Accurate thyroid nodule segmentation with uncertainty maps in ultrasound images

Thyroid Nodule Segmentation in Ultrasound Images with Conformal Uncertainty Estimation

Computer Vision and Pattern Recognition

Summary

Thyroid nodules are common, and while most are harmless, some can be cancerous. Doctors use ultrasound images to check nodules, but they need precise outlines of these nodules for better diagnosis. The authors created a computer method that not only finds these nodules accurately in the images but also shows how confident it is about each pixel it labels. This helps improve the first step in diagnosing whether a nodule might be dangerous. Their method improves on previous techniques and provides a way to understand uncertainty in the segmentation.

What this means in practice

  • For medical imaging teams: Integrate thyroid nodule identification with reliable confidence scores into diagnostic ultrasound analysis pipelines.
  • For clinical decision support developers: Build computer-aided diagnosis systems that use accurate nodule outlines and estimated pixel-level uncertainty to assess malignancy risk.$Commercial implications: Enables development of advanced CAD tools for thyroid cancer assessment with improved reliability, suitable for medical device markets.

Authors

Francesco Teodori, Pierpaolo Brutti, Umberto Ferraro Petrillo

Abstract

Thyroid nodules affect a large proportion of the general population. Although most are benign, a non-negligible fraction is malignant. Ultrasound imaging is the primary diagnostic modality, and accurate nodule segmentation is a prerequisite for CAD systems to classify malignancy and assess metastatic risk.\\ In this work, we propose a thyroid nodule segmentation framework that integrates a DeepLabV3+, channel-attention modules and post-hoc conformal prediction, providing both accurate mask and pixel-level uncertainty estimates. We address thyroid ultrasound nodule segmentation as the first stage of a pipeline that also includes malignancy classification and metastatic risk prediction. We adopt DeepLabV3+, whose Atrous Spatial Pyramid Pooling (ASPP) captures multi-scale context, with an EfficientNet-B5 backbone for its accuracy-efficiency trade-off. Additionally, we test three channel-attention modules: Squeeze-and-Excitation, CBAM and Grouped Channel Attention (GCA), paired with two loss formulations (Dice-BCE and Boundary).\\ Since binary masks do not indicate prediction confidence, we wrap the trained model with a split conformal prediction layer that produces pixel-level uncertainty maps with statistical coverage guarantees.\\ We evaluate all configurations on the TN3K public benchmark using a fixed split and directly compare them with state-of-the-art methods. The plain backbone already improves upon previously reported results, with CBAM + Dice-BCE emerging as the best overall configuration.