Diagnosis Of Cholesteatoma Research Articles

Middle ear-acquired cholesteatoma diagnosis based on CT scan image mining using supervised machine learning models

BackgroundDistinguishing between middle ear cholesteatoma and chronic suppurative otitis media (CSOM) is an ongoing challenge. While temporal bone computed tomography (CT) scan is highly accurate for diagnosing middle ear conditions, its specificity in discerning between cholesteatoma and CSOM is only moderate. To address this issue, we utilized trained machine learning models to enhance the specificity of temporal bone CT scan in diagnosing middle ear cholesteatoma. Our database consisted of temporal bone CT scan native images from 122 patients diagnosed with middle ear cholesteatoma and a control group of 115 patients diagnosed with CSOM, with both groups labeled based on surgical findings. We preprocessed the native images to isolate the region of interest and then utilized the Inception V3 convolutional neural network for image embedding into data vectors. Classification was performed using machine learning models including support vector machine (SVM), k-nearest neighbors (k-NN), random forest, and neural network. Statistical metrics employed to interpret the results included classification accuracy, precision, recall, F1 score, confusion matrix, area under the receiver operating characteristic curve (AUC), and FreeViz diagram.ResultsOur training dataset comprised 5390 images, and the testing dataset included 125 different images. The neural network, k-NN, and SVM models demonstrated significantly higher relevance in terms of classification accuracy, precision, and recall compared to the random forest model. For instance, the F1 scores were 0.974, 0.987, and 0.897, respectively, for the former three models, in contrast to 0.661 for the random forest model.ConclusionThe performance metrics of the presented trained machine learning models hold promising prospects as potentially clinically useful aids.

Colesteatoma do ápex petroso: um achado atípico

Introduction: Cholesteatoma, although relatively rare, presents significant challenges in clinical practice. Despite decades of research, its cause remains complex and elusive. Objective: This review aimed to summarize key findings on the epidemiology, pathophysiology, diagnosis and surgical management of cholesteatoma, highlighting current knowledge gaps and emerging trends in the field. Method: Narrative review carried out in the PubMed and Scielo databases. The search used the following keywords: “cholesteatoma, petros apex, minimally invasive surgical procedures”. The inclusion criteria comprised review articles, pre-clinical and clinical research published, written in Portuguese and English and available in complete text. The selected articles were analyzed based on the technologies covered, future perspectives, challenges, diseases mentioned and the central idea of the article. Result: 36 articles were included. Conclusion: Cholesteatoma is important in medical practice, despite being relatively uncommon in the general population. However, there are still doubts about its cause, but its diagnosis has been expanded through imaging tests in an attempt to reduce “second-look” operations and avoid them. Another field with constant growth is surgical treatment, since the complex anatomy requires that new techniques be managed to reduce injuries to important and vital structures in the region.

Cholesteatoma in the pediatric aerodigestive population

ObjectivesTo report the prevalence of cholesteatoma and related comorbidities in pediatric aerodigestive patients requiring tracheostomy or airway reconstruction procedures. To use study findings to inform clinical management of these complex patients. MethodsA repository of clinical data drawn from our institution's electronic medical records was queried to identify airway reconstruction (airway) and complex hospital control (control) patient cohorts. Retrospective chart review was then performed to investigate the occurrence of cholesteatoma and related pathologies in these patients, as well as clinical management. ResultsThe prevalence of cholesteatoma in airway and control patients was 6/374 (1.60 %) and 35/30,565 (0.11 %), respectively. The relative risk of cholesteatoma diagnosis in airway patients was 14.01 (95 % CI 6.06–32.14). Airway patients were more likely than control patients to have pressure equalization tube history (relative risk 3.25, 95 % CI 2.73–3.82). Age at cholesteatoma diagnosis and first surgical intervention was younger in airway compared to control patients (5.43 vs. 8.33, p = 0.0182, and 6.07 vs. 8.82, p = 0.0236). However, time from diagnosis to intervention and extent of surgery were similar between the groups. ConclusionThis is the first study to investigate the prevalence of cholesteatoma in the pediatric aerodigestive population. The relative risk of cholesteatoma diagnosis was found to be 14 times higher in patients with tracheostomy or airway reconstruction history. Underlying eustachian tube and palatal dysfunction are likely contributing factors to the elevated risk. Additionally, cholesteatoma in this population was diagnosed and required surgical intervention at a younger age, which may suggest a more aggressive disease course. Providers should maintain a high degree of suspicion for cholesteatoma in this complex population.

