Endoscopic Tactile Capsule for Non-Polypoid Colorectal Tumour Detection. Camboni, D., Massari, L., Chiurazzi, M., Calio, R., Alcaide, J. O., D'Abbraccio, J., Mazomenos, E., Stoyanov, D., Menciassi, A., Carrozza, M. C., Dario, P., Oddo, C. M., & Ciuti, G. IEEE Transactions on Medical Robotics and Bionics, 3(1):64–73, February, 2021. ZSCC: NoCitationData[s0]![Endoscopic Tactile Capsule for Non-Polypoid Colorectal Tumour Detection [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Objective: In this work, an endoscopic tactile robotic capsule embedding miniaturized MEMS force sensors is presented. The capsule is conceived to provide automatic palpation of non-polypoid colorectal tumours during colonoscopic procedures, since they are characterized by a high degree of dysplasia, higher invasiveness and lower detection rates with respect to polyps. Methods: A first test was performed employing a silicone phantom that embedded a set of inclusions with variable hardness and curvature. In this scenario, a hardness-based classification was implemented, demonstrating detection robustness to curvature variation. By following a comparison of several well-known supervised classification algorithms, we chose a weighted 3-nearest neighbor classifier to detect the inclusions. We also introduced a bias force normalization model in order to make different acquisition sets consistent. The parameters of this model were chosen through a particle swarm optimization method. Additionally, an ex-vivo test was performed to assess the capsule detection performance when magnetically driven along a colonic tissue. An external permanent magnet positioned at the end-effector of an anthropomorphic robotic arm was used to drive the capsule. In this framework, lumps were identified as voltage peaks with a prominence depending on the total magnetic force applied to the capsule. Results: In a 94 % accuracy in hardness classification is achieved, while a 100% accuracy is obtained for the lump detection within a tolerance of 5 mm from the central path described by the capsule. Conclusion: In the real application scenario, we foresee our device aiding the physician to detect tumorous tissues.
@article{camboni_endoscopic_2021,
title = {Endoscopic {Tactile} {Capsule} for {Non}-{Polypoid} {Colorectal} {Tumour} {Detection}},
volume = {3},
issn = {2576-3202},
url = {https://ieeexplore.ieee.org/document/9253531/},
doi = {10/gm97w8},
abstract = {Objective: In this work, an endoscopic tactile robotic capsule embedding miniaturized MEMS force sensors is presented. The capsule is conceived to provide automatic palpation of non-polypoid colorectal tumours during colonoscopic procedures, since they are characterized by a high degree of dysplasia, higher invasiveness and lower detection rates with respect to polyps. Methods: A first test was performed employing a silicone phantom that embedded a set of inclusions with variable hardness and curvature. In this scenario, a hardness-based classification was implemented, demonstrating detection robustness to curvature variation. By following a comparison of several well-known supervised classification algorithms, we chose a weighted 3-nearest neighbor classifier to detect the inclusions. We also introduced a bias force normalization model in order to make different acquisition sets consistent. The parameters of this model were chosen through a particle swarm optimization method. Additionally, an ex-vivo test was performed to assess the capsule detection performance when magnetically driven along a colonic tissue. An external permanent magnet positioned at the end-effector of an anthropomorphic robotic arm was used to drive the capsule. In this framework, lumps were identified as voltage peaks with a prominence depending on the total magnetic force applied to the capsule. Results: In a 94 \% accuracy in hardness classification is achieved, while a 100\% accuracy is obtained for the lump detection within a tolerance of 5 mm from the central path described by the capsule. Conclusion: In the real application scenario, we foresee our device aiding the physician to detect tumorous tissues.},
