A foundation model for clinical-grade computational pathology and rare cancers detection.

The analysis of histopathology images with artificial intelligence aims to enable clinical decision support systems and precision medicine. The success of such applications depends on the ability to model the diverse patterns observed in pathology images. To this end, we present Virchow, the largest foundation model for computational pathology to date. In addition to the evaluation of biomarker prediction and cell identification, we demonstrate that a large foundation model enables pan-cancer detection, achieving 0.95 specimen-level area under the (receiver operating characteristic) curve across nine common and seven rare cancers. Furthermore, we show that with less training data, the pan-cancer detector built on Virchow can achieve similar performance to tissue-specific clinical-grade models in production and outperform them on some rare variants of cancer. Virchow's performance gains highlight the value of a foundation model and open possibilities for many high-impact applications with limited amounts of labeled training data.

Using DICOM Metadata for Radiological Image Series Categorization: a Feasibility Study on Large Clinical Brain MRI Datasets.

The growing interest in machine learning (ML) in healthcare is driven by the promise of improved patient care. However, how many ML algorithms are currently being used in clinical practice? While the technology is present, as demonstrated in a variety of commercial products, clinical integration is hampered by a lack of infrastructure, processes, and tools. In particular, automating the selection of relevant series for a particular algorithm remains challenging. In this work, we propose a methodology to automate the identification of brain MRI sequences so that we can automatically route the relevant inputs for further image-related algorithms. The method relies on metadata required by the Digital Imaging and Communications in Medicine (DICOM) standard, resulting in generalizability and high efficiency (less than 0.4 ms/series). To support our claims, we test our approach on two large brain MRI datasets (40,000 studies in total) from two different institutions on two different continents. We demonstrate high levels of accuracy (ranging from 97.4 to 99.96%) and generalizability across the institutions. Given the complexity and variability of brain MRI protocols, we are confident that similar techniques could be applied to other forms of radiological imaging.

Fast Simulation of Mitral Annuloplasty for Surgical Planning.

Mitral valve repair is a complex procedure that requires the ability to predict closed valve shape through the examination of an unpressurized, accid valve. These procedures typically include the remodeling of the mitral annulus through the insertion of an annuloplasty ring. While simulations could facilitate the planning of the procedure, traditional finite-element models of mitral annuloplasty are too slow to be clinically feasible and have never been validated in tissue. This work presents a fast method for simulating valve closure post-annuloplasty using a mass-spring tissue model and subject-specific valve geometry. Closed valve shape is predicted in less than one second. The results are validated by implanting an annuloplasty ring in an excised porcine heart and comparing simulated to imaged results. Results indicate that not only can mitral annuloplasty be simulated quickly, but also with submillimeter accuracy.

Patient-specific mitral leaflet segmentation from 4D ultrasound.

Segmenting the mitral valve during closure and throughout a cardiac cycle from four dimensional ultrasound (4DUS) is important for creation and validation of mechanical models and for improved visualization and understanding of mitral valve behavior. Current methods of segmenting the valve from 4DUS either require extensive user interaction and initialization, do not maintain the valve geometry across a cardiac cycle, or are incapable of producing a detailed coaptation line and surface. We present a method of segmenting the mitral valve annulus and leaflets from 4DUS such that a detailed, patient-specific annulus and leaflets are tracked throughout mitral valve closure, resulting in a detailed coaptation region. The method requires only the selection of two frames from a sequence indicating the start and end of valve closure and a single point near a closed valve. The annulus and leaflets are first found through direct segmentation in the appropriate frames and then by tracking the known geometry to the remaining frames. We compared the automatically segmented meshes to expert manual tracings for both a normal and diseased mitral valve, and found an average difference of 0.59 +/- 0.49 mm, which is on the order of the spatial resolution of the ultrasound volumes (0.5-1.0 mm/voxel).

On the Design of an Interactive, Patient-Specific Surgical Simulator for Mitral Valve Repair.

Surgical repair of the mitral valve is a difficult procedure that is often avoided in favor of less effective valve replacement because of the associated technical challenges facing non-expert surgeons. In the interest of increasing the rate of valve repair, an accurate, interactive surgical simulator for mitral valve repair was developed. With a haptic interface, users can interact with a mechanical model during simulation to aid in the development of a surgical plan and then virtually implement the procedure to assess its efficacy. Sub-millimeter accuracy was achieved in a validation study, and the system was successfully used by a cardiac surgeon to repair three virtual pathological valves.