Advances in image registration and machine learning have recently enabled volumetric analysis of postmortem brain tissue from conventional photographs of coronal slabs, which are routinely collected in brain banks and neuropathology laboratories worldwide. One caveat of this methodology is the requirement of segmentation of the tissue from photographs, which currently requires costly manual intervention. In this article, we present a deep learning model to automate this process. The automatic segmentation tool relies on a U-Net architecture that was trained with a combination of 1,414 manually segmented images of both fixed and fresh tissue, from specimens with varying diagnoses, photographed at two different sites. Automated model predictions on a subset of photographs not seen in training were analyzed to estimate performance compared to manual labels, including both inter- and intra-rater variability. Our model achieved a median Dice score over 0.98, mean surface distance under 0.4mm, and 95\% Hausdorff distance under 1.60mm, which approaches inter-/intra-rater levels. Our tool is publicly available at surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools.

With the demand for human donor organs desperately outstripping supply, scientists are working to see if genetically edited pig organs can bridge the gap. Leonardo Riella, medical director for kidney transplantation at Massachusetts General Hospital, checks on Tim Andrews after his pig kidney transplant. Surgeons at Massachusetts General Hospital have removed a genetically engineered pig kidney from a 67-year-old New Hampshire man after a period of decreasing kidney function, the hospital confirmed to WIRED in a statement. The organ functioned for nearly nine months, longer than previous pig organ transplants, before it was removed on October 23. Tim Andrews received the pig kidney on January 25 after being on dialysis for more than two years due to end-stage kidney disease.

Respiration rate (RR) is an important vital sign for clinical monitoring of hospitalized patients, with changes in RR being strongly tied to changes in clinical status leading to adverse events. Human labels for RR, based on counting breaths, are known to be inaccurate and time consuming for medical staff. Automated monitoring of RR is in place for some patients, typically those in intensive care units (ICUs), but is absent for the majority of inpatients on standard medical wards who are still at risk for clinical deterioration. This work trains a neural network (NN) to label RR from electrocardiogram (ECG) telemetry waveforms, which like many biosignals, carry multiple signs of respiratory variation. The NN shows high accuracy on multiple validation sets (internal and external, same and different sources of RR labels), with mean absolute errors less than 1.78 breaths per minute (bpm) in the worst case. The clinical utility of such a technology is exemplified by performing a retrospective analysis of two patient cohorts that suffered adverse events including respiratory failure, showing that continuous RR monitoring could reveal dynamics that strongly tracked with intubation events. This work exemplifies the method of combining pre-existing telemetry monitoring systems and artificial intelligence (AI) to provide accurate, automated and scalable patient monitoring, all of which builds towards an AI-based hospital-wide early warning system (EWS).

First, the integration of artificial intelligence-facilitated algorithms for the early detection of cardiovascular illness, which will move us closer toward early prevention. We also envision a focus on using genetically informed treatments to reduce the risk of atherosclerotic heart disease, valvular heart disease and heart failure. Together, these important advances will usher in an era of personalized health care in cardiovascular disease."

Automated fetal brain extraction from full-uterus MRI is a challenging task due to variable head sizes, orientations, complex anatomy, and prevalent artifacts. While deep-learning (DL) models trained on synthetic images have been successful in adult brain extraction, adapting these networks for fetal MRI is difficult due to the sparsity of labeled data, leading to increased false-positive predictions. To address this challenge, we propose a test-time strategy that reduces false positives in networks trained on sparse, synthetic labels. The approach uses a breadth-fine search (BFS) to identify a subvolume likely to contain the fetal brain, followed by a deep-focused sliding window (DFS) search to refine the extraction, pooling predictions to minimize false positives. We train models at different window sizes using synthetic images derived from a small number of fetal brain label maps, augmented with random geometric shapes. Each model is trained on diverse head positions and scales, including cases with partial or no brain tissue. Our framework matches state-of-the-art brain extraction methods on clinical HASTE scans of third-trimester fetuses and exceeds them by up to 5\% in terms of Dice in the second trimester as well as EPI scans across both trimesters. Our results demonstrate the utility of a sliding-window approach and combining predictions from several models trained on synthetic images, for improving brain-extraction accuracy by progressively refining regions of interest and minimizing the risk of missing brain mask slices or misidentifying other tissues as brain.

