Deep Multi-Scale Resemblance Network for the Sub-class Differentiation of Adrenal Masses on Computed Tomography Images

TL;DR

This paper introduces a deep multi-scale resemblance network (DMRN) that improves the classification of adrenal masses on CT images by addressing intra-class variation, inter-class similarity, and data imbalance, achieving state-of-the-art accuracy.

Contribution

The paper presents a novel DMRN architecture leveraging paired CNNs and multi-scale features to enhance adrenal mass classification accuracy on CT scans.

Findings

Achieved 89.52% accuracy on adrenal mass classification.

Outperformed existing methods with statistical significance (p<0.05).

Demonstrated generalizability on the ImageCLEF 2016 dataset.

Abstract

The accurate classification of mass lesions in the adrenal glands (adrenal masses), detected with computed tomography (CT), is important for diagnosis and patient management. Adrenal masses can be benign or malignant and benign masses have varying prevalence. Classification methods based on convolutional neural networks (CNNs) are the state-of-the-art in maximizing inter-class differences in large medical imaging training datasets. The application of CNNs, to adrenal masses is challenging due to large intra-class variations, large inter-class similarities and imbalanced training data due to the size of the mass lesions. We developed a deep multi-scale resemblance network (DMRN) to overcome these limitations and leveraged paired CNNs to evaluate the intra-class similarities. We used multi-scale feature embedding to improve the inter-class separability by iteratively combining complementary information produced at different scales of the input to create structured feature descriptors. We augmented the training data with randomly sampled paired adrenal masses to reduce the influence of imbalanced training data. We used 229 CT scans of patients with adrenal masses for evaluation. In a five-fold cross-validation, our method had the best results (89.52% in accuracy) when compared to the state-of-the-art methods (p<0.05). We conducted a generalizability analysis of our method on the ImageCLEF 2016 competition dataset for medical subfigure classification, which consists of a training set of 6,776 images and a test set of 4,166 images across 30 classes. Our method achieved better classification performance (85.90% in accuracy) when compared to the existing methods and was competitive when compared with methods that require additional training data (1.47% lower in accuracy). Our DMRN sub-classified adrenal masses on CT and was superior to state-of-the-art approaches.