Label‐Free Leukemia Monitoring by Computer Vision

Acute lymphoblastic leukemia (ALL) is the most common childhood cancer. While there are a number of well‐recognized prognostic biomarkers at diagnosis, the most powerful independent prognostic factor is the response of the leukemia to induction chemotherapy (Campana and Pui: Blood 129 (2017) 1913–1918). Given the potential for machine learning to improve precision medicine, we tested its capacity to monitor disease in children undergoing ALL treatment. Diagnostic and on‐treatment bone marrow samples were labeled with an ALL‐discriminating antibody combination and analyzed by imaging flow cytometry. Ignoring the fluorescent markers and using only features extracted from bright‐field and dark‐field cell images, a deep learning model was able to identify ALL cells at an accuracy of >88%. This antibody‐free, single cell method is cheap, quick, and could be adapted to a simple, laser‐free cytometer to allow automated, point‐of‐care testing to detect slow early responders. Adaptation to other types of leukemia is feasible, which would revolutionize residual disease monitoring. © 2020 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

[1]  K. Spiekermann,et al.  Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks , 2019, Nat. Mach. Intell..

[2]  Hayden Kwok-Hay So,et al.  Quantitative Phase Imaging Flow Cytometry for Ultra‐Large‐Scale Single‐Cell Biophysical Phenotyping , 2019, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[3]  Stefan W Krause,et al.  Label‐Free High‐Throughput Leukemia Detection by Holographic Microscopy , 2018, Advanced science.

[4]  Anne E Carpenter,et al.  CellProfiler 3.0: Next-generation image processing for biology , 2018, PLoS biology.

[5]  Vittorio Bianco,et al.  Label-Free Optical Marker for Red-Blood-Cell Phenotyping of Inherited Anemias. , 2018, Analytical chemistry.

[6]  Samuel J. Yang,et al.  In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images , 2018, Cell.

[7]  M. Loh,et al.  Flow-cytometric vs. -morphologic assessment of remission in childhood acute lymphoblastic leukemia: a report from the Children’s Oncology Group (COG) , 2017, Leukemia.

[8]  Mary M. Maleckar,et al.  Three dimensional cross-modal image inference: label-free methods for subcellular structure prediction , 2017, bioRxiv.

[9]  Paolo A. Netti,et al.  Single-cell screening of multiple biophysical properties in leukemia diagnosis from peripheral blood by pure light scattering , 2017, Scientific Reports.

[10]  Cheng Lei,et al.  Label-free detection of cellular drug responses by high-throughput bright-field imaging and machine learning , 2017, Scientific Reports.

[11]  Anne E Carpenter,et al.  Reconstructing cell cycle and disease progression using deep learning , 2017, Nature Communications.

[12]  Dario Campana,et al.  Minimal residual disease-guided therapy in childhood acute lymphoblastic leukemia. , 2017, Blood.

[13]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[14]  R. Wade,et al.  Use of Minimal Residual Disease Assessment to Redefine Induction Failure in Pediatric Acute Lymphoblastic Leukemia. , 2017, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[15]  Y. Lo,et al.  Review: imaging technologies for flow cytometry. , 2016, Lab on a chip.

[16]  E. Thompson,et al.  Minimal residual disease in breast cancer: an overview of circulating and disseminated tumour cells , 2016, Clinical & Experimental Metastasis.

[17]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[18]  Anne E Carpenter,et al.  Label-free cell cycle analysis for high-throughput imaging flow cytometry , 2016, Nature Communications.

[19]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Chris Eliasmith,et al.  Hyperopt: a Python library for model selection and hyperparameter optimization , 2015 .

[21]  Alberto Orfao,et al.  Minimal residual disease diagnostics in acute lymphoblastic leukemia: need for sensitive, fast, and standardized technologies. , 2015, Blood.

[22]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[23]  R. Wade,et al.  Augmented post-remission therapy for a minimal residual disease-defined high-risk subgroup of children and young people with clinical standard-risk and intermediate-risk acute lymphoblastic leukaemia (UKALL 2003): a randomised controlled trial. , 2014, The Lancet. Oncology.

[24]  G. Chagaluka,et al.  Remote and rapid pathological diagnosis in a resource challenged unit , 2014, Journal of Clinical Pathology.

[25]  Robert K Hills,et al.  Prognostic relevance of treatment response measured by flow cytometric residual disease detection in older patients with acute myeloid leukemia. , 2013, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[26]  R. Wade,et al.  Treatment reduction for children and young adults with low-risk acute lymphoblastic leukaemia defined by minimal residual disease (UKALL 2003): a randomised controlled trial. , 2013, The Lancet. Oncology.

[27]  Hongying Zhu,et al.  Optofluidic fluorescent imaging cytometry on a cell phone. , 2011, Analytical chemistry.

[28]  Jeremy Hancock,et al.  Establishment and validation of a standard protocol for the detection of minimal residual disease in B lineage childhood acute lymphoblastic leukemia by flow cytometry in a multi-center setting; , 2009, Haematologica.

[29]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[30]  William E. Ortyn,et al.  Cellular image analysis and imaging by flow cytometry. , 2007, Clinics in laboratory medicine.

[31]  J. Byrd,et al.  International standardized approach for flow cytometric residual disease monitoring in chronic lymphocytic leukaemia , 2007, Leukemia.

[32]  Anne E Carpenter,et al.  CellProfiler: image analysis software for identifying and quantifying cell phenotypes , 2006, Genome Biology.

[33]  D. Campana,et al.  Advances in the immunological monitoring of childhood acute lymphoblastic leukaemia. , 2002, Best practice & research. Clinical haematology.