Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification

2025-05-28 · Long Hui, Wai Lok Yeung

Limited DXA access hinders osteoporosis screening. This proof-of-concept study proposes using widely available knee X-rays for opportunistic Bone Mineral Density (BMD) estimation via deep learning, emphasizing robust uncertainty quantification essential for clinical use. An EfficientNet model was trained on the OAI dataset to predict BMD from bilateral knee radiographs. Two Test-Time Augmentation (TTA) methods were compared: traditional averaging and a multi-sample approach. Crucially, Split Conformal Prediction was implemented to provide statistically rigorous, patient-specific prediction intervals with guaranteed coverage. Results showed a Pearson correlation of 0.68 (traditional TTA). While traditional TTA yielded better point predictions, the multi-sample approach produced slightly tighter confidence intervals (90%, 95%, 99%) while maintaining coverage. The framework appropriately expressed higher uncertainty for challenging cases. Although anatomical mismatch between knee X-rays and standard DXA limits immediate clinical use, this method establishes a foundation for trustworthy AI-assisted BMD screening using routine radiographs, potentially improving early osteoporosis detection.

📄 PDF Abstract BibTeX arXiv:2505.22551

Code (0)

등록된 구현이 없습니다.

Tasks

Conformal PredictionPrediction IntervalsUncertainty Quantification

Methods 이 논문이 사용한 방법론

Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…

Sigmoid Activation 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …

Squeeze-and-Excitation Block The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature…

Quantifying Deep Learning Model Uncertainty in Conformal Prediction

2023-06-01 · Hamed Karimi, Reza Samavi

Precise estimation of predictive uncertainty in deep neural networks is a critical requirement for reliable decision-making in machine learning and statistical modeling, particularly in the context of medical AI. Conform…

Conformal Prediction Decision Making Deep Learning model+2

Reliable uncertainty quantification for 2D/3D anatomical landmark localization using multi-output conformal prediction

2025-03-18 · Jef Jonkers, Frank Coopman, Luc Duchateau, Glenn Van Wallendael 외

Automatic anatomical landmark localization in medical imaging requires not just accurate predictions but reliable uncertainty quantification for effective clinical decision support. Current uncertainty quantification app…

Conformal Prediction Prediction regression Uncertainty Quantification

Minimax Multi-Target Conformal Prediction with Applications to Imaging Inverse Problems

2025-11-17 · Jeffrey Wen, Rizwan Ahmad, Philip Schniter arxiv

In ill-posed imaging inverse problems, uncertainty quantification remains a fundamental challenge, especially in safety-critical applications. Recently, conformal prediction has been used to quantify the uncertainty that…

Image Quality Assessment Image Classification

From predictions to confidence intervals: an empirical study of conformal prediction methods for in-context learning

2025-04-22 · Zhe Huang, Simone Rossi, Rui Yuan, Thomas Hannagan

Transformers have become a standard architecture in machine learning, demonstrating strong in-context learning (ICL) abilities that allow them to learn from the prompt at inference time. However, uncertainty quantificati…

Conformal Prediction In-Context Learning Prediction Prediction Intervals+2

Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks

2024-02-23 · Christian Moya, Amirhossein Mollaali, Zecheng Zhang, Lu Lu 외

In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification (UQ) framework, to obtain confidence prediction intervals with coverage guarantees for Deep Operator Network (DeepONet) regress…

Conformal Prediction Prediction Prediction Intervals regression+1