# A Leakage-Aware Comparative Benchmark of Machine Learning, Deep Learning, and Transformer Models for Reliable Leukemia Detection

arXiv: https://arxiv.org/abs/2606.24944 · HTML: https://mlsanity.com/paper/2606.24944/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Why rankings of biomedical image analysis competitions should be interpreted with care](https://mlsanity.com/paper/1806.02051/) (2018)
- [A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methods](https://mlsanity.com/paper/2310.06873/) (2023)
- [How I failed machine learning in medical imaging -- shortcomings and recommendations](https://mlsanity.com/paper/2103.10292/) (2021)
- [How You Split Matters: Data Leakage and Subject Characteristics Studies in Longitudinal Brain MRI Analysis](https://mlsanity.com/paper/2309.00350/) (2023)
- [SDCT-AuxNetθ: DCT Augmented Stain Deconvolutional CNN with Auxiliary Classifier for Cancer Diagnosis](https://mlsanity.com/paper/2006.00304/) (2020)
- [False Promises in Medical Imaging AI? Assessing Validity of Outperformance Claims](https://mlsanity.com/paper/2505.04720/) (2025)
- [Acute Lymphoblastic Leukemia Classification from Microscopic Images using Convolutional Neural Networks](https://mlsanity.com/paper/1906.09020/) (2019)
- [Segmentation and Classification of Pap Smear Images for Cervical Cancer Detection Using Deep Learning](https://mlsanity.com/paper/2508.17728/) (2025)
- [Systematic Evaluation of Vision Transformers for Automated Cervical Cancer Classification: Optimization, Statistical Validation, and Clinical Interpretability](https://mlsanity.com/paper/2605.17236/) (2026)
- [Acute Lymphoblastic Leukemia Detection from Microscopic Images Using Weighted Ensemble of Convolutional Neural Networks](https://mlsanity.com/paper/2105.03995/) (2021)
- [Enhanced Leukemic Cell Classification Using Attention-Based CNN and Data Augmentation](https://mlsanity.com/paper/2601.01026/) (2026)

## Built on by (most cited first, 1 of 1)

- [Reliability-Aware CT-MRI Registration: A Quality Engineering Framework with Stability Analysis and Risk Classification](https://mlsanity.com/paper/2607.02585/) (2026)

## Abstract (arXiv)

Automated classification of acute lymphoblastic leukemia (ALL) from peripheral blood smear images has often reported near-perfect performance on the C-NMC 2019 dataset. We show that such results can be inflated by patient-level data leakage caused by random image-level partitioning, where cells from the same subject may appear in both training and test folds. We establish a leakage-aware benchmark under a strict subject-disjoint protocol, comparing LightGBM, RBF-SVM, EfficientNet-B0, EfficientNet-B1, and ViT-Tiny. Models are developed using three subject-disjoint folds from 73 subjects and evaluated on an external preliminary-phase test set of 1,867 images from 28 unseen subjects with zero patient overlap. Beyond discrimination, we assess calibration using expected calibration error, Brier score, and temperature scaling. Under honest evaluation, EfficientNet-B1 achieves the best performance, with AUROC 0.913, sensitivity 0.87, specificity 0.80, and calibrated ECE 0.024. Frozen-feature classifiers and ViT-Tiny show high sensitivity but poor specificity, indicating a tendency to over-predict the malignant class. A random-versus-subject-disjoint ablation shows that random splitting inflates AUROC by about 0.04 even in the conservative frozen-feature setting. These findings caution against image-level evaluation on C-NMC 2019 and provide a reproducible, calibration-aware benchmark for future work.