Patient-Level Diagnosis of Acute Myeloid Leukemia via Deep Learning Analysis of Bone Marrow Smear

• URL: http://arxiv.org/abs/2606.10735v1
• Date: Tue, 09 Jun 2026 11:45:19 GMT
• Title: Patient-Level Diagnosis of Acute Myeloid Leukemia via Deep Learning Analysis of Bone Marrow Smear
• Abstract summary: We present a cell-to-patient deep learning pipeline for AML-assisted diagnosis from bone marrow smear images.<n>A 16-category cell annotation vocabulary was used to describe the global cellular composition.<n>The pipeline achieved stable internal validation and maintained external generalization, with ensemble weighted F1-scores of 0.9076, 0.8696, and 0.9124 on Centers 4, 5, and 6, respectively.
• Score: 3.524484110386522
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Bone marrow smear review remains important for acute myeloid leukemia (AML) assessment, but manual single-cell interpretation is labor-intensive and patient-level diagnosis requires aggregation of many cellular observations. We present a cell-to-patient deep learning pipeline for AML-assisted diagnosis from bone marrow smear images. The study included 258 patients from six anonymized centers, including a main cohort of 169 patients from Centers 1-3 and an external validation cohort of 89 patients from Centers 4-6. A 16-category cell annotation vocabulary was used to describe the global cellular composition, including granulocytic, monocytic, erythroid, lymphoid, eosinophilic, and other cells. Rather than identifying strict AML blasts or leukemic blasts, the model targets an expert-defined composite category termed Composite Blast-like Cells (CBLC), comprising N, N1, M, M1, R, R1, J, and J1 according to the project-wide morphological standard. A fixed YOLO-based segmentation module detected cells, predicted contours were matched to expert polygon annotations by contour IoU, and standardized single-cell crops were generated. An EfficientNet-B0 classifier was trained through a two-stage GT-to-YOLO and YOLO-to-YOLO strategy with class-imbalance correction, center-border regularization, and morphology-assisted supervision. Cell-level predictions were aggregated into patient-level CBLC ratios for AML-oriented diagnostic support. The pipeline achieved stable internal validation and maintained external generalization, with ensemble weighted F1-scores of 0.9076, 0.8696, and 0.9124 on Centers 4, 5, and 6, respectively.

