OrganoID: A versatile deep learning platform for tracking and analysis of single-organoid dynamics.

Organoids have immense potential as ex vivo disease models for drug discovery and personalized drug screening. Dynamic changes in individual organoid morphology, number, and size can indicate important drug responses. However, these metrics are difficult and labor-intensive to obtain for high-throughput image datasets. Here, we present OrganoID, a robust image analysis platform that automatically recognizes, labels, and tracks single organoids, pixel-by-pixel, in brightfield and phase-contrast microscopy experiments. The platform was trained on images of pancreatic cancer organoids and validated on separate images of pancreatic, lung, colon, and adenoid cystic carcinoma organoids, which showed excellent agreement with manual measurements of organoid count (95%) and size (97%) without any parameter adjustments. Single-organoid tracking accuracy remained above 89% over a four-day time-lapse microscopy study. Automated single-organoid morphology analysis of a chemotherapy dose-response experiment identified strong dose effect sizes on organoid circularity, solidity, and eccentricity. OrganoID enables straightforward, detailed, and accurate image analysis to accelerate the use of organoids in high-throughput, data-intensive biomedical applications.

An Embedded Device for Real-Time Noninvasive Intracranial Pressure Estimation.

OBJECTIVE: The monitoring of intracranial pressure (ICP) is indicated for diagnosing and guiding therapy in many neurological conditions. Current monitoring methods, however, are highly invasive, limiting their use to the most critically ill patients only. Our goal is to develop and test an embedded device that performs all necessary mathematical operations in real-time for noninvasive ICP (nICP) estimation based on a previously developed model-based approach that uses cerebral blood flow velocity (CBFV) and arterial blood pressure (ABP) waveforms. MATERIALS AND METHODS: The nICP estimation algorithm along with the required preprocessing steps were implemented on an NXP LPC4337 microcontroller unit (MCU). A prototype device using the MCU was also developed, complete with display, recording functionality, and peripheral interfaces for ABP and CBFV monitoring hardware. RESULTS: The device produces an estimate of mean ICP once per minute and performs the necessary computations in 410 ms, on average. Real-time nICP estimates differed from the original batch-mode MATLAB implementation of theestimation algorithm by 0.63 mmHg (root-mean-square error). CONCLUSIONS: We have demonstrated that real-time nICP estimation is possible on a microprocessor platform, which offers the advantages of low cost, small size, and product modularity over a general-purpose computer. These attributes take a step toward the goal of real-time nICP estimation at the patient's bedside in a variety of clinical settings.

Blockade of miR-150 maturation by MLL-fusion/MYC/LIN-28 is required for MLL-associated leukemia.

Expression of microRNAs (miRNAs) is under stringent regulation at both transcriptional and posttranscriptional levels. Disturbance at either level could cause dysregulation of miRNAs. Here, we show that MLL fusion proteins negatively regulate production of miR-150, an miRNA widely repressed in acute leukemia, by blocking miR-150 precursors from being processed to mature miRNAs through MYC/LIN28 functional axis. Forced expression of miR-150 dramatically inhibited leukemic cell growth and delayed MLL-fusion-mediated leukemogenesis, likely through targeting FLT3 and MYB and thereby interfering with the HOXA9/MEIS1/FLT3/MYB signaling network, which in turn caused downregulation of MYC/LIN28. Collectively, we revealed a MLL-fusion/MYC/LIN28⊣miR-150⊣FLT3/MYB/HOXA9/MEIS1 signaling circuit underlying the pathogenesis of leukemia, where miR-150 functions as a pivotal gatekeeper and its repression is required for leukemogenesis.