Faculty Bibliography

Foundation models are revolutionising pathology by leveraging large-scale, pretrained artificial intelligence (AI) systems to enhance diagnostics, automate workflows and expand applications. These models address computational challenges in gigapixel whole-slide images with architectures like GigaPath, enabling state-of-the-art performance in cancer subtyping and biomarker identification by capturing cellular variations and microenvironmental changes. Visual-language models such as CONCH integrate histopathological images with biomedical text, facilitating text-to-image retrieval and classification with minimal fine-tuning, mirroring how pathologists synthesise multimodal information. Open-source foundation models will drive accessibility and innovation, allowing researchers to refine AI systems collaboratively while reducing dependency on proprietary solutions. Combined with decentralised learning approaches like federated and swarm learning, these models enable secure, large-scale training without centralised data sharing, preserving patient confidentiality while improving generalisability across populations. Despite these advancements, challenges remain in ensuring scalability, mitigating bias and aligning AI insights with clinical decision-making. Explainable AI techniques, such as saliency maps and feature attribution, are critical for fostering trust and interpretability. As multimodal integration-combining pathology, radiology and genomics-advances personalised medicine, foundation models stand as a transformative force in computational pathology, bridging the gap between AI innovation and real-world clinical implementation.

Cancer is a complex disease with heterogeneous mutational and gene expression patterns. Subgroups of patients who share a phenotype might share a specific genetic architecture including protein-protein interactions (PPIs). We developed the Atlas of Protein-Protein Interactions in Cancer (APPIC), an interactive webtool that provides PPI subnetworks of 10 cancer types and their subtypes shared by cohorts of patients. To achieve this, we analyzed publicly available RNA sequencing data from patients and identified PPIs specific to 26 distinct cancer subtypes. APPIC compiles biological and clinical information from various databases, including the Human Protein Atlas, Hugo Gene Nomenclature Committee, g:Profiler, cBioPortal and Clue.io. The user-friendly interface allows for both 2D and 3D PPI network visualizations, enhancing the usability and interpretability of complex data. For advanced users seeking greater customization, APPIC conveniently provides all output files for further analysis and visualization on other platforms or tools. By offering comprehensive insights into PPIs and their role in cancer, APPIC aims to support the discovery of tumor subtype-specific novel targeted therapeutics and drug repurposing. APPIC is freely available at https://appic.brown.edu.

BACKGROUND:Axillary lymph node status is valuable in determining systemic and radiation therapy. Following neoadjuvant therapy for patients with clinically involved axillary nodes, the role of axillary lymph node dissection (ALND) following a positive sentinel lymph node biopsy (SLNB) is a subject of controversy. MATERIALS AND METHODS/METHODS:We retrospectively analyzed 224 neoadjuvant chemotherapy-treated node-positive breast cancer cases and evaluated the role of ALND in optimizing staging accuracy and treatment outcomes. RESULTS:About 63 (27.8%) underwent ALND based on post neoadjuvant persistent positive lymph nodes on exam /imaging. SLNBs were performed in 161 (71.9%) patients as initial surgical planning; 67 (41.6%) patients had positive SLNB results, and 51 (76.1%) underwent further ALND. In patients with 1 positive sentinel lymph node, follow-up ALND yielded additional positive lymph nodes in 10.5% of cases, whereas in patients with 2 or more positive sentinel lymph nodes, follow-up ALND yielded additional positive lymph nodes in 87.5% of cases. The presence of 2 positive macro-metastatic sentinel lymph nodes significantly predicts additional nodal involvement, especially in patients without a pathologic complete response. CONCLUSION/CONCLUSIONS:De-escalation of axillary surgery to SLNB alone in this context may be safely considered in neoadjuvant-treated clinical node positive patient with <2 positive sentinel lymph nodes. Our findings help guide surgeons to appropriately select patients who can potentially benefit from ALND for locoregional control and recommendation for adjuvant radiation.

ChatGPT represents a transformative technology in healthcare, with demonstrated impacts across clinical practice, medical education, and research. Studies show significant efficiency gains, including 70% reduction in administrative time for discharge summaries and achievement of medical professional-level performance on standardized tests (60% accuracy on USMLE, 78.2% on PubMedQA). ChatGPT offers personalized learning platforms, automated scoring, and instant access to vast medical knowledge in medical education, addressing resource limitations and enhancing training efficiency. It streamlines clinical workflows by supporting triage processes, generating discharge summaries, and alleviating administrative burdens, allowing healthcare professionals to focus more on patient care. Additionally, ChatGPT facilitates remote monitoring and chronic disease management, providing personalized advice, medication reminders, and emotional support, thus bridging gaps between clinical visits. Its ability to process and synthesize vast amounts of data accelerates research workflows, aiding in literature reviews, hypothesis generation, and clinical trial designs. This paper aims to gather and analyze published studies involving ChatGPT, focusing on exploring its advantages and disadvantages within the healthcare context. To aid in understanding and progress, our analysis is organized into six key areas: (1) Information and Education, (2) Triage and Symptom Assessment, (3) Remote Monitoring and Support, (4) Mental Healthcare Assistance, (5) Research and Decision Support, and (6) Language Translation. Realizing ChatGPT's full potential in healthcare requires addressing key limitations, such as its lack of clinical experience, inability to process visual data, and absence of emotional intelligence. Ethical, privacy, and regulatory challenges further complicate its integration. Future improvements should focus on enhancing accuracy, developing multimodal AI models, improving empathy through sentiment analysis, and safeguarding against artificial hallucination. While not a replacement for healthcare professionals, ChatGPT can serve as a powerful assistant, augmenting their expertise to improve efficiency, accessibility, and quality of care. This collaboration ensures responsible adoption of AI in transforming healthcare delivery. While ChatGPT demonstrates significant potential in healthcare transformation, systematic evaluation of its implementation across different healthcare settings reveals varying levels of evidence quality-from robust randomized trials in medical education to preliminary observational studies in clinical practice. This heterogeneity in evidence quality necessitates a structured approach to future research and implementation.

BACKGROUND/UNASSIGNED:Distributed ledger technology (DLT) enables the creation of tamper-resistant, decentralized, and secure digital ledgers. A non-fungible token (NFT) represents a record on-chain associated with a digital or physical asset, such as a whole-slide image (WSI). The InterPlanetary File System (IPFS) represents an off-chain network, hypermedia, and file sharing peer-to-peer protocol for storing and sharing data in a distributed file system. Today, we need cheaper, more efficient, highly scalable, and transparent solutions for WSI data storage and access of medical records and medical imaging data. METHODS/UNASSIGNED:WSIs were created from non-human tissues and H&E-stained sections were scanned on a Philips Ultrafast WSI scanner at 40× magnification objective lens (1 μm/pixel). TIFF images were stored on IPFS, while NFTs were minted on the Ethereum blockchain network in ERC-1155 standard. WSI-NFTs were stored on MetaMask and OpenSea was used to display the WSI-NFT collection. Filebase storage application programing interface (API) were used to create dedicated gateways and content delivery networks (CDN). RESULTS/UNASSIGNED:A total of 10 WSI-NFTs were minted on the Ethereum blockchain network, found on our collection "Whole Slide Images as Non-fungible Tokens Project" on Open Sea: https://opensea.io/collection/untitled-collection-126765644. WSI TIFF files ranged in size from 1.6 to 2.2 GB and were stored on IPFS and pinned on 3 separate nodes. Under optimal conditions, and using a dedicated CDN, WSI reached retrieved at speeds of over 10 mb/s, however, download speeds and WSI retrieval times varied significantly depending on the file and gateway used. Overall, the public IPFS gateway resulted in variably poorer WSI download retrieval performance compared to gateways provided by Filebase storage API. CONCLUSION/UNASSIGNED:Whole-slide images, as the most complex and substantial data files in healthcare, demand innovative solutions. In this technical report, we identify pitfalls in IPFS, and demonstrate proof-of-concept using a 3-layer architecture for scalable, decentralized storage, and access. Optimized through dedicated gateways and CDNs, which can be effectively applied to all medical data and imaging modalities across the healthcare sector. DLT and off-chain network solutions present numerous opportunities for advancements in clinical care, education, and research. Such approaches uphold the principles of equitable healthcare data ownership, security, and democratization, and are poised to drive significant innovation.

Wnt family member 9b (Wnt9b) has been demonstrated as a valuable marker for breast cancer diagnosis in surgical pathology. In this study, we examined the utility of Wnt9b in diagnosing metastatic breast carcinoma in cytology samples. Cell blocks from fine needle aspirations (FNA) and fluid specimens of 96 metastatic breast carcinomas and 123 primary and metastatic non-breast neoplasms from various organ systems were evaluated by Wnt9b and GATA3 immunohistochemistry (IHC). Wnt9b and GATA3 were positive in 81.3% and 92.7% of metastatic breast carcinomas, respectively. Conversely, 93.5% and 90.0% of non-breast, non-urothelial carcinomas were negative for Wnt9b and GATA3, respectively. Wnt9b expression was positive in rare gastrointestinal, gynecological, lung, pancreas, and salivary gland tumors. All twenty-eight urothelial carcinomas were negative for Wnt9b, while twenty-six (92.9%) were positive for GATA3. Wnt9b was slightly less sensitive but more specific than GATA3 in diagnosing metastatic breast cancer in cytology samples. Particularly, Wnt9b shows higher specificity in differentiating breast and urothelial primaries. The combined use of Wnt9b and GATA3 may increase diagnostic accuracy.

