1
|
Abstract
The dicentric chromosome (DC) assay accurately quantifies exposure to radiation; however, manual and semi-automated assignment of DCs has limited its use for a potential large-scale radiation incident. The Automated Dicentric Chromosome Identifier and Dose Estimator (ADCI) software automates unattended DC detection and determines radiation exposures, fulfilling IAEA criteria for triage biodosimetry. This study evaluates the throughput of high-performance ADCI (ADCI-HT) to stratify exposures of populations in 15 simulated population scale radiation exposures. ADCI-HT streamlines dose estimation using a supercomputer by optimal hierarchical scheduling of DC detection for varying numbers of samples and metaphase cell images in parallel on multiple processors. We evaluated processing times and accuracy of estimated exposures across census-defined populations. Image processing of 1744 samples on 16,384 CPUs required 1 h 11 min 23 s and radiation dose estimation based on DC frequencies required 32 sec. Processing of 40,000 samples at 10 exposures from five laboratories required 25 h and met IAEA criteria (dose estimates were within 0.5 Gy; median = 0.07). Geostatistically interpolated radiation exposure contours of simulated nuclear incidents were defined by samples exposed to clinically relevant exposure levels (1 and 2 Gy). Analysis of all exposed individuals with ADCI-HT required 0.6–7.4 days, depending on the population density of the simulation.
Collapse
|
2
|
Qin Y, Wen J, Zheng H, Huang X, Yang J, Song N, Zhu YM, Wu L, Yang GZ. Varifocal-Net: A Chromosome Classification Approach Using Deep Convolutional Networks. IEEE TRANSACTIONS ON MEDICAL IMAGING 2019; 38:2569-2581. [PMID: 30908259 DOI: 10.1109/tmi.2019.2905841] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/13/2023]
Abstract
Chromosome classification is critical for karyotyping in abnormality diagnosis. To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks. The approach consists of one global-scale network (G-Net) and one local-scale network (L-Net). It follows three stages. The first stage is to learn both global and local features. We extract global features and detect finer local regions via the G-Net. By proposing a varifocal mechanism, we zoom into local parts and extract local features via the L-Net. Residual learning and multi-task learning strategies are utilized to promote high-level feature extraction. The detection of discriminative local parts is fulfilled by a localization subnet of the G-Net, whose training process involves both supervised and weakly supervised learning. The second stage is to build two multi-layer perceptron classifiers that exploit features of both two scales to boost classification performance. The third stage is to introduce a dispatch strategy of assigning each chromosome to a type within each patient case, by utilizing the domain knowledge of karyotyping. The evaluation results from 1909 karyotyping cases showed that the proposed Varifocal-Net achieved the highest accuracy per patient case (%) of 99.2 for both type and polarity tasks. It outperformed state-of-the-art methods, demonstrating the effectiveness of our varifocal mechanism, multi-scale feature ensemble, and dispatch strategy. The proposed method has been applied to assist practical karyotype diagnosis.
Collapse
|
3
|
Shirley B, Li Y, Knoll JHM, Rogan PK. Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification (ADCI) and Dose Estimation. J Vis Exp 2017. [PMID: 28892030 PMCID: PMC5619684 DOI: 10.3791/56245] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
Biological radiation dose can be estimated from dicentric chromosome frequencies in metaphase cells. Performing these cytogenetic dicentric chromosome assays is traditionally a manual, labor-intensive process not well suited to handle the volume of samples which may require examination in the wake of a mass casualty event. Automated Dicentric Chromosome Identifier and Dose Estimator (ADCI) software automates this process by examining sets of metaphase images using machine learning-based image processing techniques. The software selects appropriate images for analysis by removing unsuitable images, classifies each object as either a centromere-containing chromosome or non-chromosome, further distinguishes chromosomes as monocentric chromosomes (MCs) or dicentric chromosomes (DCs), determines DC frequency within a sample, and estimates biological radiation dose by comparing sample DC frequency with calibration curves computed using calibration samples. This protocol describes the usage of ADCI software. Typically, both calibration (known dose) and test (unknown dose) sets of metaphase images are imported to perform accurate dose estimation. Optimal images for analysis can be found automatically using preset image filters or can also be filtered through manual inspection. The software processes images within each sample and DC frequencies are computed at different levels of stringency for calling DCs, using a machine learning approach. Linear-quadratic calibration curves are generated based on DC frequencies in calibration samples exposed to known physical doses. Doses of test samples exposed to uncertain radiation levels are estimated from their DC frequencies using these calibration curves. Reports can be generated upon request and provide summary of results of one or more samples, of one or more calibration curves, or of dose estimation.
