Learning from Ambiguous Labels for Lung Nodule Malignancy Prediction

by   Zehui Liao, et al.

Lung nodule malignancy prediction is an essential step in the early diagnosis of lung cancer. Besides the difficulties commonly discussed, the challenges of this task also come from the ambiguous labels provided by annotators, since deep learning models may learn, even amplify, the bias embedded in them. In this paper, we propose a multi-view "divide-and-rule" (MV-DAR) model to learn from both reliable and ambiguous annotations for lung nodule malignancy prediction. According to the consistency and reliability of their annotations, we divide nodules into three sets: a consistent and reliable set (CR-Set), an inconsistent set (IC-Set), and a low reliable set (LR-Set). The nodule in IC-Set is annotated by multiple radiologists inconsistently, and the nodule in LR-Set is annotated by only one radiologist. The proposed MV-DAR contains three DAR submodels to characterize a lung nodule from three orthographic views. Each DAR consists of a prediction network (Prd-Net), a counterfactual network (CF-Net), and a low reliable network (LR-Net), learning on CR-Set, IC-Set, and LR-Set, respectively. The image representation ability learned by CF-Net and LR-Net is then transferred to Prd-Net by negative-attention module (NA-Module) and consistent-attention module (CA-Module), aiming to boost the prediction ability of Prd-Net. The MV-DAR model has been evaluated on the LIDC-IDRI dataset and LUNGx dataset. Our results indicate not only the effectiveness of the proposed MV-DAR model in learning from ambiguous labels but also its superiority over present noisy label-learning models in lung nodule malignancy prediction.


page 1

page 2

page 4

page 8


CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction

Lung nodule malignancy prediction has been enhanced by advanced deep-lea...

Lung Nodule Segmentation and Low-Confidence Region Prediction with Uncertainty-Aware Attention Mechanism

Radiologists have different training and clinical experiences, so they m...

Pairwise Relation Learning for Semi-supervised Gland Segmentation

Accurate and automated gland segmentation on histology tissue images is ...

Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2

We present deepflash2, a deep learning solution that facilitates the obj...

iW-Net: an automatic and minimalistic interactive lung nodule segmentation deep network

We propose iW-Net, a deep learning model that allows for both automatic ...

Faithful learning with sure data for lung nodule diagnosis

Recent evolution in deep learning has proven its value for CT-based lung...

Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network

Automatic diagnosing lung cancer from Computed Tomography (CT) scans inv...

Please sign up or login with your details

Forgot password? Click here to reset