1
|
Tampu IE, Eklund A, Johansson K, Gimm O, Haj-Hosseini N. Diseased thyroid tissue classification in OCT images using deep learning: Towards surgical decision support. JOURNAL OF BIOPHOTONICS 2023; 16:e202200227. [PMID: 36203247 DOI: 10.1002/jbio.202200227] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Revised: 09/15/2022] [Accepted: 09/16/2022] [Indexed: 06/16/2023]
Abstract
Intraoperative guidance tools for thyroid surgery based on optical coherence tomography (OCT) could aid distinguish between normal and diseased tissue. However, OCT images are difficult to interpret, thus, real-time automatic analysis could support the clinical decision-making. In this study, several deep learning models were investigated for thyroid disease classification on 2D and 3D OCT data obtained from ex vivo specimens of 22 patients undergoing surgery and diagnosed with several thyroid pathologies. Additionally, two open-access datasets were used to evaluate the custom models. On the thyroid dataset, the best performance was achieved by the 3D vision transformer model with a Matthew's correlation coefficient (MCC) of 0.79 (accuracy = 0.90) for the normal-versus-abnormal classification. On the open-access datasets, the custom models achieved the best performance (MCC > 0.88, accuracy > 0.96). Results obtained for the normal-versus-abnormal classification suggest OCT, complemented with deep learning-based analysis, as a tool for real-time automatic diseased tissue identification in thyroid surgery.
Collapse
Affiliation(s)
- Iulian Emil Tampu
- Department of Biomedical Engineering, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden
| | - Anders Eklund
- Department of Biomedical Engineering, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden
- Division of Statistics & Machine Learning, Department of Computer and Information Science, Linköping University, Linköping, Sweden
| | - Kenth Johansson
- Department of Surgery, Västervik Hospital, Västervik, Sweden
- Department of Surgery, Örebro University Hospital, Örebro, Sweden
| | - Oliver Gimm
- Department of Surgery, Linköping University Hospital, Linköping, Sweden
- Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
| | - Neda Haj-Hosseini
- Department of Biomedical Engineering, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden
| |
Collapse
|
2
|
Wang Q, Xiangli W, Chen X, Zhang J, Teng G, Cui X, Idrees BS, Wei K. Primary study of identification of parathyroid gland based on laser-induced breakdown spectroscopy. BIOMEDICAL OPTICS EXPRESS 2021; 12:1999-2014. [PMID: 33996212 PMCID: PMC8086479 DOI: 10.1364/boe.417738] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/16/2020] [Revised: 03/02/2021] [Accepted: 03/03/2021] [Indexed: 06/01/2023]
Abstract
The identification and preservation of parathyroid glands (PGs) is a major issue in thyroidectomy. The PG is particularly difficult to distinguish from the surrounding tissues. Accidental damage or removal of the PG may result in temporary or permanent postoperative hypoparathyroidism and hypocalcemia. In this study, a novel method for identification of the PG was proposed based on laser-induced breakdown spectroscopy (LIBS) for the first time. LIBS spectra were collected from the smear samples of PG and non-parathyroid gland (NPG) tissues (thyroid and neck lymph node) of rabbits. The emission lines (related to K, Na, Ca, N, O, CN, C2, etc.) observed in LIBS spectra were ranked and selected based on the important weight calculated by random forest (RF). Three machine learning algorithms were used as classifiers to distinguish PGs from NPGs. The artificial neural network classifier provided the best classification performance. The results demonstrated that LIBS can be adopted to discriminate between smear samples of PG and NPG, and it has a potential in intra-operative identification of PGs.
