Journal Article

Interpretable multiple instance learning for hematologic diagnosis from peripheral blood smears

McVoy, Lauren, Paulsen, Sean, Dilip, Deepika, Manzo, Allyne, Sanchez, Nicolas, Cleave, Jacob G Van, Sun, Shenghuan, Sarkar, Argho, McCash, Samuel I, Gupta, Riya, Wang, Linlin, Yan, Ethan S, Lin, Oscar, Ardon, Orly, Isgor, Irem S, Kezlarian-Sachs, Brie, Mantha, Simon, Roshal, Mikhail, Vanderbilt, Chad, Yabe, Mariko, Kim, David, Dogan, Ahmet, Kumar, Neeraj, Chan, Alexander, Singi, Siddharth, Fried, Brenda, Carmichael, Iain, Yin, Zhanghan, Zhu, Menglei, Xiao, Wenbin, Baik, Jeeyeon, Kamali, Ali, Bilal, Khawaja H, Fenelus, Maly, Goldgof, Gregory M, Webb, Dylan C, Cardillo, Anthony, Syed, Aijazuddin, Colorado-Jimenez, Cesar, Boiocchi, Leonardo, Nanda, Swaraj

2026

Overview

Accurate diagnosis of hematologic malignancies from peripheral blood smears (PBSs) requires integrating cellular morphology and composition across numerous white blood cells. Existing computational approaches predominantly automate single-cell classifications and do not provide holistic, slide-level diagnostic predictions. We present a framework that employs a high-performance cell-based encoder (DeepHeme) for feature extraction, integrated with our weakly supervised, attention-based multiple instance learning (MIL) model, termed CAREMIL (Cell AggRegation, Explainable, Multiple Instance Learning). Through comprehensive evaluations of leading image encoders and MIL architectures, the combination of DeepHeme and CAREMIL demonstrated superior performance on disease classification tasks. CAREMIL functions as a robust aggregation mechanism, consistently outperforming established slide-level MIL methods (gated MIL and Dual-stream MIL Network) across multiple encoder types. The most pronounced performance gains were observed with out-of-domain encoders, including ImageNet-pretrained and open-source pathology foundation models (UNI2 and Virchow2). CAREMIL combined with DeepHeme achieves the highest diagnostic accuracy across acute myeloid leukemia (AML), myelodysplastic syndromes (MDS), and hairy cell leukemia (HCL), with AUROCs of 0.999, 0.891, and 0.945, respectively, and successfully identifies AML even in cases with minimal or absent circulating blasts. Attention values assigned by CAREMIL highlight diagnostically relevant cells and reveal disease-specific morphometric patterns, enabling biological interpretability and case-level insights. The framework remains resilient to individual cell misclassifications and does not require explicit cell-level supervision. These findings establish CAREMIL as an effective and interpretable MIL framework for hematologic slide diagnosis, extendable to bone marrow aspirates, cytology, and other liquid biopsy specimens, supporting a shift toward quantitative, morphology-informed hematologic diagnostics.