CCS-Net: Cascade Detection Network With the Convolution Kernel Switch Block and Statistics Optimal Anchors Block in Hypopharyngeal Cancer MRI

Magnetic resonance imaging (MRI) is a common diagnostic method for hypopharyngeal cancer (HPC). It is a challenge to automatically detect HPC tumors and swollen lymph nodes (HPC risk areas) from MRI slices because of the small size and irregular shape of HPC risk areas. Herein, we propose a cascade detection network with Convolution Kernel Switch (CKS) Block and Statistics Optimal Anchors (SOA) Block in HPC MRI (CCS-Net). CKS Block can adaptively switch standard convolution to deformable convolution in some appropriate layers to detect irregular objects more efficiently without taking up too much computing resources. SOA Block can automatically generate the optimal anchors based on the size distribution of objects. Compared with other methods, our method achieves splendid detection performance and outperforms other methods on the HPC dataset (more than 1800 T2 MRI slices), achieving the highest AP50 of 78.90%. Experiments show that the proposed network can be the basis of a computer aided diagnosis utility that helps achieve faster and more accurate diagnostic decisions for HPC.

[1]  Jinmin Ding,et al.  Faster-RCNN based intelligent detection and localization of dental caries , 2022, Displays.

[2]  Kehong Yuan,et al.  Improved FCOS for Detecting the Breast Cancers. , 2022, Current medical imaging.

[3]  J. Roper,et al.  Deep-learning-based extraprostatic nodal lesion segmentation on 18F-fluciclovine PET , 2022, Medical Imaging.

[4]  Z. Tian,et al.  Automated CT segmentation for rapid assessment of anatomical variations in head-and-neck radiation therapy , 2022, Medical Imaging.

[5]  Suryadiputra Liawatimena,et al.  Lung nodule detection and classification from Thorax CT-scan using RetinaNet with transfer learning , 2020, Journal of King Saud University - Computer and Information Sciences.

[6]  Shudong Wang,et al.  AT-Cascade R-CNN: a novel attention-based cascade R-CNN model for ovarian cancer lesion identification , 2021, International Journal of Adaptive and Innovative Systems.

[7]  Qiu Guan,et al.  An adaptive learning method of anchor shape priors for biological cells detection and segmentation , 2021, Comput. Methods Programs Biomed..

[8]  Yu Haiying,et al.  False-Positive Reduction of Pulmonary Nodule Detection Based on Deformable Convolutional Neural Networks , 2021, 2021 IEEE 9th International Conference on Bioinformatics and Computational Biology (ICBCB).

[9]  Kuan-Bing Chen,et al.  Esophageal cancer detection based on classification of gastrointestinal CT images using improved Faster RCNN , 2021, Comput. Methods Programs Biomed..

[10]  Bruno César Gregório da Silva,et al.  Detecting cells in intravital video microscopy using a deep convolutional neural network , 2020, Comput. Biol. Medicine.

[11]  Anselmo Cardoso de Paiva,et al.  An automatic method for segmentation of liver lesions in computed tomography images using deep neural networks , 2021, Expert Syst. Appl..

[12]  Jun Huang,et al.  CSABlock-based Cascade RCNN for Breast Mass Detection in Mammogram , 2020, 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[13]  Ran Liu,et al.  Automated detection of lesion in computer tomography images based on Cascade R-CNN , 2020, Other Conferences.

[14]  Weixiang Liu,et al.  Automated mammographic mass detection using deformable convolution and multiscale features , 2020, Medical & Biological Engineering & Computing.

[15]  Dorit Merhof,et al.  Circular Anchors for the Detection of Hematopoietic Cells Using Retinanet , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[16]  Junhua Gu,et al.  Pulmonary Nodules Detection Based on Deformable Convolution , 2020, IEEE Access.

[17]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Ran Liu,et al.  Automatic Detection of Cervical Cells Using Dense-Cascade R-CNN , 2020, PRCV.

[19]  Qing Chang,et al.  Accurate Gastric Cancer Segmentation in Digital Pathology Images Using Deformable Convolution and Multi-Scale Embedding Networks , 2019, IEEE Access.

[20]  Hao Chen,et al.  FCOS: Fully Convolutional One-Stage Object Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[21]  Maheshi B. Dissanayake,et al.  Brain tumor Classification and Segmentation using Faster R-CNN , 2019, 2019 Advances in Science and Engineering Technology International Conferences (ASET).

[22]  Xiangzhi Bai,et al.  Efficient Multiple Organ Localization in CT Image Using 3D Region Proposal Network , 2019, IEEE Transactions on Medical Imaging.

[23]  Nuno Vasconcelos,et al.  Cascade R-CNN: Delving Into High Quality Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Yi Li,et al.  Deformable Convolutional Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  J. Locher,et al.  Survival trends in Hypopharyngeal cancer: A population‐based review , 2015, The Laryngoscope.

[28]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[29]  B. O'Sullivan,et al.  The Natural History of Patients With Squamous Cell Carcinoma of the Hypopharynx , 2008, The Laryngoscope.

[30]  A. Carvalho,et al.  Trends in incidence and prognosis for head and neck cancer in the United States: A site‐specific analysis of the SEER database , 2005, International journal of cancer.

[31]  Geoffrey H. Ball,et al.  ISODATA, A NOVEL METHOD OF DATA ANALYSIS AND PATTERN CLASSIFICATION , 1965 .