Dual-Centre Harmonised Multimodal Positron Emission Tomography/Computed Tomography Image Radiomic Features and Machine Learning Algorithms for Non-small Cell Lung Cancer Histopathological Subtype Phenotype Decoding.

AIMS: We aimed to build radiomic models for classifying non-small cell lung cancer (NSCLC) histopathological subtypes through a dual-centre dataset and comprehensively evaluate the effect of ComBat harmonisation on the performance of single- and multimodality radiomic models. MATERIALS AND METHODS: A public dataset of NSCLC patients from two independent centres was used. Two image fusion methods, namely guided filtering-based fusion and image fusion based on visual saliency map and weighted least square optimisation, were used. Radiomic features were extracted from each scan, including first-order, texture and moment-invariant features. Subsequently, ComBat harmonisation was applied to the extracted features from computed tomography (CT), positron emission tomography (PET) and fused images to correct the centre effect. For feature selection, least absolute shrinkage and selection operator (Lasso) and recursive feature elimination (RFE) were investigated. For machine learning, logistic regression (LR), support vector machine (SVM) and AdaBoost were evaluated for classifying NSCLC subtypes. Training and evaluation of the models were carried out in a robust framework to offset plausible errors and performance was reported using area under the curve, balanced accuracy, sensitivity and specificity before and after harmonisation. N-way ANOVA was used to assess the effect of different factors on the performance of the models. RESULTS: Support vector machine fed with selected features by recursive feature elimination from a harmonised PET feature set achieved the highest performance (area under the curve = 0.82) in classifying NSCLC histopathological subtypes. Although the performance of the models did not significantly improve for CT images after harmonisation, the performance of PET and guided filtering-based fusion feature signatures significantly improved for almost all models. Although the selection of the image modality and feature selection methods was effective on the performance of the model (ANOVA P-values <0.001), machine learning and harmonisation did not change the performance significantly (ANOVA P-values = 0.839 and 0.292, respectively). CONCLUSION: This study confirmed the potential of radiomic analysis on PET, CT and hybrid images for histopathological classification of NSCLC subtypes.

Discrimination of normal and cancerous human skin tissues based on laser-induced spectral shift fluorescence microscopy.

A homemade spectral shift fluorescence microscope (SSFM) is coupled with a spectrometer to record the spectral images of specimens based on the emission wavelength. Here a reliable diagnosis of neoplasia is achieved according to the spectral fluorescence properties of ex-vivo skin tissues after rhodamine6G (Rd6G) staining. It is shown that certain spectral shifts occur for nonmelanoma/melanoma lesions against normal/benign nevus, leading to spectral micrographs. In fact, there is a strong correlation between the emission wavelength and the sort of skin lesions, mainly due to the Rd6G interaction with the mitochondria of cancerous cells. The normal tissues generally enjoy a significant red shift regarding the laser line (37 nm). Conversely, plenty of fluorophores are conjugated to unhealthy cells giving rise to a relative blue shift i.e., typically SCC (6 nm), BCC (14 nm), and melanoma (19 nm) against healthy tissues. In other words, the redshift takes place with respect to the excitation wavelength i.e., melanoma (18 nm), BCC (23 nm), and SCC (31 nm) with respect to the laser line. Consequently, three data sets are available in the form of micrographs, addressing pixel-by-pixel signal intensity, emission wavelength, and fluorophore concentration of specimens for prompt diagnosis.