Titanium Implant Obscuring Residual Cholesteatoma on Magnetic Resonance Imaging: A Case Report.

Cholesteatomas are benign growths of squamous epithelial tissue in the middle ear resulting in conductive hearing loss and/or erosion of the structures of the middle ear space. These lesions are surgically removed but require postoperative surveillance due to risk of recurrence or residual disease. Second-look surgery remains the gold standard for diagnosis and treatment of residual or recurrent cholesteatoma; however, advanced imaging modalities such as non-echoplanar diffusion weighted magnetic resonance imaging (non-EPI DWI-MRI) offer a less invasive alternative for surveillance. As surgeons become more reliant on advanced imaging, it is important to understand the limitations of the technology. We present a case of a delay in diagnosis of residual cholesteatoma due to a false-negative finding on non-EPI DWI-MRI screening in the presence of a titanium implant.

Advancements in Cholesteatoma Diagnosis and Management: The Role of Diffusion - Weighted Imaging

Advancements in Cholesteatoma Diagnosis and Management: The Role of Diffusion - Weighted Imaging

Improved reconstruction for highly accelerated propeller diffusion 1.5T clinical MRI.

Propeller fast-spin-echo diffusion magnetic resonance imaging (FSE-dMRI) is essential for the diagnosis of Cholesteatoma. However, at clinical 1.5T MRI, its signal-to-noise ratio (SNR) remains relatively low. To gain sufficient SNR, signal averaging (number of excitations, NEX) is usually used with the cost of prolonged scan time. In this work, we leveraged the benefits of Locally Low Rank (LLR) constrained reconstruction to enhance the SNR. Furthermore, we enhanced both the speed and SNR by employing Convolutional Neural Networks (CNNs) for the accelerated PROPELLER FSE-dMRI on a 1.5T clinical scanner. Residual U-Net (RU-Net) was found to be efficient for propeller FSE-dMRI data. It was trained to predict 2-NEX images obtained by Locally Low Rank (LLR) constrained reconstruction and used 1-NEX images obtained via simplified reconstruction as the inputs. The brain scans from healthy volunteers and patients with cholesteatoma were performed for model training and testing. The performance of trained networks was evaluated with normalized root-mean-square-error (NRMSE), structural similarity index measure (SSIM), and peak SNR (PSNR). For 4 × under-sampled with 7 blades data, online reconstruction appears to provide suboptimal images-some small details are missing due to high noise interferences. Offline LLR enables suppression of noises and discovering some small structures. RU-Net demonstrated further improvement compared to LLR by increasing 18.87% of PSNR, 2.11% of SSIM, and reducing 53.84% of NRMSE. Moreover, RU-Net is about 1500 × faster than LLR (0.03 vs. 47.59s/slice). The LLR remarkably enhances the SNR compared to online reconstruction. Moreover, RU-Net improves propeller FSE-dMRI as reflected in PSNR, SSIM, and NRMSE. It requires only 1-NEX data, which allows a 2 × scan time reduction. In addition, its speed is approximately 1500 times faster than that of LLR-constrained reconstruction.

High-Resolution Computed Tomography in Middle Ear Cholesteatoma: How Much Do We Need It?

Background and Objectives: The diagnosis of cholesteatoma is usually clinic, and the only efficient treatment is surgical. High-resolution computed tomography (HRCT) is not considered absolutely necessary for the management of an uncomplicated cholesteatoma, but unsuspected situations from a clinical point of view can be discovered using the scans, warning the surgeon. Our objective is to compare HRCT scan information with intraoperative findings in patients with cholesteatoma and analyze the usefulness of a preoperative HRCT scan from a surgical point of view. Materials and Methods: This is a prospective descriptive study conducted in the Department of Otolaryngology, Victor Babes University of Medicine and Pharmacy Timisoara, Romania, from May 2021 to April 2022. It was carried out on 46 patients with a clinical diagnosis of cholesteatoma who were consequently operated on in our department. All patients received full clinical and audiological examinations. In all cases, an HRCT scan was performed preoperatively as a mandatory investigation. Preoperative HRCT scans were analyzed, and their findings were compared to the intraoperative notes. The two sets of observations were analyzed using standard statistical methods. Results: Extensive cholesteatoma was the most common type of disease, involving 46% of the patients, followed by pars flaccida cholesteatoma (35%) and pars tensa cholesteatoma (19%). Eroded scutum was the most frequent lesion involving 70% of the patients, followed by incus erosion (67%). Comparison of the HRCT and intraoperative findings revealed a very good correlation for tegmen tympani erosion, sigmoid plate erosion, scutum and malleus erosion, and a moderate-to-good correlation for lateral semicircular canal erosion, incus and stapes erosion, and fallopian canal erosion. Conclusions: HRCT is a valuable tool in the preoperative assessment of cholesteatoma, helping in making surgical decisions. It can accurately predict the extent of disease and is helpful for detecting unapparent dangerous situations. However, it is not very accurate in detecting fallopian canal and stapes erosion.

Comparison of the outcomes of endoscopic versus microscopic approach in cholesteatoma surgery: a randomized clinical study

BackgroundEndoscopic ear surgery is a new, less invasive otologic procedure. Since 1990s, it has been grown in prominence because of anatomical and physiological theories. It offers a view of hidden places, avoids mastoidectomies and endaural vertical and postauricular incisions, and has many other benefits over microscopic surgery. The purpose of this study was to distinguish the difference between the outcomes of microscopic and endoscopic cholesteatoma surgery.MethodsEighty individuals who were diagnosed with cholesteatoma participated in this randomized clinical research. Patients were randomly allocated into two equivalent treatment groups. One group submitted to tympanoplasty via microscopic ear surgery and the other group had exclusive trans-canal endoscopic ear surgery. All patients had preoperative otomicroscopic and radiologic assessment to ensure cholesteatoma diagnosis. Audiological evaluations were also obtained.ResultsThere was no discernible difference in the tested groups’ operational times, air-bone gaps, or air conduction. The endoscopic surgery group healed significantly more quickly than the microscopic surgery group (5.4 0.5 vs 7.7 0.5 weeks, p > 0.001). The frequency of residual lesions (5.0% vs 22.5%, p = 0.023) and recurrence (7.5% vs 27.5%, p = 0.019) was significantly lower in the endoscopic group of patients.ConclusionsWhen comparing healing times, rates of residual disease and rates of recurrence, endoscopic surgery clearly outperforms microscopic surgery. The endoscope encourages visualization and magnification of anatomy while being less invasive thanks to its improved picture quality, lighting, and capacity to “see around the corner.” Additionally, a significant portion of viable mastoid tissues and healthy mucosa were preserved.

Comparison of Computed Tomography-Based Artificial Intelligence Modeling and Magnetic Resonance Imaging in Diagnosis of Cholesteatoma.

In this study, we aimed to compare the success rates of computed tomography image-based artificial intelligence models and magnetic resonance imaging in the diagnosis of preoperative cholesteatoma. The files of 75 patients who underwent tympanomastoid surgery with the diagnosis of chronic otitis media between January 2010 and January 2021 in our clinic were reviewed retrospectively. The patients were classified into the chronic otitis group without cholesteatoma (n=34) and the chronic otitis group with cholesteatoma (n=41) according to the presence of cholesteatoma at surgery. A dataset was created from the preoperative computed tomography images of the patients. In this dataset, the success rates of artificial intelligence in the diagnosis of cholesteatoma were determined by using the most frequently used artificial intelligence models in the literature. In addition, preoperative MRI were evaluated and the success rates were compared. Among the artificial intelligence architectures used in the paper, the lowest result was obtained in MobileNetV2 with an accuracy of 83.30%, while the highest result was obtained in DenseNet201 with an accuracy of 90.99%. In our paper, the specificity of preoperative magnetic resonance imaging in the diagnosis of cholesteatoma was 88.23% and the sensitivity was 87.80%. In this study, we showed that artificial intelligence can be used with similar reliability to magnetic resonance imaging in the diagnosis of cholesteatoma. This is the first study that, to our knowledge, compares magnetic resonance imaging with artificial intelligence models for the purpose of identifying preoperative cholesteatomas.

PROPELLER diffusion weighted imaging for diagnosis of cholesteatoma in comparison with surgical and histopathological results: emphasis on false positivity and false negativity.