The generative artificial intelligence (AI) model ChatGPT holds transformative prospects in medicine. The development of such models has signaled the beginning of a new era where complex biological data can be made more accessible and interpretable. ChatGPT is a natural language processing tool that can process, interpret, and summarize vast data sets. It can serve as a digital assistant for physicians and researchers, aiding in integrating medical imaging data with other multiomics data and facilitating the understanding of complex biological systems. The physician's and AI's viewpoints emphasize the value of such AI models in medicine, providing tangible examples of how this could enhance patient care. The editorial also discusses the rise of generative AI, highlighting its substantial impact in democratizing AI applications for modern medicine. While AI may not supersede health care professionals, practitioners incorporating AI into their practices could potentially have a competitive edge.

This rapid communication highlights the correlations between digital pathology-whole slide imaging (WSI) and radiomics-magnetic resonance imaging (MRI) features in triple-negative breast cancer (TNBC) patients. The research collected 12 patients who had both core needle biopsy and MRI performed to evaluate pathologic complete response (pCR). The results showed that higher collagenous values in pathology data were correlated with more homogeneity, whereas higher tumor expression values in pathology data correlated with less homogeneity in the appearance of tumors on MRI by size zone non-uniformity normalized (SZNN). Higher myxoid values in pathology data are correlated with less similarity of gray-level non-uniformity (GLN) in tumor regions on MRIs, while higher immune values in WSIs correlated with the more joint distribution of smaller-size zones by small area low gray-level emphasis (SALGE) in the tumor regions on MRIs. Pathologic complete response (pCR) was associated with collagen, tumor, and myxoid expression in WSI and GLN and SZNN in radiomic features. The correlations of WSI and radiomic features may further our understanding of the TNBC tumoral microenvironment (TME) and could be used in the future to better tailor the use of neoadjuvant chemotherapy (NAC). This communication will focus on the post-NAC MRI features correlated with pCR and their association with WSI features from core needle biopsies.

The use of social media platforms in pathology and medical laboratory science has increased in recent years, revolutionizing the way professionals in these fields interact, disseminate information, and collaborate. To gain an understanding of the current landscape regarding social media use in pathology and medical laboratory science, a novel systematic review was conducted. A search of PubMed, Medline, Embase, and Scopus was performed to identify articles evaluating social media use within pathology and medical laboratory science. Articles published in English within the previous 10 years were searched on December 22, 2022. Inclusion criteria were articles containing information regarding social media utility in pathology or laboratory medicine and related articles that mentioned specific hashtags for pathology. The review process involved analyzing the social media platforms referenced, hashtags mentioned, and the presence of international authors as key endpoints of interest. 802 publications were identified; 54 studies met inclusion criteria. Subspecialties represented were considered, but none were found to be statistically significant. X/Twitter (n = 42) was the most discussed social media platform. The top hashtags discussed were #pathJC (5.1%), #dermpathJC (4.2%), #USCAP2016 (3.4%), and #PathBoards (3.4%). Analysis of these articles provides insights into current trends, including the social media platforms referenced, hashtags used, and involvement of international authors. This review will contribute to a deeper understanding of the role and impact of social media in these fields, highlighting opportunities and challenges for future research and practice in pathology and lab medicine.

Do traditional prognostic factors fully account for the diversity of clinical behavior in breast cancer? Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer seen to have a poor prognosis, although there is great variation in clinical outcomes. Most recently, novel approaches have targeted the tumoral microenvironment (TME) to determine prognosis and tumor-associated stroma has become increasingly recognized as a potential biomarker to predict treatment response and prognosis in TNBC. The principle aim of this paper is to demonstrate an approach to stromal grading in TNBC, with consideration of its utility for predicting pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) and clinical survival outcomes. We evaluated 152 TNBC cases from the Firehose Legacy TCGA Cohort and validated our findings in a series of 110 patients from our health system. Stromal grading correlated with clinical outcomes related to prognosis and response to NAC, advanced pathologic stage, as well as clinical demographics like age over 50 years with good interobserver reliability (83.6-89.1%). Looking forward, the TME could carve out a more precision-based care in TNBC and breast cancer generally.