Hyperspectral Imaging for Lateral Tumour Demarcation of High-risk Basal Cell Carcinomas during Mohs Micrographic Surgery

Sep 23, 2026

Uploaded by nayy☆

Hyperspectral imaging offers a non-invasive approach for delineating tumour margins before Mohs micrographic surgery. This pilot study evaluated its feasibility for marking lateral margins of high-risk facial basal cell carcinomas in 30 recruited patients. Lesions were first demarcated using dermoscopy, followed by hyperspectral imaging scans. Supervised pixel-wise learning was validated via half-split and leave-one-out image-level cross-validation, achieving pixel-wise accuracy 0.76, sensitivity 0.75, specificity 0.78, and AUC 0.84.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Hyperspectral imaging study overview

Patient recruitment and workflow

Imaging, margin comparison, and validation

Performance metrics and conclusions

1/8 ORIGINAL REPORT Hyperspectral Imaging for Lateral Tumour Demarcation of High-risk Basal Cell Carcinomas during Mohs Micrographic Surgery Hannah CEDER1,2, Mari SALMIVUORI1,2,3, Ilkka PÖLÖNEN4, John PAOLI1,2 and Noora NEITTAANMÄKI5,6 1Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, 2Region Västra Götaland, Sahlgrenska University Hospital, Department of Dermatology and Venereology, Gothenburg, 3Department of Dermatology, Allergology and Venereology, Helsinki University Hospital and University of Helsinki, Helsinki, 4Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland, 5Department of Laboratory Medicine, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, 6Department of Pathology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden Hyperspectral imaging is a non-invasive imaging modality showing potential in delineating tumour margins preoperatively. This pilot study evaluated the feasibility of using hyperspectral imaging to demarcate lateral margins of high-risk facial basal cell carcinomas (BCC) prior to Mohs micrographic surgery. Thirty patients with high-risk BCCs were recruited from the Department of Dermatology, Sahlgrenska University Hospital, Sweden. Lesions were initially demarcated using dermoscopy, followed by hyperspectral imaging scans. During the first stage, a superficial vertical incision was performed along the demarcation line before adding a 3-mm clinical margin for the bowl-shaped excision of the tumour. Hyperspectral imaging-based tumour margins were compared with histopathologically verified borders, serving as ground truth. The data analysis used supervised learning; 2 complementary validation strategies were employed: a half-split approach where the left half of each annotated image was used for training and the right half for testing, anda leave-one-out cross-validation at the image level. A pixel-wise classification approach was used, treating each pixel as an independent sample. Hyperspectral imaging achieved a pixel-wise classification accuracy of 0.76, sensitivity of 0.75, specificity of 0.78, and an area under the receiver operating characteristic curve of 0.84. Hyperspectral imaging demonstrated potential for tumour demarcation, providing a basis for future research. Key words: high-risk basal cell carcinoma; Mohs micrographic surgery; tumour demarcation; hyperspectral imaging. Submitted Apr 22, 2025. Accepted after revision Nov 4, 2025 Published Dec 2, 2025. DOI: 10.2340/actadv.v105.43614 Acta Derm Venereol 2025; 105: adv43614 . Corr: Noora Neittaanmäki, Department of Pathology, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, SE-413 45 Gothenburg, Sweden. E-mail: [noora.neittaanmaki@gu.se](noora.neittaanmaki@gu.se) Basofaslcekinlcarcanceinromandaa(BmCajCoisptuhe mblic hoestalcommonth probletympien fair-skinned populations. Although it rarely metastasizes, BCC can cause morbidity due to aggressive and destructive local growth (1) . Histopathologically, BCCs can be classified by their morphological growth pattern into SIGNIFICANCE Hyperspectral imaging combines digital imaging and spectroscopy for non-invasive, in vivo diagnosis of skin cancer. Its advantages include large field of view and rapid imaging process. This pilot study assessed the feasibility of a convolutional neural network trained on hyperspectral images for detecting the lateral borders of high-risk basal cell carcinomas prior to Mohs micrographic surgery. The results indicate that hyperspectral imaging provides relatively high sensitivity and specificity for this task. These results will serve as a basis for future development as well as further validation with larger datasets. low-risk (nodular or superficial) or high-risk subtypes (aggressive growth patterns) . The aggressive growth patterns are infiltrative, mic

FAQs

What question did the pilot study investigate?

Whether hyperspectral imaging can demarcate the lateral tumour margins of high-risk facial basal cell carcinomas prior to Mohs micrographic surgery.

How were tumour margins assessed and validated?

Initial demarcation used dermoscopy, followed by hyperspectral imaging scans. Hyperspectral imaging-based margins were compared with histopathologically verified borders using half-split and leave-one-out cross-validation.

What performance results were reported for the imaging model?

The method achieved pixel-wise classification accuracy of 0.76, sensitivity of 0.75, specificity of 0.78, and AUC of 0.84 for lateral margin classification.

Sep 23, 2026

Uploaded by nayy☆