To investigate the role of non-echo planar diffusion weighted imaging (DWI) using "periodically rotated overlapping parallel lines with enhanced reconstruction" (PROPELLER) sequence for the diagnosis of cholesteatoma compared to surgical and histopathological results in an attempt to determine the factors causing false negative and false positive diagnoses. Patients who had PROPELLER DWI before ear surgery were retrospectively reviewed. The presence of a lesion with diffusion restriction on PROPELLER DWI was accepted as positive for cholesteatoma, and the results were compared to the intraoperative and histopathological findings. A total of 112 ears in 109 patients were reviewed. On PROPELLER DWI, a lesion with diffusion restriction was found in 101 (90.2%) ears, while in 11 (9.8%) of the patients, no diffusion restriction was found. Surgery and histopathological analysis revealed a cholesteatoma in 100 (89.3%) ears, while in 12 (10.7%) ears, no cholesteatoma was found surgically. There were 96 (85.7%) true positives, 7 (6.2%) true negatives, 5 (4.5%) false positives and 4 (3.6%) false negatives. The accuracy, sensitivity, specificity, positive predictive and negative predictive values of non-echo planar DWI were calculated to be 91.96%, 96%, 58.33%, 95.05%, and 63.64%, respectively. Non-echo planar DWI using PROPELLER sequence has high accuracy, sensitivity and positive predictive value and can be used for the detection of cholesteatoma. The external auditory canal, postoperative ears and small lesions should be evaluated with caution to avoid false results.

The diagnostic utility of diffusion-weighted magnetic resonance imaging and high-resolution computed tomography for cholesteatoma: A meta-analysis.

The purpose of this meta-analysis was to compare the efficiency of high-resolution computed tomography (HRCT) and diffusion-weighted magnetic resonance imaging (DWI) in guiding the diagnosis of middle ear cholesteatoma in clinical practice. Cochrane Library, Medline, Embase, PubMed, and Web of Science were searched for studies that evaluated the sensitivity and specificity of HRCT or DWI in detecting middle ear cholesteatoma. A random-effects model was used to calculate and summarize the pooled estimates of sensitivity, specificity, and diagnostic odds ratios. Postoperative pathological results were considered as the diagnostic gold standard for middle ear cholesteatoma. Fourteen published articles (860 patients) met the inclusion criteria. The sensitivity and specificity of DWI when diagnosing cholesteatoma (regardless of type) were 0.88 (95% confidence interval [CI], 0.80-0.93) and 0.93 (95% CI, 0.86-0.97), respectively, while those of HRCT were 0.68 (95% CI, 0.57-0.77) and 0.78 (95% CI, 0.60-0.90), respectively. Notably, the sensitivity and specificity levels of DWI were similar to those of HRCT (p=.1178 for sensitivity, p=.2144 for specificity; pair-sampled t tests). The sensitivity and specificity of DWI or HRCT for the diagnosis of primary cholesteatoma were 0.78 (95% CI, 0.65-0.88) and 0.84 (95% CI, 0.69-0.93), respectively, while that for recurrent cholesteatoma were 0.93 (95% CI, 0.61-0.99) and 0.94 (95% CI, 0.82-0.98), respectively. DWI and HRCT have similar levels of high sensitivity and specificity in detecting various cholesteatomas. Also, the diagnostic efficiency of HRCT or DWI for recurrent cholesteatoma is identical to that of primary cholesteatoma. Therefore, HRCT may be used in clinical settings to reduce the use of DWI and save clinical resources. Data on the use of diffusion-weighted magnetic resonance imaging and high-resolution computed tomography in the diagnosis of cholesteatoma were obtained through a literature search. They were analyzed to guide the clinical diagnosis and treatment of cholesteatoma. NA.

A Case of Primary EAC Cholesteatoma Extending into Antrum with Normal Middle Ear

Introduction A cholesteatoma is a three-dimensional sac lined by keratinized squamous epithelium containing desquamated keratinized epithelial cell which secretes enzymes that have the tendency to expand and erode the bony structure underlying it and cause intracranial and extracranial complications. This cystic mass is in an abnormal location such as the middle ear, the petrous apex, or the external auditory canal (EAC). It is mostly found in the middle ear and rarely in the EAC. Here we have reported a rare case of unilateral primary EAC cholesteatoma with mild hearing loss in a middle-aged male. Case Report We have reported a case of a 34-year-old male with complaints of right-sided ear discharge and right-sided decreased hearing for the last 5 to 6 years. On examination, right ear EAC was found to be dry, and a sac was observed in posterior wall extending to mastoid present with clear attic, and intact retracted tympanic membrane that was then followed by radiological evaluation to establish the diagnosis of EAC cholesteatoma. This was surgically treated and ear was cleared of all disease. Patient’s symptoms improved postoperatively. Conclusion Primary EAC cholesteatoma with disease-free middle ear is a rare finding and there is very less definitive literature available on the pathogenesis of the same.

