3D magnetization transfer (MT) for the visualization of cardiac free-running Purkinje fibers: an ex vivo proof of concept.

OBJECTIVES: We investigate the possibility to exploit high-field MRI to acquire 3D images of Purkinje network which plays a crucial role in cardiac function. Since Purkinje fibers (PF) have a distinct cellular structure and are surrounded by connective tissue, we investigated conventional contrast mechanisms along with the magnetization transfer (MT) imaging technique to improve image contrast between ventricular structures of differing macromolecular content. METHODS: Three fixed porcine ventricular samples were used with free-running PFs on the endocardium. T1, T2*, T2, and M0 were evaluated on 2D slices for each sample at 9.4 T. MT parameters were optimized using hard pulses with different amplitudes, offset frequencies and durations. The cardiac structure was assessed through 2D and 3D T1w images with isotropic resolutions of 150 µm. Histology, immunofluorescence, and qPCR were performed to analyze collagen contents of cardiac tissue and PF. RESULTS: An MT preparation module of 350 ms duration inserted into the sequence with a B1 = 10 µT and frequency offset = 3000 Hz showed the best contrast, approximately 0.4 between PFs and myocardium. Magnetization transfer ratio (MTR) appeared higher in the cardiac tissue (MTR = 44.7 ± 3.5%) than in the PFs (MTR = 25.2 ± 6.3%). DISCUSSION: MT significantly improves contrast between PFs and ventricular myocardium and appears promising for imaging the 3D architecture of the Purkinje network.

Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides.

Mismatch Repair Deficiency (dMMR)/Microsatellite Instability (MSI) is a key biomarker in colorectal cancer (CRC). Universal screening of CRC patients for MSI status is now recommended, but contributes to increased workload for pathologists and delayed therapeutic decisions. Deep learning has the potential to ease dMMR/MSI testing and accelerate oncologist decision making in clinical practice, yet no comprehensive validation of a clinically approved tool has been conducted. We developed MSIntuit, a clinically approved artificial intelligence (AI) based pre-screening tool for MSI detection from haematoxylin-eosin (H&E) stained slides. After training on samples from The Cancer Genome Atlas (TCGA), a blind validation is performed on an independent dataset of 600 consecutive CRC patients. Inter-scanner reliability is studied by digitising each slide using two different scanners. MSIntuit yields a sensitivity of 0.96-0.98, a specificity of 0.47-0.46, and an excellent inter-scanner agreement (Cohen's κ: 0.82). By reaching high sensitivity comparable to gold standard methods while ruling out almost half of the non-MSI population, we show that MSIntuit can effectively serve as a pre-screening tool to alleviate MSI testing burden in clinical practice.