Cancer Detection with Multiple Radiologists via Soft Multiple Instance Logistic Regression and $L_1$ Regularization
This work addresses the challenge of handling multiple expert annotations in medical imaging for cancer detection, offering a more practical solution with lower complexity, though it is incremental in nature.
The paper tackled the problem of cancer detection in medical images with multiple radiologists' annotations by using soft multiple instance logistic regression with L1 regularization, achieving similar performance to existing methods but with reduced model complexity.
This paper deals with the multiple annotation problem in medical application of cancer detection in digital images. The main assumption is that though images are labeled by many experts, the number of images read by the same expert is not large. Thus differing with the existing work on modeling each expert and ground truth simultaneously, the multi annotation information is used in a soft manner. The multiple labels from different experts are used to estimate the probability of the findings to be marked as malignant. The learning algorithm minimizes the Kullback Leibler (KL) divergence between the modeled probabilities and desired ones constraining the model to be compact. The probabilities are modeled by logit regression and multiple instance learning concept is used by us. Experiments on a real-life computer aided diagnosis (CAD) problem for CXR CAD lung cancer detection demonstrate that the proposed algorithm leads to similar results as learning with a binary RVMMIL classifier or a mixture of binary RVMMIL models per annotator. However, this model achieves a smaller complexity and is more preferable in practice.