1
|
Anichini G, Leiloglou M, Hu Z, O'Neill K, Daniel Elson. Hyperspectral and multispectral imaging in neurosurgery: a systematic literature review and meta-analysis. EUROPEAN JOURNAL OF SURGICAL ONCOLOGY 2024:108293. [PMID: 38658267 DOI: 10.1016/j.ejso.2024.108293] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2023] [Revised: 01/21/2024] [Accepted: 03/20/2024] [Indexed: 04/26/2024]
Abstract
INTRODUCTION The neuro-surgical community is witnessing a rising interest for surgical application of multispectral/hyperspectral imaging. Several potential technical applications of this optical imaging are reported, but the set-up is variable and so are the processing methods. We present a systematic review of the relevant literature on the topic. MATERIALS AND METHODS A literature search based on the PRISMA principles was performed on PubMed, SCOPUS, and Web of Science, using MESH terms and Boolean operators. Papers regarding intra-operative in-vivo application of multispectral and/or hyperspectral imaging in humans during neurosurgical procedures were included. Papers reporting technologies related to radiological applications were excluded. A meta-analysis on the performance metrics was also conducted. RESULTS Our search string retrieved 20 papers. The main applications of optical imaging during neurosurgery concern tumour detection and improvement of the extent of resection (15 papers) or visualization of perfusion changes during neuro-oncology or neuro-vascular surgery (5 papers). All the retrieved articles were pilot studies, proof of concepts, or case reports, with limited number of patients recruited. Sensitivity, specificity, and accuracy were promising in most of the reports, but the metanalysis showed heterogeneous approaches and results among studies. CONCLUSIONS The present review shows that several approaches are currently being tested to integrate hyperspectral imaging in neurosurgery, but most of the studies reported a limited pool of patients, with different approaches to data collection and analysis. Further studies on larger cohorts of patients are therefore desirable to fully explore the potential of this imaging technique.
Collapse
Affiliation(s)
- Giulio Anichini
- Department of Brain Sciences, Imperial College of London, United Kingdom; Department of Neurosurgery, Neuroscience, Imperial College Healthcare NHS Trust, United Kingdom.
| | - Maria Leiloglou
- Department of Surgery and Cancer, Imperial College of London, United Kingdom; The Hamlyn Centre, Imperial College of London, United Kingdom
| | - Zepeng Hu
- Department of Surgery and Cancer, Imperial College of London, United Kingdom; The Hamlyn Centre, Imperial College of London, United Kingdom
| | - Kevin O'Neill
- Department of Brain Sciences, Imperial College of London, United Kingdom; Department of Neurosurgery, Neuroscience, Imperial College Healthcare NHS Trust, United Kingdom
| | - Daniel Elson
- Department of Surgery and Cancer, Imperial College of London, United Kingdom; The Hamlyn Centre, Imperial College of London, United Kingdom
| |
Collapse
|
2
|
Lindholm V, Annala L, Koskenmies S, Pitkänen S, Isoherranen K, Järvinen A, Jeskanen L, Pölönen I, Ranki A, Raita‐Hakola A, Salmivuori M. Discriminating basal cell carcinoma and Bowen's disease from benign skin lesions with a 3D hyperspectral imaging system and convolutional neural networks. Skin Res Technol 2024; 30:e13677. [PMID: 38558486 PMCID: PMC10982671 DOI: 10.1111/srt.13677] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2023] [Accepted: 02/12/2024] [Indexed: 04/04/2024]
Affiliation(s)
- Vivian Lindholm
- Department of Dermatology and AllergologyUniversity of Helsinki and Helsinki University HospitalHelsinkiFinland
| | - Leevi Annala
- Faculty of Information TechnologyUniversity of JyväskyläJyväskyläFinland
- Department of Food and NutritionUniversity of HelsinkiHelsinkiFinland
- Department of Computer ScienceUniversity of HelsinkiHelsinkiFinland
| | - Sari Koskenmies
- Department of Dermatology and AllergologyUniversity of Helsinki and Helsinki University HospitalHelsinkiFinland
| | - Sari Pitkänen
