PDC-Net: Parallel Dilated Convolutional Network with Channel Attention Mechanism for Pituitary Adenoma Segmentation

Overview

Journal Front Physiol

Date 2023 Sep 15

PMID 37711463

Authors

Qile Zhang

Jianzhen Cheng

Chun Zhou

Xiaoliang Jiang

Yuanxiang Zhang

Jiantao Zeng

Li Liu

Affiliations

Soon will be listed here.

Abstract

Accurate segmentation of the medical image is the basis and premise of intelligent diagnosis and treatment, which has a wide range of clinical application value. However, the robustness and effectiveness of medical image segmentation algorithms remains a challenging subject due to the unbalanced categories, blurred boundaries, highly variable anatomical structures and lack of training samples. For this reason, we present a parallel dilated convolutional network (PDC-Net) to address the pituitary adenoma segmentation in magnetic resonance imaging images. Firstly, the standard convolution block in U-Net is replaced by a basic convolution operation and a parallel dilated convolutional module (PDCM), to extract the multi-level feature information of different dilations. Furthermore, the channel attention mechanism (CAM) is integrated to enhance the ability of the network to distinguish between lesions and non-lesions in pituitary adenoma. Then, we introduce residual connections at each layer of the encoder-decoder, which can solve the problem of gradient disappearance and network performance degradation caused by network deepening. Finally, we employ the dice loss to deal with the class imbalance problem in samples. By testing on the self-established patient dataset from Quzhou People's Hospital, the experiment achieves 90.92% of Sensitivity, 99.68% of Specificity, 88.45% of Dice value and 79.43% of Intersection over Union (IoU).

References

Tang H, Mao L, Zeng S, Deng S, Ai Z . Discriminative dictionary learning algorithm with pairwise local constraints for histopathological image classification. Med Biol Eng Comput. 2021; 59(1):153-164. DOI: 10.1007/s11517-020-02281-y. View

Rundo L, Militello C, Vitabile S, Casarino C, Russo G, Midiri M . Combining split-and-merge and multi-seed region growing algorithms for uterine fibroid segmentation in MRgFUS treatments. Med Biol Eng Comput. 2015; 54(7):1071-84. DOI: 10.1007/s11517-015-1404-6. View

Sedghi Gamechi Z, Arias-Lorza A, Saghir Z, Bos D, De Bruijne M . Assessment of fully automatic segmentation of pulmonary artery and aorta on noncontrast CT with optimal surface graph cuts. Med Phys. 2021; 48(12):7837-7849. PMC: 9298252. DOI: 10.1002/mp.15289. View

You J, Yu P, Tsang A, Tsui E, Woo P, Lui C . 3D dissimilar-siamese-u-net for hyperdense Middle cerebral artery sign segmentation. Comput Med Imaging Graph. 2021; 90:101898. DOI: 10.1016/j.compmedimag.2021.101898. View

Zhang T, Zhang J, Xue T, Rashid M . A Brain Tumor Image Segmentation Method Based on Quantum Entanglement and Wormhole Behaved Particle Swarm Optimization. Front Med (Lausanne). 2022; 9:794126. PMC: 9127532. DOI: 10.3389/fmed.2022.794126. View

Liang B, Tang C, Xu M, Wu T, Lei Z . Fusion network based on the dual attention mechanism and atrous spatial pyramid pooling for automatic segmentation in retinal vessel images. J Opt Soc Am A Opt Image Sci Vis. 2022; 39(8):1393-1402. DOI: 10.1364/JOSAA.459912. View

Shen C, Roth H, Hayashi Y, Oda M, Miyamoto T, Sato G . A cascaded fully convolutional network framework for dilated pancreatic duct segmentation. Int J Comput Assist Radiol Surg. 2021; 17(2):343-354. DOI: 10.1007/s11548-021-02530-x. View

Byra M, Jarosik P, Szubert A, Galperin M, Ojeda-Fournier H, Olson L . Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network. Biomed Signal Process Control. 2021; 61. PMC: 8545275. DOI: 10.1016/j.bspc.2020.102027. View

Ni J, Wu J, Tong J, Wei M, Chen Z . SSCA-Net: Simultaneous Self- and Channel-Attention Neural Network for Multiscale Structure-Preserving Vessel Segmentation. Biomed Res Int. 2021; 2021:6622253. PMC: 8026298. DOI: 10.1155/2021/6622253. View

10.

Gavirni R, Gupta D, Mishra D, Gupta A, Viswamitra S . Clinically Relevant Myocardium Segmentation in Cardiac Magnetic Resonance Images. IEEE J Biomed Health Inform. 2023; 27(5):2423-2431. DOI: 10.1109/JBHI.2023.3250429. View

11.

Biratu E, Schwenker F, Debelee T, Kebede S, Negera W, Molla H . Enhanced Region Growing for Brain Tumor MR Image Segmentation. J Imaging. 2021; 7(2). PMC: 8321280. DOI: 10.3390/jimaging7020022. View

12.

Ghaderi S, Ghaderi K, Ghaznavi H . Using Marker-Controlled Watershed Transform to Detect Baker's Cyst in Magnetic Resonance Imaging Images: A Pilot Study. J Med Signals Sens. 2022; 12(1):84-89. PMC: 8804590. DOI: 10.4103/jmss.JMSS_49_20. View

13.

Lan K, Cheng J, Jiang J, Jiang X, Zhang Q . Modified UNet++ with atrous spatial pyramid pooling for blood cell image segmentation. Math Biosci Eng. 2023; 20(1):1420-1433. DOI: 10.3934/mbe.2023064. View

14.

Zhu C, Wang X, Chen S, Teng Z, Bai C, Huang X . Complex carotid artery segmentation in multi-contrast MR sequences by improved optimal surface graph cuts based on flow line learning. Med Biol Eng Comput. 2022; 60(9):2693-2706. DOI: 10.1007/s11517-022-02622-z. View

15.

Sergioli G, Militello C, Rundo L, Minafra L, Torrisi F, Russo G . A quantum-inspired classifier for clonogenic assay evaluations. Sci Rep. 2021; 11(1):2830. PMC: 7854718. DOI: 10.1038/s41598-021-82085-8. View

16.

Shahvaran Z, Kazemi K, Fouladivanda M, Helfroush M, Godefroy O, Aarabi A . Morphological active contour model for automatic brain tumor extraction from multimodal magnetic resonance images. J Neurosci Methods. 2021; 362:109296. DOI: 10.1016/j.jneumeth.2021.109296. View

17.

Han Z, Wei B, Xi X, Chen B, Yin Y, Li S . Unifying neural learning and symbolic reasoning for spinal medical report generation. Med Image Anal. 2020; 67:101872. DOI: 10.1016/j.media.2020.101872. View

18.

Jha D, Smedsrud P, Johansen D, de Lange T, Johansen H, Halvorsen P . A Comprehensive Study on Colorectal Polyp Segmentation With ResUNet++, Conditional Random Field and Test-Time Augmentation. IEEE J Biomed Health Inform. 2021; 25(6):2029-2040. DOI: 10.1109/JBHI.2021.3049304. View

19.

Wang J, Lv P, Wang H, Shi C . SAR-U-Net: Squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography. Comput Methods Programs Biomed. 2021; 208:106268. DOI: 10.1016/j.cmpb.2021.106268. View

20.

Wang L, Gu J, Chen Y, Liang Y, Zhang W, Pu J . Automated segmentation of the optic disc from fundus images using an asymmetric deep learning network. Pattern Recognit. 2021; 112. PMC: 8336919. DOI: 10.1016/j.patcog.2020.107810. View