Learning from Noisy Labels in Medical Image Classification: Transition-Matrix Estimation, Loss Correction, and Sample Selection on MedMNIST Benchmarks

Loss corrections based on the noise transition matrix T promise to undo the annotation errors that deep networks memorize in medical images. On six public MedMNIST benchmarks with synthetic label noise, we separately evaluate the estimation of T, the selection of clean examples, and the clean test accuracy. Two propositions show that backward correction inflates the loss variance and that forward correction with an estimate changes decisions only where the clean margin is below twice an explicit error measure of the estimate. In 2175 runs, backward correction was below cross-entropy in 29 of 30 noisy settings, and the cost of forward correction grew with this error measure. The proposed validation-gated forward correction (VGFC), which chooses between forward correction and small-loss selection without clean labels or a known noise rate, was more accurate on average than either candidate but not clearly better than a disagreement-gated variant (+0.13 percentage points, 95% CI [−1.41, +1.24]). Post hoc, it was close to self-adaptive training on the four datasets with accurate estimates of T (above it with ResNet-18 on three of them) and below it on the other two. The benefit of transition-based methods is thus bounded by the accuracy of the estimated matrix. The conclusions are limited to synthetic noise on benchmark data.

Authors

Institutions

Publication Details

Journal
Electronics
Published
2026-11-16
DOI
https://doi.org/10.3390/electronics15225333
Primary Topic
Machine Learning and Data Classification
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Learning from Noisy Labels in Medical Image Classification: Transition-Matrix Estimation, Loss Correction, and Sample Selection on MedMNIST Benchmarks

Kwang-Seong Shin, Dong-Hyun Won
3 links
Electronics
Machine Learning and Data Classification
article

Learning from Noisy Labels in Medical Image Classification: Transition-Matrix Estimation, Loss Correction, and Sample Selection on MedMNIST Benchmarks

Kwang-Seong Shin, Dong-Hyun Won
article en

Abstract

Loss corrections based on the noise transition matrix T promise to undo the annotation errors that deep networks memorize in medical images. On six public MedMNIST benchmarks with synthetic label noise, we separately evaluate the estimation of T, the selection of clean examples, and the clean test accuracy. Two propositions show that backward correction inflates the loss variance and that forward correction with an estimate changes decisions only where the clean margin is below twice an explicit error measure of the estimate. In 2175 runs, backward correction was below cross-entropy in 29 of 30 noisy settings, and the cost of forward correction grew with this error measure. The proposed validation-gated forward correction (VGFC), which chooses between forward correction and small-loss selection without clean labels or a known noise rate, was more accurate on average than either candidate but not clearly better than a disagreement-gated variant (+0.13 percentage points, 95% CI [−1.41, +1.24]). Post hoc, it was close to self-adaptive training on the four datasets with accurate estimates of T (above it with ResNet-18 on three of them) and below it on the other two. The benefit of transition-based methods is thus bounded by the accuracy of the estimated matrix. The conclusions are limited to synthetic noise on benchmark data.

ElectronicsVol. 15(22)
Sunchon National University (KR), Wonkwang University (KR)
Wonkwang University
Good health and well-being
Machine Learning and Data Classification
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon