Combiner and HyperCombiner Networks: Rules to Combine Multimodality MR Images for Prostate Cancer Localisation
This work addresses the need for efficient and interpretable AI tools in medical imaging for prostate cancer diagnosis, though it is incremental as it builds on existing modality combination methods.
The authors tackled the problem of automating prostate cancer localization from multiparametric MR images by modeling radiologists' decision rules for combining modality-specific scores, showing that low-dimensional parametric models (linear or nonlinear) can achieve this without compromising accuracy. They developed Combiner and HyperCombiner networks, which improved efficiency and enabled interpretability, with experimental validation on data from 850 patients.
One of the distinct characteristics in radiologists' reading of multiparametric prostate MR scans, using reporting systems such as PI-RADS v2.1, is to score individual types of MR modalities, T2-weighted, diffusion-weighted, and dynamic contrast-enhanced, and then combine these image-modality-specific scores using standardised decision rules to predict the likelihood of clinically significant cancer. This work aims to demonstrate that it is feasible for low-dimensional parametric models to model such decision rules in the proposed Combiner networks, without compromising the accuracy of predicting radiologic labels: First, it is shown that either a linear mixture model or a nonlinear stacking model is sufficient to model PI-RADS decision rules for localising prostate cancer. Second, parameters of these (generalised) linear models are proposed as hyperparameters, to weigh multiple networks that independently represent individual image modalities in the Combiner network training, as opposed to end-to-end modality ensemble. A HyperCombiner network is developed to train a single image segmentation network that can be conditioned on these hyperparameters during inference, for much improved efficiency. Experimental results based on data from 850 patients, for the application of automating radiologist labelling multi-parametric MR, compare the proposed combiner networks with other commonly-adopted end-to-end networks. Using the added advantages of obtaining and interpreting the modality combining rules, in terms of the linear weights or odds-ratios on individual image modalities, three clinical applications are presented for prostate cancer segmentation, including modality availability assessment, importance quantification and rule discovery.