Automated frame selection process for high-resolution microendoscopy

Ishijima, Ayumu; Schwarz, Richard A.; Shin, Dongsuk; Mondrik, Sharon; Vigneswaran, Nadarajah; Gillenwater, Ann M.; Anandasabapathy, Sharmila; Richards‐Kortum, Rebecca

doi:10.1117/1.jbo.20.4.046014

Cited by 18 publications

(15 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HRME videos were reviewed from each site to select a single, representative image for each imaging site. A single frame was first selected from every movie acquired using an automated frame selection algorithm described by Ishijima et al (40). Single frames were then reviewed together at each corresponding imaging site.…”

Section: Methodsmentioning

confidence: 99%

Prospective Evaluation of Multimodal Optical Imaging with Automated Image Analysis to Detect Oral Neoplasia In Vivo

Quang

Tran

Schwarz

et al. 2017

Cancer Prevention Research

Self Cite

View full text Add to dashboard Cite

The five-year survival rate for patients with oral cancer remains low, in part because diagnosis often occurs at a late stage. Early and accurate identification of oral high-grade dysplasia and cancer can help improve patient outcomes. Multi-modal optical imaging is an adjunctive diagnostic technique in which autofluorescence imaging is used to identify high-risk regions within the oral cavity, followed by high resolution microendoscopy to confirm or rule out the presence of neoplasia. Multi-modal optical images were obtained from 206 sites in 100 patients. Histologic diagnosis, either from a punch biopsy or an excised surgical specimen, was used as the gold standard for all sites. Histopathologic diagnoses of moderate dysplasia or worse were considered neoplastic. Images from 92 sites in the first 30 patients were used as a training set to develop automated image analysis methods for identification of neoplasia. Diagnostic performance was evaluated prospectively using images from 114 sites in the remaining 70 patients as a test set. In the training set, multi-modal optical imaging with automated image analysis correctly classified 95% of non-neoplastic sites and 94% of neoplastic sites. Among the 56 sites in the test set that were biopsied, multi-modal optical imaging correctly classified 100% of non-neoplastic sites and 85% of neoplastic sites. Among the 58 sites in the test set that corresponded to a surgical specimen, multi-modal imaging correctly classified 100% of non-neoplastic sites and 61% of neoplastic sites. These findings support the potential of multi-modal optical imaging to aid in the early detection of oral cancer.

show abstract

Section: Methodsmentioning

confidence: 99%

Prospective Evaluation of Multimodal Optical Imaging with Automated Image Analysis to Detect Oral Neoplasia In Vivo

Quang

Tran

Schwarz

et al. 2017

Cancer Prevention Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Improvements in image contrast enable improved recognition of nuclear morphometry, particularly in areas of precancer and cancer. Although visually compelling, the improved nuclear recognition could also improve automated algorithms designed to identify neoplasia in real time that would otherwise struggle in highly scattering tissue (14,32,33). Additionally, because DSIMe maintains the small size of the probe, this technique could be used to improve high resolution microendoscopy imaging in a wider array of tissues.…”

Section: Discussionmentioning

confidence: 99%

Differential structured illumination microendoscopy for in vivo imaging of molecular contrast agents

Keahey

Ramalingam

Schmeler

et al. 2016

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Fiber optic microendoscopy has shown promise for visualization of molecular contrast agents used to study disease in vivo. However, fiber optic microendoscopes have limited optical sectioning capability, and image contrast is limited by out-of-focus light generated in highly scattering tissue. Optical sectioning techniques have been used in microendoscopes to remove out-of-focus light but reduce imaging speed or rely on bulky optical elements that prevent in vivo imaging. Here, we present differential structured illumination microendoscopy (DSIMe), a fiber optic system that can perform structured illumination in real time for optical sectioning without any opto-mechanical components attached to the distal tip of the fiber bundle. We demonstrate the use of DSIMe during in vivo fluorescence imaging in patients undergoing surgery for cervical adenocarcinoma in situ. Images acquired using DSIMe show greater contrast than standard microendoscopy, improving the ability to detect cellular atypia associated with neoplasia.

show abstract

“…This technique has almost identical possibility with cytology and invasive biopsy procedures. The HRME technique therefore has a promising development in the future [36,40].…”

Section: Early Diagnosis Of Precancerous and Oral Cancer Lesion Technmentioning

confidence: 99%

Early Detection and Multidisciplinary Approach to Oral Cancer Patients

Akbulut¹,

Altan²

2019

Prevention, Detection and Management of Oral Cancer

View full text Add to dashboard Cite

"Oral cancer" is a term usually describing oral cavity and oropharyngeal malign tumors. The most histologic type of carcinoma is squamous cell carcinoma, seen in oral and oropharyngeal region with the incidence of 90%. Prevention or early diagnosis of premalignant and oral cancer requires increased public awareness and educating practitioners to be skillful in identifying oropharyngeal region pathology. To prevent oral cancers, the etiological factors should be known, and measures must be taken according to those factors. Premalignant lesions are leukoplakia, lichen planus in oral and cutaneous form, erythroplakia, stomatitis nicotina, and submucous fibrosis. Premalignant lesions should be treated, if possible, or followed up on carefully. To date, there are many clinical, histopathological, radiological, and optical techniques to diagnose or capture precancerous and oral cancer lesions early. The routine management of oral cancers is firstly surgical resection with or without postoperative adjuncts and other therapies such as the use of postoperative chemoradiation and radiation. Successful treatment of oral cancer patients is a complex issue that requires a multidisciplinary approach, including oral and maxillofacial surgeons, oral and maxillofacial radiologists, ENT specialists, medical and radiological oncologists, prosthodontists, dentists, speech therapists, supportive care experts, and also pathologists or, if possible, oral and maxillofacial pathologists.

show abstract

Automated frame selection process for high-resolution microendoscopy

Cited by 18 publications

References 28 publications

Prospective Evaluation of Multimodal Optical Imaging with Automated Image Analysis to Detect Oral Neoplasia In Vivo

Prospective Evaluation of Multimodal Optical Imaging with Automated Image Analysis to Detect Oral Neoplasia In Vivo

Differential structured illumination microendoscopy for in vivo imaging of molecular contrast agents

Early Detection and Multidisciplinary Approach to Oral Cancer Patients

Contact Info

Product

Resources

About