AI Algorithms

Novel deep learning system for estimation of biological age from face photographs

Guidelines for studies using large language models

Responding to patient messages using LLMs

AIM Researchers build foundation model to discover new cancer imaging biomarkers

AIM study investigates if AI can highlight social determinants of health from clinical notes

AIM investigators developed AI to track muscle mass for children through young adulthood

AIM researchers investigate ChatGPT for its ability to provide cancer treatment recommendations

AIM researchers developed AI that can diagnose sarcopenia in head and neck cancer.

AIM researchers and ethicists establish standards for informing patients in AI clinical trials.

In Nature Comm, AIM scientists show that AI applied to X-rays can be used as a new biomarker source in cancer.

AIM investigators published a clinical evaluation of AI algorithms to screen for extranodal-extension on CT.

In Nature Medicine, AIM and TRACERx investigators show the importance of AI-based body composition.

AIM investigators developed an oncology AI Fact Sheet to facilitate the safe translation of AI models into cancer clinics.

A recent publication validated a lung cancer prediction model in 14,737 patients from Mass General Brigham.

We developed an AI model that can accurately predict distant metastases after treatment for lung cancer patients.

AIM investigators found that clinical trials with AI algorithms showed high variability in quality.

In Lancet Digital Health, we published a clinical validation of deep learning algorithms to target lung cancer tumors.

In this paper we demonstrate that deep learning applied to x-rays can be used as a new biomarker source.

In Cancer Cell, we published our perspective on the impact of AI in Clinical Oncology.

Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks

As Published in Nature Comm, we developed a deep learning pipeline to automatically predict cardiovascular events by quantifying coronary calcium on CT scans.

In Nature Comm, we show that deep learning can automatically predict cardiovascular events.

We developed several heart segmentation algorithms that work on gated and non-gated CT scans.

Scientific American discusses the hype in AI and highlights study from AIM.

AIM investigators describe their view on AI reproducibility and transparency.

An automated deep-learning approach based on chest x-rays can improve lung cancer screening.

In The Lancet Digital Health, AIM investigators have defined the levels of autonomy in medical AI.

In Nature Reviews Clinical Oncology, we highlight how AI is transforming the field of radiation oncology to treat patients more accurately and efficiently.

Science Magazine published our perspective on the application of Artificial intelligence in resource-poor health care settings.

At the annual meeting, a study about AI for cardiovascular risk prediction was awarded.