A deep learning method for automatic segmentation of the bony orbit in MRI and CT images

Application of artificial intelligence in oculoplastics

Oculoplastics is a subspecialty of ophthalmology/dermatology concerned with eyelid, orbital, and lacrimal diseases. Artificial intelligence (AI), with its powerful ability to analyze large data sets, has dramatically benefited oculoplastics. The cutting-edge AI technology is widely applied to extract ocular parameters and to use these results for further assessment, such as screening and diagnosis of blepharoptosis and predicting the progression of thyroid eye disease. AI also assists in treatment procedures, such as surgical strategy planning in blepharoptosis. High efficiency and high reliability are the most apparent advantages of AI, with promising prospects. The possibilities of AI in oculoplastics may lie in three-dimensional modeling technology and image generation. We retrospectively summarize AI applications involving eyelid, orbital, and lacrimal diseases in oculoplastics, and we also examine the strengths and weaknesses of AI technology in oculoplastics.

Semiautomated MRI-Based Method for Orbital Volume and Contour Analysis

OBJECTIVE

The architecture of the orbital cavity is intricate, and precise measurement of its growth is essential for managing ocular and orbital pathologies. Most methods for those measurements are by CT imaging, although MRI for soft tissue assessment is indicated in many cases, specifically pediatric patients. This study introduces a novel semiautomated MRI-based approach for depicting orbital shape and dimensions.

DESIGN

A retrospective cohort study.

PARTICIPANTS

Patients with at least 1 normal orbit who underwent both CT and MRI imaging at a single center from 2015 to 2023.

METHODS

Orbital dimensions included volume, horizontal and vertical lengths, and depth. These were determined by manual segmentation followed by 3-dimensional image processing software.

MAIN OUTCOME MEASURES

Differences in orbital measurements between MRI and CT scans.

RESULTS

Thirty-one patients (mean age 47.7 ± 23.8 years, 21 [67.7%]) females, were included. The mean differences in delta values between orbital measurements on CT versus MRI were: volume 0.03 ± 2.01 ml, horizontal length 0.53 ± 2.12 mm, vertical length, 0.36 ± 2.53 mm, and depth 0.97 ± 3.90 mm. The CT and. MRI orbital measurements were strongly correlated: volume (r = 0.92, p < 0.001), horizontal length (r = 0.65, p < 0.001), vertical length (r = 0.57, p = 0.001), and depth (r = 0.46, p = 0.009). The mean values of all measurements were similar on the paired-samples t test: p = 0.9 for volume (30.86 ± 5.04 ml on CT and 30.88 ± 4.92 ml on MRI), p = 0.2 for horizontal length, p = 0.4 for vertical length, and p = 0.2 for depth.

CONCLUSIONS

We present an innovative semiautomated method capable of calculating orbital volume and demonstrating orbital contour by MRI validated against the gold standard CT-based measurements. This method can serve as a valuable tool for evaluating diverse orbital processes.

Semi-supervised segmentation of orbit in CT images with paired copy-paste strategy

The segmentation of the orbit in computed tomography (CT) images plays a crucial role in facilitating the quantitative analysis of orbital decompression surgery for patients with Thyroid-associated Ophthalmopathy (TAO). However, the task of orbit segmentation, particularly in postoperative images, remains challenging due to the significant shape variation and limited amount of labeled data. In this paper, we present a two-stage semi-supervised framework for the automatic segmentation of the orbit in both preoperative and postoperative images, which consists of a pseudo-label generation stage and a semi-supervised segmentation stage. A Paired Copy-Paste strategy is concurrently introduced to proficiently amalgamate features extracted from both preoperative and postoperative images, thereby augmenting the network discriminative capability in discerning changes within orbital boundaries. More specifically, we employ a random cropping technique to transfer regions from labeled preoperative images (foreground) onto unlabeled postoperative images (background), as well as unlabeled preoperative images (foreground) onto labeled postoperative images (background). It is imperative to acknowledge that every set of preoperative and postoperative images belongs to the identical patient. The semi-supervised segmentation network (stage 2) utilizes a combination of mixed supervisory signals from pseudo labels (stage 1) and ground truth to process the two mixed images. The training and testing of the proposed method have been conducted on the CT dataset obtained from the Eye Hospital of Wenzhou Medical University. The experimental results demonstrate that the proposed method achieves a mean Dice similarity coefficient (DSC) of 91.92% with only 5% labeled data, surpassing the performance of the current state-of-the-art method by 2.4%.