- Department of Dermatology and AllergologyUniversity of Helsinki and Helsinki University HospitalHelsinkiFinland
| | - Kirsi Isoherranen
- Department of Dermatology and AllergologyUniversity of Helsinki and Helsinki University HospitalHelsinkiFinland
| | - Anna Järvinen
- Department of Dermatology and AllergologyUniversity of Helsinki and Helsinki University HospitalHelsinkiFinland
| | - Leila Jeskanen
- Department of Dermatology and AllergologyUniversity of Helsinki and Helsinki University HospitalHelsinkiFinland
| | - Ilkka Pölönen
- Faculty of Information TechnologyUniversity of JyväskyläJyväskyläFinland
| | - Annamari Ranki
- Department of Dermatology and AllergologyUniversity of Helsinki and Helsinki University HospitalHelsinkiFinland
| | | | - Mari Salmivuori
- Department of Dermatology and AllergologyUniversity of Helsinki and Helsinki University HospitalHelsinkiFinland
| |
Collapse
|
3
|
PAOLI J, PÖLÖNEN I, SALMIVUORI M, RÄSÄNEN J, ZAAR O, POLESIE S, KOSKENMIES S, PITKÄNEN S, ÖVERMARK M, ISOHERRANEN K, JUTEAU S, RANKI A, GRÖNROOS M, NEITTAANMÄKI N. Hyperspectral Imaging for Non-invasive Diagnostics of Melanocytic Lesions. Acta Derm Venereol 2022; 102:adv00815. [PMID: 36281811 PMCID: PMC9811300 DOI: 10.2340/actadv.v102.2045] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022] Open
Abstract
Malignant melanoma poses a clinical diagnostic problem, since a large number of benign lesions are excised to find a single melanoma. This study assessed the accuracy of a novel non-invasive diagnostic technology, hyperspectral imaging, for melanoma detection. Lesions were imaged prior to excision and histopathological analysis. A deep neural network algorithm was trained twice to distinguish between histopathologically verified malignant and benign melanocytic lesions and to classify the separate subgroups. Furthermore, 2 different approaches were used: a majority vote classification and a pixel-wise classification. The study included 325 lesions from 285 patients. Of these, 74 were invasive melanoma, 88 melanoma in situ, 115 dysplastic naevi, and 48 non-dysplastic naevi. The study included a training set of 358,800 pixels and a validation set of 7,313 pixels, which was then tested with a training set of 24,375 pixels. The majority vote classification achieved high overall sensitivity of 95% and a specificity of 92% (95% confidence interval (95% CI) 0.024-0.029) in differentiating malignant from benign lesions. In the pixel-wise classification, the overall sensitivity and specificity were both 82% (95% CI 0.005-0.005). When divided into 4 subgroups, the diagnostic accuracy was lower. Hyperspectral imaging provides high sensitivity and specificity in distinguishing between naevi and melanoma. This novel method still needs further validation.
Collapse
Affiliation(s)
- John PAOLI
- Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg,Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Ilkka PÖLÖNEN
- Faculty of Information Technology, University of Jyväskylä
| | - Mari SALMIVUORI
- Department of Dermatology and Allergology, Päijät-Häme Social and Health Care Group, Lahti,Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, Helsinki
| | - Janne RÄSÄNEN
- Department of Dermatology and Allergology, Päijät-Häme Social and Health Care Group, Lahti,Department of Dermatology, Tampere University Hospital and Faculty of Medicine and Medical technology, Tampere University, Tampere
| | - Oscar ZAAR
- Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg,Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Sam POLESIE
- Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg,Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Sari KOSKENMIES
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, Helsinki
| | - Sari PITKÄNEN
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, Helsinki
| | - Meri ÖVERMARK
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, Helsinki
| | - Kirsi ISOHERRANEN
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, Helsinki
| | - Susanna JUTEAU
- Department of Pathology, University of Helsinki and HUSLAB, Helsinki, Finland
| | - Annamari RANKI
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, Helsinki
