Hyperspectral Imaging of Head and Neck Squamous Cell Carcinoma for Cancer Margin Detection in Surgical Specimens from 102 Patients Using Deep Learning

Abstract

Surgical resection of head and neck (H and N) squamous cell carcinoma (SCC) may yield inadequate surgical cancer margins in 10 to 20% of cases. This study investigates the performance of label-free, reflectance-based hyperspectral imaging (HSI) and autofluorescence imaging for SCC detection at the cancer margin in excised tissue specimens from 102 patients and uses fluorescent dyes for comparison. Fresh surgical specimens (n = 293) were collected during H and N SCC resections (n = 102). The tissue specimens were imaged with reflectance-based HSI and autofluorescence imaging and afterwards with two fluorescent dyes for comparison. A histopathological ground truth was made. Deep learning tools were developed to detect SCC with new patient samples (inter-patient) and machine learning for intra-patient tissue samples. Area under the curve (AUC) of the receiver-operator characteristic was used as the main evaluation metric. Additionally, the performance was estimated in mm increments circumferentially from the tumor-normal margin. In intra-patient experiments, HSI classified conventional SCC with an AUC of 0.82 up to 3 mm from the cancer margin, which was more accurate than proflavin dye and autofluorescence (both p < 0.05). Intra-patient autofluorescence imaging detected human papilloma virus positive (HPV+) SCC with an AUC of 0.99 at 3 mm and greater accuracy than proflavin dye (p < 0.05). The inter-patient results showed that reflectance-based HSI and autofluorescence imaging outperformed proflavin dye and standard red, green, and blue (RGB) images (p < 0.05). In new patients, HSI detected conventional SCC in the larynx, oropharynx, and nasal cavity with 0.85–0.95 AUC score, and autofluorescence imaging detected HPV+ SCC in tonsillar tissue with 0.91 AUC score. This study demonstrates that label-free, reflectance-based HSI and autofluorescence imaging methods can accurately detect the cancer margin in ex-vivo specimens within minutes. This non-ionizing optical imaging modality could aid surgeons and reduce inadequate surgical margins during SCC resections.

Most Relevant Spectral Bands Identification for Brain Cancer Detection Using Hyperspectral Imaging

“…In particular, HSI has started to achieve promising results in the recent years with respect to cancer detection through the utilization of cutting-edge machine-learning algorithms [4,[19][20][21]. Several types of cancer have been investigated using HSI including both in vivo and ex vivo tissue samples, such as gastric and colon cancer [22][23][24][25], breast cancer [26,27], head and neck cancer [28][29][30][31][32][33], and brain cancer [34][35][36], among others.…”

Information Extraction Techniques in Hyperspectral Imaging Biomedical Applications

“…In HSI digital histology, Ortega et al detected glioblastoma brain cancer in digital slides using a patch-based 2D-CNN approach [70]. Additionally, Halicek et al has employed very deep 2D-CNNs for classification, specifically the widely-used Inception v4 model (Figure 4) implemented in a sliding patch-based approach for head and neck squamous cancer [71] and thyroid and salivary gland cancers [72]. For comparing 2D-CNN and 3D-CNNs, in [73] Halicek et al explored spatial-spectral convolutions in 3D CNNs with 3D convolutional kernels to 2D approaches.…”

“…In-vivo brain tumor detection ‡ [27] Deep learning 2D-CNN and 1D-DNN In-vivo brain tumor detection ‡ [69] 2D-CNN (Inception v4) Head and neck cancer [71] Salivary gland cancer [72] 2D-CNN and 3D-CNN Head and neck cancer [73] 2D-CNN (U-Net) Tongue cancer detection [74] Breast cancer [75] GAN HS image generation from RGB [76] RNNs, 2D-CNN and 3D-CNN Head and neck cancer detection [77] Publicly available datasets are marked with ‡ .…”

Machine Learning in Otolaryngology-Head and Neck surgery: A Systematic Review Protocol

“…Otolaryngology-Head and Neck surgery is no exception. For example, studies have reported its use in diagnosing plethora of diseases of the head and neck through evaluation of patients' presenting complaint (for example, voice analysis) (7,8), or through evaluation of radiological, histological and/or endoscopic images (9)(10)(11). Other studies have reported its use in disease prognostication (for example, predicting hearing outcomes in sudden sensorineural hearing loss) (12), or in terms of predicting post-operative outcomes (for example, predicting post-operative complications in head and neck microvascular free tissue transfer) (13).…”