arXiv Machine Learning October 23, 2026 By Ignacy Kolton, Wenxuan Li, Zongwei Zhou, Jaros{\l}aw B. \'Cwik{\l}a, Arkadiusz Sitek, Pedro R. A. S. Bassi, Szymon P{\l}otka

Diagnostic Loss: Asymmetric Supervision for Radiology Report Generation

Read the original on arXiv Machine Learning →

The paper introduces Diagnostic Loss (DLoss), an objective designed to align radiology report generation with the asymmetric requirement of accurately stating supported diagnoses while avoiding unsupported ones. DLoss operates on decoder token probabilities, aggregating mass over vocabularies for supported and unsupported diagnoses and applying asymmetric pooling to encourage correct diagnoses and suppress spurious ones. Applied to various 3D MedVLMs on 50,000 abdominal CT scans, DLoss improves diagnostic faithfulness without compromising conventional language‑generation metrics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Sep 15

Generating Reports or Repeating Templates? Measuring and Mitigating Template Collapse in 3D CT Report Generation

arXiv:2605.30984v2 Announce Type: replace-cross Abstract: Modern 3D medical vision-language models (VLMs) can generate fluent radiology-style text while exhibit critically low pathology detection and...

By Tom Maye-Lasserre, Yitong Li, Bailiang Jian, Morteza Ghahremani, Benedikt Wiestler, Christian Wachinger

llms multimodal benchmarks safety

arXiv AI

Aug 5

CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

arXiv:2608. 03890v1 Announce Type: cross Abstract: A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend.

By Mercy Prasanna Ranjit, Anirban Porya, Sathvik Joel, Niharika Vadlamudi, Nikhilesh Chowdary Eathamukkala, Prasanth V V, Abhyuday Kumara Swamy, Pranay Narhari Umredkar, Pradeep Narayan, Vivek Rajagopal, Tanuja Ganu

llms nlp multimodal benchmarks

arXiv AI

Jul 8

Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context

arXiv:2607. 05880v1 Announce Type: cross Abstract: Imaging demand is growing faster than the radiology workforce can expand, and reporting backlogs cannot be resolved through training and recruitment alone.

By Suneeta Mall, Vladimir Nekrasov, Ashnil Kumar, Sajith Karunasena, Aiden Nibali, Alix Bird, Mateo Diaz Shine, Jarrel Seah

llms fine-tuning multimodal

Hugging Face Trending Papers

Jun 29

SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation

Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical overlap or aggregate clinical correctness. However, such metrics do not test whether individual diagnostic statements stem from the actual pathological evidence visible in the image.

llms multimodal benchmarks

arXiv AI

Sep 1

Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models

arXiv:2608.30021v1 Announce Type: cross Abstract: Errors in radiology reports can adversely affect patient treatment, yet automated report quality assurance remains challenging because errors are oft...

By Hermione Warr, Harry Anthony, Lilli J Freischem, Yasin Ibrahim, Daniel R McGowan, Konstantinos Kamnitsas

llms benchmarks

arXiv AI

Jul 21

BUSTR: Descriptor-Aware Vision-Language Learning for Breast Ultrasound Report Generation

arXiv:2511. 20956v2 Announce Type: replace-cross Abstract: Breast ultrasound (BUS) reporting relies on clinically meaningful lesion descriptors, including BI-RADS category, lesion shape, margin, echogenicity, posterior features, pathology, and histology.

By Rawa Mohammed, Mina Attin, Laxmi Gewali, Bryar Shareef

llms multimodal safety

One email a morning, machine-written

Related stories

Generating Reports or Repeating Templates? Measuring and Mitigating Template Collapse in 3D CT Report Generation

CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context

SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation

Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models

BUSTR: Descriptor-Aware Vision-Language Learning for Breast Ultrasound Report Generation