Collapse
Affiliation(s)
| | | | - Joan H M Knoll
- CytoGnomix Inc.; Department of Pathology and Laboratory Medicine, Western University
| | - Peter K Rogan
- CytoGnomix Inc.; Department of Biochemistry, Western University;
| |
Collapse
|
4
|
Liu J, Li Y, Wilkins R, Flegal F, Knoll JHM, Rogan PK. Accurate cytogenetic biodosimetry through automated dicentric chromosome curation and metaphase cell selection. F1000Res 2017; 6:1396. [PMID: 29026522 PMCID: PMC5583746 DOI: 10.12688/f1000research.12226.1] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 08/07/2017] [Indexed: 12/04/2022] Open
Abstract
Accurate digital image analysis of abnormal microscopic structures relies on high quality images and on minimizing the rates of false positive (FP) and negative objects in images. Cytogenetic biodosimetry detects dicentric chromosomes (DCs) that arise from exposure to ionizing radiation, and determines radiation dose received based on DC frequency. Improvements in automated DC recognition increase the accuracy of dose estimates by reclassifying FP DCs as monocentric chromosomes or chromosome fragments. We also present image segmentation methods to rank high quality digital metaphase images and eliminate suboptimal metaphase cells. A set of chromosome morphology segmentation methods selectively filtered out FP DCs arising primarily from sister chromatid separation, chromosome fragmentation, and cellular debris. This reduced FPs by an average of 55% and was highly specific to these abnormal structures (≥97.7%) in three samples. Additional filters selectively removed images with incomplete, highly overlapped, or missing metaphase cells, or with poor overall chromosome morphologies that increased FP rates. Image selection is optimized and FP DCs are minimized by combining multiple feature based segmentation filters and a novel image sorting procedure based on the known distribution of chromosome lengths. Applying the same image segmentation filtering procedures to both calibration and test samples reduced the average dose estimation error from 0.4 Gy to <0.2 Gy, obviating the need to first manually review these images. This reliable and scalable solution enables batch processing for multiple samples of unknown dose, and meets current requirements for triage radiation biodosimetry of high quality metaphase cell preparations.
Collapse
Affiliation(s)
- Jin Liu
- Department of Biochemistry, Schulich School of Medicine and Dentistry, University of Western Ontario, London, ON, N6A 5C1, Canada
| | - Yanxin Li
- Cytognomix Inc., London, ON, N5X 3X5, Canada
| | - Ruth Wilkins
- Consumer and Clinical Radiation Protection Bureau, Health Canada, Ottawa, ON, K1A 1C1, Canada
| | - Farrah Flegal
- Canadian Nuclear Laboratories Radiobiology & Health, Chalk River, ON, K0J 1J0, Canada
| | - Joan H M Knoll
- Cytognomix Inc., London, ON, N5X 3X5, Canada.,Department of Pathology and Laboratory Medicine, Schulich School of Medicine and Dentistry, University of Western Ontario, London, ON, N6A 5C1, Canada
| | - Peter K Rogan
- Department of Biochemistry, Schulich School of Medicine and Dentistry, University of Western Ontario, London, ON, N6A 5C1, Canada.,Cytognomix Inc., London, ON, N5X 3X5, Canada
| |
Collapse
|
5
|
Prakash S, Chaudhury NK. Dicentric Chromosome Image Classification Using Fourier Domain Based Shape Descriptors and Support Vector Machine. ADVANCES IN INTELLIGENT SYSTEMS AND COMPUTING 2017:221-227. [DOI: 10.1007/978-981-10-2107-7_20] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/19/2023]
|
6
|
Rogan PK, Li Y, Wilkins RC, Flegal FN, Knoll JHM. Radiation Dose Estimation by Automated Cytogenetic Biodosimetry. RADIATION PROTECTION DOSIMETRY 2016; 172:207-217. [PMID: 27412514 DOI: 10.1093/rpd/ncw161] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
The dose from ionizing radiation exposure can be interpolated from a calibration curve fit to the frequency of dicentric chromosomes (DCs) at multiple doses. As DC counts are manually determined, there is an acute need for accurate, fully automated biodosimetry calibration curve generation and analysis of exposed samples. Software, the Automated Dicentric Chromosome Identifier (ADCI), is presented which detects and discriminates DCs from monocentric chromosomes, computes biodosimetry calibration curves and estimates radiation dose. Images of metaphase cells from samples, exposed at 1.4-3.4 Gy, that had been manually scored by two reference laboratories were reanalyzed with ADCI. This resulted in estimated exposures within 0.4-1.1 Gy of the physical dose. Therefore, ADCI can determine radiation dose with accuracies comparable to standard triage biodosimetry. Calibration curves were generated from metaphase images in ~10 h, and dose estimations required ~0.8 h per 500 image sample. Running multiple instances of ADCI may be an effective response to a mass casualty radiation event.
