PMID- 35719939
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20220716
IS  - 2234-943X (Print)
IS  - 2234-943X (Electronic)
IS  - 2234-943X (Linking)
VI  - 12
DP  - 2022
TI  - Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to 
      White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic 
      Images.
PG  - 900451
LID - 10.3389/fonc.2022.900451 [doi]
LID - 900451
AB  - INTRODUCTION: Narrow Band Imaging (NBI) is an endoscopic visualization technique 
      useful for upper aero-digestive tract (UADT) cancer detection and margins 
      evaluation. However, NBI analysis is strongly operator-dependent and requires 
      high expertise, thus limiting its wider implementation. Recently, artificial 
      intelligence (AI) has demonstrated potential for applications in UADT 
      videoendoscopy. Among AI methods, deep learning algorithms, and especially 
      convolutional neural networks (CNNs), are particularly suitable for delineating 
      cancers on videoendoscopy. This study is aimed to develop a CNN for automatic 
      semantic segmentation of UADT cancer on endoscopic images. MATERIALS AND METHODS: 
      A dataset of white light and NBI videoframes of laryngeal squamous cell carcinoma 
      (LSCC) was collected and manually annotated. A novel DL segmentation model 
      (SegMENT) was designed. SegMENT relies on DeepLabV3+ CNN architecture, modified 
      using Xception as a backbone and incorporating ensemble features from other CNNs. 
      The performance of SegMENT was compared to state-of-the-art CNNs (UNet, ResUNet, 
      and DeepLabv3). SegMENT was then validated on two external datasets of NBI images 
      of oropharyngeal (OPSCC) and oral cavity SCC (OSCC) obtained from a previously 
      published study. The impact of in-domain transfer learning through an ensemble 
      technique was evaluated on the external datasets. RESULTS: 219 LSCC patients were 
      retrospectively included in the study. A total of 683 videoframes composed the 
      LSCC dataset, while the external validation cohorts of OPSCC and OCSCC contained 
      116 and 102 images. On the LSCC dataset, SegMENT outperformed the other DL 
      models, obtaining the following median values: 0.68 intersection over union 
      (IoU), 0.81 dice similarity coefficient (DSC), 0.95 recall, 0.78 precision, 0.97 
      accuracy. For the OCSCC and OPSCC datasets, results were superior compared to 
      previously published data: the median performance metrics were, respectively, 
      improved as follows: DSC=10.3% and 11.9%, recall=15.0% and 5.1%, precision=17.0% 
      and 14.7%, accuracy=4.1% and 10.3%. CONCLUSION: SegMENT achieved promising 
      performances, showing that automatic tumor segmentation in endoscopic images is 
      feasible even within the highly heterogeneous and complex UADT environment. 
      SegMENT outperformed the previously published results on the external validation 
      cohorts. The model demonstrated potential for improved detection of early tumors, 
      more precise biopsies, and better selection of resection margins.
CI  - Copyright (c) 2022 Azam, Sampieri, Ioppi, Benzi, Giordano, De Vecchi, Campagnari, 
      Li, Guastini, Paderno, Moccia, Piazza, Mattos and Peretti.
FAU - Azam, Muhammad Adeel
AU  - Azam MA
AD  - Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy.
FAU - Sampieri, Claudio
AU  - Sampieri C
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, IRCCS Ospedale Policlinico 
      San Martino, Genoa, Italy.
AD  - Department of Surgical Sciences and Integrated Diagnostics (DISC), University of 
      Genoa, Genoa, Italy.
FAU - Ioppi, Alessandro
AU  - Ioppi A
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, IRCCS Ospedale Policlinico 
      San Martino, Genoa, Italy.
AD  - Department of Surgical Sciences and Integrated Diagnostics (DISC), University of 
      Genoa, Genoa, Italy.
FAU - Benzi, Pietro
AU  - Benzi P
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, IRCCS Ospedale Policlinico 
      San Martino, Genoa, Italy.
