任务引导的径向基网络对乳腺病理图像有丝分裂检测

刘子仪; 唐奇伶; 蔡玉

doi:10.12263/DZXB.20230014

您当前的位置：

首页 >

文章列表页 >

任务引导的径向基网络对乳腺病理图像有丝分裂检测

学术论文 | 更新时间：2025-12-08

- 任务引导的径向基网络对乳腺病理图像有丝分裂检测
- Task-Guided Radial Basis Function Network for Mitosis Detection in Breast Histopathology Images
- 电子学报 2023年51卷第11期页码：3146-3154
- 作者机构：
  
  1.中南民族大学生物医学工程学院，湖北武汉 430074
  2.青岛大学附属烟台毓璜顶医院医学工程处，山东烟台 264001
- 作者简介：
  
  [ "刘子仪女，1997年1月出生于山东省烟台市.2023年毕业于中南民族大学生物医学工程学院，获工程硕士学位.现工作于青岛大学附属烟台毓璜顶医院医学工程处.主要研究方向为医学人工智能，计算机视觉. E-mail: 2020120605@mail.scuec.edu.cn" ]
  [ "唐奇伶（通讯作者）男，1973年2月出生于湖北省公安县，毕业于华中科技大学模式识别与智能系统专业，获工学博士学位.中南民族大学副教授，硕士生导师.主要研究方向为医学影像分析、计算机视觉、人工智能." ]
  [ "蔡玉女，1998年12月出生于山东省青岛市.2021年毕业于济宁医学院生物医学工程专业，获工学学士学位，现为中南民族大学生物医学工程学院硕士研究生.主要研究方向为医学人工智能，计算机视觉. E-mail: 2021120703@mail.scuec.edu.cn" ]
- 基金信息：
  
  中央高校基本科研业务费专项资金(CZY22014)
- DOI：10.12263/DZXB.20230014
  中图分类号： TP391
- 收稿：2023-01-03，
  
  修回：2023-04-15，
  
  纸质出版：2023-11-25
- 稿件说明：
移动端阅览
刘子仪,唐奇伶,蔡玉.任务引导的径向基网络对乳腺病理图像有丝分裂检测[J].电子学报,2023,51(11):3146-3154.

LIU Zi-yi,TANG Qi-ling,CAI Yu.Task-Guided Radial Basis Function Network for Mitosis Detection in Breast Histopathology Images[J].ACTA ELECTRONICA SINICA,2023,51(11):3146-3154.
刘子仪,唐奇伶,蔡玉.任务引导的径向基网络对乳腺病理图像有丝分裂检测[J].电子学报,2023,51(11):3146-3154. DOI： 10.12263/DZXB.20230014.

LIU Zi-yi,TANG Qi-ling,CAI Yu.Task-Guided Radial Basis Function Network for Mitosis Detection in Breast Histopathology Images[J].ACTA ELECTRONICA SINICA,2023,51(11):3146-3154. DOI： 10.12263/DZXB.20230014.

摘要

有丝分裂数目是判别乳腺癌恶性程度的重要指标，在诊断、治疗及预后中具有重要的意义.然而，在临床实践上乳腺癌切片中有丝分裂细胞的检测主要是通过病理学医生进行人工计数，这个过程繁琐耗时且具有很强主观性.本文提出了一种乳腺病理图像有丝分裂自动检测的两阶段方法.在第一个阶段，利用卷积神经网络作为主干融合深监督与注意力机制进行有丝分裂细胞候选块的定位.在第二个阶段，将获取的候选块输入融合了径向基函数网络的验证模型，进一步提高有丝细胞识别准确率.针对有丝细胞类内存在较大差异的问题，本文通过任务来引导径向基函数中心的确定，利用径向基函数的“局部响应”特性来表达有丝分裂细胞的形态多样性.通过在弱标签数据集ICPR 2014和AMIDA 2013上进行评估，本文所提出的网络模型取得了最优的

-score，与竞争方法相比，分别提高了5.4%和3.0%，从而证明了该方法对于有丝分裂检测的有效性.

Abstract

The number of mitosis is an important index to judge the malignancy of breast cancer

and it is of great significance in diagnosis

treatment and prognosis. However

in clinical practice

the detection of mitotic cells in breast cancer histopathology slices is mainly performed by manual counting by pathologists. This process is tedious

time-consuming and highly subjective. In this paper

we propose a two-stage method for automatic detection of mitosis in breast histopathology images

. In the first stage

the localization of mitotic cell candidate patches is performed using a convolutional neural network as the backbone with deep supervision and attention mechanisms. In the second stage

the generated candidate patches are input into the verification model of radial basis function network to further improve the accuracy of mitotic cell identification. Aiming at the problem of large differences within mitotic cell types

this paper uses tasks to guide the definition of the radial basis function centers and uses the “local response” property of radial basis function to express the morphological diversity of mitotic cells. By evaluating on the weak label datasets ICPR 2014 and AMIDA 2013

the proposed network model has achieved the best

-score

which is 5.4% and 3.0% higher than the existing methods

thus proving that the validity of the method for mitosis detection.

关键词

Keywords

references

GIAQUINTO A N , SUNG H , MILLER K D , et al . Breast cancer statistics, 2022 [J ] . CA: A Cancer Journal for Clinicians , 2022 , 72 ( 6 ): 524 - 541 .

FRIERSON H F , WOLBER R A , BEREAN K W , et al . Interobserver reproducibility of the Nottingham modification of the bloom and Richardson histologic grading scheme for infiltrating ductal carcinoma [J ] . American Journal of Clinical Pathology , 1995 , 103 ( 2 ): 195 - 198 .

