Detection of cancer metastasis: past, present and future

Predicting lung cancer's metastats' locations using bioclinical model

Background

Lung cancer is a global leading cause of cancer-related deaths, and metastasis profoundly influences treatment outcomes. The limitations of conventional imaging in detecting small metastases highlight the crucial need for advanced diagnostic approaches.

Methods

This study developed a bioclinical model using three-dimensional CT scans to predict the spatial spread of lung cancer metastasis. Utilizing a three-layer biological model, we identified regions with a high probability of metastasis colonization and validated the model on real-world data from 10 patients.

Findings

The validated bioclinical model demonstrated a promising 74% accuracy in predicting metastasis locations, showcasing the potential of integrating biophysical and machine learning models. These findings underscore the significance of a more comprehensive approach to lung cancer diagnosis and treatment.

Interpretation

This study's integration of biophysical and machine learning models contributes to advancing lung cancer diagnosis and treatment, providing nuanced insights for informed decision-making.

Skin Cancer Detection and Classification Using Neural Network Algorithms: A Systematic Review

In recent years, there has been growing interest in the use of computer-assisted technology for early detection of skin cancer through the analysis of dermatoscopic images. However, the accuracy illustrated behind the state-of-the-art approaches depends on several factors, such as the quality of the images and the interpretation of the results by medical experts. This systematic review aims to critically assess the efficacy and challenges of this research field in order to explain the usability and limitations and highlight potential future lines of work for the scientific and clinical community. In this study, the analysis was carried out over 45 contemporary studies extracted from databases such as Web of Science and Scopus. Several computer vision techniques related to image and video processing for early skin cancer diagnosis were identified. In this context, the focus behind the process included the algorithms employed, result accuracy, and validation metrics. Thus, the results yielded significant advancements in cancer detection using deep learning and machine learning algorithms. Lastly, this review establishes a foundation for future research, highlighting potential contributions and opportunities to improve the effectiveness of skin cancer detection through machine learning.

Targeting lymph node delivery with nanovaccines for cancer immunotherapy: recent advances and future directions

Although cancer immunotherapy is a compelling approach against cancer, its effectiveness is hindered by the challenge of generating a robust and durable immune response against metastatic cancer cells. Nanovaccines, specifically engineered to transport cancer antigens and immune-stimulating agents to the lymph nodes, hold promise in overcoming these limitations and eliciting a potent and sustained immune response against metastatic cancer cells. This manuscript provides an in-depth exploration of the lymphatic system's background, emphasizing its role in immune surveillance and tumor metastasis. Furthermore, it delves into the design principles of nanovaccines and their unique capability to target lymph node metastasis. The primary objective of this review is to provide a comprehensive overview of the current advancements in nanovaccine design for targeting lymph node metastasis, while also discussing their potential to enhance cancer immunotherapy. By summarizing the state-of-the-art in nanovaccine development, this review aims to shed light on the promising prospects of harnessing nanotechnology to potentiate cancer immunotherapy and ultimately improve patient outcomes.

Mechanobiology and survival strategies of circulating tumor cells: a process towards the invasive and metastatic phenotype

Metastatic progression is the deadliest feature of cancer. Cancer cell growth, invasion, intravasation, circulation, arrest/adhesion and extravasation require specific mechanical properties to allow cell survival and the completion of the metastatic cascade. Circulating tumor cells (CTCs) come into contact with the capillary bed during extravasation/intravasation at the beginning of the metastatic cascade. However, CTC mechanobiology and survival strategies in the bloodstream, and specifically in the microcirculation, are not well known. A fraction of CTCs can extravasate and colonize distant areas despite the biomechanical constriction forces that are exerted by the microcirculation and that strongly decrease tumor cell survival. Furthermore, accumulating evidence shows that several CTC adaptations, via molecular factors and interactions with blood components (e.g., immune cells and platelets inside capillaries), may promote metastasis formation. To better understand CTC journey in the microcirculation as part of the metastatic cascade, we reviewed how CTC mechanobiology and interaction with other cell types in the bloodstream help them to survive the harsh conditions in the circulatory system and to metastasize in distant organs.

Non-invasive molecular imaging for precision diagnosis of metastatic lymph nodes: opportunities from preclinical to clinical applications

Lymph node metastasis is an indicator of the invasiveness and aggressiveness of cancer. It is a vital prognostic factor in clinical staging of the disease and therapeutic decision-making. Patients with positive metastatic lymph nodes are likely to develop recurrent disease, distant metastasis, and succumb to death in the coming few years. Lymph node dissection and histological analysis are needed to detect whether regional lymph nodes have been infiltrated by cancer cells and determine the likely outcome of treatment and the patient's chances of survival. However, these procedures are invasive, and tissue biopsies are prone to sampling error. In recent years, advanced molecular imaging with novel imaging probes has provided new technologies that are contributing to comprehensive management of cancer, including non-invasive investigation of lymphatic drainage from tumors, identifying metastatic lymph nodes, and guiding surgeons to operate efficiently in patients with complex lesions. In this review, first, we outline the current status of different molecular imaging modalities applied for lymph node metastasis management. Second, we summarize the multi-functional imaging probes applied with the different imaging modalities as well as applications of cancer lymph node metastasis from preclinical studies to clinical translations. Third, we describe the limitations that must be considered in the field of molecular imaging for improved detection of lymph node metastasis. Finally, we propose future directions for molecular imaging technology that will allow more personalized treatment plans for patients with lymph node metastasis.

Web-Based Skin Cancer Assessment and Classification Using Machine Learning and Mobile Computerized Adaptive Testing in a Rasch Model: Development Study

Background

Web-based computerized adaptive testing (CAT) implementation of the skin cancer (SC) risk scale could substantially reduce participant burden without compromising measurement precision. However, the CAT of SC classification has not been reported in academics thus far.

Objective

We aim to build a CAT-based model using machine learning to develop an app for automatic classification of SC to help patients assess the risk at an early stage.

Methods

We extracted data from a population-based Australian cohort study of SC risk (N=43,794) using the Rasch simulation scheme. All 30 feature items were calibrated using the Rasch partial credit model. A total of 1000 cases following a normal distribution (mean 0, SD 1) based on the item and threshold difficulties were simulated using three techniques of machine learning—naïve Bayes, k-nearest neighbors, and logistic regression—to compare the model accuracy in training and testing data sets with a proportion of 70:30, where the former was used to predict the latter. We calculated the sensitivity, specificity, receiver operating characteristic curve (area under the curve [AUC]), and CIs along with the accuracy and precision across the proposed models for comparison. An app that classifies the SC risk of the respondent was developed.

Results

We observed that the 30-item k-nearest neighbors model yielded higher AUC values of 99% and 91% for the 700 training and 300 testing cases, respectively, than its 2 counterparts using the hold-out validation but had lower AUC values of 85% (95% CI 83%-87%) in the k-fold cross-validation and that an app that predicts SC classification for patients was successfully developed and demonstrated in this study.

Conclusions

The 30-item SC prediction model, combined with the Rasch web-based CAT, is recommended for classifying SC in patients. An app we developed to help patients self-assess SC risk at an early stage is required for application in the future.