Automating dicentric chromosome detection from cytogenetic biodosimetry data

Rogan, Peter K.; Li, Yanxin; Wickramasinghe, Asanka; Subasinghe, Akila; Caminsky, Natasha; Khan, Wahab; Samarabandu, Jagath; Wilkins, Ruth; Flegal, Farrah; Knoll, Joan H.M.

doi:10.1093/rpd/ncu133

Cited by 29 publications

(40 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used ADCI to carry out this task, which has been demonstrated to provide accurate dose estimates for samples of unknown exposure, based on IAEA compliant triage criteria. ADCI estimates radiation exposures using a fully automated process based on a calibration curve derived from the same biodosimetry laboratory [14][15][16]. The Windows-based Desktop version of ADCI was migrated to the PowerPC operating system of IBM BlueGene/Q (BGQ) as ADCI-HT, which significantly improved the throughput of these analyses.…”

Section: Resultsmentioning

confidence: 99%

“…Full automation of sample preparation, metaphase cell imaging, and interpretations of the DCA could substantially contribute to meeting testing capacity requirements to ensure timely administration of therapies. The Automated Dicentric Chromosome Identifier and Dose Estimator (ADCI) is a medical image processing system that leverages machine learning to analyze metaphase cell samples from different individuals, in the form of images, to identify dicentric chromosomes as an indicator of the patient's level of radiation exposure that would then be used to determine the treatment needed, if any [14][15][16]. The current Windows-based implementation of the system substantially reduces the time required for laboratories to estimate radiation exposures relative to the manual and semiautomated analysis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Cytogenetic Biodosimetry at Population-Scale

Rogan

Ali

et al. 2019

Preprint

View full text Add to dashboard Cite

Introduction. 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 Chromosome (ADCI) software automates unattended DC detection and determines radiation exposures, fulfilling IAEA criteria for triage biodosimetry. We present high performance ADCI (ADCI-HT), with the requisite throughput to stratify exposures of populations in large scale radiation events.Methods. ADCI-HT streamlines dose estimation by optimal scheduling of DC detection, given that the numbers of samples and metaphase cell images in each sample vary. A supercomputer analyzes these data in parallel, with each processor handling a single image at a time. Processor resources are managed hierarchically to maximize a constant stream of sample and image analysis. Metaphase data from populations of individuals with clinically relevant radiation exposures after simulated large nuclear incidents were analyzed. Sample counts were derived from US Census data. Analysis times and exposures were quantified for 15 different scenarios.Results. Processing of metaphase images from 1,744 samples (500 images each) used 16,384 CPUs and was completed in 1hr 11min 23sec, with radiation dose of all samples determined in 32 sec with 1,024 CPUs. Processing of 40,000 samples with varying numbers of metaphase cells, 10 different exposures from 5 different biodosimetry labs met IAEA accuracy criteria (dose estimate differences were < 0.5 Gy; median = 0.07) and was completed in ~25 hours. Population-scale metaphase image datasets within radiation contours of nuclear incidents were defined by exposure levels (either >1 Gy or >2 Gy). The time needed to analyze samples of all individuals receiving exposures from a high yield airborne nuclear device ranged from 0.6-7.4 days, depending on the population density.Conclusion. ADCI-HT delivers timely and accurate dose estimates in a simulated population-scale radiation incident. * This step was omitted from Romm et al. 2013. J. Moquet determined: "system detected 2899 metaphase spreads. It then took 25 mins to look through the gallery and leave 1250 metaphases ready to capture"; ^IAEA criteria for DCA; Bolded text: requires expert review, assuming 8 hr/day, continuously.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automated Cytogenetic Biodosimetry at Population-Scale

Rogan

Ali

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Peer reviewed articles seldom address time needed to transport the sample to the laboratory, in the expected circumstance of compromised infrastructures. Some peer-reviewed evidence exists regarding the requirements for and availability of expertise and facilities for the methods we selected for simulation, including capacity to handle a large scale event (assuming world wide collaboration of laboratories and experts [Ainsbury et al, 2014; Martin et al 2007]) and potential for implementing triage-mode methods (including use of automation, high throughput devices and computer enhanced image processing if available [Repin et al 2014]; Rogan et al 2014]). Few if any take into account the impact on time delays from difficulties in transmitting the results from the laboratory to the decision maker or in relocating victims who are displaced from their homes and unlikely to wait at the triage site for several days.…”

