Using Artificial Intelligence as a Melanoma Screening Tool in Self-Referred Patients.

INTRODUCTION: Early detection of melanoma requires timely access to medical care. In this study, we examined the feasibility of using artificial intelligence (AI) to flag possible melanomas in self-referred patients concerned that a skin lesion might be cancerous. METHODS: Patients were recruited for the study through advertisements in 2 hospitals in Halifax, Nova Scotia, Canada. Lesions of concern were initially examined by a trained medical student and if the study criteria were met, the lesions were then scanned using the FotoFinder System®. The images were analyzed using their proprietary computer software. Macroscopic and dermoscopic images were evaluated by 3 experienced dermatologists and a senior dermatology resident, all blinded to the AI results. Suspicious lesions identified by the AI or any of the 3 dermatologists were then excised. RESULTS: Seventeen confirmed malignancies were found, including 10 melanomas. Six melanomas were not flagged by the AI. These lesions showed ambiguous atypical melanocytic proliferations, and all were diagnostically challenging to the dermatologists and to the dermatopathologists. Eight malignancies were seen in patients with a family history of melanoma. The AI's ability to diagnose malignancy is not inferior to the dermatologists examining dermoscopic images. CONCLUSION: AI, used in this study, may serve as a practical skin cancer screening aid. While it does have technical and diagnostic limitations, its inclusion in a melanoma screening program, directed at those with a concern about a particular lesion would be valuable in providing timely access to the diagnosis of skin cancer.

Designing a Mucoadhesive ChemoPatch to Ablate Oral Dysplasia for Cancer Prevention.

Oral cancer has a high mortality rate, and its treatment often causes debilitating complications. More than 90% of oral cancers are oral squamous cell carcinomas (OSCCs) that may develop from clinically recognizable oral premalignant lesions (OPLs). To eradicate OPLs before they turn into cancers, a non-invasive topical formulation is developed based on a novel combination of synergistically acting oxaliplatin (OXP) and mycophenolate (MPS) embedded in a controlled-release mucoadhesive patch fabricated by computer-aided 3D printing. After multiple rounds of testing and optimization, a v6.4 ChemoPatch is designed, which shows sustained release of OXP and MPS in vitro, minimal side leakage of drugs, an average elastic modulus of 2.38 MPa, and suitable drug stability at 4 °C or below for up to 12 months. In vivo analyses show almost all patches adhere to the dorsal tongue surface for 4 hours, and display a sustained release of OXP and MPS to tongue tissue for 3-4 hours. When applied in the 4-nitroquinoline-1-oxide-induced OPL rat model, the OXP-MPS patch significantly ablates dysplastic lesions with no damage to normal epithelial cells and minimal systemic absorption and side effects. This study reports the design of a novel mucoadhesive ChemoPatch as a noninvasive therapy to treat OPLs.

On the Cutting Edge of Oral Cancer Prevention: Finding Risk-Predictive Markers in Precancerous Lesions by Longitudinal Studies.

Early identification and management of precancerous lesions at high risk of developing cancers is the most effective and economical way to reduce the incidence, mortality, and morbidity of cancers as well as minimizing treatment-related complications, including pain, impaired functions, and disfiguration. Reliable cancer-risk-predictive markers play an important role in enabling evidence-based decision making as well as providing mechanistic insight into the malignant conversion of precancerous lesions. The focus of this article is to review updates on markers that may predict the risk of oral premalignant lesions (OPLs) in developing into oral squamous cell carcinomas (OSCCs), which can logically be discovered only by prospective or retrospective longitudinal studies that analyze pre-progression OPL samples with long-term follow-up outcomes. These risk-predictive markers are different from those that prognosticate the survival outcome of cancers after they have been diagnosed and treated, or those that differentiate between different lesion types and stages. Up-to-date knowledge on cancer-risk-predictive markers discovered by longitudinally followed studies will be reviewed. The goal of this endeavor is to use this information as a starting point to address some key challenges limiting our progress in this area in the hope of achieving effective translation of research discoveries into new clinical interventions.

Nucleostemin upregulation and STAT3 activation as early events in oral epithelial dysplasia progression to squamous cell carcinoma.

Most low-grade oral epithelial dysplasia remains static or regress, but a significant minority of them (4-11%) advances to oral squamous cell carcinoma (OSCC) within a few years. To monitor the progression of epithelial dysplasia for early cancer detection, we investigated the expression profiles of nucleostemin (NS) and phospho-STAT3 (p-STAT3) in rodent and human samples of dysplasia and OSCCs. In a 4NQO-induced rat oral carcinogenesis model, the number and distribution of NS and p-STAT3-positive cells increased in hyperplastic, dysplastic, and neoplastic lesions compared to normal epithelium. In human samples, the NS signal significantly increased in high-grade dysplasia and poorly differentiated OSCC, whereas p-STAT3 was more ubiquitously expressed than NS and showed increased intensity in high-grade dysplasia and both well and poorly differentiated OSCC. Analyses of human dysplastic samples with longitudinally followed outcomes revealed that cells with prominent nucleolar NS signals were more abundant in low-grade dysplasia that advanced to OSCC in 2 or 3 years than those remaining static for 7-14 years. These results suggest that NS upregulation and STAT3 activation are early events in the progression of low-grade dysplasia to OSCC.