language = {en},
number = {1},
urldate = {2021-11-02},
journal = {IEEE Transactions on Medical Robotics and Bionics},
author = {Camboni, Domenico and Massari, Luca and Chiurazzi, Marcello and Calio, Renato and Alcaide, Joan Ortega and D'Abbraccio, Jessica and Mazomenos, Evangelos and Stoyanov, Danail and Menciassi, Arianna and Carrozza, Maria Chiara and Dario, Paolo and Oddo, Calogero Maria and Ciuti, Gastone},
month = feb,
year = {2021},
note = {ZSCC: NoCitationData[s0]},
pages = {64--73},
}
Downloads: 0
{"_id":"Q3zyffgpnL4kKPTkh","bibbaseid":"camboni-massari-chiurazzi-calio-alcaide-dabbraccio-mazomenos-stoyanov-etal-endoscopictactilecapsulefornonpolypoidcolorectaltumourdetection-2021","author_short":["Camboni, D.","Massari, L.","Chiurazzi, M.","Calio, R.","Alcaide, J. O.","D'Abbraccio, J.","Mazomenos, E.","Stoyanov, D.","Menciassi, A.","Carrozza, M. C.","Dario, P.","Oddo, C. M.","Ciuti, G."],"bibdata":{"bibtype":"article","type":"article","title":"Endoscopic Tactile Capsule for Non-Polypoid Colorectal Tumour Detection","volume":"3","issn":"2576-3202","url":"https://ieeexplore.ieee.org/document/9253531/","doi":"10/gm97w8","abstract":"Objective: In this work, an endoscopic tactile robotic capsule embedding miniaturized MEMS force sensors is presented. The capsule is conceived to provide automatic palpation of non-polypoid colorectal tumours during colonoscopic procedures, since they are characterized by a high degree of dysplasia, higher invasiveness and lower detection rates with respect to polyps. Methods: A first test was performed employing a silicone phantom that embedded a set of inclusions with variable hardness and curvature. In this scenario, a hardness-based classification was implemented, demonstrating detection robustness to curvature variation. By following a comparison of several well-known supervised classification algorithms, we chose a weighted 3-nearest neighbor classifier to detect the inclusions. We also introduced a bias force normalization model in order to make different acquisition sets consistent. The parameters of this model were chosen through a particle swarm optimization method. Additionally, an ex-vivo test was performed to assess the capsule detection performance when magnetically driven along a colonic tissue. An external permanent magnet positioned at the end-effector of an anthropomorphic robotic arm was used to drive the capsule. In this framework, lumps were identified as voltage peaks with a prominence depending on the total magnetic force applied to the capsule. Results: In a 94 % accuracy in hardness classification is achieved, while a 100% accuracy is obtained for the lump detection within a tolerance of 5 mm from the central path described by the capsule. Conclusion: In the real application scenario, we foresee our device aiding the physician to detect tumorous tissues.","language":"en","number":"1","urldate":"2021-11-02","journal":"IEEE Transactions on Medical Robotics and Bionics","author":[{"propositions":[],"lastnames":["Camboni"],"firstnames":["Domenico"],"suffixes":[]},{"propositions":[],"lastnames":["Massari"],"firstnames":["Luca"],"suffixes":[]},{"propositions":[],"lastnames":["Chiurazzi"],"firstnames":["Marcello"],"suffixes":[]},{"propositions":[],"lastnames":["Calio"],"firstnames":["Renato"],"suffixes":[]},{"propositions":[],"lastnames":["Alcaide"],"firstnames":["Joan","Ortega"],"suffixes":[]},{"propositions":[],"lastnames":["D'Abbraccio"],"firstnames":["Jessica"],"suffixes":[]},{"propositions":[],"lastnames":["Mazomenos"],"firstnames":["Evangelos"],"suffixes":[]},{"propositions":[],"lastnames":["Stoyanov"],"firstnames":["Danail"],"suffixes":[]},{"propositions":[],"lastnames":["Menciassi"],"firstnames":["Arianna"],"suffixes":[]},{"propositions":[],"lastnames":["Carrozza"],"firstnames":["Maria","Chiara"],"suffixes":[]},{"propositions":[],"lastnames":["Dario"],"firstnames":["Paolo"],"suffixes":[]},{"propositions":[],"lastnames":["Oddo"],"firstnames":["Calogero","Maria"],"suffixes":[]},{"propositions":[],"lastnames":["Ciuti"],"firstnames":["Gastone"],"suffixes":[]}],"month":"February","year":"2021","note":"ZSCC: NoCitationData[s0]","pages":"64–73","bibtex":"@article{camboni_endoscopic_2021,\n\ttitle = {Endoscopic {Tactile} {Capsule} for {Non}-{Polypoid} {Colorectal} {Tumour} {Detection}},\n\tvolume = {3},\n\tissn = {2576-3202},\n\turl = {https://ieeexplore.ieee.org/document/9253531/},\n\tdoi = {10/gm97w8},\n\tabstract = {Objective: In this work, an endoscopic tactile robotic capsule embedding miniaturized MEMS force sensors is presented. The capsule is conceived to provide automatic palpation of non-polypoid colorectal tumours during colonoscopic procedures, since they are characterized by a high degree of dysplasia, higher invasiveness and lower detection rates with respect to polyps. Methods: A first test was performed employing a silicone phantom that embedded a set of inclusions with variable hardness and curvature. In this scenario, a hardness-based classification was implemented, demonstrating detection robustness to curvature variation. By following a comparison of several well-known supervised classification algorithms, we chose a weighted 3-nearest neighbor classifier to detect the inclusions. We also introduced a bias force normalization model in order to make different acquisition sets consistent. The parameters of this model were chosen through a particle swarm optimization method. Additionally, an ex-vivo test was performed to assess the capsule detection performance when magnetically driven along a colonic tissue. An external permanent magnet positioned at the end-effector of an anthropomorphic robotic arm was used to drive the capsule. In this framework, lumps were identified as voltage peaks with a prominence depending on the total magnetic force applied to the capsule. Results: In a 94 \\% accuracy in hardness classification is achieved, while a 100\\% accuracy is obtained for the lump detection within a tolerance of 5 mm from the central path described by the capsule. Conclusion: In the real application scenario, we foresee our device aiding the physician to detect tumorous tissues.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2021-11-02},\n\tjournal = {IEEE Transactions on Medical Robotics and Bionics},\n\tauthor = {Camboni, Domenico and Massari, Luca and Chiurazzi, Marcello and Calio, Renato and Alcaide, Joan Ortega and D'Abbraccio, Jessica and Mazomenos, Evangelos and Stoyanov, Danail and Menciassi, Arianna and Carrozza, Maria Chiara and Dario, Paolo and Oddo, Calogero Maria and Ciuti, Gastone},\n\tmonth = feb,\n\tyear = {2021},\n\tnote = {ZSCC: NoCitationData[s0]},\n\tpages = {64--73},\n}\n\n\n\n","author_short":["Camboni, D.","Massari, L.","Chiurazzi, M.","Calio, R.","Alcaide, J. O.","D'Abbraccio, J.","Mazomenos, E.","Stoyanov, D.","Menciassi, A.","Carrozza, M. C.","Dario, P.","Oddo, C. M.","Ciuti, G."],"key":"camboni_endoscopic_2021","id":"camboni_endoscopic_2021","bibbaseid":"camboni-massari-chiurazzi-calio-alcaide-dabbraccio-mazomenos-stoyanov-etal-endoscopictactilecapsulefornonpolypoidcolorectaltumourdetection-2021","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/9253531/"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/nikitaj.greenidge","dataSources":["uXDRqZDxuAtbLLS2T"],"keywords":[],"search_terms":["endoscopic","tactile","capsule","non","polypoid","colorectal","tumour","detection","camboni","massari","chiurazzi","calio","alcaide","d'abbraccio","mazomenos","stoyanov","menciassi","carrozza","dario","oddo","ciuti"],"title":"Endoscopic Tactile Capsule for Non-Polypoid Colorectal Tumour Detection","year":2021}