Section: Putting It Altogether: How Well Can Each Biodosimetry Methodmentioning

confidence: 99%

Evaluating the Special Needs of The Military for Radiation Biodosimetry for Tactical Warfare Against Deployed Troops

et al. 2016

View full text Add to dashboard Cite

Objectives The aim of this paper is to delineate characteristics of biodosimetry most suitable for assessing individuals who have potentially been exposed to significant radiation from a nuclear device explosion, when the primary population targeted by the explosion and needing rapid assessment for triage is civilians vs. deployed military personnel. Methods We first carry out a systematic analysis of the requirements for biodosimetry to meet the military's needs to assess deployed troops in a warfare situation, which include accomplishing the military mission. We then systematically compare and contrast the military's special capabilities to respond and carry out biodosimetry for deployed troops in warfare, in contrast to those available to respond and conduct biodosimetry for civilians who have been targeted, e.g., by terrorists. We then compare the effectiveness of different biodosimetry methods to address military vs. civilian needs and capabilities in these scenarios and, using five representative types of biodosimetry with sufficient published data to be useful for the simulations, we estimate the number of individuals who could be assessed by military vs. civilian responders within the timeframe needed for triage decisions. Conclusions Analyses based on these scenarios indicate that, in comparison to responses for a civilian population, a wartime military response for deployed troops has both more complex requirements for and greater capabilities to utilize different types of biodosimetry to evaluate radiation exposure in a very short timeframe after the exposure occurs. Greater complexity for the deployed military is based on factors such as a greater likelihood of partial or whole body exposure, conditions that include exposure to neutrons, and a greater likelihood of combined injury. Our simulations showed, for both the military and civilian response, that a very fast rate of initiating the processing (24,000 per day) is needed to have at least some methods capable of completing the assessment of 50,000 people within a 2 or 6 day timeframe following exposure. This in turn suggests a very high capacity (i.e., laboratories, devices, supplies and expertise) would be necessary to achieve these rates. These simulations also demonstrated the practical importance of the military's superior capacity to minimize time to transport samples to offsite facilities and utilize the results to carry out triage quickly. Assuming sufficient resources and the fastest daily rate to initiate processing victims, the military scenario revealed that two biodosimetry methods could achieve the necessary throughput to triage 50,000 victims in 2 days (i.e., the timeframe needed for injured victims) and all five achieved the targeted throughput within 6 days. In contrast, simulations based on the civilian scenario revealed that no method could process 50,000 people in 2 days and only two could succeed within 6 days.

show abstract

“…During this process, images of cells with incomplete chromosome complements and those with higher densities of overlapping or touching chromosomes were discarded using a content-based classification procedure as described by others 10 . We have also developed Automated Dicentric Chromosome Identifier (ADCI) software which can automatically select individual chromosomes 11 . However, it was not used in this study.…”

Section: Methodsmentioning

confidence: 99%

Centromere detection of human metaphase chromosome images using a candidate based method

Subasinghe

Samarabandu

et al. 2016

F1000Res

View full text Add to dashboard Cite

Accurate detection of the human metaphase chromosome centromere is a critical element of cytogenetic diagnostic techniques, including chromosome enumeration, karyotyping and radiation biodosimetry. Existing centromere detection methods tends to perform poorly in the presence of irregular boundaries, shape variations and premature sister chromatid separation. We present a centromere detection algorithm that uses a novel contour partitioning technique to generate centromere candidates followed by a machine learning approach to select the best candidate that enhances the detection accuracy. The contour partitioning technique evaluates various combinations of salient points along the chromosome boundary using a novel feature set and is able to identify telomere regions as well as detect and correct for sister chromatid separation. This partitioning is used to generate a set of centromere candidates which are then evaluated based on a second set of proposed features. The proposed algorithm outperforms previously published algorithms and is shown to do so with a larger set of chromosome images. A highlight of the proposed algorithm is the ability to rank this set of centromere candidates and create a centromere confidence metric which may be used in post-detection analysis. When tested with a larger metaphase chromosome database consisting of 1400 chromosomes collected from 40 metaphase cell images, the proposed algorithm was able to accurately localize 1220 centromere locations yielding a detection accuracy of 87%.

show abstract

Automating dicentric chromosome detection from cytogenetic biodosimetry data

Cited by 29 publications

References 7 publications

Automated Cytogenetic Biodosimetry at Population-Scale

Automated Cytogenetic Biodosimetry at Population-Scale

Evaluating the Special Needs of The Military for Radiation Biodosimetry for Tactical Warfare Against Deployed Troops

Centromere detection of human metaphase chromosome images using a candidate based method

Contact Info

Product

Resources

About