# Semi-supervised multi-task learning for lung cancer diagnosis

arXiv: https://arxiv.org/abs/1802.06181 · HTML: https://mlsanity.com/paper/1802.06181/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2018.

## Built on by (most cited first, 6 of 6)

- [When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review](https://mlsanity.com/paper/2307.14382/) (2023)
- [ASL to PET Translation by a Semi-supervised Residual-based Attention-guided Convolutional Neural Network](https://mlsanity.com/paper/2103.05116/) (2021)
- [Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Network](https://mlsanity.com/paper/2104.01032/) (2021)
- [EXACT-Net:EHR-guided lung tumor auto-segmentation for non-small cell lung cancer radiotherapy](https://mlsanity.com/paper/2402.14099/) (2024)
- [Exploring learning environments for label-efficient cancer diagnosis](https://mlsanity.com/paper/2408.07988/) (2024)
- [Alleviating Hyperparameter-Tuning Burden in SVM Classifiers for Pulmonary Nodules Diagnosis with Multi-Task Bayesian Optimization](https://mlsanity.com/paper/2411.06184/) (2024)

## Abstract (arXiv)

Early detection of lung nodules is of great importance in lung cancer screening. Existing research recognizes the critical role played by CAD systems in early detection and diagnosis of lung nodules. However, many CAD systems, which are used as cancer detection tools, produce a lot of false positives (FP) and require a further FP reduction step. Furthermore, guidelines for early diagnosis and treatment of lung cancer are consist of different shape and volume measurements of abnormalities. Segmentation is at the heart of our understanding of nodules morphology making it a major area of interest within the field of computer aided diagnosis systems. This study set out to test the hypothesis that joint learning of false positive (FP) nodule reduction and nodule segmentation can improve the computer aided diagnosis (CAD) systems' performance on both tasks. To support this hypothesis we propose a 3D deep multi-task CNN to tackle these two problems jointly. We tested our system on LUNA16 dataset and achieved an average dice similarity coefficient (DSC) of 91% as segmentation accuracy and a score of nearly 92% for FP reduction. As a proof of our hypothesis, we showed improvements of segmentation and FP reduction tasks over two baselines. Our results support that joint training of these two tasks through a multi-task learning approach improves system performance on both. We also showed that a semi-supervised approach can be used to overcome the limitation of lack of labeled data for the 3D segmentation task.