| | - Mari GRÖNROOS
- Department of Dermatology and Allergology, Päijät-Häme Social and Health Care Group, Lahti
| | - Noora NEITTAANMÄKI
- Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg,Department of Laboratory Medicine, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg,Department of Clinical Pathology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| |
Collapse
|
4
|
Lindholm V, Raita-Hakola AM, Annala L, Salmivuori M, Jeskanen L, Saari H, Koskenmies S, Pitkänen S, Pölönen I, Isoherranen K, Ranki A. Differentiating Malignant from Benign Pigmented or Non-Pigmented Skin Tumours-A Pilot Study on 3D Hyperspectral Imaging of Complex Skin Surfaces and Convolutional Neural Networks. J Clin Med 2022; 11:jcm11071914. [PMID: 35407522 PMCID: PMC8999463 DOI: 10.3390/jcm11071914] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2022] [Accepted: 03/28/2022] [Indexed: 02/08/2023] Open
Abstract
Several optical imaging techniques have been developed to ease the burden of skin cancer disease on our health care system. Hyperspectral images can be used to identify biological tissues by their diffuse reflected spectra. In this second part of a three-phase pilot study, we used a novel hand-held SICSURFIS Spectral Imager with an adaptable field of view and target-wise selectable wavelength channels to provide detailed spectral and spatial data for lesions on complex surfaces. The hyperspectral images (33 wavelengths, 477–891 nm) provided photometric data through individually controlled illumination modules, enabling convolutional networks to utilise spectral, spatial, and skin-surface models for the analyses. In total, 42 lesions were studied: 7 melanomas, 13 pigmented and 7 intradermal nevi, 10 basal cell carcinomas, and 5 squamous cell carcinomas. All lesions were excised for histological analyses. A pixel-wise analysis provided map-like images and classified pigmented lesions with a sensitivity of 87% and a specificity of 93%, and 79% and 91%, respectively, for non-pigmented lesions. A majority voting analysis, which provided the most probable lesion diagnosis, diagnosed 41 of 42 lesions correctly. This pilot study indicates that our non-invasive hyperspectral imaging system, which involves shape and depth data analysed by convolutional neural networks, is feasible for differentiating between malignant and benign pigmented and non-pigmented skin tumours, even on complex skin surfaces.
Collapse
Affiliation(s)
- Vivian Lindholm
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, 00290 Helsinki, Finland; (M.S.); (L.J.); (S.K.); (S.P.); (K.I.); (A.R.)
- Correspondence: (V.L.); (A.-M.R.-H.); Tel.: +358-9471-86355 (V.L.)
| | - Anna-Maria Raita-Hakola
- Faculty of Information Technology, University of Jyväskylä, 40100 Jyväskylä, Finland; (L.A.); (I.P.)
- Correspondence: (V.L.); (A.-M.R.-H.); Tel.: +358-9471-86355 (V.L.)
| | - Leevi Annala
- Faculty of Information Technology, University of Jyväskylä, 40100 Jyväskylä, Finland; (L.A.); (I.P.)
| | - Mari Salmivuori
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, 00290 Helsinki, Finland; (M.S.); (L.J.); (S.K.); (S.P.); (K.I.); (A.R.)
| | - Leila Jeskanen
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, 00290 Helsinki, Finland; (M.S.); (L.J.); (S.K.); (S.P.); (K.I.); (A.R.)
| | - Heikki Saari
- VTT Technical Research Centre of Finland, 02150 Espoo, Finland;
| | - Sari Koskenmies
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, 00290 Helsinki, Finland; (M.S.); (L.J.); (S.K.); (S.P.); (K.I.); (A.R.)
| | - Sari Pitkänen
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, 00290 Helsinki, Finland; (M.S.); (L.J.); (S.K.); (S.P.); (K.I.); (A.R.)
| | - Ilkka Pölönen
- Faculty of Information Technology, University of Jyväskylä, 40100 Jyväskylä, Finland; (L.A.); (I.P.)
| | - Kirsi Isoherranen
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, 00290 Helsinki, Finland; (M.S.); (L.J.); (S.K.); (S.P.); (K.I.); (A.R.)
| | - Annamari Ranki
- Department of Dermatology and Allergology, University of Helsinki and Helsinki University Hospital, 00290 Helsinki, Finland; (M.S.); (L.J.); (S.K.); (S.P.); (K.I.); (A.R.)
| |
Collapse
|