Deep learning classification of inverted papilloma malignant transformation using 3D convolutional neural networks and magnetic resonance imaging

Computer Vision-Radiomics & Pathognomics

The role of computer vision in extracting radiographic (radiomics) and histopathologic (pathognomics) features is an extension of molecular biomarkers that have been foundational to our understanding across the spectrum of head and neck disorders. Especially within head and neck cancers, machine learning and deep learning applications have yielded advances in the characterization of tumor features, nodal features, and various outcomes. This review aims to overview the landscape of radiomic and pathognomic applications, informing future work to address gaps. Novel methodologies will be needed to potentially engineer ways of integrating multidimensional data inputs to examine disease features to guide prognosis comprehensively and ultimately clinical management.

Enhancing nasal endoscopy: Classification, detection, and segmentation of anatomic landmarks using a convolutional neural network

KEY POINTS

A convolutional neural network (CNN)-based model can accurately localize and segment turbinates in images obtained during nasal endoscopy (NE). This model represents a starting point for algorithms that comprehensively interpret NE findings.

Self-supervised learning for classifying paranasal anomalies in the maxillary sinus

PURPOSE

Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies, supervised learning methods require large labelled dataset exhibiting diverse anomaly morphology. Self-supervised learning (SSL) can be used to learn representations from unlabelled data. However, there are no SSL methods designed for the downstream task of classifying paranasal anomalies in the maxillary sinus (MS).

METHODS

Our approach uses a 3D convolutional autoencoder (CAE) trained in an unsupervised anomaly detection (UAD) framework. Initially, we train the 3D CAE to reduce reconstruction errors when reconstructing normal maxillary sinus (MS) image. Then, this CAE is applied to an unlabelled dataset to generate coarse anomaly locations by creating residual MS images. Following this, a 3D convolutional neural network (CNN) reconstructs these residual images, which forms our SSL task. Lastly, we fine-tune the encoder part of the 3D CNN on a labelled dataset of normal and anomalous MS images.

RESULTS

The proposed SSL technique exhibits superior performance compared to existing generic self-supervised methods, especially in scenarios with limited annotated data. When trained on just 10% of the annotated dataset, our method achieves an area under the precision-recall curve (AUPRC) of 0.79 for the downstream classification task. This performance surpasses other methods, with BYOL attaining an AUPRC of 0.75, SimSiam at 0.74, SimCLR at 0.73 and masked autoencoding using SparK at 0.75.

CONCLUSION

A self-supervised learning approach that inherently focuses on localizing paranasal anomalies proves to be advantageous, particularly when the subsequent task involves differentiating normal from anomalous maxillary sinuses. Access our code at https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly .

Artificial Intelligence in Rhinology

Rhinology, allergy, and skull base surgery are fields primed for the integration and implementation of artificial intelligence (AI). The heterogeneity of the disease processes within these fields highlights the opportunity for AI to augment clinical care and promote personalized medicine. Numerous research studies have been published demonstrating the development and clinical potential of AI models within the field. Most describe in silico evaluation models without direct clinical implementation. The major themes of existing studies include diagnostic or clinical decisions support, clustering patients into specific phenotypes or endotypes, predicting post-treatment outcomes, and surgical planning.

Multiple instance learning for eosinophil quantification of sinonasal histopathology images: A hierarchical determination on whole slide images

KEY POINTS

We proposed a hierarchical framework including an unsupervised candidate image selection and a weakly supervised patch image detection based on multiple instance learning (MIL) to effectively estimate eosinophil quantities in tissue samples from whole slide images. MIL is an innovative approach that can help deal with the variability in cell distribution detection and enable automated eosinophil quantification from sinonasal histopathological images with a high degree of accuracy. The study lays the foundation for further research and development in the field of automated histopathological image analysis, and validation on more extensive and diverse datasets will contribute to real-world application.

[Inverted papilloma of the nose and paranasal sinuses : Diagnosis, treatment, and malignant transformation]

Inverted papilloma (IP) are benign tumors that show a locally aggressive behavior, a high rate of recurrence, and a potential for malignant transformation. Specific radiological signs such as hyperostosis at the origin of the IP and convoluted cerebriform patterns, as well as the typical endoscopic aspect, can lead to diagnosis and enable preoperative planning of surgical access and the extent of surgery. Endonasal endoscopic techniques are considered the gold standard and the introduction of extended surgical techniques such as the prelacrimal approach, frontal drillout, or orbital transposition facilitate complete subperiosteal resection with preservation of important physiological structures. There is a risk of synchronous and metachronous squamous cell carcinomas (IP-SCC). Research focuses on radiological criteria to differentiate benign IP from IP-SCC, genetic and epigenetic factors in the process of malignant transformation, and estimation of the risk of IP progressing to IP-SCC.

