Skip to main content
Search

Lehigh University

3 related articles

Subscribe to updates
  1. EchoMed Agent needs only 20 labeled cases to estimate ejection fraction, cutting median error to 4.33%

    With only 20 locally labeled cases, an agentic framework for echocardiographic video performs left ventricular segmentation and ejection fraction estimation. It chains a low-rank-adapted video segmentation foundation model, a mask-guided long-axis regression module and a natural-language interface; on a 98-case Mayo Clinic cohort it lowers median ejection fraction error from 5.47% to 4.33% and raises the share of cases within ±10 percentage points from 80.6% to 83.3%. On the public EchoNet-Dynamic set, segmentation Dice is 0.934 and median ejection fraction error is 4.24%.

  2. arXiv

    Decision models stop answering in one pass: looping the same weights lifts JevBench hard questions, 63.2% to 76.2%

    Decision models that answer fixed-option questions usually score every option in one forward pass, with a depth fixed at training time, so easy and hard questions cost the same. LEV swaps in a language-model backbone pretrained as a loop, reads the options after every step and trains all steps jointly, so one checkpoint answers at any depth; on JevBench the 2.6B model rises from 63.2% at depth one to 76.2% at depth four, mostly on hard questions. A small stopper sets depth per question with a threshold fitted on unlabelled requests, saving 15% to 24% of the computation at under one accuracy point.

  3. bioRxiv

    Hierarchical Temporal Transformer for Cancer Grade Prediction and Cross-Cancer Transfer Learning from Pathology Reports

    This work presents the Hierarchical Temporal Transformer (HTT), a two-level architecture in which level 1 encodes each report with BiomedBERT adapted by LoRA and level 2 is a temporal transformer that reads a patient's full report sequence using a continuous-time positional encoding built from the measured number of days between visits plus learnable cancer-type embeddings; on a controlled synthetic corpus of sequential radiology reports it reaches validation AUROC 0.942 versus 0.881 for a single-report baseline and transfers to held-out pancreatic cancer at 0.995 versus 0.949, and on 4,786 real pathology reports from TCGA-Reports spanning 14 cancer types it predicts tumor grade for three types withheld entirely from training with AUROC 1.000 on thyroid carcinoma, 0.960 on sarcoma and 0.

You’re all caught up