Use of bonalive in obliterative mastoidectomy: anatomical results and clinical outcome.

To investigate safety and efficacy of mastoid obliteration in canal-wall-down tympanoplasty performed for cholesteatoma using bioactive glass (BAG). The authors routinely adopt CWD tympanoplasty in case of massive cholesteatoma or revision surgery, performing obliteration with BAG to reduce the mastoid cavity and related disadvantages. We assessed anatomical results, infection control and cholesteatoma recurrence in obliterative mastoidectomy using BAG. The authors evaluated 66 patients treated with obliterative mastoidectomy using BAG during the period 2010-2021. 48.5% of the cases had first diagnosis of cholesteatoma, 48.5% had cholesteatoma recidivisms, and two patients underwent obliteration to improve clinical outcome. BAG granules were always moistened with venous blood to enhance their adhesion and reduce the risk of dispersion. Anatomical results were evaluated in otomicroscopy and infection control was assessed during follow-up visits. Periodical otomicroscopy was performed to check recurrent cholesteatoma. MRI-DWI was indicated only in case of clinical suspect of cholesteatoma. Authors followed 66 patients during a mean of 23months. No post-operative wound infections occured. The mean re-epithelialization time was 45days. At the last visit, control of infection was achieved in 97% of patients and a clinical stable anatomical cavity in all patients. No clinical suspect for recurrent cholesteatoma was found. The use of bioactive glass is safe and effective as obliteration material in cholesteatoma surgery. Authors pay a particular attention to obliterate only patients without suspect of epithelial residual, to correctly calibrate the ear canal and to completely cover the granules with graft.

DETECTABILITY AND ANATOMICAL CORRELATION OF MIDDLE EAR CHOLESTEATOMA USING NON ECHO PLANAR DIFFUSION-WEIGHTED IMAGING AND HIGH RESOLUTION COMPUTED TOMOGRAPHY

This study was conducted to evaluate the role of non-echoplanar diffusion weighted imaging with apparent decient coefcient values and high resolution computed tomography in detection and anatomical extend of middle ear cholesteatoma, the extent of invasion of cholesteatoma using diffusion weighted imaging and high resolution computed tomography, and ability of MRI non-echoplanar DWI sequence unequivocally conrming the diagnosis of cholesteatoma. A cross sectional study with a t Materials and method: otal of 32 patients was conducted at Chettinad Hospitals and Research Institute's Department of Radiology between January 2020 and July 2021 after being diagnosed with chronic otitis media using otoscope as per inclusion and exclusion crietria . Written informed consent was taken to participate in the study, which was authorised by our institution's ethics committee. All statistical analyses we Results: re carried out on Microsoft Windows PCs using the SPSS, version 17. The descriptive data was represented using numbers and %ages. The data was expressed using the mean and standard deviation. To analyse qualitative data, the chi-square test was used. The screening test was carried out utilising a receiver operating characteristic (ROC) curve developed by the researchers. A p value 0.05 was judged statistically signicant on both sides of the equation. Combining DWI with HRCT is a Conclusion: valuable method for evaluating the soft tissue of the middle ear. It has high sensitivity and specicity for detecting all primary cholesteatomas in their various stages of development

Use of artificial intelligence for the diagnosis of cholesteatoma.

