Deep Active Learning for Computer-Aided Detection of Nasopharyngeal Carcinoma in MRI Images

Early detection and treatment of nasopharyngeal carcinoma has an important impact on improving the survival rate of patients. Computer-aided detection based on deep learning methods can automatically detect the presence of nasopharyngeal carcinoma on patient magnetic resonance images (MRI), assisting in the assessment of tumor progression. However, large-scale annotation of MRI images is not feasible because it is time-consuming and burdens the healthcare system. This paper proposes a weakly supervised nasopharyngeal carcinoma detection method suitable for MRI images, which can obtain better detection performance with a small amount of labeled data. We first generate a pseudo-color version of the MRI image based on a multi-window sampling method, which preserves richer information and improves the information utilization of the image. Then, active learning and deep learning are combined to construct an active detection model for nasopharyngeal cancer, and the most representative image set is selected from a large-scale unlabeled set by using instance-level image uncertainty for further annotation by experts, which significantly reduces the demand for image annotation in deep network. The proposed method is verified on the MRI image set of 800 patients with nasopharyngeal carcinoma. The experimental results show that the resampling method based on multi-window settings can improve the performance of the classical depth detection model by 1.5 %, while the active detection model of nasopharyngeal carcinoma only uses 20 % labeled data to achieve 92.6 % of the performance of the deep learning detector trained with all samples. Good performance is obtained when the label set is small. Our active detection method for nasopharyngeal carcinoma can detect the lesion area of nasopharyngeal carcinoma with high accuracy without large-scale labeled data, which significantly reduces the sample labeling burden of doctors.

[1]  Jia-Bin Huang,et al.  SeqSeg: A sequential method to achieve nasopharyngeal carcinoma segmentation free from background dominance , 2022, Medical Image Anal..

[2]  Shu Wu,et al.  Deep Active Learning for Text Classification with Diverse Interpretations , 2021, CIKM.

[3]  Xiangyang Ji,et al.  Multiple Instance Active Learning for Object Detection , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  A. Jemal,et al.  Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries , 2021, CA: a cancer journal for clinicians.

[5]  Cheng Chen,et al.  COVID-AL: The diagnosis of COVID-19 with deep active learning , 2020, Medical Image Analysis.

[6]  Ming Yang,et al.  Deep Reinforcement Active Learning for Medical Image Classification , 2020, MICCAI.

[7]  Zhihui Li,et al.  A Survey of Deep Active Learning , 2020, ACM Comput. Surv..

[8]  Monther Aldwairi,et al.  Particle Swarm Optimization Based Swarm Intelligence for Active Learning Improvement: Application on Medical Data Classification , 2020, Cognitive Computation.

[9]  Mohammad Sadegh Norouzzadeh,et al.  A deep active learning system for species identification and counting in camera trap images , 2019, Methods in Ecology and Evolution.

[10]  Bernhard Kainz,et al.  A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis , 2019, Medical Image Anal..

[11]  Xiabi Liu,et al.  Hybrid resampling and multi-feature fusion for automatic recognition of cavity imaging sign in lung CT , 2019, Future Gener. Comput. Syst..

[12]  In So Kweon,et al.  Learning Loss for Active Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Pedro Costa,et al.  MedAL: Accurate and Robust Deep Active Learning for Medical Image Analysis , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[14]  Shuying Li,et al.  Active-Learning-Incorporated Deep Transfer Learning for Hyperspectral Image Classification , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[15]  Yifei Lu,et al.  Deep Active Self-paced Learning for Accurate Pulmonary Nodule Segmentation , 2018, MICCAI.

[16]  Jitendra Malik,et al.  Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection , 2018, MICCAI.

[17]  Andreas Nürnberger,et al.  The Power of Ensembles for Active Learning in Image Classification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  Lin Yang,et al.  Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation , 2017, MICCAI.

[20]  Pascal Fua,et al.  Learning Active Learning from Data , 2017, NIPS.

[21]  Ruimao Zhang,et al.  Cost-Effective Active Learning for Deep Image Classification , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[22]  Kristen Grauman,et al.  Active Image Segmentation Propagation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Bram van Ginneken,et al.  On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis , 2016, IEEE Transactions on Medical Imaging.

[24]  Y. Mekada,et al.  Lesion Image Generation Using Conditional GAN for Metastatic Liver Cancer Detection , 2021 .

[25]  Y. Iwamoto,et al.  Automatic Segmentation of Infant Brain Ventricles with Hydrocephalus in MRI Based on 2.5D U-Net and Transfer Learning , 2020 .

[26]  T. Zaharia,et al.  Deep Active Learning with Simulated Rationales for Text Classification , 2020, ICPRAI.

[27]  Vinay P. Namboodiri,et al.  Deep active learning for object detection , 2018, BMVC.

[28]  Daphne Koller,et al.  Active learning: theory and applications , 2001 .