MP26-19 AUTOMATED AND DYNAMIC CLASSIFICATION OF BLADDER CANCER USING DEEP LEARNING ON REAL-TIME CONFOCAL LASER ENDOMICROSCOPY IMAGES

AbstractProbe-based confocal laser endomicroscopy (pCLE) allows for real-time diagnosis of dysplasia and cancer in Barrett’s esophagus (BE) but is limited by low sensitivity. Even the gold standard of histopathology is hindered by poor agreement between pathologists. We deployed deep-learning-based image and video analysis in order to improve diagnostic accuracy of pCLE videos and biopsy images. Blinded experts categorized biopsies and pCLE videos as squamous, non-dysplastic BE, or dysplasia/cancer, and deep learning models were trained to classify the data into these three categories. Biopsy classification was conducted using two distinct approaches—a patch-level model and a whole-slide-image-level model. Gradient-weighted class activation maps (Grad-CAMs) were extracted from pCLE and biopsy models in order to determine tissue structures deemed relevant by the models. 1970 pCLE videos, 897,931 biopsy patches, and 387 whole-slide images were used to train, test, and validate the models. In pCLE analysis, models achieved a high sensitivity for dysplasia (71%) and an overall accuracy of 90% for all classes. For biopsies at the patch level, the model achieved a sensitivity of 72% for dysplasia and an overall accuracy of 90%. The whole-slide-image-level model achieved a sensitivity of 90% for dysplasia and 94% overall accuracy. Grad-CAMs for all models showed activation in medically relevant tissue regions. Our deep learning models achieved high diagnostic accuracy for both pCLE-based and histopathologic diagnosis of esophageal dysplasia and its precursors, similar to human accuracy in prior studies. These machine learning approaches may improve accuracy and efficiency of current screening protocols.

Download Full-text

Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time

Scientific Reports ◽

10.1038/s41598-021-89365-3 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Song-Quan Ong ◽

Hamdan Ahmad ◽

Gomesh Nair ◽

Pradeep Isawasan ◽

Abdul Hafiz Ab Majid

Keyword(s):

Deep Learning ◽

Aedes Aegypti ◽

Real Time ◽

Aedes Albopictus ◽

Automated Classification ◽

Expert Performance ◽

Deep Convolutional Neural Networks ◽

Significant Difference ◽

Set Up

AbstractClassification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) by humans remains challenging. We proposed a highly accessible method to develop a deep learning (DL) model and implement the model for mosquito image classification by using hardware that could regulate the development process. In particular, we constructed a dataset with 4120 images of Aedes mosquitoes that were older than 12 days old and had common morphological features that disappeared, and we illustrated how to set up supervised deep convolutional neural networks (DCNNs) with hyperparameter adjustment. The model application was first conducted by deploying the model externally in real time on three different generations of mosquitoes, and the accuracy was compared with human expert performance. Our results showed that both the learning rate and epochs significantly affected the accuracy, and the best-performing hyperparameters achieved an accuracy of more than 98% at classifying mosquitoes, which showed no significant difference from human-level performance. We demonstrated the feasibility of the method to construct a model with the DCNN when deployed externally on mosquitoes in real time.

Download Full-text

MP35-04 FIBEROPTIC CONFOCAL LASER ENDOMICROSCOPY OF SMALL RENAL MASSES: TOWARDS REAL TIME OPTICAL DIAGNOSTIC BIOPSY

The Journal of Urology ◽

10.1016/j.juro.2015.02.1105 ◽

2015 ◽

Vol 193 (4S) ◽

Cited By ~ 1

Author(s):

Li-Ming Su ◽

Robert Allan ◽

Kellie Ritari ◽

Patrick Tomeny ◽

Christopher Carter

Keyword(s):

Real Time ◽

Confocal Laser Endomicroscopy ◽

Confocal Laser ◽

Small Renal Masses ◽

Renal Masses ◽

Optical Diagnostic ◽

Diagnostic Biopsy

Download Full-text

Probe-based confocal laser endomicroscopy and Barrett's esophagus – just a scientific toy or significant improvement in diagnosis?