Accurate diagnosis of cholesteatomas is crucial. However, cholesteatomas can easily be missed in routine otoscopic exams. Convolutional neural networks (CNNs) have performed well in medical image classification, so we evaluated their use for detecting cholesteatomas in otoscopic images. Design and evaluation of artificial intelligence driven workflow for cholesteatoma diagnosis. Otoscopic images collected from the faculty practice of the senior author were deidentified and labeled by the senior author as cholesteatoma, abnormal non-cholesteatoma, or normal. An image classification workflow was developed to automatically differentiate cholesteatomas from other possible tympanic membrane appearances. Eight pretrained CNNs were trained on our otoscopic images, then tested on a withheld subset of images to evaluate their final performance. CNN intermediate activations were also extracted to visualize important image features. A total of 834 otoscopic images were collected, further categorized into 197 cholesteatoma, 457 abnormal non-cholesteatoma, and 180 normal. Final trained CNNs demonstrated strong performance, achieving accuracies of 83.8%-98.5% for differentiating cholesteatoma from normal, 75.6%-90.1% for differentiating cholesteatoma from abnormal non-cholesteatoma, and 87.0%-90.4% for differentiating cholesteatoma from non-cholesteatoma (abnormal non-cholesteatoma + normal). DenseNet201 (100% sensitivity, 97.1% specificity), NASNetLarge (100% sensitivity, 88.2% specificity), and MobileNetV2 (94.1% sensitivity, 100% specificity) were among the best performing CNNs in distinguishing cholesteatoma versus normal. Visualization of intermediate activations showed robust detection of relevant image features by the CNNs. While further refinement and more training images are needed to improve performance, artificial intelligence-driven analysis of otoscopic images shows great promise as a diagnostic tool for detecting cholesteatomas. 3.

A Case of Supralabyrinthine Petrous Bone Cholesteatoma Mimicking Facial Nerve Schwannoma

We report the case of a 31-year-old woman with a supralabyrinthine petrous bone cholesteatoma who presented with acute facial paralysis, without other symptoms; she had first noticed the symptoms 2 months earlier. She was prescribed oral steroid therapy at a previous clinic, which had proved ineffective. Examination revealed a normal appearance of the tympanic membrane, and pure tone audiometry showed no evidence of hearing loss. Computed tomography (CT) revealed a spindle-shaped soft-tissue lesion occupying the labyrinthine segment of the facial nerve coursing to the epitympanum. Gadolinium-enhanced magnetic resonance imaging (MRI) revealed a non-enhancing mass in the same region. A provisional diagnosis of facial nerve schwannoma was made on clinical and radiological grounds, and surgical resection was performed via a middle fossa approach. Keratin debris was found along the labyrinthine segment of the facial nerve coursing to the ossicles, which led us to make the diagnosis of cholesteatoma. The lesion was completely resected along with the head of the malleus and incus by mastoidectomy, and ossiculoplasty was performed. Histological examination confirmed the diagnosis of cholesteatoma. The patient’s facial paralysis failed to recover. In patients with a small lesion in the petrous bone who present with isolated facial palsy as the only clinical manifestation, it is often difficult to differentiate between a cholesteatoma and facial nerve schwannoma, and gadolinium-enhanced MRI is a useful imaging examination to differentiate between the two diseases. In the present case, facial nerve schwannoma was suspected as the most likely diagnosis based on the clinical presentation and CT findings; however, the lack of enhancement on gadolinium MRI pointed to the diagnosis of cholesteatoma. Physicians should be aware of these clinical aspects for appropriate treatment planning.

How advantageous is it to use computed tomography image-based artificial intelligence modelling in the differential diagnosis of chronic otitis media with and without cholesteatoma?

Cholesteatoma (CHO) developing secondary to chronic otitis media (COM) can spread rapidly and cause important health problems such as hearing loss. Therefore, the presence of CHO should be diagnosed promptly with high accuracy and then treated surgically. The aim of this study was to investigate the effectiveness of artificial intelligence applications (AIA) in documenting the presence of CHO based on computed tomography (CT) images. The study was performed on CT images of 100 CHO, 100 non-cholesteatoma (N-CHO) COM, and 100 control patients. Two AIA models including ResNet50 and MobileNetV2 were used for the classification of the images. Overall accuracy rate was 93.33% for the ResNet50 model and 86.67% for the MobilNetV2 model. Moreover, the diagnostic accuracy rates of these two models were 100% and 95% in the CHO group, 90% and 85% in the N-CHO group, and 90% and 80% in the control group, respectively. These results indicate that the use of AIA in the diagnosis of CHO will improve the diagnostic accuracy rates and will also help physicians in terms of reducing their workload and facilitating the selection of the correct treatment strategy.