Collapse
Affiliation(s)
- Peter K Rogan
- Department of Biochemistry, Schulich School of Medicine and Dentistry, University of Western Ontario, London, Ontario N6A 5C1, Canada
- Cytognomix Inc., 60 North Centre Rd., Box 27052, London, Ontario N5X 3X5, Canada
| | - Yanxin Li
- Department of Biochemistry, Schulich School of Medicine and Dentistry, University of Western Ontario, London, Ontario N6A 5C1, Canada
| | - Ruth C Wilkins
- Consumer and Clinical Radiation Protection Bureau, Health Canada, 775 Brookfield Rd., K1A 1C1, Ottawa, Ontario, Canada
| | - Farrah N Flegal
- Canadian Nuclear Laboratories, Radiobiology & Health, Plant Road, Chalk River, Ontario, K0J 1J0, Canada
| | - Joan H M Knoll
- Cytognomix Inc., 60 North Centre Rd., Box 27052, London, Ontario N5X 3X5, Canada
- Department of Pathology and Laboratory Medicine, Schulich School of Medicine and Dentistry, University of Western Ontario, London, Ontario N6A 5C1, Canada
| |
Collapse
|
7
|
|
8
|
Li Y, Knoll JH, Wilkins RC, Flegal FN, Rogan PK. Automated discrimination of dicentric and monocentric chromosomes by machine learning-based image processing. Microsc Res Tech 2016; 79:393-402. [PMID: 26929213 DOI: 10.1002/jemt.22642] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2015] [Accepted: 02/06/2016] [Indexed: 11/09/2022]
Abstract
Dose from radiation exposure can be estimated from dicentric chromosome (DC) frequencies in metaphase cells of peripheral blood lymphocytes. We automated DC detection by extracting features in Giemsa-stained metaphase chromosome images and classifying objects by machine learning (ML). DC detection involves (i) intensity thresholded segmentation of metaphase objects, (ii) chromosome separation by watershed transformation and elimination of inseparable chromosome clusters, fragments and staining debris using a morphological decision tree filter, (iii) determination of chromosome width and centreline, (iv) derivation of centromere candidates, and (v) distinction of DCs from monocentric chromosomes (MC) by ML. Centromere candidates are inferred from 14 image features input to a Support Vector Machine (SVM). Sixteen features derived from these candidates are then supplied to a Boosting classifier and a second SVM which determines whether a chromosome is either a DC or MC. The SVM was trained with 292 DCs and 3135 MCs, and then tested with cells exposed to either low (1 Gy) or high (2-4 Gy) radiation dose. Results were then compared with those of 3 experts. True positive rates (TPR) and positive predictive values (PPV) were determined for the tuning parameter, σ. At larger σ, PPV decreases and TPR increases. At high dose, for σ = 1.3, TPR = 0.52 and PPV = 0.83, while at σ = 1.6, the TPR = 0.65 and PPV = 0.72. At low dose and σ = 1.3, TPR = 0.67 and PPV = 0.26. The algorithm differentiates DCs from MCs, overlapped chromosomes and other objects with acceptable accuracy over a wide range of radiation exposures.
