Automatic segmentation of skin cells in multiphoton data using multi-stage merging

Prinke, Philipp; Haueisen, Jens; Klee, Sascha; Rizqie, Muhammad Qurhanul; Supriyanto, Eko; König, Karsten; Breunig, Hans Georg; Piątek, Łukasz

doi:10.1038/s41598-021-93682-y

Cited by 4 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[115][116][117][118][119][120]124) and advances in fast image processing by artificial intelligence (e.g. 83,125), MPT may become a valuable clinical routine method to obtain noninvasively and rapid optical biopsies as well as for researchers in the cosmetic and pharmaceutical industry to evaluate their active components in situ in human subjects under native physiological conditions.…”

Section: Discussionmentioning

confidence: 99%

Review: history of multiphoton tomography

König

2023

Multiphoton Microscopy in the Biomedical Sciences XXIII

Self Cite

View full text Add to dashboard Cite

Two decades ago, the very first prototype of a multiphoton tomograph was built and delivered as a high-resolution skin imaging device to the cosmetic company Beiersdorf AG on November 2, 2001. The tomograph was based on a tunable 80 MHz NIR femtosecond laser system and able to detect two-photon excited autofluorescence intensity and fluorescence lifetime based on time-correlated single photon counting (TCSPC) as well as second harmonic generation (SHG) with 300 nm lateral resolution and 250 ps temporal resolution. Two-photon fluorescence lifetime imaging (FLIM) was performed based in a biexponential decay and false-color coding. The first clinical in vivo study on melanocytic lesions with the DermaInspect started at the Department of Dermatology of the University Jena on September 5, 2003. The study was performed on 53 patients and resulted in optical biopsies based on 2108 optical sections. The tomograph worked under clinical conditions without any problem. Finally, the CE0118 certificate for the multiphoton tomograph DermaInspect as medical device was granted by the European Certified Body Thuringian State Authority of Metrology and Verification (LMET) on December 22, 2004. The DermaInspect became the world’s first femtosecond laser medical device for clinical imaging. The CE0118 certificate for the 2nd generation of multiphoton tomographs, the portable medical device with a tunable titanium:sapphire laser, an optical arm and a 360° measurement head mounted on a mechanical arm, the “MPTflex”, was granted on Nov 8, 2010. The third generation, the multimodal multiphoton tomograph MPTcompact, is based on a chiller-free ultracompact femtosecond fiber laser and miniaturized detectors to measure autofluorescence, SHG, FLIM, and confocal reflectance. The first two MPTcompact prototypes were delivered to hospitals in Heidelberg and Gera in 2018 to realize a multicenter clinical study on the detection of malignant melanoma. JenLab’s multiphoton tomographs have been used to realize the word’s first clinical in vivo two-photon imaging of patients, including (i) the first two-photon fluorescence lifetime imaging, (ii) the first microendoscopy, the first (iii) diseased skin imaging, (iv) brain imaging, and (v) the first CARS studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Review: history of multiphoton tomography

König

2023

Multiphoton Microscopy in the Biomedical Sciences XXIII

Self Cite

View full text Add to dashboard Cite

show abstract

“…The graph-based approaches treat each pixel as a node in a graph 4 , 5 . The clustering-based algorithms group pixels into clusters and iteratively refine them until some convergence criteria are satisfied 4 , 6 .…”

Section: Introductionmentioning

confidence: 99%

Refining skin lesions classification performance using geometric features of superpixels

Moldovanu

Miron

Rusu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

This paper introduces superpixels to enhance the detection of skin lesions and to discriminate between melanoma and nevi without false negatives, in dermoscopy images. An improved Simple Linear Iterative Clustering (iSLIC) superpixels algorithm for image segmentation in digital image processing is proposed. The local graph cut method to identify the region of interest (i.e., either the nevi or melanoma lesions) has been adopted. The iSLIC algorithm is then exploited to segment sSPs. iSLIC discards all the SPs belonging to image background based on assigned labels and preserves the segmented skin lesions. A shape and geometric feature extraction task is performed for each segmented SP. The extracted features are fed into six machine learning algorithms such as: random forest, support vector machines, AdaBoost, k-nearest neighbor, decision trees (DT), Gaussian Naïve Bayes and three neural networks. These include Pattern recognition neural network, Feed forward neural network, and 1D Convolutional Neural Network for classification. The method is evaluated on the 7-Point MED-NODE and PAD-UFES-20 datasets and the results have been compared to the state-of-art findings. Extensive experiments show that the proposed method outperforms the compared existing methods in terms of accuracy.

show abstract

Interactive image segmentation based on multi-layer random forest classifiers

Shan

Liao

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

Automatic segmentation of skin cells in multiphoton data using multi-stage merging

Cited by 4 publications

References 44 publications

Review: history of multiphoton tomography

Review: history of multiphoton tomography

Refining skin lesions classification performance using geometric features of superpixels

Interactive image segmentation based on multi-layer random forest classifiers

Contact Info

Product

Resources

About