Localization Evaluation of Primary Middle Ear Cholesteatoma With Fusion of Turbo Spin-Echo Diffusion-Weighted Imaging and High-Resolution Computed Tomography.

The aim of the study is to evaluate the application of high-resolution computed tomography (HRCT) and turbo spin-echo diffusion-weighted imaging (TSE-DWI) fusion imaging for localization of middle ear cholesteatomas. Eighty-six patients with clinically suspected middle ear cholesteatomas were enrolled prospectively. Ear TSE-DWI and HRCT scans were performed using a postprocessing workstation to generate a TSE-DWI-CT fusion image. Subsequently, all the enrolled patients received surgical treatment. According to the STAM system (difficult access sites [S], the tympanic cavity [T], the attic [A], and the mastoid [M]), the agreement between the localization of lesions evaluated by HRCT, TSE-DWI, and TSE-DWI-CT fusion images and the intraoperatively recorded localization were computed using Cohen κ statistic. Based on the pathological results, the enrolled patients were divided into a cholesteatoma (n = 50) and a noncholesteatoma group (n = 36). The area under the receiver operator characteristic curve for diagnosis of cholesteatoma with TSE-DWI-CT fusion imaging was identical to that using the TSE-DWI images (0.924 vs 0.924, P > 0.05), but was significantly higher than that with HRCT imaging (0.924 vs 0.767, P = 0.0005). Furthermore, the diagnostic sensitivity and specificity of TSE-DWI-CT fusion imaging for cholesteatomas were 96.0% and 88.9%, respectively. Depending on whether the cholesteatoma extended to the mastoid, TSE-DWI-CT fusion imaging demonstrated good agreement with the intraoperative record for localization of lesions (κ = 0.808) and had a high accuracy of localization by the STAM system. Turbo spin-echo-DWI-CT fusion images have a very high diagnostic value for the preoperative localization of cholesteatomas.

Diagnosis and Treatment Modalities of Cholesteatomas: A Review.

A cholesteatoma is an abnormal, noncancerous skin growth that can appear beneath the eardrum in the center of your ear. Although it might be a congenital condition, frequent middle ear infections are the main culprit. A cholesteatoma frequently appears as a cyst or sac that exfoliates the skin's outer layers. As these dead skin cells build up, the growth can enlarge and penetrate intratemporal tissues, leading to various intracranial and extracranial difficulties that can compromise facial muscles, hearing, and balance. Cholesteatomas were recognized more than three centuries ago. A cholesteatoma can develop into a serious condition if it is not treated right away. Because of its fast development and invasive nature, it can cause several consequences, some of which can be fatal for people without access to advanced medical treatment. There are no effective nonsurgical treatments available right now. It will be necessary to have a thorough awareness of both previous developments and more current ones to develop an appropriate management approach for this condition. The background information on acquired middle ear cholesteatomas is briefly reviewed in this paper. We also take into account categorization-, epidemiology-, histology-, and pathogenesis-related difficulties, and we carefully review current management and diagnosis approaches.

Automated multi-class classification for prediction of tympanic membrane changes with deep learning models.

Evaluating the tympanic membrane (TM) using an otoendoscope is the first and most important step in various clinical fields. Unfortunately, most lesions of TM have more than one diagnostic name. Therefore, we built a database of otoendoscopic images with multiple diseases and investigated the impact of concurrent diseases on the classification performance of deep learning networks. This retrospective study investigated the impact of concurrent diseases in the tympanic membrane on diagnostic performance using multi-class classification. A customized architecture of EfficientNet-B4 was introduced to predict the primary class (otitis media with effusion (OME), chronic otitis media (COM), and 'None' without OME and COM) and secondary classes (attic cholesteatoma, myringitis, otomycosis, and ventilating tube). Deep-learning classifications accurately predicted the primary class with dice similarity coefficient (DSC) of 95.19%, while misidentification between COM and OME rarely occurred. Among the secondary classes, the diagnosis of attic cholesteatoma and myringitis achieved a DSC of 88.37% and 88.28%, respectively. Although concurrent diseases hampered the prediction performance, there was only a 0.44% probability of inaccurately predicting two or more secondary classes (29/6,630). The inference time per image was 2.594 ms on average. Deep-learning classification can be used to support clinical decision-making by accurately and reproducibly predicting tympanic membrane changes in real time, even in the presence of multiple concurrent diseases.