Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Clinical evaluation of PolyDeep, a computer-aided detection system: a multicenter randomized tandem colonoscopy trial

  • Davila Piñón, Pedro
  • Díez Martín, Astrid Irene
  • Nogueira Rodríguez, Alba
  • Domínguez Carbajales, Rubén
  • Fernández Riverola, Florentino
  • Zarraquiños, Sara
  • de Castro, Luisa
  • Herrero, Jesús
  • Fernández, Nereida
  • Vega, Pablo
  • Remedios, David
  • Martínez, Alfonso
  • Puga, Manuel
  • Alonso, Sara
  • Pin, Noel
  • García Morales, Natalia
  • Rivas, Laura
  • Ledo, Alejandro
  • Macenlle, Ramiro
  • Cid, Lucia
  • Rodríguez, Antonio
  • Soto, Santiago
  • Baiocchi, Franco
  • Pérez Medrano, Indhira
  • Sánchez, Eloy
  • González Peña, Daniel
  • Reboiro Jato, Miguel
  • López Fernández, Hugo
  • Cubiella, Joaquín
Background/Objectives: Computer-aided detection (CADe) systems are increasingly used in endoscopy to enhance lesion recognition. PolyDeep is a CADe/x tool previously assessed in an observational study. The aim of our study is to determine if PolyDeep-assisted colonoscopy reduces the adenoma miss rate (AMR) compared with conventional colonoscopy. Methods: We carried out a multicenter randomized controlled trial with a tandem colonoscopy design in participants from a colorectal cancer screening program (positive fecal immunochemical test-FIT or surveillance). Expert endoscopists performed all colonoscopies, and patients were allocated to groups by a computer-generated sequence. The primary endpoint was AMR; secondary endpoints included polyp miss rate (PMR), serrated lesion miss rate (SLMR) and advanced polyp miss rate (APMR). Results: From May to November 2023, we recruited 260 patients and excluded 20, leaving 240 for analysis. Baseline characteristics were balanced between groups (62.1% male; mean age 62.3 ± 6.5 years; 65.8% FIT-positive; mean first withdrawal time 13:38 ± 08:07 min; mean second withdrawal time 07:50 ± 03:38 min; lesion detection rate 76.6%; mean polyps per patient 3.4 ± 3.1). We did not find statistically significant differences between PolyDeep-assisted and conventional colonoscopy groups in AMR (21.3% vs. 18.1%, p = 0.5), PMR (21.8% vs. 20.3%, p = 0.7), SLMR (23.4% vs. 25.6%, p = 0.9) or APMR (7.3% vs. 11.3%, p = 0.5). In the subgroup analysis according to indication, we did not find any statistically significant differences. Conclusions: In the context of a CRC screening program, PolyDeep-assisted colonoscopy did not reduce AMR., Agencia Estatal de Investigación | Ref. DPI2017-87494, Agencia Estatal de Investigación | Ref. PDC2021-121644-I00, Instituto de Salud Carlos III | Ref. PI21/01771, Instituto de Salud Carlos III | Ref. CD22/00087, Instituto de Salud Carlos III | Ref. INT22/00009, Instituto de Salud Carlos III | Ref. FI22/00203, Xunta de Galicia | Ref. ED431G 2019/06, Xunta de Galicia | Ref. ED431C 2022/03, Xunta de Galicia | Ref. ED481B 2023/005, Asociación Española de Gastroenterología
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Horizontally distributed inference of deep neural networks for AI-enabled IoT

  • Rodríguez Conde, Iván
  • Campos Bastos, Celso
  • Fernández Riverola, Florentino
Motivated by the pervasiveness of artificial intelligence (AI) and the Internet of Things (IoT) in the current “smart everything” scenario, this article provides a comprehensive overview of the most recent research at the intersection of both domains, focusing on the design and development of specific mechanisms for enabling a collaborative inference across edge devices towards the in situ execution of highly complex state-of-the-art deep neural networks (DNNs), despite the resource-constrained nature of such infrastructures. In particular, the review discusses the most salient approaches conceived along those lines, elaborating on the specificities of the partitioning schemes and the parallelism paradigms explored, providing an organized and schematic discussion of the underlying workflows and associated communication patterns, as well as the architectural aspects of the DNNs that have driven the design of such techniques, while also highlighting both the primary challenges encountered at the design and operational levels and the specific adjustments or enhancements explored in response to them., Agencia Estatal de Investigación | Ref. DPI2017-87494-R, Ministerio de Ciencia e Innovación | Ref. PDC2021-121644-I00, Xunta de Galicia | Ref. ED431C 2022/03-GRC
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Negative samples for improving object detection—A case study in aI-assisted colonoscopy for polyp detection

  • Nogueira Rodríguez, Alba
  • González Peña, Daniel
  • Reboiro Jato, Miguel
  • López Fernández, Hugo
Deep learning object-detection models are being successfully applied to develop computer-aided diagnosis systems for aiding polyp detection during colonoscopies. Here, we evidence the need to include negative samples for both (i) reducing false positives during the polyp-finding phase, by including images with artifacts that may confuse the detection models (e.g., medical instruments, water jets, feces, blood, excessive proximity of the camera to the colon wall, blurred images, etc.) that are usually not included in model development datasets, and (ii) correctly estimating a more realistic performance of the models. By retraining our previously developed YOLOv3-based detection model with a dataset that includes 15% of additional not-polyp images with a variety of artifacts, we were able to generally improve its F1 performance in our internal test datasets (from an average F1 of 0.869 to 0.893), which now include such type of images, as well as in four public datasets that include not-polyp images (from an average F1 of 0.695 to 0.722)., Ministerio de Ciencia y Competitividad y Ministerio de Ciencia e Innovación | Ref. DPI2017-87494-R, Ministerio de Ciencia y Competitividad y Ministerio de Ciencia e Innovación | Ref. PDC2021-121644-I00, Xunta de Galicia | Ref. ED431C2018/55-GRC, Xunta de Galicia | Ref. ED431C 2022/03-GRC
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

PIBAdb: a public cohort of multimodal colonoscopy videos and images including polyps with histological information

  • Nogueira Rodríguez, Alba
  • Domínguez Carbajales, Rubén
  • Campos Tato, Fernando
  • Herrero, Jesús
  • Puga, Manuel
  • Rivas, Laura
  • Sánchez, Eloy
  • Iglesias, Águeda
  • Codesido, Laura
  • Díez Martín, Astrid Irene
  • Davila Piñón, Pedro
  • Cubiella, Joaquín
  • Fernández Riverola, Florentino
  • López Fernández, Hugo
  • González Peña, Daniel
  • Reboiro Jato, Miguel
Colorectal cancer is the third most common cancer worldwide and presents a high mortality rate. Colonoscopy is the gold standard for screening, as it can reduce its incidence and mortality. Deep Learning techniques have become state-of-the-art in lesion detection and classification, and several Deep-Learning-based Computer-Aided Diagnosis systems are already undergoing clinical evaluation or commercialization. However, the development of reliable models requires large, high-quality datasets, which are costly and time-consuming to create. Thus, the availability of public datasets is critical for the scientific community to develop artificial intelligent models. This work aims to contribute to the available resources by presenting PIBAdb, a new multimodal public cohort of colorectal videos and images., Asociación Española de Gastroenteroloxía | Ref. Beca de Oncología - Tamarite 2022, Instituto de Salud Carlos III | Ref. FI22/00203, Instituto de Salud Carlos III | Ref. PI21/01771, Instituto de Salud Carlos III | Ref. INT22/00009, Xunta de Galicia | Ref. ED481B-2023-005, Universidade de Vigo/CISUG, Xunta de Galicia | Ref. ED431C 2022/03-GRC, Xunta de Galicia | Ref. ED431G 2019/06, Agencia Estatal de Investigación | Ref. DPI2017-87494-R, Agencia Estatal de Investigación | Ref. PDC2021-121644-I00
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Performance of convolutional neural networks for polyp localization on public colonoscopy image datasets

