Augmenting Pathologists with NaviPath: Design and Evaluation of a Human-AI Collaborative Navigation System

Surgment: Segmentation-enabled Semantic Search and Creation of Visual Question and Feedback to Support Video-Based Surgery Learning

“…Studies like Hegde et al [29] and Cai et al [7] use neural features for pattern matching and image fetching, focusing on pathology images with rich texture features. Conversely, xPath [26] and NaviPath [27] adopt quantitative criteria for identifying regions of interest in pathological images. In the surgical context, where images are more about anatomic components than textures, SurgXplore [46] and IMOTION [71] allow searches based on color patterns.…”

Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for Radiology

“…Developing AI systems for healthcare is a complex space with many, wide-ranging sociotechnical challenges [3,9,46,60,150], spanning: (i) concerns about patient autonomy and ability to explicitly consent or withdraw from healthcare data uses, and its privacy protection in AI development or use [123,134]; (ii) investigations into AI workflow integration [9,21,27] and how best to configure clinician-AI relationships to effectively empower care providers [50,54,125,141,147]; as well as (iii) challenges around acceptance, trust and adoption of AI insights into clinical practice [52,60,86,114,139]. This is mostly addressed in the field of eXplainable AI (XAI) through research into AI transparency via explanations and other mechanisms to help clinicians contest [53] or learn about AI outputs [24] to be able to develop an appropriate mental model of AI capabilities and their limitations.…”

“…Within this vast, growing space, our research and design exploration within medical AI imaging (e.g., ophthalmology [7,9], pathology [23,49,50,80]), specifically in radiology [5, 13, 26-28, 97, 132, 136], seeks to better understand -early within AI development processes -if and how specific, anticipated VLM capabilities could be beneficial in assisting clinical workflows.…”

Enhancing mitosis quantification and detection in meningiomas with computational digital pathology

“…The recent advancements in digital pathology and artificial intelligence (AI) technologies have shown promise in assisting pathologists in mitosis examination: A study of Aubreville et al demonstrated that AI could outperform pathologists in localizing mitotic hotspots from digitized pathology slides [23]. AI-assisted systems have been developed to calculate and recommend hotspots equivalent to 10 consecutive HPFs for pathologists [25,26]. The use of AI can save pathologists' effort in searching for mitoses under high magnification, leading to improved sensitivities [25,27], agreement rates [28], and confidence [26] in identifying mitotic figures.…”

“…AI-assisted systems have been developed to calculate and recommend hotspots equivalent to 10 consecutive HPFs for pathologists [25,26]. The use of AI can save pathologists' effort in searching for mitoses under high magnification, leading to improved sensitivities [25,27], agreement rates [28], and confidence [26] in identifying mitotic figures. However, the current AI approaches have two major limitations:…”