Multi-task Learning-based Ultrasound Image Segmentation and Auxiliary Diagnosis in End-stage Renal Diseases

End-stage renal disease (ESRD) is a severe kidney disorder; kidney ultrasound, as a non invasive diagnostic tool, is widely used in its clinical diagnosis. However, due to the morphological changes caused by ESRD, such as kidney shrinkage, cortical thinning, and increased echogenicity, traditional u...

Full description

Saved in:
Bibliographic Details
Published in:IEEE Conference on Industrial Electronics and Applications (Online) pp. 1 - 7
Main Authors: Lin, Ruishi, Li, Guanghan, Zheng, Min, Yu, Yuan, Ma, Liyong
Format: Conference Proceeding
Language:English
Published: IEEE 03.08.2025
Subjects:
Accuracy
Diseases
End-Stage Renal Disease
Faces
Feature extraction
Image edge detection
Image segmentation
Industrial electronics
Kidney
Kidney Ultrasound
Multi-Task Learning
Multitasking
Ultrasonic imaging
ISSN:2158-2297
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract End-stage renal disease (ESRD) is a severe kidney disorder; kidney ultrasound, as a non invasive diagnostic tool, is widely used in its clinical diagnosis. However, due to the morphological changes caused by ESRD, such as kidney shrinkage, cortical thinning, and increased echogenicity, traditional ultrasound image segmentation and diagnosis still face significant challenges. To improve segmentation accuracy and diagnostic performance, this paper proposes a multi-task learning-based approach for ultrasound kidney segmentation and auxiliary diagnosis. The method combines the classical UNet architecture with the advanced RKAN-ResNet34 encoder and incorporates an improved Convolutional Block Attention Module (CBAM), which integrates edge attention and deformable convolutions, to address the issues of blurred boundaries and morphological changes in kidney images. By jointly optimizing segmentation and classification tasks, the model simultaneously enhances both kidney segmentation accuracy and auxiliary diagnostic performance. Experimental results show that the proposed method achieves a Dice coefficient of 0.9233 and an IoU of 0.8592 for segmentation, along with an accuracy of 98.64% and an F1 score of 0.9882 for auxiliary diagnosis, outperforming existing methods. This study provides an effective solution for the automation of the ultrasound kidney image segmentation and diagnosis, contributing to the auxiliary diagnosis of end-stage renal disease.
AbstractList End-stage renal disease (ESRD) is a severe kidney disorder; kidney ultrasound, as a non invasive diagnostic tool, is widely used in its clinical diagnosis. However, due to the morphological changes caused by ESRD, such as kidney shrinkage, cortical thinning, and increased echogenicity, traditional ultrasound image segmentation and diagnosis still face significant challenges. To improve segmentation accuracy and diagnostic performance, this paper proposes a multi-task learning-based approach for ultrasound kidney segmentation and auxiliary diagnosis. The method combines the classical UNet architecture with the advanced RKAN-ResNet34 encoder and incorporates an improved Convolutional Block Attention Module (CBAM), which integrates edge attention and deformable convolutions, to address the issues of blurred boundaries and morphological changes in kidney images. By jointly optimizing segmentation and classification tasks, the model simultaneously enhances both kidney segmentation accuracy and auxiliary diagnostic performance. Experimental results show that the proposed method achieves a Dice coefficient of 0.9233 and an IoU of 0.8592 for segmentation, along with an accuracy of 98.64% and an F1 score of 0.9882 for auxiliary diagnosis, outperforming existing methods. This study provides an effective solution for the automation of the ultrasound kidney image segmentation and diagnosis, contributing to the auxiliary diagnosis of end-stage renal disease.
Author Li, Guanghan
Ma, Liyong
Lin, Ruishi
Yu, Yuan
Zheng, Min
Author_xml – sequence: 1
  givenname: Ruishi
  surname: Lin
  fullname: Lin, Ruishi
  email: 23s030129@stu.hit.edu.cn
  organization: Harbin Institute of Technology,School of Information Science and Engineering,Weihai,China
– sequence: 2
  givenname: Guanghan