Neuroplasticity in honey bee brains: An enhanced micro-computed tomography protocol for precise mushroom body volume measurement

BACKGROUND

In insect brains, mushroom bodies are associated with memory and learning behavior. It has been demonstrated that the volume of the mushroom bodies in the brain of a worker honey bee changes during the adult stage. Changes in mushroom body volume imply high neuroplasticity in the brains and may be related to the age polyethism of honey bees. A suitable volume measurement method is needed to understand the correlation between behavioral changes and mushroom body volume changes in honey bees.

NEW METHOD

We developed a new protocol for insect micro-computed tomography by modifying a previously reported method. Permount™ mounting medium was used as the embedding medium for micro-computed tomography scanning.

RESULTS

This protocol can generate images with high contrast inside the brain and reduce the marked shape changes during specimen processing. From the resulting high-contrast images, we used freeware to generate a three-dimensional model and calculate the volumes of the mushroom bodies in honey bees. The measured volumes of the mushroom bodies were larger than the values reported in most previous studies. There was no significant difference between the left and right mushroom body volumes, but the volumes of honey bee mushroom bodies significantly increased with age.

COMPARISON WITH EXISTING METHODS

Previous protocols for micro-computed tomography using dried samples would cause brain shrinkage; protocols using ethanol-preserved or resin-embedded samples generated images with lower contrast.

CONCLUSIONS

The embedding protocol for micro-computed tomography is suitable for calculating volume of the mushroom bodies in honey bee brains.

Insights into Orbital Symmetry: A Comprehensive Retrospective Study of 372 Computed Tomography Scans

Background: The operation planning and production of individualized implants with the help of AI-based software after orbital fractures have become increasingly important in recent years. This retrospective study aimed to investigate the healthy orbitae of 372 patients from CT images in the bone and soft tissue windows using the Disior™ Bonelogic™ CMF Orbital software. (version 2.1.28). Methods: We analyzed the variables orbital volume, length, and area as a function of age and gender and compared bone and soft tissue windows. Results: For all variables, the intraclass correlation showed excellent agreement between the bone and soft tissue windows (p < 0.001). All variables showed higher values when calculated based on bone fenestration with, on average, 1 mL more volume, 0.35 mm more length, and 0.71 cm2 more area (p < 0.001). Across all age groups, men displayed higher values than women with, on average, 8.1 mL larger volume, a 4.78 mm longer orbit, and an 8.5 cm2 larger orbital area (p < 0.001). There was also a non-significant trend in all variables and both sexes toward growth with increasing age. Conclusions: These results mean that, due to the symmetry of the orbits in both the bone and soft tissue windows, the healthy orbit can be mirrored for surgical planning in the event of a fracture.

Nonspecific Orbital Inflammation (NSOI): Unraveling the Molecular Pathogenesis, Diagnostic Modalities, and Therapeutic Interventions

Nonspecific orbital inflammation (NSOI), colloquially known as orbital pseudotumor, sometimes presents a diagnostic and therapeutic challenge in ophthalmology. This review aims to dissect NSOI through a molecular lens, offering a comprehensive overview of its pathogenesis, clinical presentation, diagnostic methods, and management strategies. The article delves into the underpinnings of NSOI, examining immunological and environmental factors alongside intricate molecular mechanisms involving signaling pathways, cytokines, and mediators. Special emphasis is placed on emerging molecular discoveries and approaches, highlighting the significance of understanding molecular mechanisms in NSOI for the development of novel diagnostic and therapeutic tools. Various diagnostic modalities are scrutinized for their utility and limitations. Therapeutic interventions encompass medical treatments with corticosteroids and immunomodulatory agents, all discussed in light of current molecular understanding. More importantly, this review offers a novel molecular perspective on NSOI, dissecting its pathogenesis and management with an emphasis on the latest molecular discoveries. It introduces an integrated approach combining advanced molecular diagnostics with current clinical assessments and explores emerging targeted therapies. By synthesizing these facets, the review aims to inform clinicians and researchers alike, paving the way for molecularly informed, precision-based strategies for managing NSOI.

Automatic segmentation of inconstant fractured fragments for tibia/fibula from CT images using deep learning

Orthopaedic surgeons need to correctly identify bone fragments using 2D/3D CT images before trauma surgery. Advances in deep learning technology provide good insights into trauma surgery over manual diagnosis. This study demonstrates the application of the DeepLab v3+ -based deep learning model for the automatic segmentation of fragments of the fractured tibia and fibula from CT images and the results of the evaluation of the performance of the automatic segmentation. The deep learning model, which was trained using over 11 million images, showed good performance with a global accuracy of 98.92%, a weighted intersection over the union of 0.9841, and a mean boundary F1 score of 0.8921. Moreover, deep learning performed 5-8 times faster than the experts' recognition performed manually, which is comparatively inefficient, with almost the same significance. This study will play an important role in preoperative surgical planning for trauma surgery with convenience and speed.

