Deeply Explainable Artificial Neural Network

TL;DR

The paper introduces DxANN, a deep learning architecture that incorporates explainability directly into its training, providing transparent, per-sample, per-feature explanations especially suited for medical imaging and other data types.

Contribution

It presents DxANN, a novel deep neural network architecture that embeds explainability during training, reducing reliance on post hoc interpretation methods.

Findings

DxANN produces accurate predictions with integrated explanations.

It is adaptable to various data modalities beyond images.

The architecture enhances trust and accountability in deep learning models.

Abstract

While deep learning models have demonstrated remarkable success in numerous domains, their black-box nature remains a significant limitation, especially in critical fields such as medical image analysis and inference. Existing explainability methods, such as SHAP, LIME, and Grad-CAM, are typically applied post hoc, adding computational overhead and sometimes producing inconsistent or ambiguous results. In this paper, we present the Deeply Explainable Artificial Neural Network (DxANN), a novel deep learning architecture that embeds explainability ante hoc, directly into the training process. Unlike conventional models that require external interpretation methods, DxANN is designed to produce per-sample, per-feature explanations as part of the forward pass. Built on a flow-based framework, it enables both accurate predictions and transparent decision-making, and is particularly well-suited for image-based tasks. While our focus is on medical imaging, the DxANN architecture is readily adaptable to other data modalities, including tabular and sequential data. DxANN marks a step forward toward intrinsically interpretable deep learning, offering a practical solution for applications where trust and accountability are essential.