Technology Innovation

Recent study evaluated the AI deep-learning model Mirai for predicting interval breast cancers (ICs)—cancers that appear between scheduled mammogram screenings—in a screening program for women aged 50–70. The study analyzed 134,217 negative screening mammograms, including 524 ICs. Mirai’s 3-year risk scores were significantly higher in women who later developed ICs, with an overall C index […]

A new machine learning model has been developed to predict the risk of secondary cancers in patients who have undergone radiation therapy. These secondary cancers can appear years later due to the effects of ionizing radiation. The model, a Random Forest Regressor, uses data from clinical, pathology, and genomic sources—such as cancer type, age, radiation

Skin cancer includes melanoma (MSC) and non-melanoma types (NMSC) such as basal cell carcinoma (BCC) and squamous cell carcinoma (SCC). Melanoma is less common but more deadly, with about 324,000 new cases and 57,000 deaths annually. NMSCs are far more common, especially BCC, though SCC causes most related deaths. Conventional treatments like surgery, radiation, chemotherapy,

Colorectal cancer (CRC) is rising worldwide, particularly early-onset cases, creating an urgent need for earlier detection to improve survival. Traditional screening methods have limitations: colonoscopy is invasive and resource-intensive, while stool-based tests like FIT often miss early-stage cancers. CRC arises from adenomas through cumulative mutations (e.g., APC, KRAS, TP53) and exhibits molecular heterogeneity, classified into

Scientists have developed a breakthrough method for engineering CAR-NK (natural killer) cells—an advanced, immune-based cancer therapy. This innovation, from MIT and Harvard Medical School, overcomes the critical limitation of cell-based therapies: immune rejection of donor cells. The key is a single-step genetic construct that modifies donor NK cells to both express the cancer-targeting Chimeric Antigen Receptor (CAR) and silence

Cancer of unknown primary (CUP) accounts for 2%–5% of new cancer diagnoses and is defined by the presence of metastatic disease without an identifiable primary tumor despite extensive investigation. Due to its complexity and heterogeneity, CUP carries a poor prognosis, contributing to around 8% of all cancer-related deaths, with only 16%–20% of patients surviving beyond

Breast cancer incidence is rising globally, making it the leading cause of cancer death in women. Conventional imaging—mammography, ultrasound, and MRI—remains essential but limited: mammography performs poorly in dense breasts, ultrasound is operator-dependent with low specificity, and MRI is costly, slow, and unsuitable for real-time monitoring. This highlights the need for a fast, safe, and

Gastric cancer peritoneal metastasis (PM) is driven by a protective tumor microenvironment (TME), with cancer-associated fibroblasts (CAFs) contributing to therapy resistance via high GPX4 levels that prevent ferroptosis. To overcome this barrier, researchers developed a multifunctional theranostic nanoplatform, CDDP2@MSPION@GP3/FAPI. This system combines iron oxide nanoparticles (MSPION) that release Fe²⁺/Fe³⁺ in the acidic TME to trigger

AI is revolutionizing gynecologic cancer care (cervical, ovarian, endometrial) by improving early detection, diagnosis, and treatment planning. Machine learning (ML) and deep learning (DL) enhance screening accuracy, automate workflows, and integrate complex clinical data, addressing gaps in traditional methods and increasing efficiency in EHR management and clinical trial enrollment. In screening, AI enables automated Pap

Ionizing radiation from medical imaging, particularly CT scans, is a major source of radiation exposure for children in the U.S. and a known carcinogen linked to hematologic malignancies (blood cancers). The large RIC cohort study (3.7 million children in the U.S. and Canada) found a significant dose-response relationship between cumulative bone marrow radiation dose and cancer risk. A