Dataset Information

Intraoperative Assessment of Tumor Margins in Tissue Sections with Hyperspectral Imaging and Machine Learning.

ABSTRACT: The intraoperative assessment of tumor margins of head and neck cancer is crucial for complete tumor resection and patient outcome. The current standard is to take tumor biopsies during surgery for frozen section analysis by a pathologist after H&E staining. This evaluation is time-consuming, subjective, methodologically limited and underlies a selection bias. Optical methods such as hyperspectral imaging (HSI) are therefore of high interest to overcome these limitations. We aimed to analyze the feasibility and accuracy of an intraoperative HSI assessment on unstained tissue sections taken from seven patients with oral squamous cell carcinoma. Afterwards, the tissue sections were subjected to standard histopathological processing and evaluation. We trained different machine learning models on the HSI data, including a supervised 3D convolutional neural network to perform tumor detection. The results were congruent with the histopathological annotations. Therefore, this approach enables the delineation of tumor margins with artificial HSI-based histopathological information during surgery with high speed and accuracy on par with traditional intraoperative tumor margin assessment (Accuracy: 0.76, Specificity: 0.89, Sensitivity: 0.48). With this, we introduce HSI in combination with ML hyperspectral imaging as a potential new tool for intraoperative tumor margin assessment.

SUBMITTER: Pertzborn D

PROVIDER: S-EPMC9818424 | biostudies-literature | 2022 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Intraoperative Assessment of Tumor Margins in Tissue Sections with Hyperspectral Imaging and Machine Learning.

Pertzborn David D Nguyen Hoang-Ngan HN Hüttmann Katharina K Prengel Jonas J Ernst Günther G Guntinas-Lichius Orlando O von Eggeling Ferdinand F Hoffmann Franziska F

Cancers 20221229 1

The intraoperative assessment of tumor margins of head and neck cancer is crucial for complete tumor resection and patient outcome. The current standard is to take tumor biopsies during surgery for frozen section analysis by a pathologist after H&E staining. This evaluation is time-consuming, subjective, methodologically limited and underlies a selection bias. Optical methods such as hyperspectral imaging (HSI) are therefore of high interest to overcome these limitations. We aimed to analyze the ...[more]

PMID: 36612208

Similar Datasets

Project description:Soft tissue sarcomas (STS) are rare malignant tumors often associated with poor outcomes and high local recurrence rates. Current tools for intraoperative and definitive margin assessment include intraoperative frozen section and permanent pathology, respectively. Indocyanine green dye (ICG) is a historically safe fluorophore dye that has demonstrated efficacy for intraoperative margin assessment in the surgical management of both breast and gastrointestinal cancers. The utility of ICG in the surgical management of sarcoma surgery has primarily been studied in pre-clinical mouse models and warrants further investigation as a potential adjunct to achieving negative margins. This study is a prospective, non-randomized clinical study conducted on patients with confirmed or suspected STS. Patients younger than 18 years, with a prior adverse reaction to iodine or fluorescein, or with renal disease were excluded from the study. Intravenous ICG was infused approximately three hours prior to surgery at a dosage of 2.0-2.5 mg/kg, and following tumor resection, the excised tumor and tumor bed were imaged for fluorescence intensity. When scanning the tumor bed, a threshold of 77% calibrated to the region of maximum intensity in the resected tumor was defined as a positive ICG margin, according to published protocols from the breast cancer literature. ICG results were then compared with the surgeon's clinical impression of margin status and permanent pathology results. Out of 26 subjects recruited for the original study, 18 soft tissue sarcomas (STS) were included for analysis. Three subjects were excluded for having bone sarcomas, and five subjects were excluded due to final pathology, which was ultimately inconsistent with sarcoma. The average age of patients was 64.1 years old (range: 28-83), with an average ICG dose of 201.8 mg. In 56% (10/18) of patients, ICG margins were consistent with the permanent pathology margins, with 89% specificity. The use of ICG as an intraoperative adjunct to obtaining negative margins in soft tissue sarcoma surgery is promising. However, studies with larger sample sizes are warranted to further delineate the accuracy, optimal dosage, timing, and types of sarcoma in which this diagnostic tool may be most useful.

Dataset Information

Intraoperative Assessment of Tumor Margins in Tissue Sections with Hyperspectral Imaging and Machine Learning.

Publications

Intraoperative Assessment of Tumor Margins in Tissue Sections with Hyperspectral Imaging and Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets