Salvato in:
Dettagli Bibliografici
Autori principali: Srivastava, Utkarsh Prakash, Gupta, Kaushik, Nath, Kaushik
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.07801
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914150104432640
author Srivastava, Utkarsh Prakash
Gupta, Kaushik
Nath, Kaushik
author_facet Srivastava, Utkarsh Prakash
Gupta, Kaushik
Nath, Kaushik
contents We study multilabel classification of chest X-rays and present a simple, strong pipeline built on SE-ResNeXt101 $(32 \times 4d)$. The backbone is finetuned for 14 thoracic findings with a sigmoid head, trained using Multilabel Iterative Stratification (MIS) for robust cross-validation splits that preserve label co-occurrence. To address extreme class imbalance and asymmetric error costs, we optimize with Asymmetric Loss, employ mixed-precision (AMP), cosine learning-rate decay with warm-up, gradient clipping, and an exponential moving average (EMA) of weights. We propose a lightweight Label-Graph Refinement module placed after the classifier: given per-label probabilities, it learns a sparse, trainable inter-label coupling matrix that refines logits via a single message-passing step while adding only an L1-regularized parameter head. At inference, we apply horizontal flip test-time augmentation (TTA) and average predictions across MIS folds (a compact deep ensemble). Evaluation uses macro AUC averaging classwise ROC-AUC and skipping single-class labels in a fold to reflect balanced performance across conditions. On our dataset, a strong SE-ResNeXt101 baseline attains competitive macro AUC (e.g., 92.64% in our runs). Adding the Label-Graph Refinement consistently improves validation macro AUC across folds with negligible compute. The resulting method is reproducible, hardware-friendly, and requires no extra annotations, offering a practical route to stronger multilabel CXR classifiers.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07801
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Sparse Label Couplings for Multilabel Chest X-Ray Diagnosis
Srivastava, Utkarsh Prakash
Gupta, Kaushik
Nath, Kaushik
Computer Vision and Pattern Recognition
We study multilabel classification of chest X-rays and present a simple, strong pipeline built on SE-ResNeXt101 $(32 \times 4d)$. The backbone is finetuned for 14 thoracic findings with a sigmoid head, trained using Multilabel Iterative Stratification (MIS) for robust cross-validation splits that preserve label co-occurrence. To address extreme class imbalance and asymmetric error costs, we optimize with Asymmetric Loss, employ mixed-precision (AMP), cosine learning-rate decay with warm-up, gradient clipping, and an exponential moving average (EMA) of weights. We propose a lightweight Label-Graph Refinement module placed after the classifier: given per-label probabilities, it learns a sparse, trainable inter-label coupling matrix that refines logits via a single message-passing step while adding only an L1-regularized parameter head. At inference, we apply horizontal flip test-time augmentation (TTA) and average predictions across MIS folds (a compact deep ensemble). Evaluation uses macro AUC averaging classwise ROC-AUC and skipping single-class labels in a fold to reflect balanced performance across conditions. On our dataset, a strong SE-ResNeXt101 baseline attains competitive macro AUC (e.g., 92.64% in our runs). Adding the Label-Graph Refinement consistently improves validation macro AUC across folds with negligible compute. The resulting method is reproducible, hardware-friendly, and requires no extra annotations, offering a practical route to stronger multilabel CXR classifiers.
title Learning Sparse Label Couplings for Multilabel Chest X-Ray Diagnosis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.07801