Staging of Skin Cancer Based on Hyperspectral Microscopic Imaging and Machine Learning

Liu, Lixin; Qi, Meijie; Li, Yanru; Liu, Yujie; Liu, Xing; Zhang, Zhoufeng; Qu, Junle

doi:10.3390/bios12100790

Cited by 16 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Sun collected 880 scenes of multidimensional hyperspectral cholangiocarcinoma images and realized further diagnose based on the features from patch prediction [38]. Liu found that the spectral data of nuclear compartments contribute more to the accurate staging of squamous cell carcinoma compared with peripheral regions [39]. In order to have a clearer understanding of this diagnostic process, we calculated the probability of each pixel being classified as gastric cancer based on the spectral-spatial joint diagnosis results, as shown in Figure 11d.…”

Section: Discussionmentioning

confidence: 99%

Joint Diagnostic Method of Tumor Tissue Based on Hyperspectral Spectral-Spatial Transfer Features

Tao

Xue

et al. 2023

Diagnostics

Self Cite

View full text Add to dashboard Cite

In order to improve the clinical application of hyperspectral technology in the pathological diagnosis of tumor tissue, a joint diagnostic method based on spectral-spatial transfer features was established by simulating the actual clinical diagnosis process and combining micro-hyperspectral imaging with large-scale pathological data. In view of the limited sample volume of medical hyperspectral data, a multi-data transfer model pre-trained on conventional pathology datasets was applied to the classification task of micro-hyperspectral images, to explore the differences in spectral-spatial transfer features in the wavelength of 410–900 nm between tumor tissues and normal tissues. The experimental results show that the spectral-spatial transfer convolutional neural network (SST-CNN) achieved a classification accuracy of 95.46% for the gastric cancer dataset and 95.89% for the thyroid cancer dataset, thus outperforming models trained on single conventional digital pathology and single hyperspectral data. The joint diagnostic method established based on SST-CNN can complete the interpretation of a section of data in 3 min, thus providing a new technical solution for the rapid diagnosis of pathology. This study also explored problems involving the correlation between tumor tissues and typical spectral-spatial features, as well as the efficient transformation of conventional pathological and transfer spectral-spatial features, which solidified the theoretical research on hyperspectral pathological diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

Joint Diagnostic Method of Tumor Tissue Based on Hyperspectral Spectral-Spatial Transfer Features

Tao

Xue

et al. 2023

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The sensitivity and specificity for the differential diagnosis of benign and malignant pigmentary skin lesions were 87.5% and 100%, respectively. Liu et al 10 combined HMI with machine learning methods for staging identification of squamous cell carcinoma (SCC) based on hyperspectral data and obtained the highest staging accuracy of 0.952±0.014, and a KAPPA value of 0.928±0.022.…”

Section: Introductionmentioning

confidence: 99%

Classification of skin cancer based on hyperspectral microscopic imaging and machine learning

Liu

et al. 2023

SPIE-CLP Conference on Advanced Photonics 2022

Self Cite

View full text Add to dashboard Cite

Hyperspectral microscopic imaging (HMI) technology is a non-contact optical diagnostic method, which combines hyperspectral imaging (HSI) technology with microscopy to provide both spectral information and image information of the samples to be measured. In this paper, basal cell carcinoma (BCC), squamous cell carcinoma (SCC) and malignant melanoma (MM) were classified based on synthetic RGB image data from HMI cube by using four classification methods extreme learning machine (ELM), support vector machine (SVM), decision tree and random forest (RF). The highest classification accuracy of 0.791±0.060 and a KAPPA value of 0.685±0.095 were obtained when color moment, gray level co-occurrence matrix (GLCM) and local binary pattern (LBP) were used for image feature extraction, feature dimensions were reduced by the PLS, the sample sets were divided by the hold-out method, and the tissues were classified by the SVM model.

show abstract

“…In several research areas, HSI has shown its great potential to discriminate between several tissue structures by analyzing the tissue–light interactions, measured as specific spectral signatures, allowing tissue perfusion assessment [ 8 , 9 ] and tissue differentiation [ 10 , 11 ]. HSI has been successfully evaluated to detect skin cancer [ 12 , 13 , 14 ], gastric cancer [ 15 ], oral cancer [ 16 ], breast cancer [ 17 ], brain cancer [ 18 , 19 , 20 , 21 , 22 ], head and neck cancer [ 23 ], as well as colorectal cancer [ 24 ] in humans. In these previous works, approaches such as support vector machines (SVMs), random forest (RF), and logistic regression (LR) as well as deep learning networks were used to analyze the hyperspectral (HS) image data.…”

Section: Introductionmentioning

confidence: 99%

Impact of Pre- and Post-Processing Steps for Supervised Classification of Colorectal Cancer in Hyperspectral Images

Tkachenko

Chalopin

Jansen-Winkeln

et al. 2023

Cancers

View full text Add to dashboard Cite

Background: Recent studies have shown that hyperspectral imaging (HSI) combined with neural networks can detect colorectal cancer. Usually, different pre-processing techniques (e.g., wavelength selection and scaling, smoothing, denoising) are analyzed in detail to achieve a well-trained network. The impact of post-processing was studied less. Methods: We tested the following methods: (1) Two pre-processing techniques (Standardization and Normalization), with (2) Two 3D-CNN models: Inception-based and RemoteSensing (RS)-based, with (3) Two post-processing algorithms based on median filter: one applies a median filter to a raw predictions map, the other applies the filter to the predictions map after adopting a discrimination threshold. These approaches were evaluated on a dataset that contains ex vivo hyperspectral (HS) colorectal cancer records of 56 patients. Results: (1) Inception-based models perform better than RS-based, with the best results being 92% sensitivity and 94% specificity; (2) Inception-based models perform better with Normalization, RS-based with Standardization; (3) Our outcomes show that the post-processing step improves sensitivity and specificity by 6.6% in total. It was also found that both post-processing algorithms have the same effect, and this behavior was explained. Conclusion: HSI combined with tissue classification algorithms is a promising diagnostic approach whose performance can be additionally improved by the application of the right combination of pre- and post-processing.

show abstract

Staging of Skin Cancer Based on Hyperspectral Microscopic Imaging and Machine Learning

Cited by 16 publications

References 17 publications

Joint Diagnostic Method of Tumor Tissue Based on Hyperspectral Spectral-Spatial Transfer Features

Joint Diagnostic Method of Tumor Tissue Based on Hyperspectral Spectral-Spatial Transfer Features

Classification of skin cancer based on hyperspectral microscopic imaging and machine learning

Impact of Pre- and Post-Processing Steps for Supervised Classification of Colorectal Cancer in Hyperspectral Images

Contact Info

Product

Resources

About