Cutaneous squamous cell carcinoma ranks as the second most common skin malignancy in Sweden, trailing only basal cell carcinoma. Its incidence is rising sharply, with over 10,000 new cases diagnosed annually across the country. cSCC primarily affects sun-exposed anatomical regions such as the face and neck, where cumulative ultraviolet (UV) radiation inflicts molecular damage over many years, initiating oncogenic mutations in keratinocytes—the predominant cell type in the epidermis.

Dr. Sam Polesie, an associate professor specializing in dermatology and venereology at the University of Gothenburg, led the research team that spearheaded the AI model’s development. “The pathogenesis of squamous cell carcinoma is intimately linked to chronic UV exposure, which induces mutagenic alterations in skin cells. Clinically, these tumors often present on sun-damaged skin characterized by irregular pigmentation, thickened, ulcerated lesions, and compromised elasticity,” explains Polesie. Despite the relative ease of recognizing the disease itself, stratifying tumors according to their biological aggressiveness remains a formidable clinical challenge.

Current medical protocols in Sweden and many other countries generally forgo preoperative punch biopsies in suspected cSCC cases. Instead, patients undergo surgery based solely on clinical suspicion, and the excised tissue undergoes subsequent histopathological examination to confirm diagnosis and guide follow-up care. However, without a biopsy guiding initial treatment, clinicians face significant uncertainty regarding the tumor’s growth potential, complicating surgical planning. Aggressive tumors necessitate prompt, extensive surgical excision with wider margins to minimize recurrence risk, whereas less aggressive lesions may be addressed using more conservative approaches.

Acknowledging these diagnostic hurdles, the research team focused on leveraging machine learning to analyze a robust dataset comprising 1,829 close-up clinical images of pathologically confirmed squamous cell carcinomas. The AI was trained to categorize tumors into three distinct tiers of aggressiveness based on morphological features extracted through advanced image processing algorithms. Subsequent validation utilized an independent test set of 300 images, comparing the AI’s predictive accuracy directly against evaluations performed by a cohort of seven experienced dermatologists.

The study, published in the Journal of the American Academy of Dermatology, revealed that the AI model’s performance in differentiating tumor aggressiveness was statistically indistinguishable from that of the expert clinicians. Intriguingly, the interobserver variability among dermatologists themselves was only moderate, highlighting inherent subjectivity and complexity in human assessments. These findings illustrate that AI can standardize and potentially enhance diagnostic reliability in preoperative settings, offering consistent and swift decision support.

Among the salient clinical indicators identified as correlating strongly with aggressive tumor phenotypes were the presence of ulcerations and flat, non-elevated skin surfaces. Tumors with these characteristics exhibited more than double the likelihood of belonging to higher aggressiveness categories. This insight underscores the importance of integrating specific morphological cues into computational models to refine prognostic accuracy.

Despite mounting enthusiasm for AI applications in dermatology, practical integration into routine clinical workflows has been limited to date. Polesie emphasizes that successful adoption hinges upon targeting AI development toward well-defined clinical problems where enhanced decision-making can tangibly improve patient outcomes. “Our focus has been the preoperative assessment of suspected skin cancers, an area ripe for AI’s capabilities. While our model requires further validation and optimization, its value lies in augmenting—not replacing—clinical expertise,” he asserts.

The AI employed convolutional neural networks (CNNs), a deep learning architecture adept at recognizing intricate spatial patterns within images. By training on a sizeable and diverse image repository gathered between 2015 and 2023 at the Sahlgrenska University Hospital dermatology department, the system learned to discern subtle textural and color variations indicative of tumor biology. This data-driven approach represents a leap beyond traditional diagnostic heuristics, harnessing computational power to harness cellular and tissue-level heterogeneity captured visually.

From a technical perspective, the model’s success rests on sophisticated preprocessing steps—such as normalization, segmentation, and augmentation—that enhance image quality while mitigating noise and variability inherent to clinical photography. The subsequent feature extraction phase employs filters designed to capture edges, gradients, and color contrasts associated with pathological changes. Finally, classification layers map these features onto clinically relevant aggressiveness labels, delivering probabilistic outputs that clinicians can interpret alongside their assessments.

