Breast cancer was a prevalent form of cancer worldwide. Thermography, a method for diagnosing breast cancer, involves recording the thermal patterns of the breast. This article explores the use of a convolutional neural network (CNN) algorithm to extract features from a dataset of thermographic images. Initially, the CNN network was used to extract a feature vector from the images. Subsequently, machine learning techniques can be used for image classification. This study utilizes four classification methods, namely Fully connected neural network (FCnet), support vector machine (SVM), classification linear model (CLINEAR), and KNN, to classify breast cancer from thermographic images. The accuracy rates achieved by the FCnet, SVM, CLINEAR, and k-nearest neighbors (KNN) algorithms were 94.2%, 95.0%, 95.0%, and 94.1%, respectively. Furthermore, the reliability parameters for these classifiers were computed as 92.1%, 97.5%, 96.5%, and 91.2%, while their respective sensitivities were calculated as 95.5%, 94.1%, 90.4%, and 93.2%. These findings can assist experts in developing an expert system for breast cancer diagnosis.

Cancer is the 3rd leading cause of death globally, and the countries with low-to-middle income account for most cancer cases. The current diagnostic tools, including imaging, molecular detection, and immune histochemistry (IHC), have intrinsic limitations, such as poor accuracy. However, researchers have been working to improve anti-cancer treatment using different drug delivery systems (DDS) to target tumor cells more precisely. Current advances, however, are enough to meet the growing call for more efficient drug delivery systems, but the adverse effects of these systems are a major problem. Nanorobots are typically controlled devices made up of nanometric component assemblies that can interact with and even diffuse the cellular membrane due to their small size, offering a direct channel to the cellular level. The nanorobots improve treatment efficiency by performing advanced biomedical therapies using minimally invasive operations. Chemotherapy’s harsh side effects and untargeted drug distribution necessitate new cancer treatment trials. The nanorobots are currently designed to recognize 12 different types of cancer cells. Nanorobots are an emerging field of nanotechnology with nanoscale dimensions and are predictable to work at an atomic, molecular, and cellular level. Nanorobots to date are under the line of investigation, but some primary molecular models of these medically programmable machines have been tested. This review on nanorobots presents the various aspects allied, i.e., introduction, history, ideal characteristics, approaches in nanorobots, basis for the development, tool kit recognition and retrieval from the body, and application considering diagnosis and treatment.

This review discusses the significant progress made in the development of CNT/GO-based biosensors for disease biomarker detection. It highlights the specific applications of CNT/GO-based biosensors in the detection of various disease biomarkers, including cancer, cardiovascular diseases, infectious diseases, and neurodegenerative disorders. The superior performance of these biosensors, such as their high sensitivity, low detection limits, and real-time monitoring capabilities, makes them highly promising for early disease diagnosis. Moreover, the challenges and future directions in the field of CNT/GO-based biosensors are discussed, focusing on the need for standardization, scalability, and commercialization of these biosensing platforms. In conclusion, CNT/GO-based biosensors have demonstrated immense potential in the field of disease biomarker detection, offering a promising approach towards early diagnosis. Continued research and development in this area hold great promise for advancing personalized medicine and improving patient outcomes.

Instant and accurate evaluation of drug resistance in tumors before and during chemotherapy is important for patients with advanced colon cancer and is beneficial for prolonging their progression-free survival time. Here, the possible biomarkers that reflect the drug resistance of colon cancer were investigated using proton magnetic resonance spectroscopy (1H-MRS) in vivo. SW480[5-fluorouracil(5-FU)-responsive] and SW480/5-FU (5-FU-resistant) xenograft models were generated and subjected to in vivo 1H-MRS examinations when the maximum tumor diameter reached 1–1.5 cm. The areas under the peaks for metabolites, including choline (Cho), lactate (Lac), glutamine/glutamate (Glx), and myo-inositol (Ins)/creatine (Cr) in the tumors, were analyzed between two groups. The resistance-related protein expression, cell morphology, necrosis, apoptosis, and cell survival of these tumor specimens were assessed. The content for tCho, Lac, Glx, and Ins/Cr in the tumors of the SW480 group was significantly lower than that of the SW480/5-FU group (P < 0.05). While there was no significant difference in the degree of necrosis and apoptosis rate of tumor cells between the two groups (P > 0.05), the tumor cells of the SW480/5-FU showed a higher cell density and larger nuclei. The expression levels of resistance-related proteins (P-gp, MPR1, PKC) in the SW480 group were lower than those in the SW480/5-FU group (P < 0.01). The survival rate of 5-FU-resistant colon cancer cells was significantly higher than that of 5-FU-responsive ones at 5-FU concentrations greater than 2.5 μg/mL (P < 0.05). These results suggest that alterations in tCho, Lac, Glx1, Glx2, and Ins/Cr detected by 1H-MRS may be used for monitoring tumor resistance to 5-FU in vivo.