Towards high performance cell segmentation in multispectral fine needle aspiration cytology of thyroid lesions

Gabriel, Edgar; Venkatesan, Vishwanath; Shah, Shishir K.

doi:10.1016/j.cmpb.2009.07.008

Cited by 16 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides being used in combination with quantum dots, spectral image analysis has been used for cytology (68, 69), breast cancer SLN metastases (70) and proliferation and mitosis measurements (71) with promising results.…”

Section: Future Perspectives and Conclusionmentioning

confidence: 99%

Digital image analysis: a review of reproducibility, stability and basic requirements for optimal results

Riber-Hansen

Vainer

Steiniche

2011

APMIS

View full text Add to dashboard Cite

Riber-Hansen R, Vainer B, Steiniche T. Digital image analysis: a review of reproducibility, stability and basic requirements for optimal results. APMIS 2012; 120: 276-89.Digital image analysis (DIA) is increasingly implemented in histopathological research to facilitate truly quantitative measurements, decrease inter-observer variation and reduce hands-on time. Originally, efforts were made to enable DIA to reproduce manually obtained results on histological slides optimized for light microscopy and the human eye. With improved technical methods and the acknowledgement that computerized readings are different from analysis by human eye, recognition has been achieved that to really empower DIA, histological slides must be optimized for the digital 'eye', with reproducible results correlating with clinical findings. In this review, we focus on the basic expectations and requirements for DIA to gain wider use in histopathological research and diagnostics. With a reference to studies that specifically compare DIA with conventional methods, this review discusses reproducibility, application of stereology-based quantitative measurements, time consumption, optimization of histological slides, regions of interest selection and recent developments in staining and imaging techniques. Key words: Image processing; computer-assisted; pathology; immunohistochemistry; reproducibility of results.Rikke Riber-Hansen, Institute of Pathology, Aarhus University Hospital, Noerrebrogade 44, DK-8000 Aarhus C, Denmark. e-mail: rikrib@rm.dk Digital image analysis (DIA) in histopathology is a process of obtaining digitalized images by a microscope connected to a video camera and a frame-grabber or a digital camera, or by whole slide scanning to conduct computer-based analyses to extract meaningful information from the images. In histopathological research, the motivation for implementing DIA has from its invention been to optimize and standardize diagnostic and prognostic processes. The fast development in technology entailed the expectation that DIA would be able to address the intra-and inter-observer variation inherent to manual pathology, to allow truly quantitative measurements to replace semi-quantitative scores and to reduce the workload for the pathologist.For these hopes to come true, some basic requirements have to be met by the DIA process, covering all steps from removal of the tissue of interest to the final assessment. These requirements include optimization and standardization of tissue fixation, sampling and staining as well as image capturing, region of interest (ROI) selection, algorithm design and output.Generally, comparing digital studies performed over a time span of more than 60 years is complicated by the often rapid technological advancement; however, the basic expectations and requirements are unchanged. In this article, we therefore review studies focused on quality

show abstract

Section: Future Perspectives and Conclusionmentioning

confidence: 99%

Digital image analysis: a review of reproducibility, stability and basic requirements for optimal results

Riber-Hansen

Vainer

Steiniche

2011

APMIS

View full text Add to dashboard Cite

show abstract

“…Previous work in multispectral analysis of thyroid FNAs has demonstrated improved accuracy in the classification of images when compared with analysis of standard RGB images 8. Other reports have addressed aspects of full automation feasibility 9. In our laboratory, Mansoor et al developed a machine‐learning algorithm based on spectral images to differentiate between morphologically indistinguishable thyroid follicular adenoma and parathyroid adenoma on FNA cytologic specimens, proving clinical feasibility in this uncommon clinical circumstance in which a parathyroid gland has been sampled via FNA 7.…”

Section: Introductionmentioning

confidence: 98%

“…When combined with the use of spatial‐morphologic relations, spectral information can provide enhanced discriminatory capacity 7, 8. Beyond the potential gains in diagnostic accuracy, this modality also lends itself to standardization through semiautomated or fully automated analysis 7, 9. Furthermore, it may be used in conjunction with conventional Papanicolaou (Pap) staining, avoiding the time‐ or resource‐consuming steps of immunoperoxidase staining for cancer antibodies7 or other molecular tests.…”

Section: Introductionmentioning

confidence: 99%

Spatial spectral imaging as an adjunct to the Bethesda classification of thyroid fine‐needle aspiration specimens

Hahn

Hoyt

Rimm

et al. 2012

Cancer Cytopathology

View full text Add to dashboard Cite

BACKGROUND: Thyroid fine-needle aspiration (FNA) biopsy, the preoperative diagnostic standard of care for patients with thyroid nodules, has limitations. Spectral imaging captures visible light information that is beyond the capability of the human eye, potentially increasing the accuracy of FNA biopsy. In the current study, the authors demonstrated the feasibility of using spectral imaging in combination with automated spatial analysis based on trainable pattern recognition as an adjunct test for thyroid FNA classification by developing an algorithm that distinguishes between images of papillary thyroid carcinoma (PTC) and benign goiter (BG). METHODS: A multispectral camera was used to capture spectral images representing 100 cases of PTC and BG. Used in conjunction with commercial software, 10 cases were used as a training set to develop a ''classifier,'' a classification algorithm that segments digitized multispectral images into regions of PTC, BG, and ''nonfeature.'' This algorithm was used to generate a screening test and a diagnostic test that were validated on

show abstract

“…This application is used to analyze smear sample from fine needle aspiration cytology, with the overall goal being to assist medical doctors in identifying cancer cells [9]. The challenge imposed by this application is due to the high resolution of the microscopes and the fact that images are captured at various wave-length to identify different chemical properties of the cells.…”

Section: An Application Scenariomentioning

confidence: 99%

Design and Evaluation of Nonblocking Collective I/O Operations

Venkatesan

Chaarawi

Gabriel

et al. 2011

Recent Advances in the Message Passing Interface

Self Cite

View full text Add to dashboard Cite

Abstract. Nonblocking operations have successfully been used to hide network latencies in large scale parallel applications. This paper presents the challenges associated with developing nonblocking collective I/O operations, in order to help hiding the costs of I/O operations. We also present an implementation based on the libNBC library, and evaluate the benefits of nonblocking collective I/O over a PVFS2 file system for a micro-benchmark and a parallel image processing application. Our results indicate the potential benefit of our approach, but also highlight the challenges to achieve appropriate overlap between I/O and compute operations.

show abstract

Towards high performance cell segmentation in multispectral fine needle aspiration cytology of thyroid lesions

Cited by 16 publications

References 22 publications

Digital image analysis: a review of reproducibility, stability and basic requirements for optimal results

Digital image analysis: a review of reproducibility, stability and basic requirements for optimal results

Spatial spectral imaging as an adjunct to the Bethesda classification of thyroid fine‐needle aspiration specimens

Design and Evaluation of Nonblocking Collective I/O Operations

Contact Info

Product

Resources

About