Pith Number

pith:EEJZUK3S

pith:2025:EEJZUK3SPL3N7TE5YT6EZGRKQS

not attested not anchored not stored refs resolved

Transformer-Based Hematological Malignancy Prediction from Peripheral Blood Smears in a Real-World Cohort

Ario Sadafi, Carsten Marr, Christian Pohlkamp, Fatih Ozlugedik, Ivan Kukuljan, Karsten Spiekermann, Matthias Hehr, Muhammed Furkan Dasdelen, Peter Lienemann

Transformer model on peripheral blood images classifies hematological malignancies and lowers false discovery rate for acute leukemia from 13.5% to 8.7% without missing cases.

arxiv:2509.20402 v3 · 2025-09-23 · q-bio.QM

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EEJZUK3SPL3N7TE5YT6EZGRKQS}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Our model's calibrated prediction probabilities reduce the false discovery rate from 13.5% to 8.7% without missing any acute leukemia cases, thereby decreasing the number of unnecessary bone marrow aspirations based on peripheral blood smears.

C2weakest assumption

That the coarse eight-class labels derived from comprehensive bone-marrow cytomorphology, cytogenetics, molecular genetics and immunophenotyping constitute reliable ground truth for training and evaluating a model that sees only peripheral-blood images.

C3one line summary

cAItomorph applies a transformer aggregator on DinoBloom embeddings to predict eight coarse hematological malignancy classes from peripheral blood single-cell images, achieving 0.72 accuracy and reducing false discovery rate for acute leukemia referrals.

References

3 extracted · 3 resolved · 0 Pith anchors

[1] de Lima, M., Castillo, J., Merli, M. & Garcia-Gutierrez, V. Editorial: Epidemiological trends in hematological malignancies. Front. Oncol. 13 , 1151774 (2023). 2. Kantarjian, H. et al. Acute myeloid l 2023

[2] Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again 2019

[3] Virchow2: Scaling self-supervised mixed magnification models in pathology 2018 · doi:10.48550/arxiv.2408.00738

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-06-25T01:17:46.295850Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

21139a2b727af6dfcc9dc4fc4c9a2a849c554137c1a44ca9acf445786a896f26

Aliases

arxiv: 2509.20402 · arxiv_version: 2509.20402v3 · doi: 10.48550/arxiv.2509.20402 · pith_short_12: EEJZUK3SPL3N · pith_short_16: EEJZUK3SPL3N7TE5 · pith_short_8: EEJZUK3S

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/EEJZUK3SPL3N7TE5YT6EZGRKQS \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 21139a2b727af6dfcc9dc4fc4c9a2a849c554137c1a44ca9acf445786a896f26

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "70a2aae8eaf50aa9fd650e0d3ef74072958d71c706ba4ae5ed09c5bdf90d02e1",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "q-bio.QM",
    "submitted_at": "2025-09-23T19:18:37Z",
    "title_canon_sha256": "ccc951909f1bd0f4f1a31a3dde1da4a5aa67965a67da9e910a5224ef9a13016c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2509.20402",
    "kind": "arxiv",
    "version": 3
  }
}