The fast-growing field of nanotheranostics is revolutionizing cancer treatment by allowing for precise diagnosis and targeted therapy at the cellular and molecular levels. These nanoscale platforms provide considerable benefits in oncology, including improved disease and therapy specificity, lower systemic toxicity, and real-time monitoring of therapeutic outcomes. However, nanoparticles' complicated interactions with biological systems, notably the immune system, present significant obstacles for clinical translation. While certain nanoparticles can elicit favorable anti-tumor immune responses, others cause immunotoxicity, including complement activation-related pseudoallergy (CARPA), cytokine storms, chronic inflammation, and organ damage. Traditional toxicity evaluation approaches are frequently time-consuming, expensive, and insufficient to capture these intricate nanoparticle-biological interactions. Artificial intelligence (AI) and machine learning (ML) have emerged as transformational solutions to these problems. This paper summarizes current achievements in nanotheranostics for cancer, delves into the causes of nanoparticle-induced immunotoxicity, and demonstrates how AI/ML may help anticipate and create safer nanoparticles. Integrating AI/ML with modern computational approaches allows for the detection of potentially dangerous nanoparticle qualities, guides the optimization of physicochemical features, and speeds up the development of immune-compatible nanotheranostics suited to individual patients. The combination of nanotechnology with AI/ML has the potential to completely realize the therapeutic promise of nanotheranostics while assuring patient safety in the age of precision medicine.

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 myoinositol (Ins)/creatine (Cr) in the tumors, were analyzed between two groups. The resistancerelated 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-FUresponsive 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.

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.

Colorectal cancer is the fourth leading cause of death worldwide and the fifth leading cause of cancer death in Colombia. Magnetic resonance imaging is the ideal modality for the evaluation of colorectal cancer, since it allows staging by determining invasion beyond the muscularis propria, extension towards adjacent organs, identification of patients who are candidates for chemotherapy or pre-surgical radiotherapy and planning of the surgical procedure. The key point is based on the differentiation between T2 and T3 stages through the use of sequences with high-resolution T2 information. In addition to this, it allows the assessment of the size and morphology of the lymph nodes, and considerably increases the specificity for the detection of lymph node involvement. MRI is a technique with high specificity and high reproducibility.