1
|
Chiu SUF, Hung CM, Chiu CC. A commentary on 'Approved and investigational fluorescent optical imaging agents for disease detection in surgery'. Int J Surg 2024; 110:611-612. [PMID: 37800572 PMCID: PMC10793771 DOI: 10.1097/js9.0000000000000799] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2023] [Accepted: 09/17/2023] [Indexed: 10/07/2023]
Affiliation(s)
- Si-Un Frank Chiu
- Department of Computer Science
- Department of Economics, Brown University, Providence, Rhode Island, USA
| | - Chao-Ming Hung
- Department of General Surgery
- School of Medicine, College of Medicine, I-Shou University, Kaohsiung, Taiwan
| | - Chong-Chi Chiu
- Department of General Surgery
- Department of Medical Education and Research, E-Da Cancer Hospital
- School of Medicine, College of Medicine, I-Shou University, Kaohsiung, Taiwan
| |
Collapse
|
2
|
Yu X, Dong M, Yang D, Wang L, Wang H, Ma L. Deep learning for differentiating benign from malignant tumors on breast-specific gamma image. Technol Health Care 2023; 31:61-67. [PMID: 37038782 DOI: 10.3233/thc-236007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/12/2023]
Abstract
BACKGROUND Breast diseases are a significant health threat for women. With the fast-growing BSGI data, it is becoming increasingly critical for physicians to accurately diagnose benign as well as malignant breast tumors. OBJECTIVE The purpose of this study is to diagnose benign and malignant breast tumors utilizing the deep learning model, with the input of breast-specific gamma imaging (BSGI). METHODS A benchmark dataset including 144 patients with benign tumors and 87 patients with malignant tumors was collected and divided into a training dataset and a test dataset according to the ratio of 8:2. The convolutional neural network ResNet18 was employed to develop a new deep learning model. The model proposed was compared with neural network and autoencoder models. Accuracy, specificity, sensitivity and ROC were used to evaluate the performance of different models. RESULTS The accuracy, specificity and sensitivity of the model proposed are 99.1%, 98.8% and 99.3% respectively, which achieves the best performance among all methods. Additionally, the Grad-CAM method is used to analyze the interpretability of the diagnostic results based on the deep learning model. CONCLUSION This study demonstrates that the proposed deep learning method could help physicians diagnose benign and malignant breast tumors quickly as well as reliably.
Collapse
Affiliation(s)
- Xia Yu
- Weihai Maternal and Children Health Hospital, Weihai, Shandong, China
| | - Mengchao Dong
- School of Information Science and Engineering, Harbin Institute of Technology, Weihai, Shandong, China
| | - Dongzhu Yang
- Weihai Municipal Hospital, Weihai, Shandong, China
| | - Lianfang Wang
- School of Information Science and Engineering, Harbin Institute of Technology, Weihai, Shandong, China
| | - Hongjie Wang
- Weihai Maternal and Children Health Hospital, Weihai, Shandong, China
| | - Liyong Ma
- School of Information Science and Engineering, Harbin Institute of Technology, Weihai, Shandong, China
| |
Collapse
|
3
|
Chen Y, Streeter SS, Hunt B, Sardar HS, Gunn JR, Tafe LJ, Paydarfar JA, Pogue BW, Paulsen KD, Samkoe KS. Fluorescence molecular optomic signatures improve identification of tumors in head and neck specimens. FRONTIERS IN MEDICAL TECHNOLOGY 2023; 5:1009638. [PMID: 36875185 PMCID: PMC9975724 DOI: 10.3389/fmedt.2023.1009638] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2022] [Accepted: 01/16/2023] [Indexed: 02/17/2023] Open
Abstract
Background Fluorescence molecular imaging using ABY-029, an epidermal growth factor receptor (EGFR)-targeted, synthetic Affibody peptide labeled with a near-infrared fluorophore, is under investigation for surgical guidance during head and neck squamous cell carcinoma (HNSCC) resection. However, tumor-to-normal tissue contrast is confounded by intrinsic physiological limitations of heterogeneous EGFR expression and non-specific agent uptake. Objective In this preliminary study, radiomic analysis was applied to optical ABY-029 fluorescence image data for HNSCC tissue classification through an approach termed "optomics." Optomics was employed to improve tumor identification by leveraging textural pattern differences in EGFR expression conveyed by fluorescence. The study objective was to compare the performance of conventional fluorescence intensity thresholding and optomics for binary classification of malignant vs. non-malignant HNSCC tissues. Materials and Methods Fluorescence image data collected through a Phase 0 clinical trial of ABY-029 involved a total of 20,073 sub-image patches (size of 1.8 × 1.8 mm2) extracted from 24 bread-loafed slices of HNSCC surgical resections originating from 12 patients who were stratified into three dose groups (30, 90, and 171 nanomoles). Each dose group was randomly partitioned on the specimen-level 75%/25% into training/testing sets, then all training and testing sets were aggregated. A total of 1,472 standardized radiomic features were extracted from each patch and evaluated by minimum redundancy maximum relevance feature selection, and 25 top-ranked features were used to train a support vector machine (SVM) classifier. Predictive performance of the SVM classifier was compared to fluorescence intensity thresholding for classifying testing set image patches with histologically confirmed malignancy status. Results Optomics provided consistent improvement in prediction accuracy and false positive rate (FPR) and similar false negative rate (FNR) on all testing set slices, irrespective of dose, compared to fluorescence intensity thresholding (mean accuracies of 89% vs. 81%, P = 0.0072; mean FPRs of 12% vs. 21%, P = 0.0035; and mean FNRs of 13% vs. 17%, P = 0.35). Conclusions Optomics outperformed conventional fluorescence intensity thresholding for tumor identification using sub-image patches as the unit of analysis. Optomics mitigate diagnostic uncertainties introduced through physiological variability, imaging agent dose, and inter-specimen biases of fluorescence molecular imaging by probing textural image information. This preliminary study provides a proof-of-concept that applying radiomics to fluorescence molecular imaging data offers a promising image analysis technique for cancer detection in fluorescence-guided surgery.
Collapse
Affiliation(s)
- Yao Chen
- Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
| | - Samuel S. Streeter
- Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
- Department of Orthopaedics, Dartmouth Health, Lebanon, NH, United States
- Geisel School of Medicine, Dartmouth College, Hanover, NH, United States
| | - Brady Hunt
- Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
| | - Hira S. Sardar
- Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
| | - Jason R. Gunn
- Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
| | - Laura J. Tafe
- Geisel School of Medicine, Dartmouth College, Hanover, NH, United States
- Department of Pathology, Dartmouth Health, Lebanon, NH, United States
| | - Joseph A. Paydarfar
- Geisel School of Medicine, Dartmouth College, Hanover, NH, United States
- Department of Surgery, Dartmouth Health, Lebanon, NH, United States
- Department of Otolaryngology, Dartmouth Health, Lebanon, NH, United States
| | - Brian W. Pogue
- Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
- Geisel School of Medicine, Dartmouth College, Hanover, NH, United States
- Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, United States
| | - Keith D. Paulsen
- Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
- Geisel School of Medicine, Dartmouth College, Hanover, NH, United States
| | - Kimberley S. Samkoe
- Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
- Geisel School of Medicine, Dartmouth College, Hanover, NH, United States
- Department of Surgery, Dartmouth Health, Lebanon, NH, United States
| |
Collapse
|
5
|
Pemmaraju R, Minahan R, Wang E, Schadl K, Daldrup-Link H, Habte F. Web-Based Application for Biomedical Image Registry, Analysis, and Translation (BiRAT). Tomography 2022; 8:1453-1462. [PMID: 35736865 PMCID: PMC9228304 DOI: 10.3390/tomography8030117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Revised: 05/23/2022] [Accepted: 05/27/2022] [Indexed: 11/18/2022] Open
Abstract
Imaging has become an invaluable tool in preclinical research for its capability to non-invasively detect and monitor disease and assess treatment response. With the increased use of preclinical imaging, large volumes of image data are being generated requiring critical data management tools. Due to proprietary issues and continuous technology development, preclinical images, unlike DICOM-based images, are often stored in an unstructured data file in company-specific proprietary formats. This limits the available DICOM-based image management database to be effectively used for preclinical applications. A centralized image registry and management tool is essential for advances in preclinical imaging research. Specifically, such tools may have a high impact in generating large image datasets for the evolving artificial intelligence applications and performing retrospective analyses of previously acquired images. In this study, a web-based server application is developed to address some of these issues. The application is designed to reflect the actual experimentation workflow maintaining detailed records of both individual images and experimental data relevant to specific studies and/or projects. The application also includes a web-based 3D/4D image viewer to easily and quickly view and evaluate images. This paper briefly describes the initial implementation of the web-based application.
Collapse
Affiliation(s)
- Rahul Pemmaraju
- School of Bioengineering and Biomedical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA;
| | - Robert Minahan
- Computational and Systems Biology, University of California-Los Angeles, Los Angeles, CA 90095, USA;
| | - Elise Wang
- School of Medicine, University of Rochester, Rochester, NY 14642, USA;
| | - Kornel Schadl
- Department of Orthopedic Surgery, Stanford School of Medicine, Stanford, CA 94305, USA;
| | - Heike Daldrup-Link
- Department of Radiology, Stanford School of Medicine, Stanford, CA 94305, USA;
| | - Frezghi Habte
- Department of Radiology, Stanford School of Medicine, Stanford, CA 94305, USA;
- Correspondence:
| |
Collapse
|