Papers for

machine learning engineers in healthcare

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Detection transformers speed microstructure MRI analysis and improve accuracy

Detection Instead of Inversion: T1-T2 Microstructure Quantification With Detection Transformers

Abstract: T1-T2 correlation MRI has strong potential to quantify microstructural compartments without imposing a biological model. Traditionally, full T1-T2 spectra per voxel are reconstructed with an ill-conditioned and time-consuming Inverse Laplace Transform. We propose to view this challenge as an object detection task: A Detection Transformer (DETR) takes 64 TI/TE signals and directly predicts a set of compartments specified by T1, T2, and signal fraction. We achieve a mean average precision mAP@10 of 76.8% on simulated data, outperforming both our previous model design (53.8%) and regularized NNLS (66.1%). We show that our DETR approach outperforms NNLS in almost every setting across compartment count, compartmental signal fraction, and SNR. Reconstruction is orders of magnitude faster than NNLS. The results are fully reproducible from our public code: github.com/SebastianEndtTHI/t1t2-detr

Sun 1 NovComputer Vision and Pattern RecognitionMachine Learning
The gist
Measuring tiny structures inside the body with MRI is hard because the usual calculations take a long time and can be unstable. The authors turned this problem into something like finding objects in a photo by using a special AI called a detection transformer. This AI looks at the MRI signals and quickly figures out what types of tiny compartments are inside each tiny part of the body. Their new method is much faster and more accurate than traditional ways at identifying these compartments.
Open → 2611.01790v1

Transformer model guides safer dose choices in early drug trials

Transformer-Based Reinforcement Learning for Phase I Dose Allocation

Abstract: Phase I dose-finding trials must learn from sparse toxicity observations while limiting exposure to overly toxic doses. We develop a single reinforcement-learning policy for trials with different numbers of ordered dose levels. Each dose is represented as a token containing its normalized position, accumulated patient count, observed dose-limiting toxicities (DLTs), and current-dose indicator. A Transformer encoder summarizes the dose tokens, trial-conditioned cross-attention produces a fixed-dimensional trial representation, and a three-action policy chooses de-escalation, staying, or escalation. The final maximum tolerated dose (MTD) decision is deliberately kept outside the learned policy: after the planned sample size, weighted isotonic regression and a prespecified safety cap select the dose closest to the target toxicity probability. In the simulations, toxicity-penalized policies reduce DLT burden while unpenalized policies improve selection accuracy at the cost of greater toxicity. These results demonstrate a controllable safety--accuracy trade-off but do not establish superiority over conventional dose-finding designs.

Fri 30 OctMachine Learning
The gist
Finding the right drug dose in early trials is tricky because giving too much can be harmful, and giving too little might not work. The authors created a computer program that learns how to pick doses by looking at past patient reactions and the number of patients tried at each dose. This program uses a special AI model called a Transformer to understand the whole trial situation and then decides whether to increase, keep, or lower the dose. The final decision on the best dose is made using another method to make sure safety is prioritized. Their tests show you can balance being safe and choosing the correct dose, though it doesn't necessarily work better than current methods.
Open → 2611.00395v1