and a basis for a diagnostic-support tool for digital pathology workflows.