Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy

Guleria, Shan; Shah, Tilak; Pulido, J Vincent; Fasullo, Matthew; Ehsan, Lubaina; Lippman, Robert; Sali, Rasoul; Mutha, Pritesh; Cheng, Lin; Brown, Donald E.; Syed, Sana

doi:10.1038/s41598-021-84510-4

Cited by 14 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Tomita et al 29 decided to combine low grade and high grade dysplasia into a single class, and invasive adenocarcinoma and severe high grade dysplasia in another one, to address the lack of available data. Other works on Barrett's esophagus 30,31 didn't grade dysplasia either. Thus, a significant drawback of these studies is the limited size of their datasets, leading to insufficient training sets that struggle to identify subtle pathological features.…”

Section: Discussionmentioning

confidence: 99%

Evaluating AI-Assistance for Pathologists in Diagnosing and Grading Laryngeal Lesions

Bellahsen-Harrar,

Lubrano,

Lépine

et al. 2023

Preprint

View full text Add to dashboard Cite

Importance: Diagnosis of head and neck squamous dysplasias and carcinomas is challenging, with a moderate inter-rater agreement. Nowadays, new artificial intelligence (AI) models are developed to automatically detect and grade lesions, but their contribution to the performance of pathologists has not been assessed. Objective: To evaluate the contribution of our AI tool in assisting pathologists in diagnosing squamous dysplasia and carcinoma in the head and neck region. Design, Setting, and Participants: We evaluated the effectiveness of our previously described AI model, which combines an automatic classification of laryngeal and pharyngeal squamous lesions with a confidence score, on a panel of eight pathologists coming from different backgrounds and with different levels of experience on a subset of 115 slides. Main Outcomes and Measures: The main outcome was the inter-rater agreement, measured by the weighted linear kappa. Other outcomes on diagnostic efficiency were assessed using paired t tests. Results: AI-Assistance significantly improved the inter-rater agreement (linear kappa 0.73 with assistance versus 0.675 without assistance, p < 0.001) Moreover, the agreement was even better on high confidence predictions (linear kappa 0.8 vs 0.73, p < 0.001). This improvement was particularly strong for non-HN specialised pathologists and younger pathologists. Hence, the AI-Assistance enabled the pathologists panel to perform on par with the expert panel described in the literature. Conclusions and Relevance: Our AI-Assistance is of great value for helping pathologists in the difficult task of diagnosing squamous dysplasias and carcinomas, improving for the first time the inter-rater agreement. It demonstrates the possibility of a truly Augmented Pathology in complex tasks such as the classification of head and neck squamous lesions.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluating AI-Assistance for Pathologists in Diagnosing and Grading Laryngeal Lesions

Bellahsen-Harrar,

Lubrano,

Lépine

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In order to test the generalizability of the pose estimation model, 76 GMA videos were used: 62 for training, and 14 for testing for an optimal 80:20 ratio 31 , 32 . Splitting the train/test dataset at the infant level can give evidence to the model’s generalizability.…”

Section: Methodsmentioning

confidence: 99%

Machine learning approaches to evaluate infants’ general movements in the writhing stage—a pilot study

Letzkus,

Pulido,

Adeyemo

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The goals of this study are to describe machine learning techniques employing computer-vision movement algorithms to automatically evaluate infants’ general movements (GMs) in the writhing stage. This is a retrospective study of infants admitted 07/2019 to 11/2021 to a level IV neonatal intensive care unit (NICU). Infant GMs, classified by certified expert, were analyzed in two-steps (1) determination of anatomic key point location using a NICU-trained pose estimation model [accuracy determined using object key point similarity (OKS)]; (2) development of a preliminary movement model to distinguish normal versus cramped-synchronized (CS) GMs using cosine similarity and autocorrelation of major joints. GMs were analyzed using 85 videos from 74 infants; gestational age at birth 28.9 ± 4.1 weeks and postmenstrual age (PMA) at time of video 35.9 ± 4.6 weeks The NICU-trained pose estimation model was more accurate (0.91 ± 0.008 OKS) than a generic model (0.83 ± 0.032 OKS, p < 0.001). Autocorrelation values in the lower limbs were significantly different between normal (5 videos) and CS GMs (5 videos, p < 0.05). These data indicate that automated pose estimation of anatomical key points is feasible in NICU patients and that a NICU-trained model can distinguish between normal and CS GMs. These preliminary data indicate that machine learning techniques may represent a promising tool for earlier CP risk assessment in the writhing stage and prior to hospital discharge.

show abstract

“…Guleria, S., et al conducted a modeling study where they compared pCLE with pathological images. Their findings demonstrated that a comprehensive three-category classification task, distinguishing between normal, NDBE, and dysplasia/cancer, can be successfully achieved using multiple retrospective datasets [57].…”

Section: Applications Of Deep Learning To Assist Pathological Diagnosismentioning

confidence: 99%

Deep Learning in Barrett’s Esophagus Diagnosis: Current Status and Future Directions

Cui,

Wang,

Lin

et al. 2023

Bioengineering

View full text Add to dashboard Cite

Barrett’s esophagus (BE) represents a pre-malignant condition characterized by abnormal cellular proliferation in the distal esophagus. A timely and accurate diagnosis of BE is imperative to prevent its progression to esophageal adenocarcinoma, a malignancy associated with a significantly reduced survival rate. In this digital age, deep learning (DL) has emerged as a powerful tool for medical image analysis and diagnostic applications, showcasing vast potential across various medical disciplines. In this comprehensive review, we meticulously assess 33 primary studies employing varied DL techniques, predominantly featuring convolutional neural networks (CNNs), for the diagnosis and understanding of BE. Our primary focus revolves around evaluating the current applications of DL in BE diagnosis, encompassing tasks such as image segmentation and classification, as well as their potential impact and implications in real-world clinical settings. While the applications of DL in BE diagnosis exhibit promising results, they are not without challenges, such as dataset issues and the “black box” nature of models. We discuss these challenges in the concluding section. Essentially, while DL holds tremendous potential to revolutionize BE diagnosis, addressing these challenges is paramount to harnessing its full capacity and ensuring its widespread application in clinical practice.

show abstract

Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy

Cited by 14 publications

References 34 publications

Evaluating AI-Assistance for Pathologists in Diagnosing and Grading Laryngeal Lesions

Evaluating AI-Assistance for Pathologists in Diagnosing and Grading Laryngeal Lesions

Machine learning approaches to evaluate infants’ general movements in the writhing stage—a pilot study

Deep Learning in Barrett’s Esophagus Diagnosis: Current Status and Future Directions

Contact Info

Product

Resources

About