Collapse
Affiliation(s)
- Qianqian Wang
- School of Optics and Photonics, Beijing Institute of Technology, 100081 Beijing, China
- Key Laboratory of Photonic Information Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, 100081 Beijing, China
| | - Wenting Xiangli
- School of Optics and Photonics, Beijing Institute of Technology, 100081 Beijing, China
- Key Laboratory of Photonic Information Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, 100081 Beijing, China
| | - Xiaohong Chen
- Department of Otolaryngology Head and Neck Surgery, Beijing Tongren Hospital, Beijing 100730, China
| | - Jinghong Zhang
- Department of General Surgery, Beijing Tongren Hospital, Beijing 100730, China
| | - Geer Teng
- School of Optics and Photonics, Beijing Institute of Technology, 100081 Beijing, China
- Key Laboratory of Photonic Information Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, 100081 Beijing, China
| | - Xutai Cui
- School of Optics and Photonics, Beijing Institute of Technology, 100081 Beijing, China
- Key Laboratory of Photonic Information Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, 100081 Beijing, China
| | - Bushra Sana Idrees
- School of Optics and Photonics, Beijing Institute of Technology, 100081 Beijing, China
- Key Laboratory of Photonic Information Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, 100081 Beijing, China
| | - Kai Wei
- School of Optics and Photonics, Beijing Institute of Technology, 100081 Beijing, China
- Key Laboratory of Photonic Information Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, 100081 Beijing, China
| |
Collapse
|
3
|
Emil Tampu I, Maintz M, Koller D, Johansson K, Gimm O, Capitanio A, Eklund A, Haj-Hosseini N. Optical coherence tomography for thyroid pathology: 3D analysis of tissue microstructure. BIOMEDICAL OPTICS EXPRESS 2020; 11:4130-4149. [PMID: 32923033 PMCID: PMC7449746 DOI: 10.1364/boe.394296] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/10/2020] [Revised: 06/20/2020] [Accepted: 06/22/2020] [Indexed: 06/11/2023]
Abstract
To investigate the potential of optical coherence tomography (OCT) to distinguish between normal and pathologic thyroid tissue, 3D OCT images were acquired on ex vivo thyroid samples from adult subjects (n=22) diagnosed with a variety of pathologies. The follicular structure was analyzed in terms of count, size, density and sphericity. Results showed that OCT images highly agreed with the corresponding histopatology and the calculated parameters were representative of the follicular structure variation. The analysis of OCT volumes provides quantitative information that could make automatic classification possible. Thus, OCT can be beneficial for intraoperative surgical guidance or in the pathology assessment routine.
Collapse
Affiliation(s)
- Iulian Emil Tampu
- Department of Biomedical Engineering, Linköping University, Linköping 581 85, Sweden
| | - Michaela Maintz
- Department of Biomedical Engineering, Linköping University, Linköping 581 85, Sweden
| | - Daniela Koller
- Department of Biomedical Engineering, Linköping University, Linköping 581 85, Sweden
| | - Kenth Johansson
- Department of Surgery, Västervik Hospital and Örebro University Hospital, Västervik and Örebro, Sweden
| | - Oliver Gimm
- Department of Surgery, and Department of Biomedical and Clinical Sciences, Linköping University Hospital and Linköping University, Linköping 581 85, Sweden
| | - Arrigo Capitanio
- Department of Clinical Pathology, and Department of Biomedical and Clinical Sciences, Linköping University, Linköping 581 85, Sweden
| | - Anders Eklund
- Department of Biomedical Engineering, Linköping University, Linköping 581 85, Sweden
- Division of Statistics & Machine Learning, Department of Computer and Information Science, Linköping University, Linköping 581 83, Sweden
- Center for Medical Image Science and Visualization, Linköping University, Linköping 581 85, Sweden
| | - Neda Haj-Hosseini
- Department of Biomedical Engineering, Linköping University, Linköping 581 85, Sweden
| |
Collapse
|
4
|
Lerchenberger M, Al Arabi N, Gallwas JKS, Stepp H, Hallfeldt KKJ, Ladurner R. Intraoperative Near-Infrared Autofluorescence and Indocyanine Green Imaging to Identify Parathyroid Glands: A Comparison. Int J Endocrinol 2019; 2019:4687951. [PMID: 31662746 PMCID: PMC6778890 DOI: 10.1155/2019/4687951] [Citation(s) in RCA: 20] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/31/2019] [Accepted: 09/11/2019] [Indexed: 01/05/2023] Open
Abstract
OBJECTIVE To investigate the feasibility of near-infrared autofluorescence (AF) and indocyanine green (ICG) fluorescence to identify parathyroid glands intraoperatively. METHODS Fluorescence imaging was carried out during open parathyroid and thyroid surgery. After visual identification, parathyroid glands were exposed to near-infrared (NIR) light with a wavelength between 690 and 770 nm. The camera of the Storz® NIR/ICG endoscopic system used detects NIR light as a blue signal. Therefore, parathyroid AF was expected to be displayed in the blue color channel in contrast to the surrounding tissue. Following AF imaging, a bolus of 5 mg ICG was applied intravenously. ICG fluorescence was detected using the same NIR/ICG imaging system. Well-vascularized parathyroid glands were expected to show a strong fluorescence in contrast to surrounding lymphatic and adipose tissue. RESULTS We investigated 78 parathyroid glands from 50 patients. 64 parathyroid glands (82%) displayed AF showing the typical bluish violet color. 63 parathyroid glands (81%) showed a strong and persistent fluorescence after application of ICG. The sensitivity of identifying a parathyroid gland by AF was 82% (64 true positive and 14 false negative results), while ICG imaging showed a sensitivity of 81% (63 true positive and 15 false negative results). The Fisher exact test revealed no significant difference between both groups at p < 0.05. Neither lymph nodes nor adipose tissue revealed substantial AF or ICG fluorescence. CONCLUSION AF and ICG fluorescence reveal a high degree of sensitivity in identifying parathyroid glands. Further, ICG imaging facilitates the assessment of parathyroid perfusion. However, in the current setting both techniques are not suitable as screening tools to identify parathyroid glands at an early stage of the operation.
