Knee-xRAI: An Explainable AI Framework for Automatic Kellgren-Lawrence Grading of Knee Osteoarthritis
arXiv:2604.23435v2 Announce Type: replace-cross Abstract: Grading knee osteoarthritis (KOA) on plain radiographs is poorly reproducible across readers. A single-grade disagreement on the Kellgren-Lawrence (KL) scale can alter surgical management or redirect a patient from conservative therapy to intra-articular injection. Meanwhile, deep learning models that outperform human readers often offer no explanation for their decisions. We present Knee-xRAI, a pipeline that decomposes the grading process by mimicking clinical radiological workflows. It independently measures joint space narrowing (JS
The proliferation of advanced AI in medical imaging necessitates explainability to enhance trust and clinical adoption, addressing current limitations of black-box models.
Improving diagnostic reproducibility and accuracy in osteoarthritis grading through explainable AI can lead to better patient outcomes and more efficient healthcare resource allocation.
The development of explainable AI frameworks directly influencing clinical decision-making shifts the paradigm from AI as a black box to AI as a collaborative and transparent diagnostic tool in radiology.
- · Radiologists
- · Orthopedic surgeons
- · Patients with osteoarthritis
- · AI healthcare developers
- · Traditional diagnosis methods with high inter-reader variability
- · AI models lacking explainability
Enhanced diagnostic consistency and reliability for knee osteoarthritis.
Faster, more accurate treatment pathways, potentially reducing unnecessary interventions or delays for patients.
Broader adoption of explainable AI across various medical imaging diagnostics, setting a new standard for clinical AI tools.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG