Analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methods
Background: Colorectal cancer has a high incidence rate worldwide, with over 1.8 million new cases and 880,792 deaths in 2018. Fortunately, its early detection significantly increases the survival rate, reaching a cure rate of 90% when diagnosed at a localized stage. Colonoscopy is the gold standard...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-01-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2021;volume=12;issue=1;spage=27;epage=27;aulast=Terradillos |
| _version_ | 1818229206945890304 |
|---|---|
| author | Elena Terradillos Cristina L Saratxaga Sara Mattana Riccardo Cicchi Francesco S Pavone Nagore Andraka Benjamin J Glover Nagore Arbide Jacques Velasco Mª Carmen Etxezarraga Artzai Picon |
| author_facet | Elena Terradillos Cristina L Saratxaga Sara Mattana Riccardo Cicchi Francesco S Pavone Nagore Andraka Benjamin J Glover Nagore Arbide Jacques Velasco Mª Carmen Etxezarraga Artzai Picon |
| author_sort | Elena Terradillos |
| collection | DOAJ |
| description | Background: Colorectal cancer has a high incidence rate worldwide, with over 1.8 million new cases and 880,792 deaths in 2018. Fortunately, its early detection significantly increases the survival rate, reaching a cure rate of 90% when diagnosed at a localized stage. Colonoscopy is the gold standard technique for detection and removal of colorectal lesions with potential to evolve into cancer. When polyps are found in a patient, the current procedure is their complete removal. However, in this process, gastroenterologists cannot assure complete resection and clean margins which are given by the histopathology analysis of the removed tissue, which is performed at laboratory. Aims: In this paper, we demonstrate the capabilities of multiphoton microscopy (MPM) technology to provide imaging biomarkers that can be extracted by deep learning techniques to identify malignant neoplastic colon lesions and distinguish them from healthy, hyperplastic, or benign neoplastic tissue, without the need for histopathological staining. Materials and Methods: To this end, we present a novel MPM public dataset containing 14,712 images obtained from 42 patients and grouped into 2 classes. A convolutional neural network is trained on this dataset and a spatially coherent predictions scheme is applied for performance improvement. Results: We obtained a sensitivity of 0.8228 ± 0.1575 and a specificity of 0.9114 ± 0.0814 on detecting malignant neoplastic lesions. We also validated this approach to estimate the self-confidence of the network on its own predictions, obtaining a mean sensitivity of 0.8697 and a mean specificity of 0.9524 with the 18.67% of the images classified as uncertain. Conclusions: This work lays the foundations for performing in vivo optical colon biopsies by combining this novel imaging technology together with deep learning algorithms, hence avoiding unnecessary polyp resection and allowing in situ diagnosis assessment. |
| first_indexed | 2024-12-12T10:14:55Z |
| format | Article |
| id | doaj.art-ac0514b75bb44851814576857ecf6182 |
| institution | Directory Open Access Journal |
| issn | 2153-3539 2153-3539 |
| language | English |
| last_indexed | 2024-12-12T10:14:55Z |
| publishDate | 2021-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-ac0514b75bb44851814576857ecf61822022-12-22T00:27:41ZengElsevierJournal of Pathology Informatics2153-35392153-35392021-01-01121272710.4103/jpi.jpi_113_20Analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methodsElena TerradillosCristina L SaratxagaSara MattanaRiccardo CicchiFrancesco S PavoneNagore AndrakaBenjamin J GloverNagore ArbideJacques VelascoMª Carmen EtxezarragaArtzai PiconBackground: Colorectal cancer has a high incidence rate worldwide, with over 1.8 million new cases and 880,792 deaths in 2018. Fortunately, its early detection significantly increases the survival rate, reaching a cure rate of 90% when diagnosed at a localized stage. Colonoscopy is the gold standard technique for detection and removal of colorectal lesions with potential to evolve into cancer. When polyps are found in a patient, the current procedure is their complete removal. However, in this process, gastroenterologists cannot assure complete resection and clean margins which are given by the histopathology analysis of the removed tissue, which is performed at laboratory. Aims: In this paper, we demonstrate the capabilities of multiphoton microscopy (MPM) technology to provide imaging biomarkers that can be extracted by deep learning techniques to identify malignant neoplastic colon lesions and distinguish them from healthy, hyperplastic, or benign neoplastic tissue, without the need for histopathological staining. Materials and Methods: To this end, we present a novel MPM public dataset containing 14,712 images obtained from 42 patients and grouped into 2 classes. A convolutional neural network is trained on this dataset and a spatially coherent predictions scheme is applied for performance improvement. Results: We obtained a sensitivity of 0.8228 ± 0.1575 and a specificity of 0.9114 ± 0.0814 on detecting malignant neoplastic lesions. We also validated this approach to estimate the self-confidence of the network on its own predictions, obtaining a mean sensitivity of 0.8697 and a mean specificity of 0.9524 with the 18.67% of the images classified as uncertain. Conclusions: This work lays the foundations for performing in vivo optical colon biopsies by combining this novel imaging technology together with deep learning algorithms, hence avoiding unnecessary polyp resection and allowing in situ diagnosis assessment.http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2021;volume=12;issue=1;spage=27;epage=27;aulast=Terradilloscolorectal polypsconvolutional neural networkdatasetmultiphoton microscopyoptical biopsy |
| spellingShingle | Elena Terradillos Cristina L Saratxaga Sara Mattana Riccardo Cicchi Francesco S Pavone Nagore Andraka Benjamin J Glover Nagore Arbide Jacques Velasco Mª Carmen Etxezarraga Artzai Picon Analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methods Journal of Pathology Informatics colorectal polyps convolutional neural network dataset multiphoton microscopy optical biopsy |
| title | Analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methods |
| title_full | Analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methods |
| title_fullStr | Analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methods |
| title_full_unstemmed | Analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methods |
| title_short | Analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methods |
| title_sort | analysis on the characterization of multiphoton microscopy images for malignant neoplastic colon lesion detection under deep learning methods |
| topic | colorectal polyps convolutional neural network dataset multiphoton microscopy optical biopsy |
| url | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2021;volume=12;issue=1;spage=27;epage=27;aulast=Terradillos |
| work_keys_str_mv | AT elenaterradillos analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT cristinalsaratxaga analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT saramattana analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT riccardocicchi analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT francescospavone analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT nagoreandraka analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT benjaminjglover analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT nagorearbide analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT jacquesvelasco analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT macarmenetxezarraga analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods AT artzaipicon analysisonthecharacterizationofmultiphotonmicroscopyimagesformalignantneoplasticcolonlesiondetectionunderdeeplearningmethods |