Collapse
Affiliation(s)
- Max Lerchenberger
- Department of Surgery, Ludwig Maximilians University Munich, Innenstadt Medical Campus, Nussbaumstrasse 20, 80336 Munich, Germany
| | - Norah Al Arabi
- Department of Surgery, Ludwig Maximilians University Munich, Innenstadt Medical Campus, Nussbaumstrasse 20, 80336 Munich, Germany
| | - Julia K. S. Gallwas
- Department of Obstetrics and Gynecology, Ludwig Maximilians University Munich, Maistr. 11, 80337 Munich, Germany
| | - Herbert Stepp
- Laser-Research Laboratory, LIFE-Center and Department of Urology, Ludwig Maximilians University Munich, Grosshadern Medical Campus, Feodor-Lynen-Str. 19, 81377 Munich, Germany
| | - Klaus K. J. Hallfeldt
- Department of Surgery, Ludwig Maximilians University Munich, Innenstadt Medical Campus, Nussbaumstrasse 20, 80336 Munich, Germany
| | - Roland Ladurner
- Department of Surgery, Ludwig Maximilians University Munich, Innenstadt Medical Campus, Nussbaumstrasse 20, 80336 Munich, Germany
| |
Collapse
|
5
|
Abbaci M, De Leeuw F, Breuskin I, Casiraghi O, Lakhdar AB, Ghanem W, Laplace-Builhé C, Hartl D. Parathyroid gland management using optical technologies during thyroidectomy or parathyroidectomy: A systematic review. Oral Oncol 2018; 87:186-196. [PMID: 30527238 DOI: 10.1016/j.oraloncology.2018.11.011] [Citation(s) in RCA: 51] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2018] [Accepted: 11/07/2018] [Indexed: 02/06/2023]
Abstract
New optical technologies enhancing localization or assessing viability of parathyroid glands (PG) during endocrine surgery have been reported in clinical studies. These technologies could become complementary to the surgeon's eyes and may improve surgical outcomes in thyroidectomy and parathyroidectomy. Here, we conducted a systematic review focusing on PG identification and functional assessment using optical methods to enhance surgery. A systematic literature review was performed using MEDLINE and Embase database. Two authors selected studies and extracted data; qualitative analysis was performed to summarize the characteristics of reported optical tools for thyroidectomy or parathyroidectomy. Identification and vascularisation of PG during surgery were evaluated. Clinical and biochemical outcomes were appraised when reported. Studies relating to parathyroidectomy or thyroidectomy combined with autofluorescence, fluorescent methylene blue, 5-aminolevulinic acid, indocyanine green (ICG), optical coherence tomography, laser speckle contrast imaging, dynamic optical contrast imaging and Raman spectroscopy were identified with MEDLINE and Embase. We included a total of 47 relevant articles with a total of 1615 patients enrolled. Each optical technique is described and appreciated related to its surgical purpose. Autofluorescence and ICG imaging of PG are the most widely reported optical technologies for identification and assessment of vascularisation of PG. Results are mainly based on observational studies and argue for the feasibility of both techniques in endocrine surgery but prospective randomized studies have not been performed. In vivo applications are still limited for the other methods and further investigations correlating these techniques with post-operative parathormone measurements are still needed before considering these technologies in clinical practice.
Collapse
Affiliation(s)
- Muriel Abbaci
- Gustave Roussy, Université Paris-Saclay, Plate-forme Imagerie et Cytométrie, UMS 23/3655, Villejuif F-94805, France; IR4M-UMR 8081, Université Paris-Saclay, Université Paris Sud, CNRS, Orsay F-91401, France.
