Advanced Tumor Imaging Approaches in Human Tumors

Advancing the frontier of artificial intelligence on emerging technologies to redefine cancer diagnosis and care

BACKGROUND

Artificial Intelligence (AI) is capable of revolutionizing cancer therapy and advancing precision oncology via integrating genomics data and digitized health information. AI applications show promise in cancer prediction, prognosis, and treatment planning, particularly in radiomics, deep learning, and machine learning for early cancer diagnosis. However, widespread adoption requires comprehensive data and clinical validation. While AI has demonstrated advantages in treating common malignancies like lung and breast cancers, challenges remain in managing rare tumors due to limited datasets. AI's role in processing multi-omics data and supporting precision oncology decision-making is critical as genetic and health data become increasingly digitized.

METHOD

This review article presents current knowledge on AI and associated technologies, which are being utilized in the diagnosis and therapy of cancer. The applications of AI in radiomics, deep learning, and machine learning for cancer screening and treatment planning are examined. The study also explores the capabilities and limitations of predictive AI in diagnosis and prognosis, as well as generative AI, such as advanced chatbots, in patient and provider interactions.

RESULTS

AI can improve the early diagnosis and treatment of high-incidence cancers like breast and lung cancer. However, its application in rare cancers is limited by insufficient data for training and validation. AI can effectively process large-scale multi-omics data from DNA and RNA sequencing, enhancing precision oncology. Predictive AI aids in risk assessment and prognosis, while generative AI tools improve patient-provider communication. Despite these advancements, further research and technological progress are needed to overcome existing challenges.

CONCLUSIONS

AI holds transformative potential for cancer therapy, particularly in precision oncology, early detection, and personalized treatment planning. However, challenges such as data limitations in rare cancers, the need for clinical validation, and regulatory considerations must be addressed. Future advancements in AI could significantly improve decision-support systems in oncology, ultimately enhancing patient care and quality of life. The review highlights both the opportunities and obstacles in integrating AI into cancer diagnostics and therapeutics, calling for continued research and regulatory oversight.

Targeted High-Resolution 3D Imaging of Tumor Vasculatures at Different Stages Using Far-Red AIE Nanoparticles Compatible with Tissue Clearing

The occurrence and progression of blood vessels plays a pivotal role in different stages of tumor development, while current imaging techniques exhibit limited sensitivity to capture the dynamic changes of vasculature at different tumor stages. This drawback hinders the comprehensive understanding of the tumor microenvironment, thereby impeding the development of efficacious therapeutic strategies. Herein, a high-resolution three-dimensional (3D) imaging technology is developed for mapping and analyzing vasculatures at different tumor stages using HA@TANP, a supramolecular assembly of far-red fluorescence nanoparticles with aggregation-induced emission (AIE), compatible with tissue clearing. The hyaluronic acid (HA) in HA@TANP specifically targets CD44 antigen of tumor vasculature, while the acrylic acid in HA@TANP is applied for temperature-induced polymerization to ensure the covalent attachment of AIE fluorophores. Additionally, tissue optical clearing technology boosts light penetration and imaging resolution in dense tumor tissues. This strategy allows for the quantitative analyses of vascular diameter, length, and straightness and their correlation with various responses to treatments. The findings contribute to a more comprehensive understanding of distinct tumor vascular stages, providing valuable insights for enhanced cancer diagnosis and therapies from a tumor vascular-targeted perspective.

Locoregional drug delivery for cancer therapy: Preclinical progress and clinical translation

Systemic drug delivery is the current clinically preferred route for cancer therapy. However, challenges associated with tumor localization and off-tumor toxic effects limit the clinical effectiveness of this route. Locoregional drug delivery is an emerging viable alternative to systemic therapies. With the improvement in real-time imaging technologies and tools for direct access to tumor lesions, the clinical applicability of locoregional drug delivery is becoming more prominent. Theoretically, locoregional treatments can bypass challenges faced by systemic drug delivery. Preclinically, locoregional delivery of drugs has demonstrated enhanced therapeutic efficacy with limited off-target effects while still yielding an abscopal effect. Clinically, an array of locoregional strategies is under investigation for the delivery of drugs ranging in target and size. Locoregional tumor treatment strategies can be classified into two main categories: 1) direct drug infusion via injection or implanted port and 2) extended drug elution via injected or implanted depot. The number of studies investigating locoregional drug delivery strategies for cancer treatment is rising exponentially, in both preclinical and clinical settings, with some approaches approved for clinical use. Here, we highlight key preclinical advances and the clinical relevance of such locoregional delivery strategies in the treatment of cancer. Furthermore, we critically analyze 949 clinical trials involving locoregional drug delivery and discuss emerging trends.