HUANG C H , LEE H K . Automated mitosis detection based on exclusive independent component analysis [C ] // Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) . Piscataway : IEEE , 2013 : 1856 - 1859 .

SOMMER C , FIASCHI L , HAMPRECHT F A , et al . Learning-based mitotic cell detection in histopathological images [C ] // Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) . Piscataway : IEEE , 2013 : 2306 - 2309 .

CIREŞAN D C , GIUSTI A , GAMBARDELLA L M , et al . Mitosis detection in breast cancer histology images with deep neural networks [C ] // Medical Image Computing and Computer-Assisted Intervention — MICCAI 2013 . Berlin : Springer , 2013 : 411 - 418 .

WANG H B , CRUZ-ROA A , BASAVANHALLY A , et al . Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection [C ] // Medical Imaging 2014: Digital Pathology . San Diego : SPIE , 2014 : 66 - 75 .

CHEN H , DOU Q , WANG X , et al . Mitosis detection in breast cancer histology images via deep cascaded networks [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2016 , 30 ( 1 ): 1160 - 1166 .

CHEN H , WANG X , HENG P A . Automated mitosis detection with deep regression networks [C ] // 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI2016) . Piscataway : IEEE , 2016 : 1204 - 1207 .

LI C , WANG X G , LIU W Y , et al . DeepMitosis: Mitosis detection via deep detection, verification and segmentation networks [J ] . Medical Image Analysis , 2018 , 45 : 121 - 133 .

Mitos & Atypia . ICPR 2014 mitosis detection dataset [DS/OL ] . ( 2014-07-01 )[ 2022-08-31 ] . https://mitos-atypia-14.grand-challenge.org https://mitos-atypia-14.grand-challenge.org .

CAI D , SUN X H , ZHOU N Y , et al . Efficient mitosis detection in breast cancer histology images by RCNN [C ] // 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI2019) . Piscataway : IEEE , 2019 : 919 - 922 .

VETA M , HENG Y J , STATHONIKOS N , et al . Predicting breast tumor proliferation from whole-slide images: The TUPAC16 challenge [J ] . Medical Image Analysis , 2019 , 54 : 111 - 121 .

XU J , XIANG L , HANG R L , et al . Stacked sparse autoencoder (SSAE) based framework for nuclei patch classification on breast cancer histopathology [C ] // 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI2014) . Piscataway : IEEE , 2014 : 999 - 1002 .

SIRINUKUNWATTANA K , RAZA S E A , TSANG Y W , et al . Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images [J ] . IEEE Transactions on Medical Imaging , 2016 , 35 ( 5 ): 1196 - 1206 .

WANG L , YAN X , YOU Z H , et al . SGANRDA: Semi-supervised generative adversarial networks for predicting circRNA-disease associations [J ] . Briefings in Bioinformatics , 2021 , 22 ( 5 ): bbab028 .

LIU Y , CHENG M M , HU X W , et al . Richer convolutional features for edge detection [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2017) . Piscataway : IEEE , 2017 : 5872 - 5881 .

WOO S , PARK J , LEE J Y , et al . CBAM: Convolutional block attention module [C ] // Computer Vision—ECCV 2018 . Cham : Springer International Publishing , 2018 : 3 - 19 .

BODLA N , SINGH B , CHELLAPPA R , et al . Soft-NMS—Improving object detection with one line of code [C ] // 2017 IEEE International Conference on Computer Vision (ICCV2017) . Piscataway : IEEE , 2017 : 5562 - 5570 .

CHENG P , WANG Y L , YAO B Y , et al . Cyber security situational awareness jointly utilizing ball K -means and RBF neural networks [C ] // 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP2020) . Piscataway : IEEE , 2021 : 261 - 265 .

CARON M , BOJANOWSKI P , JOULIN A , et al . Deep clustering for unsupervised learning of visual features [C ] // Computer Vision—ECCV 2018 . Cham : Springer International Publishing , 2018 : 139 - 156 .

MA M L , SHI Y H , LI W B , et al . A novel two-stage deep method for mitosis detection in breast cancer histology images [C ] // 2018 24th International Conference on Pattern Recognition (ICPR2018) . Piscataway : IEEE , 2018 : 3892 - 3897 .

LI C , WANG X G , LIU W Y , et al . Weakly supervised mitosis detection in breast histopathology images using concentric loss [J ] . Medical Image Analysis , 2019 , 53 : 165 - 178 .

WU Z H , SHEN R B , HUANG J Z , et al . Strongly supervised mitosis detection in breast histopathology images using weak labels [C ] // 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI2021) . Piscataway : IEEE , 2021 : 358 - 361 .

LI Y H , XUE Y , LI L F , et al . Domain adaptive box-supervised instance segmentation network for mitosis detection [J ] . IEEE Transactions on Medical Imaging , 2022 , 41 ( 9 ): 2469 - 2485 .

ROMO-BUCHELI D , JANOWCZYK A , GILMORE H , et al . A deep learning based strategy for identifying and associating mitotic activity with gene expression derived risk categories in estrogen receptor positive breast cancers [J ] . Cytometry Part A , 2017 , 91 ( 6 ): 566 - 573 .

WOLLMANN T , ROHR K . Deep residual Hough voting for mitotic cell detection in histopathology images [C ] // 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI2017) . Piscataway : IEEE , 2017 : 341 - 344 .

SEBAI M , WANG T J , AL-FADHLI S ALI . PartMitosis: A partially supervised deep learning framework for mitosis detection in breast cancer histopathology images [J ] . IEEE Access , 2020 , 8 : 45133 - 45147 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深监督跨尺度注意力网络的深度图像超分辨率重建

基于形状匹配变形模型的三维人脸重构

径向基函数神经网络的软竞争学习算法

基于有限状态径向基函数网络的汉语语音识别研究