Deep Learning Techniques and Imaging in Otorhinolaryngology-A State-of-the-Art Review

Over the last decades, the field of medicine has witnessed significant progress in artificial intelligence (AI), the Internet of Medical Things (IoMT), and deep learning (DL) systems. Otorhinolaryngology, and imaging in its various subspecialties, has not remained untouched by this transformative trend. As the medical landscape evolves, the integration of these technologies becomes imperative in augmenting patient care, fostering innovation, and actively participating in the ever-evolving synergy between computer vision techniques in otorhinolaryngology and AI. To that end, we conducted a thorough search on MEDLINE for papers published until June 2023, utilizing the keywords 'otorhinolaryngology', 'imaging', 'computer vision', 'artificial intelligence', and 'deep learning', and at the same time conducted manual searching in the references section of the articles included in our manuscript. Our search culminated in the retrieval of 121 related articles, which were subsequently subdivided into the following categories: imaging in head and neck, otology, and rhinology. Our objective is to provide a comprehensive introduction to this burgeoning field, tailored for both experienced specialists and aspiring residents in the domain of deep learning algorithms in imaging techniques in otorhinolaryngology.

Current State of Artificial Intelligence in Clinical Applications for Head and Neck MR Imaging

Due primarily to the excellent soft tissue contrast depictions provided by MRI, the widespread application of head and neck MRI in clinical practice serves to assess various diseases. Artificial intelligence (AI)-based methodologies, particularly deep learning analyses using convolutional neural networks, have recently gained global recognition and have been extensively investigated in clinical research for their applicability across a range of categories within medical imaging, including head and neck MRI. Analytical approaches using AI have shown potential for addressing the clinical limitations associated with head and neck MRI. In this review, we focus primarily on the technical advancements in deep-learning-based methodologies and their clinical utility within the field of head and neck MRI, encompassing aspects such as image acquisition and reconstruction, lesion segmentation, disease classification and diagnosis, and prognostic prediction for patients presenting with head and neck diseases. We then discuss the limitations of current deep-learning-based approaches and offer insights regarding future challenges in this field.

End-to-end deep learning classification of vocal pathology using stacked vowels

Objectives

Advances in artificial intelligence (AI) technology have increased the feasibility of classifying voice disorders using voice recordings as a screening tool. This work develops upon previous models that take in single vowel recordings by analyzing multiple vowel recordings simultaneously to enhance prediction of vocal pathology.

Methods

Voice samples from the Saarbruecken Voice Database, including three sustained vowels (/a/, /i/, /u/) from 687 healthy human participants and 334 dysphonic patients, were used to train 1-dimensional convolutional neural network models for multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings. Three models were trained: (1) a baseline model that analyzed individual vowels in isolation, (2) a stacked vowel model that analyzed three vowels (/a/, /i/, /u/) in the neutral pitch simultaneously, and (3) a stacked pitch model that analyzed the /a/ vowel in three pitches (low, neutral, and high) simultaneously.

Results

For multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings, the stacked vowel model demonstrated higher performance compared with the baseline and stacked pitch models (F1 score 0.81 vs. 0.77 and 0.78, respectively). Specifically, the stacked vowel model achieved higher performance for class-specific classification of hyperfunctional dysphonia voice samples compared with the baseline and stacked pitch models (F1 score 0.56 vs. 0.49 and 0.50, respectively).

Conclusions

This study demonstrates the feasibility and potential of analyzing multiple sustained vowel recordings simultaneously to improve AI-driven screening and classification of vocal pathology. The stacked vowel model architecture in particular offers promise to enhance such an approach.

Lay Summary

AI analysis of multiple vowel recordings can improve classification of voice pathologies compared with models using a single sustained vowel and offer a strategy to enhance AI-driven screening of voice disorders.

Level of Evidence

3.

Preoperative Prediction of Sinonasal Inverted Papilloma-associated Squamous Cell Carcinoma (IP-SCC)

INTRODUCTION

Sinonasal inverted papillomas (IP) can undergo transformation into IP-squamous cell carcinomas (IP-SCC). More aggressive treatment plan should be established when IP-SCC is suspected. Nevertheless, inaccuracy of the preoperative punch biopsy results to detect IP-SCC from IP raises the need for an additional strategy. The present study aimed to investigate significant clinicoradiological remarks associated with IP-SCC than IP.