Role of in vivo imaging in Head and Neck cancer management

Intravital microscopy (IVM) and optical coherency tomography (OCT) are powerful optical imaging tools that allow visualization of dynamic biological activities in living subjects with subcellular resolutions. They have been used in preclinical and clinical cancer imaging, providing insights into the complex physiological, cellular, and molecular behaviors of tumors. They have revolutionized cancer diagnosis and therapies, allowing for real-time observation of biologic processes in vivo, including angiogenesis and immune cell interactions. Recent developments in techniques for observing deep tissues of living animals have improved bioluminescent proteins, fluorescent proteins, fluorescent dyes, and detection technologies like two-photon excitation microscopy. These technologies have become indispensable tools in basic sciences, preclinical research, and modern drug development. In Vivo imaging can detect subcellular signaling or metabolic events in living animals, but depth-dependent signal attenuation limits the depth from which significant data can be obtained. Cancer cell motility and invasion are key features of metastatic tumors, but only a small portion of tumor cells are motile and metastasize due to genetic, epigenetic, and microenvironmental heterogeneities.

Recent Advances in Imaging Agents Anchored with pH (Low) Insertion Peptides for Cancer Theranostics

The acidic extracellular microenvironment has become an effective target for diagnosing and treating tumors. A pH (low) insertion peptide (pHLIP) is a kind of peptide that can spontaneously fold into a transmembrane helix in an acidic microenvironment, and then insert into and cross the cell membrane for material transfer. The characteristics of the acidic tumor microenvironment provide a new method for pH-targeted molecular imaging and tumor-targeted therapy. As research has increased, the role of pHLIP as an imaging agent carrier in the field of tumor theranostics has become increasingly prominent. In this paper, we describe the current applications of pHLIP-anchored imaging agents for tumor diagnosis and treatment in terms of different molecular imaging methods, including magnetic resonance T1 imaging, magnetic resonance T2 imaging, SPECT/PET, fluorescence imaging, and photoacoustic imaging. Additionally, we discuss relevant challenges and future development prospects.

Skin Cancer Pathobiology at a Glance: A Focus on Imaging Techniques and Their Potential for Improved Diagnosis and Surveillance in Clinical Cohorts

Early diagnosis is essential for completely eradicating skin cancer and maximizing patients' clinical benefits. Emerging optical imaging modalities such as reflectance confocal microscopy (RCM), optical coherence tomography (OCT), magnetic resonance imaging (MRI), near-infrared (NIR) bioimaging, positron emission tomography (PET), and their combinations provide non-invasive imaging data that may help in the early detection of cutaneous tumors and surgical planning. Hence, they seem appropriate for observing dynamic processes such as blood flow, immune cell activation, and tumor energy metabolism, which may be relevant for disease evolution. This review discusses the latest technological and methodological advances in imaging techniques that may be applied for skin cancer detection and monitoring. In the first instance, we will describe the principle and prospective clinical applications of the most commonly used imaging techniques, highlighting the challenges and opportunities of their implementation in the clinical setting. We will also highlight how imaging techniques may complement the molecular and histological approaches in sharpening the non-invasive skin characterization, laying the ground for more personalized approaches in skin cancer patients.

Human intravital microscopy in the study of sarcomas: an early trial of feasibility

Sarcomas comprise a vast and heterogenous group of rare tumors. Because of their diversity, it is challenging to study sarcomas as a whole with regard to their biological and molecular characteristics. This diverse set of tumors may also possess differences related to their tumor-associated vasculature, which in turn may impact the ability to deliver systemic therapies (e.g., chemotherapy, targeted therapies, and immunotherapy). Consequently, response to systemic treatment may also be variable as these depend on the ability of the therapy to reach the tumor target via the tumor-associated vasculature. There is a paucity of data regarding sarcoma-related tumor vessels, likely in part to the rarity and heterogeneity of this cancer as well as the previously limited ability to image tumor-associated vessels in real time. Our group has previously utilized confocal fluorescent imaging technology to observe and characterize tumor-associated vessels in real time during surgical resection of tumors, including cutaneous melanoma and carcinomatosis implants derived from gastrointestinal, gynecological, or primary peritoneal (e.g., mesothelioma) tumors. Our prior studies have demonstrated the feasibility of real-time, human intravital microscopy in the study of these tumor types, leading to early but important new data regarding tumor vessel characteristics and their potential implications on drug delivery and efficacy. In this brief report, we present our latest descriptive findings in a cohort of patients with sarcoma who underwent surgical resection and real-time, intravital microscopy of their tumors. Overall, intravital imaging was feasible during the surgical resection of large sarcomas.

Clinical trial registrations

ClinicalTrials.gov, identifier NCT03517852; ClinicalTrials.gov, identifier NCT03823144.