AI Article Synopsis

  • Negative surgical margins significantly affect the recurrence of cancer, highlighting the need for effective detection methods during surgery.
  • Researchers developed a tissue classifier using convolutional neural networks (CNNs) with hyperspectral imaging (HSI) to identify cancer margins in surgical specimens from 20 patients, achieving high accuracy and sensitivity rates.
  • Preliminary results show promise for HSI in detecting cancer margins, especially for thyroid carcinoma, suggesting a need for further studies with larger datasets to enhance the effectiveness of this technology.

Article Abstract

One of the largest factors affecting disease recurrence after surgical cancer resection is negative surgical margins. Hyperspectral imaging (HSI) is an optical imaging technique with potential to serve as a computer aided diagnostic tool for identifying cancer in gross specimens. We developed a tissue classifier using three distinct convolutional neural network (CNN) architectures on HSI data to investigate the ability to classify the cancer margins from human surgical specimens, collected from 20 patients undergoing surgical cancer resection as a preliminary validation group. A new approach for generating the HSI ground truth using a registered histological cancer margin is applied in order to create a validation dataset. The CNN-based method classifies the tumor-normal margin of squamous cell carcinoma (SCCa) versus normal oral tissue with an area under the curve (AUC) of 0.86 for inter-patient validation, performing with 81% accuracy, 84% sensitivity, and 77% specificity. Thyroid carcinoma cancer-normal margins are classified with an AUC of 0.94 for inter-patient validation, performing with 90% accuracy, 91% sensitivity, and 88% specificity. Our preliminary results on a limited patient dataset demonstrate the predictive ability of HSI-based cancer margin detection, which warrants further investigation with more patient data and additional processing techniques to optimize the proposed deep learning method.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6149520PMC
http://dx.doi.org/10.1117/12.2293167DOI Listing

Publication Analysis

Top Keywords

hyperspectral imaging
8
convolutional neural
8
surgical cancer
8
cancer resection
8
cancer margin
8
inter-patient validation
8
validation performing
8
cancer
7
tumor margin
4
margin classification
4

Similar Publications

Intraoperative Hyperspectral Imaging Predicts Early Allograft Dysfunction and Overall Survival in Liver Transplantation.

Ann Surg Open

December 2024

From the Department of Visceral, Transplant, Thoracic and Vascular Surgery, Division of Hepatobiliary Surgery and Visceral Transplant Surgery, University Clinic Leipzig, Germany.

Objective: This study explored the novel application of hyperspectral imaging (HSI) for in vivo allograft perfusion assessment during liver transplantation (LT) and its potential value for predicting early allograft dysfunction (EAD), graft, and overall survival (OS).

Background: LT is a well-established therapy for acute and chronic liver diseases, with excellent outcomes. However, a significant proportion of recipients experience EAD, which affects graft and OS.

View Article and Find Full Text PDF

Novel decision-level fusion strategies combined with hyperspectral imaging for the detection of soybean protein content.

Food Chem

December 2024

School of Agricultural Engineering and Food Science, Shandong University of Technology, No. 266 Xincun Xilu, Zibo, Shandong 255049, China. Electronic address:

Soybeans are used for human consumption or animal feed due to their abundant protein content. In this study, visible-near infrared (VNIR) hyperspectral imaging (HSI) and short-wave infrared HSI combined with three-levels data fusion methods were employed to detect the protein content of soybean seeds, including measurement-level fusion, feature-level fusion, and decision-level fusion. Additionally, three novel decision-level fusion methods were proposed, including binary linear regression, feature-based multiple linear regression (MLR), and model-based MLR.

View Article and Find Full Text PDF

Background: This research proposes an easy to apply quality assurance pipeline for hyperspectral imaging (HSI) systems used for plant phenotyping. Furthermore, a concept for the analysis of quality assured hyperspectral images to investigate plant disease progress is proposed. The quality assurance was applied to a handheld line scanning HSI-system consisting of evaluating spatial and spectral quality parameters as well as the integrated illumination.

View Article and Find Full Text PDF

Prediction and mapping of leaf water content in Populus alba var. pyramidalis using hyperspectral imagery.

Plant Methods

December 2024

CAS Key Laboratory of Forest Ecology and Silviculture, Institute of Applied Ecology, Chinese Academy of Sciences, Shenyang, 110016, China.

Leaf water content (LWC) encapsulates critical aspects of tree physiology and is considered a proxy for assessing tree drought stress and the risk of forest decline; however, its measurement relies on destructive sampling and is thus less efficient. Advancements in hyperspectral imaging technology present new prospects for noninvasively evaluating LWC and mapping drought severity across forested regions. In this study, leaf samples were obtained from Populus alba var.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!