Inference-specific learning for improved medical image segmentation.

Background: Deep learning networks map input data to output predictions by fitting network parameters using training data. However, applying a trained network to new, unseen inference data resembles an interpolation process, which may lead to inaccurate predictions if the training and inference data distributions differ significantly.

Purpose: This study aims to generally improve the prediction accuracy of deep learning networks on the inference case by bridging the gap between training and inference data.

Methods: We propose an inference-specific learning strategy to enhance the network learning process without modifying the network structure. By aligning training data to closely match the specific inference data, we generate an inference-specific training dataset, enhancing the network optimization around the inference data point for more accurate predictions. Taking medical image auto-segmentation as an example, we develop an inference-specific auto-segmentation framework consisting of initial segmentation learning, inference-specific training data deformation, and inference-specific segmentation refinement. The framework is evaluated on public abdominal, head-neck, and pancreas CT datasets comprising 30, 42, and 210 cases, respectively, for medical image segmentation.

Results: Experimental results show that our method improves the organ-averaged mean Dice by 6.2% (p-value = 0.001), 1.5% (p-value = 0.003), and 3.7% (p-value < 0.001) on the three datasets, respectively, with a more notable increase for difficult-to-segment organs (such as a 21.7% increase for the gallbladder [p-value = 0.004]). By incorporating organ mask-based weak supervision into the training data alignment learning, the inference-specific auto-segmentation accuracy is generally improved compared with the image intensity-based alignment. Besides, a moving-averaged calculation of the inference organ mask during the learning process strengthens both the robustness and accuracy of the final inference segmentation.

Conclusions: By leveraging inference data during training, the proposed inference-specific learning strategy consistently improves auto-segmentation accuracy and holds the potential to be broadly applied for enhanced deep learning decision-making.