Interpretable multiple instance learning for hematologic diagnosis from peripheral blood smears.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Singi Siddharth, Sun Shenghuan, Yin Zhanghan, Gupta Riya, Webb Dylan C, Bilal Khawaja H, Dilip Deepika, Wang Linlin, Kumar Neeraj, Nanda Swaraj, Sanchez Nicolas, Cleave Jacob G Van, Fried Brenda, Paulsen Sean, Yan Ethan S, Kamali Ali, Sarkar Argho, Manzo Allyne, Baik Jeeyeon, Isgor Irem S, Colorado-Jimenez Cesar, Cardillo Anthony, Boiocchi Leonardo, Syed Aijazuddin, Kim David, Kezlarian-Sachs Brie, Fenelus Maly, Chan Alexander, Yabe Mariko, McCash Samuel I, Zhu Menglei, Mantha Simon, Ardon Orly, McVoy Lauren, Xiao Wenbin, Roshal Mikhail, Lin Oscar, Dogan Ahmet, Carmichael Iain, Vanderbilt Chad, Goldgof Gregory M
Аннотация
METHODS: 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).
RESULTS: 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.
CONCLUSIONS: 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.