# Improving Computer-aided Detection using Convolutional Neural Networks and Random View Aggregation

arXiv: https://arxiv.org/abs/1505.03046 · HTML: https://mlsanity.com/paper/1505.03046/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2015.

## Built on by (most cited first, 22 of 22)

- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection](https://mlsanity.com/paper/2103.05094/) (2021)
- [Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scans](https://mlsanity.com/paper/2302.00162/) (2023)
- [Low-Rank Mixture-of-Experts for Continual Medical Image Segmentation](https://mlsanity.com/paper/2406.13583/) (2024)
- [Towards a Comprehensive, Efficient and Promptable Anatomic Structure Segmentation Model using 3D Whole-body CT Scans](https://mlsanity.com/paper/2403.15063/) (2024)
- [Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss](https://mlsanity.com/paper/2102.01897/) (2021)
- [CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregation](https://mlsanity.com/paper/2109.05443/) (2021)
- [Convolutional Neural Networks for Predictive Modeling of Lung Disease](https://mlsanity.com/paper/2408.12605/) (2024)
- [Video Pretraining Advances 3D Deep Learning on Chest CT Tasks](https://mlsanity.com/paper/2304.00546/) (2023)
- [Generative Adversarial U-Net for Domain-free Medical Image Augmentation](https://mlsanity.com/paper/2101.04793/) (2021)
- [Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformer](https://mlsanity.com/paper/2404.03819/) (2024)
- [Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation](https://mlsanity.com/paper/2103.05529/) (2021)
- [AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging: Towards Radiophenomics](https://mlsanity.com/paper/2110.10332/) (2021)
- [Predicting invasive ductal carcinoma using a Reinforcement Sample Learning Strategy using Deep Learning](https://mlsanity.com/paper/2105.12564/) (2021)
- [Deep Learning for Breast Cancer Classification: Enhanced Tangent Function](https://mlsanity.com/paper/2108.04663/) (2021)
- [Integrating features from lymph node stations for metastatic lymph node detection](https://mlsanity.com/paper/2301.03202/) (2023)
- [A Bibliography of Multiple Sclerosis Lesions Detection Methods using Brain MRIs](https://mlsanity.com/paper/2302.09516/) (2023)
- [Synthetic Skull CT Generation with Generative Adversarial Networks to Train Deep Learning Models for Clinical Transcranial Ultrasound](https://mlsanity.com/paper/2308.00206/) (2023)
- [Machine Learning Techniques for MRI Data Processing at Expanding Scale](https://mlsanity.com/paper/2404.14326/) (2024)
- [A lightweight Convolutional Neural Network based on U shape structure and Attention Mechanism for Anterior Mediastinum Segmentation](https://mlsanity.com/paper/2411.01019/) (2024)
- [Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts](https://mlsanity.com/paper/2504.03733/) (2025)
- [Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models](https://mlsanity.com/paper/2603.15525/) (2026)

## Abstract (arXiv)

Automated computer-aided detection (CADe) in medical imaging has been an important tool in clinical practice and research. State-of-the-art methods often show high sensitivities but at the cost of high false-positives (FP) per patient rates. We design a two-tiered coarse-to-fine cascade framework that first operates a candidate generation system at sensitivities of ~100% but at high FP levels. By leveraging existing CAD systems, coordinates of regions or volumes of interest (ROI or VOI) for lesion candidates are generated in this step and function as input for a second tier, which is our focus in this study. In this second stage, we generate N 2D (two-dimensional) or 2.5D views via sampling through scale transformations, random translations and rotations with respect to each ROI's centroid coordinates. These random views are used to train deep convolutional neural network (ConvNet) classifiers. In testing, the trained ConvNets are employed to assign class (e.g., lesion, pathology) probabilities for a new set of N random views that are then averaged at each ROI to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. The methods are evaluated on three different data sets with different numbers of patients: 59 patients for sclerotic metastases detection, 176 patients for lymph node detection, and 1,186 patients for colonic polyp detection. Experimental results show the ability of ConvNets to generalize well to different medical imaging CADe applications and scale elegantly to various data sets. Our proposed methods improve CADe performance markedly in all cases. CADe sensitivities improved from 57% to 70%, from 43% to 77% and from 58% to 75% at 3 FPs per patient for sclerotic metastases, lymph nodes and colonic polyps, respectively.