Digestive Diseases ◽

10.1159/000516257 ◽

2021 ◽

Author(s):

Luka Vranić ◽

Tin Nadarević ◽

Davor Štimac

Keyword(s):

Diagnostic Accuracy ◽

Real Time ◽

Barrett’S Esophagus ◽

Predictive Value ◽

Barrett's Esophagus ◽

High Reliability ◽

Confocal Laser Endomicroscopy ◽

Confocal Laser ◽

Imaging Method ◽

Increased Risk

Background: Barrett’s esophagus (BE) requires surveillance to identify potential neoplasia at early stage. Standard surveillance regimen includes random four-quadrant biopsies by Seattle protocol. Main limitations of random biopsies are high risk of sampling error, difficulties in histology interpretation, common inadequate classification of pathohistological changes, increased risk of bleeding and time necessary to acquire the final diagnosis. Probe-based confocal laser endomicroscopy (pCLE) has emerged as a potential tool with an aim to overcome these obvious limitations. Summary: pCLE represents real-time microscopic imaging method that offers evaluation of epithelial and subepithelial structures with 1000-fold magnification. In theory, pCLE has potential to eliminate the need for biopsy in BE patient. The main advantages would be real-time diagnosis and decision making, greater diagnostic accuracy and to evaluate larger area compared to random biopsies. Clinical pCLE studies in esophagus show high diagnostic accuracy and its high negative predictive value offers high reliability and confidence to exclude dysplastic and neoplastic lesions. However, it still cannot replace histopathology due to lower positive predictive value and sensitivity. Key messages: Despite promising results, its role in routine use in patients with Barrett’s esophagus remains questionable primarily due to lack of well-organized double-blind randomized trials.

Download Full-text

Real-time in vivo optical biopsy using confocal laser endomicroscopy to evaluate distal margin in situ and determine surgical procedure in low rectal cancer

Surgical Endoscopy ◽

10.1007/s00464-018-6519-z ◽

2018 ◽

Vol 33 (7) ◽

pp. 2332-2338

Author(s):

Zhangyuanzhu Liu ◽

Xiaobei Luo ◽

Wei Jiang ◽

Dexin Chen ◽

Weisheng Chen ◽

...

Keyword(s):

Rectal Cancer ◽

Real Time ◽

Surgical Procedure ◽

Low Rectal Cancer ◽

Optical Biopsy ◽

Confocal Laser Endomicroscopy ◽

Confocal Laser ◽

Distal Margin

Download Full-text

Confocal Laser Endomicroscopy in Neurosurgery: A New Technique with Much Potential

Minimally Invasive Surgery ◽

10.1155/2013/851819 ◽

2013 ◽

Vol 2013 ◽

pp. 1-5 ◽

Cited By ~ 2

Author(s):

David Breuskin ◽

Jana DiVincenzo ◽

Yoo-Jin Kim ◽

Steffi Urbschat ◽

Joachim Oertel

Keyword(s):

Real Time ◽

Histological Diagnosis ◽

New Technique ◽

Confocal Laser Endomicroscopy ◽

Confocal Laser ◽

Tissue Cell ◽

Resected Tissue ◽

Technical Innovations ◽

A New Technique ◽

Real Time Information

Technical innovations in brain tumour diagnostic and therapy have led to significant improvements of patient outcome and recurrence free interval. The use of technical devices such as surgical microscopes as well as neuronavigational systems have helped localising tumours as much as fluorescent agents, such as 5-aminolaevulinic acid, have helped visualizing pathologically altered tissue. Nonetheless, intraoperative instantaneous frozen sections and histological diagnosis remain the only method of gaining certainty of the nature of the resected tissue. This technique is time consuming and does not provide close-to-real-time information. In gastroenterology, confocal endoscopy closed the gap between tissue resection and histological examination, providing an almost real-time histological diagnosis. The potential of this technique using a confocal laser endoscope EndoMAG1 by Karl Storz Company was evaluated by our group on pig brains, tumour tissue cell cultures, and fresh human tumour specimen. Here, the authors report for the first time on the results of applying this new technique and provide first confocal endoscopic images of various brain and tumour structures. In all, the technique harbours a very promising potential to provide almost real-time intraoperative diagnosis, but further studies are needed to provide evidence for the technique’s potential.

Download Full-text