Looking forward, the integration of this AI tool into teledermatology platforms and mobile diagnostic applications could democratize access to expert-level evaluation, particularly in resource-limited settings or remote areas. Rapid, noninvasive tumor characterization facilitated by image-based algorithms might reduce unnecessary surgeries or expedite intervention for high-risk lesions, substantially improving patient care efficiency.

Given the complexity and variability of cSCC presentation, additional studies encompassing larger, multi-center image datasets and diverse patient populations are essential. Moreover, longitudinal analyses linking AI-predicted aggressiveness with actual clinical outcomes will validate the prognostic utility of these computational assessments.

In conclusion, this research from the University of Gothenburg marks a pivotal step toward harnessing artificial intelligence as an adjunct diagnostic tool in dermatological oncology. By matching expert dermatologist performance in gauging squamous cell carcinoma aggressiveness through noninvasive imaging, the AI model demonstrates immense potential to refine surgical planning, optimize resource allocation, and ultimately improve prognosis for thousands of patients afflicted by this widespread cancer. Continued technological refinement paired with clinical validation will pave the way for AI’s meaningful integration into standard dermatological practice.

Subject of Research: People

Article Title: Assessing Differentiation in Cutaneous Squamous Cell Carcinoma: A Machine Learning Approach

News Publication Date: 1-Aug-2025

Web References:
10.1016/j.jdin.2025.07.004

References:
Journal of the American Academy of Dermatology

Image Credits: Photo: Johan Wingborg

Keywords: artificial intelligence, squamous cell carcinoma, skin cancer, dermatology, machine learning, tumor aggressiveness, convolutional neural networks, preoperative assessment, medical imaging, cancer diagnostics

At the core of this investigation lies a novel Multi-Patient-Targeted (MPT) single-cell DNA sequencing approach. Unlike previous studies that have often relied on bulk sequencing methods, this technique integrates bulk exome sequencing with the high-resolution capabilities of Tapestri single-cell DNA sequencing. By designing a patient-specific targeted mutation panel, the researchers achieved an unprecedented sensitivity in detecting rare clonal mutations that drive tumor progression. The application of MPT sequencing thus represents a significant advance in the molecular characterization of heterogenous tumor populations within individual CSCC patients.

The study focused on a cohort of Chinese CSCC patients, and the genomic profiles revealed a diverse array of somatic mutations. Missense mutations emerged as the predominant mutational type across tumor samples. Among the most frequently mutated genes were NOTCH1, TP53, NOTCH2, and others involved in critical cellular pathways such as cell-cycle regulation, DNA damage repair, and signal transduction. The mutational patterns bore remarkable resemblance to those previously reported in Korean and Caucasian cohorts, underscoring certain conserved genomic features of CSCC across ethnicities.

However, the researchers also discovered significant population-specific variations. Notably, mutation frequencies in genes like HRAS, TTN, MUC16, and MUC4 deviated markedly from those observed in non-Chinese populations. These findings highlight the necessity of considering ethnic diversity when designing mutation panels and therapeutic approaches, as distinct mutational signatures may influence tumor biology and treatment response differentially.

The analytic strength of single-cell DNA sequencing transcended the identification of mutations; it provided a window into clonal architecture and tumor evolution. By dissecting individual cancer cells, the study traced dynamic clonal trajectories within tumors, revealing how distinct subclones emerge, expand, or diminish over time. Such clonal evolution patterns elucidate the heterogeneity underpinning tumor aggressiveness and metastatic potential, offering prognostic value and aiding in the anticipation of therapy resistance.

Intriguingly, the MPT scDNA-seq approach uncovered two low-frequency mutation clones involving the genes NLRP5 and HMMR. Though these clones existed in minor proportions within tumors, their influence on clonal evolution and tumor behavior appears substantial. NLRP5 and HMMR have been implicated in regulatory pathways associated with cellular proliferation and immune responses, suggesting that even rare clonal populations could orchestrate critical oncogenic processes.