  • Nogueira Rodríguez, Alba
  • Reboiro Jato, Miguel
  • González Peña, Daniel
  • López Fernández, Hugo
Colorectal cancer is one of the most frequent malignancies. Colonoscopy is the de facto standard for precancerous lesion detection in the colon, i.e., polyps, during screening studies or after facultative recommendation. In recent years, artificial intelligence, and especially deep learning techniques such as convolutional neural networks, have been applied to polyp detection and localization in order to develop real-time CADe systems. However, the performance of machine learning models is very sensitive to changes in the nature of the testing instances, especially when trying to reproduce results for totally different datasets to those used for model development, i.e., inter-dataset testing. Here, we report the results of testing of our previously published polyp detection model using ten public colonoscopy image datasets and analyze them in the context of the results of other 20 state-of-the-art publications using the same datasets. The F1-score of our recently published model was 0.88 when evaluated on a private test partition, i.e., intra-dataset testing, but it decayed, on average, by 13.65% when tested on ten public datasets. In the published research, the average intra-dataset F1-score is 0.91, and we observed that it also decays in the inter-dataset setting to an average F1-score of 0.83., Agencia Estatal de Investigación | Ref. DPI2017-87494-R, Agencia Estatal de Investigación | Ref. PDC2021-121644-I00, Xunta de Galicia | Ref. ED481A-2019/299, Xunta de Galicia | Ref. ED431C2018/55-GRC, Fundação para a Ciência e a Tecnologia | Ref. 2020.00515.CEECIND
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

PolyDeep Advance 1: clinical validation of a computer-aided detection system for colorectal polyp detection with a second observer design

  • Davila Piñón, Pedro
  • Pedrido, Teresa
  • Díez Martín, Astrid Irene
  • Herrero, Jesús
  • Puga, Manuel
  • Rivas, Laura
  • Sánchez, Eloy
  • Zarraquiños, Sara
  • Pin, Noel
  • Vega, Pablo
  • Soto, Santiago
  • Remedios, David
  • Domínguez Carbajales, Rubén
  • Fernández Riverola, Florentino
  • Nogueira Rodríguez, Alba
  • González Peña, Daniel
  • Reboiro Jato, Miguel
  • López Fernández, Hugo
  • Cubiella, Joaquín
Background: PolyDeep is a computer-aided detection and characterization system that has demonstrated a high diagnostic yield for in vitro detection of colorectal polyps. Our objective is to compare the diagnostic performance of expert endoscopists and PolyDeep for colorectal polyp detection. Methods: PolyDeep Advance 1 (NCT05514301) is an unicentric diagnostic test study with a second observer design. Endoscopists performed colonoscopy blinded to PolyDeep’s detection results. The main endpoint was the sensitivity for colorectal polyp (adenoma, serrated or hyperplastic lesion) detection. The secondary endpoints were the diagnostic performance for diminutive lesions (≤5 mm), neoplasia (adenoma, serrated lesion) and adenoma detection. Results: We included 205 patients (55.1% male, 63.0 ± 6.2 years of age) referred to colonoscopy (positive faecal immunochemical occult blood test = 60.5%, surveillance colonoscopy = 39.5%). We excluded eight patients due to incomplete colonoscopy. Endoscopists detected 384 lesions, of which 39 were not detected by PolyDeep. In contrast, PolyDeep predicted 410 possible additional lesions, 26 of these predictions confirmed by endoscopists as lesions, resulting in a potential 6.8% detection increase with respect to the 384 lesions detected by the endoscopists. In total, 410 lesions were detected, 20 were not retrieved, five were colorectal adenocarcinoma, 343 were colorectal polyps (231 adenomas, 39 serrated and 73 hyperplastic polyps), 42 were normal mucosa and 289 were ≤5 mm. We did not find statistically significant differences between endoscopists and PolyDeep for colorectal polyp detection (Sensitivity = 94.2%, 91.5%, p = 0.2; Specificity = 9.5%, 14.3%, p = 0.7), diminutive lesions (Sensitivity = 92.3%, 89.5%, p = 0.4; Specificity = 9.8%, 14.6%, p = 0.7), neoplasia (Sensitivity = 95.2%, 92.9%, p = 0.3; Specificity = 9.6%, 13.9%, p = 0.4) and adenoma detection (Sensitivity = 94.4%, 92.6%, p = 0.5; Specificity = 7.2%, 11.8%, p = 0.2). Conclusions: Expert endoscopists and PolyDeep have similar diagnostic performance for colorectal polyp detection., Instituto de Salud Carlos III | Ref. CD22/00087, Instituto de Salud Carlos III | Ref. NT22/00009, Instituto de Salud Carlos III | Ref. FI22/00203, Agencia Estatal de Investigación | Ref. DPI2017-87494-R, Agencia Estatal de Investigación | Ref. PDC2021-121644-I00, Xunta de Galicia | Ref. ED431G 2019/06, Xunta de Galicia | Ref. ED431C 2022/03-GRC, Xunta de Galicia | Ref. ED481B-2023-005, Instituto de Salud Carlos III | Ref. PI21/01771