# Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Prediction

arXiv: https://arxiv.org/abs/2007.13224 · HTML: https://mlsanity.com/paper/2007.13224/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2020.

## Built on by (most cited first, 18 of 18)

- [Improving Tuberculosis (TB) Prediction using Synthetically Generated Computed Tomography (CT) Images](https://mlsanity.com/paper/2109.11480/) (2021)
- [Improving Computed Tomography (CT) Reconstruction via 3D Shape Induction](https://mlsanity.com/paper/2208.10937/) (2022)
- [ViPTT-Net: Video pretraining of spatio-temporal model for tuberculosis type classification from chest CT scans](https://mlsanity.com/paper/2105.12810/) (2021)
- [A Gradient Mapping Guided Explainable Deep Neural Network for Extracapsular Extension Identification in 3D Head and Neck Cancer Computed Tomography Images](https://mlsanity.com/paper/2201.00895/) (2022)
- [The Canadian Cropland Dataset: A New Land Cover Dataset for Multitemporal Deep Learning Classification in Agriculture](https://mlsanity.com/paper/2306.00114/) (2023)
- [Interpretable 3D Multi-Modal Residual Convolutional Neural Network for Mild Traumatic Brain Injury Diagnosis](https://mlsanity.com/paper/2309.12572/) (2023)
- [MPBD-LSTM: A Predictive Model for Colorectal Liver Metastases Using Time Series Multi-phase Contrast-Enhanced CT Scans](https://mlsanity.com/paper/2412.01973/) (2024)
- [COVID-Net CT-S: 3D Convolutional Neural Network Architectures for COVID-19 Severity Assessment using Chest CT Images](https://mlsanity.com/paper/2105.01284/) (2021)
- [Multi-Slice Net: A novel light weight framework for COVID-19 Diagnosis](https://mlsanity.com/paper/2108.03786/) (2021)
- [A Domain Decomposition-Based CNN-DNN Architecture for Model Parallel Training Applied to Image Recognition Problems](https://mlsanity.com/paper/2302.06564/) (2023)
- [SE3D: A Framework For Saliency Method Evaluation In 3D Imaging](https://mlsanity.com/paper/2405.14584/) (2024)
- [M3Net: A Macro-to-Meso-to-Micro Clinical-inspired Hierarchical 3D Network for Pulmonary Nodule Classification](https://mlsanity.com/paper/2605.12570/) (2026)
- [Interpretable Fusion Analytics Framework for fMRI Connectivity: Self-Attention Mechanism and Latent Space Item-Response Model](https://mlsanity.com/paper/2207.01581/) (2022)
- [Enhancing mTBI Diagnosis with Residual Triplet Convolutional Neural Network Using 3D CT](https://mlsanity.com/paper/2311.14197/) (2023)
- [Towards Clinical Practice in CT-Based Pulmonary Disease Screening: An Efficient and Reliable Framework](https://mlsanity.com/paper/2412.01525/) (2024)
- [LMLCC-Net: A Semi-Supervised Deep Learning Model for Lung Nodule Malignancy Prediction from CT Scans using a Novel Hounsfield Unit-Based Intensity Filtering](https://mlsanity.com/paper/2505.06370/) (2025)
- [H-CNN-ViT: A Hierarchical Gated Attention Multi-Branch Model for Bladder Cancer Recurrence Prediction](https://mlsanity.com/paper/2511.13869/) (2025)
- [Application of deep learning techniques in non-contrast computed tomography pulmonary angiogram for pulmonary embolism diagnosis](https://mlsanity.com/paper/2601.00925/) (2026)

## Abstract (arXiv)

A common approach to medical image analysis on volumetric data uses deep 2D convolutional neural networks (CNNs). This is largely attributed to the challenges imposed by the nature of the 3D data: variable volume size, GPU exhaustion during optimization. However, dealing with the individual slices independently in 2D CNNs deliberately discards the depth information which results in poor performance for the intended task. Therefore, it is important to develop methods that not only overcome the heavy memory and computation requirements but also leverage the 3D information. To this end, we evaluate a set of volume uniformizing methods to address the aforementioned issues. The first method involves sampling information evenly from a subset of the volume. Another method exploits the full geometry of the 3D volume by interpolating over the z-axis. We demonstrate performance improvements using controlled ablation studies as well as put this approach to the test on the ImageCLEF Tuberculosis Severity Assessment 2019 benchmark. We report 73% area under curve (AUC) and binary classification accuracy (ACC) of 67.5% on the test set beating all methods which leveraged only image information (without using clinical meta-data) achieving 5-th position overall. All codes and models are made available at https://github.com/hasibzunair/uniformizing-3D.