# Probabilistic Radiomics: Ambiguous Diagnosis with Controllable Shape Analysis

arXiv: https://arxiv.org/abs/1910.08878 · HTML: https://mlsanity.com/paper/1910.08878/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2019.

## Built on by (most cited first, 5 of 5)

- [RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans](https://mlsanity.com/paper/2109.09521/) (2021)
- [Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge](https://mlsanity.com/paper/2402.09372/) (2024)
- [Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation](https://mlsanity.com/paper/2307.15645/) (2023)
- [Faithful learning with sure data for lung nodule diagnosis](https://mlsanity.com/paper/2202.12515/) (2022)
- [Precise Liver Tumor Segmentation in CT Using a Hybrid Deep Learning-Radiomics Framework](https://mlsanity.com/paper/2512.07574/) (2025)

## Abstract (arXiv)

Radiomics analysis has achieved great success in recent years. However, conventional Radiomics analysis suffers from insufficiently expressive hand-crafted features. Recently, emerging deep learning techniques, e.g., convolutional neural networks (CNNs), dominate recent research in Computer-Aided Diagnosis (CADx). Unfortunately, as black-box predictors, we argue that CNNs are "diagnosing" voxels (or pixels), rather than lesions; in other words, visual saliency from a trained CNN is not necessarily concentrated on the lesions. On the other hand, classification in clinical applications suffers from inherent ambiguities: radiologists may produce diverse diagnosis on challenging cases. To this end, we propose a controllable and explainable em Probabilistic Radiomics framework, by combining the Radiomics analysis and probabilistic deep learning. In our framework, 3D CNN feature is extracted upon lesion region only, then encoded into lesion representation, by a controllable Non-local Shape Analysis Module (NSAM) based on self-attention. Inspired from variational auto-encoders (VAEs), an Ambiguity PriorNet is used to approximate the ambiguity distribution over human experts. The final diagnosis is obtained by combining the ambiguity prior sample and lesion representation, and the whole network named DenseSharp+ is end-to-end trainable. We apply the proposed method on lung nodule diagnosis on LIDC-IDRI database to validate its effectiveness.