Latest Research
All publications from the Cancer3.AI database, newest first.
Deepath-SCC: a deep learning model for accurate tissue origin identification in squamous cell carcinoma.
Lu S, et al
Researchers developed Deepath-SCC, a deep learning model designed to identify the tissue of origin in squamous cell carcinoma (SCC), a cancer type that can arise in multiple organs and is notoriously difficult to distinguish using conventional pathology. The model was trained and validated on over 4,200 whole-slide images from patients with nasopharyngeal, head and neck, esophageal, lung, cervical, and urothelial cancers, using only standard hematoxylin and eosin staining without additional specialized tests. In internal testing, Deepath-SCC achieved 91.2% accuracy and an AUROC of 0.986, rising to 96.2% accuracy when the model's own confidence threshold was applied; external validation confirmed strong performance at 86.1% accuracy and an AUROC of 0.972. The model performed well for both primary and metastatic SCCs, demonstrating its potential utility even in complex clinical scenarios. These findings suggest that AI-based digital pathology tools like Deepath-SCC could complement existing diagnostic workflows, offering a cost-effective solution especially in resource-limited settings where access to advanced immunohistochemical or molecular testing is restricted.
NPJ precision oncology
Source →Immune phenotype and RAS/BRAF status predict outcomes after lung metastasectomy for colorectal cancer.
Martin-Cullell B, et al
Researchers at Hospital de la Santa Creu i Sant Pau in Barcelona conducted a retrospective study of 61 colorectal cancer (CRC) patients who underwent surgical removal of lung metastases between 2011 and 2023, aiming to identify which clinical, molecular, and tissue-based features best predict survival outcomes. The study found that patients whose tumors displayed an immune-desert phenotype — meaning the tumor lacked significant immune cell infiltration — had a dramatically shorter recurrence-free survival of just 4 months compared to 20.4 months in patients with immune-active tumors. Additionally, patients whose tumors carried RAS or BRAF gene mutations experienced earlier lung-specific recurrence, while those diagnosed at earlier CRC stages or with metastases confined solely to the lung enjoyed significantly better overall survival. These findings suggest that combining immune profiling, molecular mutation status, and clinical staging could help clinicians more accurately select which patients are most likely to benefit from lung metastasectomy. The results highlight the need to move beyond one-size-fits-all surgical criteria and toward personalized, biomarker-driven decision-making in the management of oligometastatic colorectal cancer.
Clinical & translational oncology : official publication of the Federation of Spanish Oncology Societies and of the National Cancer Institute of Mexico
Source →Dose-effect relationship of D90 in iodine-125 seed implantation for advanced lung cancer: gradient-based efficacy and survival outcome.
Cao G, et al
This study investigated the dose-effect relationship of D90 — the radiation dose covering 90% of the tumor volume — in patients with advanced lung cancer treated with iodine-125 radioactive seed implantation, a form of internal radiation therapy (brachytherapy). Researchers examined whether higher D90 values were associated with improved tumor control and longer patient survival, aiming to identify optimal dosing thresholds for this minimally invasive procedure. The findings revealed a gradient-based efficacy pattern, meaning that increasing D90 levels corresponded with progressively better local tumor control and improved survival outcomes, with specific dose thresholds distinguishing response groups. These results provide clinicians with actionable dosimetric targets to optimize treatment planning for iodine-125 seed implantation in advanced lung cancer patients who may not be candidates for surgery or conventional radiotherapy. Establishing clear dose-response benchmarks is a meaningful step toward personalizing brachytherapy and improving prognosis in this difficult-to-treat patient population.
BMC cancer
Source →Female-specific risk factors for lung cancer: insights from the All of Us Research Program.
Islam MR, et al
Researchers used data from the All of Us Research Program, a large and diverse U.S. cohort, to investigate risk factors for lung cancer that may be unique or particularly pronounced in women. The study examined a range of biological, hormonal, reproductive, and lifestyle variables to identify which factors most strongly predict lung cancer development in female participants. Findings highlighted several female-specific contributors to lung cancer risk beyond the well-established role of tobacco smoking, suggesting that women may face distinct biological pathways to disease. These results are clinically significant because they underscore the need for sex-stratified screening approaches and risk assessment tools that account for factors relevant to women's health. Ultimately, the research calls for greater attention to female-specific lung cancer risk in public health policy and clinical practice to improve early detection and prevention outcomes.
BMC public health
Source →Low muscle mass in interstitial lung disease: a systematic review and meta-analysis of prevalence and clinical associations.
Alsuhimi O, et al
A new systematic review and meta-analysis published in BMC Pulmonary Medicine examined the prevalence of low muscle mass among patients with interstitial lung disease (ILD), a group of chronic conditions that cause progressive scarring and stiffening of the lungs. The researchers pooled data from multiple studies to determine how commonly ILD patients suffer from reduced skeletal muscle, a condition linked to poorer physical function and worse outcomes. The analysis also investigated clinical associations, exploring how low muscle mass relates to disease severity, exercise capacity, lung function, and survival in this patient population. The findings highlight that muscle wasting is a significant but often overlooked complication in ILD, with potential implications for how these patients are monitored and managed. Clinicians treating ILD patients may benefit from routine assessment of muscle mass as part of comprehensive care, and targeted nutritional or rehabilitation interventions could improve quality of life and outcomes for affected individuals.
BMC pulmonary medicine
Source →