DOAJ Open Access 2024

Deep Learning–Based Automated Imaging Classification of ADPKD

Youngwoo Kim Seonah Bu Cheng Tao Kyongtae T. Bae Theodore Steinman +48 lainnya

Abstrak

Introduction: The Mayo imaging classification model (MICM) requires a prestep qualitative assessment to determine whether a patient is in class 1 (typical) or class 2 (atypical), where patients assigned to class 2 are excluded from the MICM application. Methods: We developed a deep learning–based method to automatically classify class 1 and 2 from magnetic resonance (MR) images and provide classification confidence utilizing abdominal T2-weighted MR images from 486 subjects, where transfer learning was applied. In addition, the explainable artificial intelligence (XAI) method was illustrated to enhance the explainability of the automated classification results. For performance evaluations, confusion matrices were generated, and receiver operating characteristic curves were drawn to measure the area under the curve. Results: The proposed method showed excellent performance for the classification of class 1 (97.7%) and 2 (100%), where the combined test accuracy was 98.01%. The precision and recall for predicting class 1 were 1.00 and 0.98, respectively, with F1-score of 0.99; whereas those for predicting class 2 were 0.87 and 1.00, respectively, with F1-score of 0.93. The weighted averages of precision and recall were 0.98 and 0.98, respectively, showing the classification confidence scores whereas the XAI method well-highlighted contributing regions for the classification. Conclusion: The proposed automated method can classify class 1 and 2 cases as accurately as the level of a human expert. This method may be a useful tool to facilitate clinical trials investigating different types of kidney morphology and for clinical management of patients with autosomal dominant polycystic kidney disease (ADPKD).

Penulis (53)

Y

Youngwoo Kim

S

Seonah Bu

C

Cheng Tao

K

Kyongtae T. Bae

T

Theodore Steinman

J

Jesse Wei

P

Peter Czarnecki

I

Ivan Pedrosa

W

William Braun

S

Saul Nurko

E

Erick Remer

A

Arlene Chapman

D

Diego Martin

F

Frederic Rahbari-Oskoui

P

Pardeep Mittal

V

Vicente Torres

M

Marie C. Hogan

Z

Ziad El-Zoghby

P

Peter Harris

J

James Glockner

B

Bernard King, Jr.

R

Ronald Perrone

N

Neil Halin

D

Dana Miskulin

R

Robert Schrier

G

Godela Brosnahan

B

Berenice Gitomer

C

Cass Kelleher

A

Amirali Masoumi

N

Nayana Patel

F

Franz Winklhofer

J

Jared Grantham

A

Alan Yu

C

Connie Wang

L

Louis Wetzel

C

Charity G. Moore

J

James E. Bost

K

Kyongtae Bae

K

Kaleab Z. Abebe

J

J. Philip Miller

P

Paul A. Thompson

J

Josephine Briggs

M

Michael Flessner

C

Catherine M. Meyers

R

Robert Star

J

James Shayman

W

William Henrich

T

Tom Greene

M

Mary Leonard

P

Peter McCullough

S

Sharon Moe

M

Michael Rocco

D

David Wendler

Format Sitasi

Kim, Y., Bu, S., Tao, C., Bae, K.T., Steinman, T., Wei, J. et al. (2024). Deep Learning–Based Automated Imaging Classification of ADPKD. https://doi.org/10.1016/j.ekir.2024.04.002

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.1016/j.ekir.2024.04.002
Informasi Jurnal
Tahun Terbit
2024
Sumber Database
DOAJ
DOI
10.1016/j.ekir.2024.04.002
Akses
Open Access ✓