Who Does Your Medical AI Miss? Age Bias in Tumor Segmentation

Kari Jaaskelainen

04 Nov 2025 — 1 min read

If your AI segments tumors, who is it serving—and who might it be failing? A new audit of the MAMA-MIA breast cancer segmentation dataset examines fairness not in classification, but in segmentation—the step that often feeds every downstream decision.

Researchers evaluated automated segmentation quality by age, ethnicity, and data source.
They found a persistent age bias: younger patients received lower-quality segmentations, even after controlling for site.
They hypothesize physiological differences may make younger cases harder—challenging for both radiologists and algorithms.
Combining data from multiple sites can reshape or hide site-specific ethnic biases, so granular analysis matters.

Why it matters: segmentation bias can compound across clinical workflows and even amplify during model iteration. The takeaway is simple: audit labels and models by subgroup, report performance by site and demographics, and don’t assume fairness transfers across datasets.

Paper: http://arxiv.org/abs/2510.27421v1 • Authors: Aditya Parikh, Sneha Das, Aasa Feragen

Paper: http://arxiv.org/abs/2510.27421v1

Register: https://www.AiFeta.com

AI Healthcare MedicalImaging BreastCancer Fairness Bias Radiology Segmentation MachineLearning Ethics

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Dynamic-K: Recommendations That Know When to Stop

Teaching chatbots to stop contradicting themselves (DECODE)