| | - Frederic De Leeuw
- Gustave Roussy, Université Paris-Saclay, Plate-forme Imagerie et Cytométrie, UMS 23/3655, Villejuif F-94805, France
| | - Ingrid Breuskin
- Gustave Roussy, Université Paris-Saclay, Départements de Cancérologie et de Chirurgie Cervico-Faciale, Villejuif F-94805, France
| | - Odile Casiraghi
- Gustave Roussy, Université Paris-Saclay, Département de Biologie et Pathologie Médicale, Villejuif F-94805, France
| | - Aïcha Ben Lakhdar
- Gustave Roussy, Université Paris-Saclay, Département de Biologie et Pathologie Médicale, Villejuif F-94805, France
| | - Wahib Ghanem
- Gustave Roussy, Université Paris-Saclay, Départements de Cancérologie et de Chirurgie Cervico-Faciale, Villejuif F-94805, France
| | - Corinne Laplace-Builhé
- Gustave Roussy, Université Paris-Saclay, Plate-forme Imagerie et Cytométrie, UMS 23/3655, Villejuif F-94805, France; IR4M-UMR 8081, Université Paris-Saclay, Université Paris Sud, CNRS, Orsay F-91401, France
| | - Dana Hartl
- Gustave Roussy, Université Paris-Saclay, Départements de Cancérologie et de Chirurgie Cervico-Faciale, Villejuif F-94805, France
| |
Collapse
|
6
|
Hou F, Yu Y, Liang Y. Automatic identification of parathyroid in optical coherence tomography images. Lasers Surg Med 2017; 49:305-311. [PMID: 28129441 DOI: 10.1002/lsm.22622] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/23/2016] [Indexed: 01/15/2023]
Abstract
BACKGROUND AND OBJECTIVE The identification and preservation of parathyroid is a major problem in thyroid surgery. In order to solve this problem, optical coherence tomography was involved as a real-time, non-invasive high-resolution imaging technique. This study demonstrated an effective and fast method to distinguish parathyroid tissue from thyroid, lymph node, and adipose tissue in their ex vivo optical coherence tomography (OCT) images automatically. METHODS OCT images were obtained from parathyroid, thyroid, lymph node, and adipose tissue, respectively. A classification and an identification system based on texture features analysis and back propagation artificial neural network (BP-ANN) were established to classify the four types of tissue and identify each of the four types automatically. RESULTS A total of 248 OCT images were taken from 16 patients undergoing thyroidectomy. The accuracy of classification for parathyroid, thyroid, lymph node, and adipose were 99.21, 98.43, 97.65, and 98.43%, respectively. CONCLUSION The proposed automatic identification method is capable of distinguishing among parathyroid, thyroid, lymph, and adipose automatically and effectively. Compared with the identification results of human, it has a better accuracy and reliability. For identifying parathyroid from the other entities, it has a satisfying performance. Lasers Surg. Med. 49:305-311, 2017. © 2017 Wiley Periodicals, Inc.
Collapse
Affiliation(s)
- Fang Hou
- Institute of Modern Optics, Nankai University, Key Laboratory of Optical Information Science and Technology, Ministry of Education, Tianjin, 300071, China
| | - Yang Yu
- Department of Thyroid and Neck Tumor, Tianjin Medical University Cancer Institute & Hospital, Oncology Key Laboratory of Cancer Prevention & Therapy, Tianjin, 300060, China
| | - Yanmei Liang
- Institute of Modern Optics, Nankai University, Key Laboratory of Optical Information Science and Technology, Ministry of Education, Tianjin, 300071, China
| |
Collapse
|
7
|
[Optical coherence tomography for differentiation of parathyroid gland tissue]. Chirurg 2015; 87:416-22. [PMID: 26661948 DOI: 10.1007/s00104-015-0120-y] [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: 10/22/2022]
Abstract
BACKGROUND Optical coherence tomography (OCT) is a high-resolution imaging technique that allows the identification of microarchitectural features in real-time. OBJECTIVE Can OCT be used to differentiate parathyroid tissue from other cervical tissue entities? MATERIAL AND METHODS All investigations were carried out during cervical operations. Initially, ex vivo images were analyzed to define morphological imaging criteria for each tissue entity. These criteria were used to evaluate a first series of ex vivo images. In a second phase the practicability of the technique was investigated in vivo and in the third phase backscattering intensity measurements were analyzed employing linear discriminant analysis (LDA). RESULTS In the ex vivo series parathyroid tissue could be differentiated from other tissue entities with a sensitivity and specificity of 84 % and 94 %, respectively. Parathyroid tissue was correctly identified in the in vivo series in only 69.2 %. The analysis of backscattering intensity profiles employing LDA reliably distinguished between the different tissue types. CONCLUSION The OCT images displayed typical characteristics for each tissue entity. Due to technical problems in handling the probe the in vivo OCT images were of much poorer quality. Backscattering intensity measurements illustrated that OCT images provide an individual profile for each tissue entity independent of the defined morphological assessment criteria. The results show that OCT is fundamentally suitable for intraoperative differentiation of tissues.
Collapse
|