AD  - Department of Surgical Sciences and Integrated Diagnostics (DISC), University of 
      Genoa, Genoa, Italy.
FAU - Giordano, Giorgio Gregory
AU  - Giordano GG
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, IRCCS Ospedale Policlinico 
      San Martino, Genoa, Italy.
AD  - Department of Surgical Sciences and Integrated Diagnostics (DISC), University of 
      Genoa, Genoa, Italy.
FAU - De Vecchi, Marta
AU  - De Vecchi M
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, IRCCS Ospedale Policlinico 
      San Martino, Genoa, Italy.
AD  - Department of Surgical Sciences and Integrated Diagnostics (DISC), University of 
      Genoa, Genoa, Italy.
FAU - Campagnari, Valentina
AU  - Campagnari V
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, IRCCS Ospedale Policlinico 
      San Martino, Genoa, Italy.
AD  - Department of Surgical Sciences and Integrated Diagnostics (DISC), University of 
      Genoa, Genoa, Italy.
FAU - Li, Shunlei
AU  - Li S
AD  - Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy.
FAU - Guastini, Luca
AU  - Guastini L
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, IRCCS Ospedale Policlinico 
      San Martino, Genoa, Italy.
AD  - Department of Surgical Sciences and Integrated Diagnostics (DISC), University of 
      Genoa, Genoa, Italy.
FAU - Paderno, Alberto
AU  - Paderno A
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, ASST Spedali Civili of 
      Brescia, Brescia, Italy.
AD  - Department of Medical and Surgical Specialties, Radiological Sciences, and Public 
      Health, University of Brescia, Brescia, Italy.
FAU - Moccia, Sara
AU  - Moccia S
AD  - The BioRobotics Institute and Department of Excellence in Robotics and AI, Scuola 
      Superiore Sant'Anna, Pisa, Italy.
FAU - Piazza, Cesare
AU  - Piazza C
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, ASST Spedali Civili of 
      Brescia, Brescia, Italy.
AD  - Department of Medical and Surgical Specialties, Radiological Sciences, and Public 
      Health, University of Brescia, Brescia, Italy.
FAU - Mattos, Leonardo S
AU  - Mattos LS
AD  - Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy.
FAU - Peretti, Giorgio
AU  - Peretti G
AD  - Unit of Otorhinolaryngology - Head and Neck Surgery, IRCCS Ospedale Policlinico 
      San Martino, Genoa, Italy.
AD  - Department of Surgical Sciences and Integrated Diagnostics (DISC), University of 
      Genoa, Genoa, Italy.
LA  - eng
PT  - Journal Article
DEP - 20220601
PL  - Switzerland
TA  - Front Oncol
JT  - Frontiers in oncology
JID - 101568867
PMC - PMC9198427
OTO - NOTNLM
OT  - computer vision
OT  - endoscopy
OT  - laryngoscopy
OT  - larynx cancer
OT  - machine learning
OT  - oral cancer
OT  - oropharynx cancer
OT  - otorhinolaryngology
COIS- The authors declare that the research was conducted in the absence of any 
      commercial or financial relationships that could be construed as a potential 
      conflict of interest.
EDAT- 2022/06/21 06:00
MHDA- 2022/06/21 06:01
PMCR- 2022/01/01
CRDT- 2022/06/20 03:36
PHST- 2022/03/20 00:00 [received]
PHST- 2022/04/26 00:00 [accepted]
PHST- 2022/06/20 03:36 [entrez]
PHST- 2022/06/21 06:00 [pubmed]
PHST- 2022/06/21 06:01 [medline]
PHST- 2022/01/01 00:00 [pmc-release]
AID - 10.3389/fonc.2022.900451 [doi]
PST - epublish
SO  - Front Oncol. 2022 Jun 1;12:900451. doi: 10.3389/fonc.2022.900451. eCollection 
      2022.