In recent years, the field of radiology has increasingly harnessed the power of artificial intelligence (AI) to enhance diagnostic accuracy, streamline workflows, and improve patient care. Large language models (LLMs) have emerged as particularly promising tools, offering significant potential in assisting radiologists with report generation, clinical decision support, and patient communication. This paper presents an advanced radiology-focused large language model: MGH Radiology Llama. It is developed using the Llama 3 70B model, building upon previous domain-specific models like Radiology-GPT and Radiology-Llama2. Leveraging a unique and comprehensive dataset from Massachusetts General Hospital, comprising over 6.5 million de-identified medical reports across various imaging modalities, the model demonstrates significant improvements in generating accurate and clinically relevant radiology impressions given the corresponding findings. Our evaluation, incorporating both traditional metrics and a GPT-4-based assessment, highlights the enhanced performance of this work over general-purpose LLMs.

Machine learning (ML) applied to routine patient monitoring within intensive care units (ICUs) has the potential to improve care by providing clinicians with novel insights into each patient's health and expected response to interventions. This paper applies deep learning to a large volume of unlabeled electrocardiogram (ECG) telemetry signals, which are commonly used for continuous patient monitoring in hospitals but have important differences from the standard, single time-point 12-lead ECG used in many prior machine learning studies. We applied self-supervised learning to pretrain a spectrum of deep networks on approximately 147,000 hours of ECG telemetry data. Our approach leverages this dataset to train models that significantly improve performance on four distinct downstream tasks compared with direct supervised learning using labeled data. These pretrained models enable medically useful predictions and estimates in smaller patient cohorts that are typically limited by the scarcity of labels. Notably, we demonstrate that our pretrained networks can continuously annotate ECG telemetry signals, thereby providing monitoring capabilities that are often unavailable due to the requirement for specialized expertise and time-consuming professional annotations.

Background: Artificial intelligence language models have shown promise in various applications, including assisting with clinical decision-making as demonstrated by strong performance of large language models on medical licensure exams. However, their ability to solve complex, open-ended cases, which may be representative of clinical practice, remains unexplored. Methods: In this study, the accuracy of large language AI models GPT4 and GPT3.5 in diagnosing complex clinical cases was investigated using published Case Records of the Massachusetts General Hospital. A total of 50 cases requiring a diagnosis and diagnostic test published from January 1, 2022 to April 16, 2022 were identified. For each case, models were given a prompt requesting the top three specific diagnoses and associated diagnostic tests, followed by case text, labs, and figure legends. Model outputs were assessed in comparison to the final clinical diagnosis and whether the model-predicted test would result in a correct diagnosis. Results: GPT4 and GPT3.5 accurately provided the correct diagnosis in 26% and 22% of cases in one attempt, and 46% and 42% within three attempts, respectively. GPT4 and GPT3.5 provided a correct essential diagnostic test in 28% and 24% of cases in one attempt, and 44% and 50% within three attempts, respectively. No significant differences were found between the two models, and multiple trials with identical prompts using the GPT3.5 model provided similar results. Conclusions: In summary, these models demonstrate potential usefulness in generating differential diagnoses but remain limited in their ability to provide a single unifying diagnosis in complex, open-ended cases. Future research should focus on evaluating model performance in larger datasets of open-ended clinical challenges and exploring potential human-AI collaboration strategies to enhance clinical decision-making.

The symptoms can be caused by acute coronary syndrome, pulmonary embolism or aortic dissection, but only a minority of patients who present with ACP are diagnosed with those serious cardiovascular conditions. As such, physicians need to take all cases of ACP very seriously despite the fact that most patients are low risk. Researchers at Massachusetts General Hospital identified deep learning as a potential way to identify high-risk patients and thereby accelerate diagnosis while improving the use of resources. The project centered on the chest radiographs that ACP patients often undergo early in the care pathway. By applying deep learning to the images, the collaborators trained a model to identify signs in the scans that a person may have one of the cardiovascular conditions.

Lung cancer is the leading cause of cancer death in the United States and around the world. Low-dose chest computed tomography (LDCT) is recommended to screen people between 50 and 80 years of age with a significant history of smoking, or who currently smoke. Lung cancer screening with LDCT has been shown to reduce death from lung cancer by up to 24 percent. But as rates of lung cancer climb among non-smokers, new strategies are needed to screen and accurately predict lung cancer risk across a wider population. A study led by investigators from the Mass General Cancer Center, a member of Mass General Brigham, in collaboration with researchers at the Massachusetts Institute of Technology (MIT), developed and tested an artificial intelligence tool known as Sybil.