Further comparative analyses probed the relationships between specific gene mutations and clinical parameters such as tumor stage and patient sex. The study illuminated previously unappreciated associations, indicating that certain mutational profiles may predispose tumors to more advanced stages or may exhibit sex-based prevalence. These correlation patterns pave the way toward more nuanced risk stratification frameworks tailored to individual genetic contexts.

The broader implications of this study lie in its provision of a robust framework for personalized oncology in CSCC. By integrating high-resolution scDNA-seq data with clinical phenotypes, the research generates actionable insights that can guide precision medicine efforts. Custom-designed mutation panels, based on comprehensive bulk and single-cell sequencing data, foster the identification of subclonal populations that might escape conventional detection yet drive disease progression.

From a technical standpoint, the collaborative use of bulk exome sequencing and the Tapestri platform for scDNA-seq exemplifies innovative cross-method integration. Bulk sequencing acted as a foundation to identify prevalent and patient-specific mutations, which then informed panel design for targeted single-cell interrogation. This layered approach optimizes resource efficiency while maximizing the depth and accuracy of mutational discovery.

The study also forms a critical comparative reference by juxtaposing mutational data derived from Chinese patients with those from Korean and Caucasian populations. This comparative genomics angle not only advances the understanding of CSCC’s ethnic variability but also calls attention to the limitations of one-size-fits-all diagnostic and therapeutic tools. Ethnic-specific panels and treatment regimens might be necessary to achieve optimal outcomes in diverse patient populations.

Interestingly, the identification of clonal mutations such as those in NOTCH1 and TP53 corroborates their established roles as key drivers in squamous cell carcinomas. Their persistent presence across populations underscores the potential for these genes to serve as universal therapeutic targets. Meanwhile, the discovery of novel mutation clones invites further research to elucidate their biological functions and therapeutic potential.

The insights gained from this study are expected to catalyze downstream clinical research, including the exploration of targeted therapies that disrupt clonal evolution pathways. By interrupting the emergence or dominance of aggressive tumor subclones, clinicians may be able to forestall metastasis and improve patient survival. Moreover, monitoring clonal dynamics through repeated single-cell sequencing could enable real-time evaluation of treatment efficacy.

This groundbreaking research not only charts the complex genomic terrain of CSCC but also exemplifies the transformative power of next-generation sequencing technologies when applied in a patient-tailored manner. The MPT scDNA-seq methodology stands poised to become a valuable tool in both basic cancer biology and clinical oncology, enabling the disentangling of tumor heterogeneity and the tailoring of personalized interventions.

In summary, the study presents a compelling paradigm shift in how cutaneous squamous cell carcinoma is studied and understood at the molecular level. It bridges technologic innovations with clinical imperatives, laying the groundwork for mutation-informed diagnostics and treatments. As genomic medicine continues its rapid evolution, such approaches hold promise for controlling a cancer that has long been notorious for its unpredictability and resistance.

Going forward, the integration of genomic data with transcriptomic and proteomic profiles could deepen the understanding of how genetic alterations translate into phenotypic behaviors. Combined multi-omics analyses at the single-cell level may unravel the full complexity of CSCC and unveil novel biomarkers for early detection, prognosis, and therapy selection.

Ultimately, this research epitomizes how methodical, high-resolution genomic investigations can reveal the underpinnings of cancer heterogeneity and evolution, which are pivotal to overcoming the challenges of metastatic and treatment-resistant skin cancers. By illuminating the mutational landscapes and clonal architectures, the study charts a path toward more effective and individualized management of cutaneous squamous cell carcinoma.

Subject of Research: Genomic heterogeneity and mutational landscape in cutaneous squamous cell carcinoma (CSCC) using multi-patient-targeted single-cell DNA sequencing.

Article Title: Analysis of genomic heterogeneity and the mutational landscape in cutaneous squamous cell carcinoma through multi-patient-targeted single-cell DNA sequencing.

Article References:
Chen, W., Xu, J., Yu, C. et al. Analysis of genomic heterogeneity and the mutational landscape in cutaneous squamous cell carcinoma through multi-patient-targeted single-cell DNA sequencing. BMC Cancer 25, 1362 (2025). https://doi.org/10.1186/s12885-025-14585-z

Image Credits: Scienmag.com

DOI: https://doi.org/10.1186/s12885-025-14585-z