MATERIAL AND METHODS

Postoperative surgical specimens obtained from patients with confirmed IP or IP-SCC at a single tertiary medical center from 1997 to 2018 were retrospectively evaluated. Patients' demographic and clinical characteristics, preoperative in-office punch biopsy results, and preoperative computed tomography (CT) or magnetic resonance images were reviewed. Univariate and multivariate analyses were performed to assess the odds ratio (OR) associated with IP-SCC. The area under the curve (AUC) in the receiver Operating Characteristic (ROC) curve was calculated in the prediction model to discriminate IP-SCC from IP.

RESULTS

The study included 44 IP-SCC and 301 patients with IP. The diagnostic sensitivity of in-office punch biopsy to detect IP-SCC was 70.7%. Multivariate analysis showed that factors significantly associated with IP-SCC included tobacco smoking >10PY (adjusted-OR [aOR]: 4.1), epistaxis (aOR: 3.4), facial pain (aOR: 4.2), bony destruction (aOR: 37.6), bony remodeling (aOR: 36.3), and invasion of adjacent structures (aOR: 31.6) (all p < 0.05). Combining all significantly related clinicoradiological features, the ability to discriminate IP-SCC from IP reached an AUC of 0.974.

CONCLUSION

IP patients with a history of tobacco smoking, facial pain, epistaxis, and bony destruction, remodeling, or invasion of an adjacent structure on preoperative images may be at higher risk for IP-SCC.

LEVEL OF EVIDENCE

3 Laryngoscope, 133:2502-2510, 2023.

Preoperative prediction of sinonasal papilloma by artificial intelligence using nasal video endoscopy: a retrospective study

Sinonasal inverted papilloma (IP) is at risk of recurrence and malignancy, and early diagnosis using nasal endoscopy is essential. We thus developed a diagnostic system using artificial intelligence (AI) to identify nasal sinus papilloma. Endoscopic surgery videos of 53 patients undergoing endoscopic sinus surgery were edited to train and evaluate deep neural network models and then a diagnostic system was developed. The correct diagnosis rate based on visual examination by otolaryngologists was also evaluated using the same videos and compared with that of the AI diagnostic system patients. Main outcomes evaluated included the percentage of correct diagnoses compared to AI diagnosis and the correct diagnosis rate for otolaryngologists based on years of practice experience. The diagnostic system had an area under the curve of 0.874, accuracy of 0.843, false positive rate of 0.124, and false negative rate of 0.191. The average correct diagnosis rate among otolaryngologists was 69.4%, indicating that the AI was highly accurate. Evidently, although the number of cases was small, a highly accurate diagnostic system was created. Future studies with larger samples to improve the accuracy of the system and expand the range of diseases that can be detected for more clinical applications are warranted.

The Evolution and Application of Artificial Intelligence in Rhinology: A State of the Art Review

OBJECTIVE

To provide a comprehensive overview on the applications of artificial intelligence (AI) in rhinology, highlight its limitations, and propose strategies for its integration into surgical practice.

DATA SOURCES

Medline, Embase, CENTRAL, Ei Compendex, IEEE, and Web of Science.

REVIEW METHODS

English studies from inception until January 2022 and those focusing on any application of AI in rhinology were included. Study selection was independently performed by 2 authors; discrepancies were resolved by the senior author. Studies were categorized by rhinology theme, and data collection comprised type of AI utilized, sample size, and outcomes, including accuracy and precision among others.

CONCLUSIONS

An overall 5435 articles were identified. Following abstract and title screening, 130 articles underwent full-text review, and 59 articles were selected for analysis. Eleven studies were from the gray literature. Articles were stratified into image processing, segmentation, and diagnostics (n = 27); rhinosinusitis classification (n = 14); treatment and disease outcome prediction (n = 8); optimizing surgical navigation and phase assessment (n = 3); robotic surgery (n = 2); olfactory dysfunction (n = 2); and diagnosis of allergic rhinitis (n = 3). Most AI studies were published from 2016 onward (n = 45).

IMPLICATIONS FOR PRACTICE

This state of the art review aimed to highlight the increasing applications of AI in rhinology. Next steps will entail multidisciplinary collaboration to ensure data integrity, ongoing validation of AI algorithms, and integration into clinical practice. Future research should be tailored at the interplay of AI with robotics and surgical education.