Collapse
Affiliation(s)
- Yanxin Li
- Department of Biochemistry, Schulich School of Medicine and Dentistry, University of Western Ontario, London, Ontario N6A 5C1, Canada
| | - Joan H Knoll
- Department of Pathology and Laboratory Medicine, Schulich School of Medicine and Dentistry, University of Western Ontario.,Cytognomix Inc, 60 North Centre Rd., Box 27052, London, Ontario N5X 3X5, Canada
| | - Ruth C Wilkins
- Consumer and Clinical Radiation Protection Bureau, Health Canada, 775 Brookfield Rd., K1A 1C1, Ottawa, Ontario, Canada
| | - Farrah N Flegal
- Biodosimetry Emergency Response Laboratory, Canadian Nuclear Laboratories, 20 Forest Avenue, Deep River, ON K0J 1P0
| | - Peter K Rogan
- Department of Biochemistry, Schulich School of Medicine and Dentistry, University of Western Ontario, London, Ontario N6A 5C1, Canada.,Cytognomix Inc, 60 North Centre Rd., Box 27052, London, Ontario N5X 3X5, Canada
| |
Collapse
|
9
|
Rogan PK, Li Y, Wickramasinghe A, Subasinghe A, Caminsky N, Khan W, Samarabandu J, Wilkins R, Flegal F, Knoll JH. Automating dicentric chromosome detection from cytogenetic biodosimetry data. RADIATION PROTECTION DOSIMETRY 2014; 159:95-104. [PMID: 24757176 PMCID: PMC4067226 DOI: 10.1093/rpd/ncu133] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/07/2023]
Abstract
We present a prototype software system with sufficient capacity and speed to estimate radiation exposures in a mass casualty event by counting dicentric chromosomes (DCs) in metaphase cells from many individuals. Top-ranked metaphase cell images are segmented by classifying and defining chromosomes with an active contour gradient vector field (GVF) and by determining centromere locations along the centreline. The centreline is extracted by discrete curve evolution (DCE) skeleton branch pruning and curve interpolation. Centromere detection minimises the global width and DAPI-staining intensity profiles along the centreline. A second centromere is identified by reapplying this procedure after masking the first. Dicentrics can be identified from features that capture width and intensity profile characteristics as well as local shape features of the object contour at candidate pixel locations. The correct location of the centromere is also refined in chromosomes with sister chromatid separation. The overall algorithm has both high sensitivity (85 %) and specificity (94 %). Results are independent of the shape and structure of chromosomes in different cells, or the laboratory preparation protocol followed. The prototype software was recoded in C++/OpenCV; image processing was accelerated by data and task parallelisation with Message Passaging Interface and Intel Threading Building Blocks and an asynchronous non-blocking I/O strategy. Relative to a serial process, metaphase ranking, GVF and DCE are, respectively, 100 and 300-fold faster on an 8-core desktop and 64-core cluster computers. The software was then ported to a 1024-core supercomputer, which processed 200 metaphase images each from 1025 specimens in 1.4 h.
Collapse
Affiliation(s)
- Peter K Rogan
- University of Western Ontario, 1151 Richmond Street, London, ON, Canada N6A 3K7
| | - Yanxin Li
- University of Western Ontario, 1151 Richmond Street, London, ON, Canada N6A 3K7
| | | | - Akila Subasinghe
- University of Western Ontario, 1151 Richmond Street, London, ON, Canada N6A 3K7
| | - Natasha Caminsky
- University of Western Ontario, 1151 Richmond Street, London, ON, Canada N6A 3K7
| | - Wahab Khan
- University of Western Ontario, 1151 Richmond Street, London, ON, Canada N6A 3K7
| | - Jagath Samarabandu
- University of Western Ontario, 1151 Richmond Street, London, ON, Canada N6A 3K7
| | - Ruth Wilkins
- Health Canada, 775 Brookfield Road, PL 6303B, Ottawa, ON, Canada K1A 1C1
| | - Farrah Flegal
- Atomic Energy of Canada Ltd., STN 51, Bldg 513, Chalk River, ON, Canada K0J 1J0
| | - Joan H Knoll
- University of Western Ontario, 1151 Richmond Street, London, ON, Canada N6A 3K7
| |
Collapse
|