  surname: Li
  fullname: Li, Guanghan
  email: ak74ebr@163.com
  organization: China-Japan Friendship Hospital,Department of Ultrasound Medicine,Beijing,China
– sequence: 3
  givenname: Min
  surname: Zheng
  fullname: Zheng, Min
  email: Zhengmin16@163.com
  organization: China-Japan Friendship Hospital,Department of Ultrasound Medicine,Beijing,China
– sequence: 4
  givenname: Yuan
  surname: Yu
  fullname: Yu, Yuan
  email: yuanyu@umich.edu
  organization: University of Michigan,Electrical Engineering and Computer Science Department,Ann Arbor,MI,USA
– sequence: 5
  givenname: Liyong
  surname: Ma
  fullname: Ma, Liyong
  email: maliyong@hit.edu.cn
  organization: Harbin Institute of Technology,School of Information Science and Engineering,Weihai,China
BookMark eNo1UMFKAzEUjKJgrf0DD_mBaPLSbJJjqVUXKoLWc3nbfbvEbrOySUH_3hX1NDDDDDNzyc5iH4kxruSNUtLflstytSiMUXADEsxIqrkHZU_YzFvvtFYG5lIXp2wCyjgB4O0Fm6X0LqXUylqn1YTtn45dDiJj2vM14RBDbEWFiWr-1uUBU3-MNS8P2BJ_pfZAMWMOfeQ40ovjZ-gCDl_8LmAb-xQSD5GvYi1S_nG8UMRuFBONiemKnTfYJZr94ZRt7leb5aNYPz-Uy8VaBK-zwAJq56RrnKy0VeMCrXa2Iudso60j7S04pNr4nUcFZtcU0BRkJVbeWQA9Zde_sYGIth9DOIwNt__36G87OFxC
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICIEA65512.2025.11149217
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798331524036
EISSN 2158-2297
EndPage 7
ExternalDocumentID 11149217
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i93t-a62d8808f80b37103631c7be887f378e39728aed59c9a125cf62f6e70ab987223
IEDL.DBID RIE
IngestDate Wed Sep 17 06:32:20 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-a62d8808f80b37103631c7be887f378e39728aed59c9a125cf62f6e70ab987223
PageCount 7
ParticipantIDs ieee_primary_11149217
PublicationCentury 2000
PublicationDate 2025-Aug.-3
PublicationDateYYYYMMDD 2025-08-03
PublicationDate_xml – month: 08
  year: 2025
  text: 2025-Aug.-3
  day: 03
PublicationDecade 2020
PublicationTitle IEEE Conference on Industrial Electronics and Applications (Online)
PublicationTitleAbbrev ICIEA
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003177831
Score 1.9172425
Snippet End-stage renal disease (ESRD) is a severe kidney disorder; kidney ultrasound, as a non invasive diagnostic tool, is widely used in its clinical diagnosis....
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accuracy
Diseases
End-Stage Renal Disease
Faces
Feature extraction
Image edge detection
Image segmentation
Industrial electronics
Kidney
Kidney Ultrasound
Multi-Task Learning
Multitasking
Ultrasonic imaging
Title Multi-task Learning-based Ultrasound Image Segmentation and Auxiliary Diagnosis in End-stage Renal Diseases
URI https://ieeexplore.ieee.org/document/11149217
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6UeNCLL4zv9OC1sGx3-zgShMiFEMWEGyndlmyAxewuRv-907KgHjx4a9o0adqZfl_a-WYQekisiKgylLSSWJBICUamYBZgyzywNrYOInyxCT4YiPFYDiuxutfCGGN88JlpuKb_y09Weu2eyprgl5EEDr2P9jnnG7HW7kEFgJAL2tpG6wSy2e_0u20GlMAJrsK4sZ3-q5CKx5He8T9XcILq34o8PNxhzSnaM9kZOvqRTPAczb2WlpSqmOMqa-qMOJBK8OuizFXhCijh_hIuEPxiZstKdJRhBd3t9Ue6SFX-iR83sXdpgdMMd7OEAH2EGc8GLA4G_XdOUUejXnfUeSJVKQWSSloSxcIEHFVYEUwpcArKaEvzqYEbxlIuDJCSUCiTxFJLBZRHWxZaZnigplJwYBAXqJatMnOJMFOGWaUlE5GOVKSFtBEToWJgkiII1RWqu22bvG2SZUy2O3b9R_8NOnSH42Pq6C2qlfna3KED_V6mRX7vj_gL6ounkA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4UTdSLvzD-tgevhbF2XXskCIGIhCgm3Ei3tWQBhmHD6H_vWxmoBw_emjZtmva135f2fe8hdB8ZwajSlNQiTxCmBCcBmAXYsu8Y45kcImyyCb_XE8Oh7BdidauF0Vpb5zNdyYv2Lz-ah8v8qawK55JJ4NDbaMdjzK2t5FqbJxWAQl_Q2tpfx5HVTqPTrHMgBbnkyvUq6wF-pVKxSNI6_OccjlD5W5OH-xu0OUZbOjlBBz_CCZ6iiVXTkkylE1zETR2THKYi_DrNFirNUyjhzgyuEPyix7NCdpRgBdX15Uc8jdXiEz-svO_iFMcJbiYRAQIJPZ412Bw02g-dtIwGreag0SZFMgUSS5oRxd0IjqowwgkosArKaS30Aw13jKG-0EBLXKF05MlQKiA9oeGu4dp3VCCFDxziDJWSeaLPEeZKc6NCyQULmWKhkIZx4SoORikcV12gcr5so7dVuIzResUu_6i_Q3vtwVN31O30Hq_Qfr5R1sOOXqNStljqG7Qbvmdxuri12_0Fzuuq1w
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE+Conference+on+Industrial+Electronics+and+Applications+%28Online%29&rft.atitle=Multi-task+Learning-based+Ultrasound+Image+Segmentation+and+Auxiliary+Diagnosis+in+End-stage+Renal+Diseases&rft.au=Lin%2C+Ruishi&rft.au=Li%2C+Guanghan&rft.au=Zheng%2C+Min&rft.au=Yu%2C+Yuan&rft.date=2025-08-03&rft.pub=IEEE&rft.eissn=2158-2297&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FICIEA65512.2025.11149217&rft.externalDocID=11149217