Related papers

• CytoFormer: A Molecularly Supervised Cell Foundation Model for Histopathology Cell Classification [1.5928576802540013]
  Training such models has relied on manual pathologist annotations, which are slow, expensive and unreliable for many cell types.<n>We instead supervise morphology with molecules.<n>We assembled 81 such paired Xenium sections spanning 16 organs, derived per-cell labels by clustering, marker-gene annotation, organ-wise human review and quality control, and mapped them onto the cell types commonly reported in each organ.<n>This yielded 15.4 million cells, each with a paired H&E image patch and one of 23 cell types, on which we trained CytoFormer, a cell foundation model with a multi-task, per-organ classification head.
  arXiv  Detail & Related papers  (2026-08-17T15:35:03Z)
• IMILIA: interpretable multiple instance learning for inflammation prediction in IBD from H&E whole slide images [2.5182612992285844]
  We introduce IMILIA, an end-to-end framework for prediction of inflammation presence in IBD digitized slides stained with hematoxylin and eosin (H&E)<n> IMILIA is composed of an inflammation prediction module, and an interpretability module, divided in two blocks: HistoPLUS, for cell instance detection, and EpiSeg, for epithelium segmentation.<n>The interpretability module yields biologically consistent insights: tiles with higher predicted scores show increased densities of immune cells, whereas lower-scored tiles predominantly contain normal epithelial cells.
  arXiv  Detail & Related papers  (2025-12-15T15:36:09Z)
• Multimodal Oncology Agent for IDH1 Mutation Prediction in Low-Grade Glioma [0.5499435453529261]
  This work introduces a Multimodal Oncology Agent (MOA) integrating a histology tool based on the TITAN foundation model for IDH1 mutation prediction in low-grade glioma.<n>Results show MOA captures complementary mutation-relevant information enriched through external biomedical sources, enabling accurate IDH1 mutation prediction.
  arXiv  Detail & Related papers  (2025-12-05T15:43:02Z)
• Automated Identification of Incidentalomas Requiring Follow-Up: A Multi-Anatomy Evaluation of LLM-Based and Supervised Approaches [5.958100741754613]
  We evaluated large language models (LLMs) against supervised baselines for fine-grained, lesion-level detection of incidentalomas.<n>We introduced a novel inference strategy using lesion-tagged inputs and anatomy-aware prompting to ground model reasoning.<n>The anatomy-informed GPT-OSS-20b model achieved the highest performance, yielding an incidentaloma-positive macro-F1 of 0.79.
  arXiv  Detail & Related papers  (2025-12-05T08:49:57Z)
• RAA-MIL: A Novel Framework for Classification of Oral Cytology [0.0]
  We introduce the first weakly supervised deep learning framework for patient-level diagnosis of oral Cytology whole slide images.<n>This study establishes the first patient-level weakly supervised benchmark for oral Cytology and moves toward reliable AI-assisted digital pathology.
  arXiv  Detail & Related papers  (2025-11-15T15:48:36Z)
• MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks [47.486705282473984]
  Large language models (LLMs) achieve near-perfect scores on medical exams.<n>These evaluations inadequately reflect complexity and diversity of real-world clinical practice.<n>We introduce MedHELM, an evaluation framework for assessing LLM performance for medical tasks.
  arXiv  Detail & Related papers  (2025-05-26T22:55:49Z)
• Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV [49.1574468325115]
  This study explores multiple ML approaches for predicting LOS in ICU specifically for the patients with neurological diseases based on the MIMIC-IV dataset.<n>The evaluated models include classic ML algorithms (K-Nearest Neighbors, Random Forest, XGBoost and CatBoost) and Neural Networks (LSTM, BERT and Temporal Fusion Transformer)
  arXiv  Detail & Related papers  (2025-05-23T14:06:42Z)
• CellVerse: Do Large Language Models Really Understand Cell Biology? [74.34984441715517]
  We introduce CellVerse, a unified language-centric question-answering benchmark that integrates four types of single-cell multi-omics data.<n>We systematically evaluate the performance across 14 open-source and closed-source LLMs ranging from 160M to 671B on CellVerse.
  arXiv  Detail & Related papers  (2025-05-09T06:47:23Z)
• Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertension [30.124231086488976]
  We propose a lead-specific electrocardiogram multimodal variational autoencoder (textscLS-EMVAE)<n>textscLS-EMVAE incorporates a hierarchical modality expert (HiME) fusion mechanism and a latent representation alignment loss.<n>We validate textscLS-EMVAE across two retrospective cohorts in a 6L-ECG setting.
  arXiv  Detail & Related papers  (2025-03-03T16:16:38Z)
• MMIL: A novel algorithm for disease associated cell type discovery [58.044870442206914]
  Single-cell datasets often lack individual cell labels, making it challenging to identify cells associated with disease. We introduce Mixture Modeling for Multiple Learning Instance (MMIL), an expectation method that enables the training and calibration of cell-level classifiers.
  arXiv  Detail & Related papers  (2024-06-12T15:22:56Z)
• FlowCyt: A Comparative Study of Deep Learning Approaches for Multi-Class Classification in Flow Cytometry Benchmarking [1.6712896227173808]
  FlowCyt is the first comprehensive benchmark for multi-class single-cell classification in flowencoded data. The dataset comprises bone marrow samples from 30 patients, with each cell characterized by twelve markers.
  arXiv  Detail & Related papers  (2024-02-28T15:01:59Z)
• Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies [62.840338941861134]
  We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset. We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis. This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
  arXiv  Detail & Related papers  (2023-02-16T17:06:23Z)
• Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN [70.76142503046782]
  We propose supplementing machine learning-based (ML) healthcare tools for bias with SLOGAN, an automatic tool for capturing local biases in a clinical prediction task. LOGAN adapts an existing tool, LOcal Group biAs detectioN, by contextualizing group bias detection in patient illness severity and past medical history. On average, SLOGAN identifies larger fairness disparities in over 75% of patient groups than LOGAN while maintaining clustering quality.
  arXiv  Detail & Related papers  (2022-11-16T08:04:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.