Artificial intelligence and emerging data science techniques are being leveraged to interpret medical image scans. Traditional image analysis relies on visual interpretation by a trained radiologist, which is time-consuming and can, to some degree, be subjective. The development of reliable, automated diagnostic tools is a key goal of radiomics, a fast-growing research field which combines medical imaging with personalized medicine. Radiomic studies have demonstrated potential for accurate lung cancer diagnoses and prognostications. The practice of delineating the tumor region of interest, known as segmentation, is a key bottleneck in the development of generalized classification models. In this study, the incremental multiple resolution residual network (iMRRN), a publicly available and trained deep learning segmentation model, was applied to automatically segment CT images collected from 355 lung cancer patients included in the dataset “Lung-PET-CT-Dx”, obtained from The Cancer Imaging Archive (TCIA), an open-access source for radiological images. We report a failure rate of 4.35% when using the iMRRN to segment tumor lesions within plain CT images in the lung cancer CT dataset. Seven classification algorithms were trained on the extracted radiomic features and tested for their ability to classify different lung cancer subtypes. Over-sampling was used to handle unbalanced data. Chi-square tests revealed the higher order texture features to be the most predictive when classifying lung cancers by subtype. The support vector machine showed the highest accuracy, 92.7% (0.97 AUC), when classifying three histological subtypes of lung cancer: adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. The results demonstrate the potential of AI-based computer-aided diagnostic tools to automatically diagnose subtypes of lung cancer by coupling deep learning image segmentation with supervised classification. Our study demonstrated the integrated application of existing AI techniques in the non-invasive and effective diagnosis of lung cancer subtypes, and also shed light on several practical issues concerning the application of AI in biomedicine.

Fluorescence and photoacoustic imaging techniques offer valuable insights into cell- and tissue-level processes. However, these optical imaging modalities are limited by scattering and absorption in tissue, resulting in the low-depth penetration of imaging. Contrast-enhanced imaging in the near-infrared window improves imaging penetration by taking advantage of reduced autofluorescence and scattering effects. Current contrast agents for fluorescence and photoacoustic imaging face several limitations from photostability and targeting specificity, highlighting the need for a novel imaging probe development. This review covers a broad range of near-infrared fluorescent and photoacoustic contrast agents, including organic dyes, polymers, and metallic nanostructures, focusing on their optical properties and applications in cellular and animal imaging. Similarly, we explore encapsulation and functionalization technologies toward building targeted, nanoscale imaging probes. Bioimaging applications such as angiography, tumor imaging, and the tracking of specific cell types are discussed. This review sheds light on recent advancements in fluorescent and photoacoustic nanoprobes in the near-infrared window. It serves as a valuable resource for researchers working in fields of biomedical imaging and nanotechnology, facilitating the development of innovative nanoprobes for improved diagnostic approaches in preclinical healthcare.

Significance: Abnormalities in potassium ion concentrations across subregions of the hippocampus have been implicated in seizures and other pathologies. Direct measurements of potassium ion concentrations are largely made using invasive electrodes, which do not allow for wide spatial coverage. This fluorescent nanoparticle potassium sensor enables direct visualization of potassium dynamics and represents a minimally invasive alternative to electrode based methods. Aim: Here, we present a DNA-based fluorescence nanoprobe capable of sensing relative concentrations of potassium ions within populations of neurons. We present its effectiveness in monitoring neuronal K+ dynamics in response to electrical stimulation ex vivo. Approach: We used widefield fluorescence microscopy to monitor changes in fluorescence intensity in labeled brain tissue in response to electrical stimulation ex vivo. Results: We found that our nanoprobe could be retained within the intracellular compartment and modulate in fluorescence intensity linearly in response to induced electrical current. Our K⁺ Sensor showed a fractional fluorescence change of approximately 1% per 10 mA of applied stimulation current in brain tissue. Optical spectroscopy confirmed the selectivity of the nanoprobes to potassium ions over other endogenous ions. Conclusions: Our findings indicate that this nanoprobe can be used to detect more complex potassium dynamics implicated in various pathologies of the nervous system, such as migraines, seizures, and trauma.