Automatic segmentation of orbital wall from CT images via a thin wall region supervision-based multi-scale feature search network

PURPOSE

Orbital wall segmentation is critical for orbital measurement and reconstruction. However, the orbital floor and medial wall are made up of thin walls (TW) with low gradient values, making it difficult to segment the blurred areas of the CT images. Clinically, doctors have to manually repair the missing parts of TW, which is time-consuming and laborious.

METHODS

To address these issues, this paper proposes an automatic orbital wall segmentation method based on TW region supervision using a multi-scale feature search network. First of all, in the encoding branch, the densely connected atrous spatial pyramid pooling based on the residual connection is adopted to achieve a multi-scale feature search. Then, for feature enhancement, multi-scale up-sampling and residual connection are applied to perform skip connection of features in multi-scale convolution. Finally, we explore a strategy for improving the loss function based on the TW region supervision, which effectively increases the TW region segmentation accuracy.

RESULTS

The test results show that the proposed network performs well in terms of automatic segmentation. For the whole orbital wall region, the Dice coefficient (Dice) of segmentation accuracy reaches 96.086 ± 1.049%, the Intersection over Union (IOU) reaches 92.486 ± 1.924%, and the 95% Hausdorff distance (HD) reaches 0.509 ± 0.166 mm. For the TW region, the Dice reaches 91.470 ± 1.739%, the IOU reaches 84.327 ± 2.938%, and the 95% HD reaches 0.481 ± 0.082 mm. Compared with other segmentation networks, the proposed network improves the segmentation accuracy while filling the missing parts in the TW region.

CONCLUSION

In the proposed network, the average segmentation time of each orbital wall is only 4.05 s, obviously improving the segmentation efficiency of doctors. In the future, it may have a practical significance in clinical applications such as preoperative planning for orbital reconstruction, orbital modeling, orbital implant design, and so on.

Automatic orbital segmentation using deep learning-based 2D U-net and accuracy evaluation: A retrospective study

The purpose of this study was to verify whether the accuracy of automatic segmentation (AS) of computed tomography (CT) images of fractured orbits using deep learning (DL) is sufficient for clinical application. In the surgery of orbital fractures, many methods have been reported to create a 3D anatomical model for use as a reference. However, because the orbit bone is thin and complex, creating a segmentation model for 3D printing is complicated and time-consuming. Here, the training of DL was performed using U-Net as the DL model, and the AS output was validated with Dice coefficients and average symmetry surface distance (ASSD). In addition, the AS output was 3D printed and evaluated for accuracy by four surgeons, each with over 15 years of clinical experience. One hundred twenty-five CT images were prepared, and manual orbital segmentation was performed in all cases. Ten orbital fracture cases were randomly selected as validation data, and the remaining 115 were set as training data. AS was successful in all cases, with good accuracy: Dice, 0.860 ± 0.033 (mean ± SD); ASSD, 0.713 ± 0.212 mm. In evaluating AS accuracy, the expert surgeons generally considered that it could be used for surgical support without further modification. The orbital AS algorithm developed using DL in this study is extremely accurate and can create 3D models rapidly at low cost, potentially enabling safer and more accurate surgeries.

Are Magnetic Resonance Imaging-Generated 3Dimensional Models Comparable to Computed Tomography-Generated 3Dimensional Models for Orbital Fracture Reconstruction? An In-Vitro Volumetric Analysis

BACKGROUND

Magnetic resonance imaging (MRI) is being increasingly considered as an alternative for the evaluation and reconstruction of orbital fractures. No previous research has compared the orbital volume of an MRI-imaged, three-dimensional (3D), reconstructed, and virtually restored bony orbit to the gold standard of computed tomography (CT).

PURPOSE

To measure the orbital volumes generated from MRI-based 3D models of fractured bony orbits with virtually positioned prebent fan plates in situ and compare them to the volumes of CT-based virtually reconstructed orbital models.

STUDY DESIGN

This retrospective in-vitro study used CT and MRI data from adult patients with orbital trauma assessed at the Royal Brisbane and Women's Hospital Outpatient Maxillofacial Clinic from 2011 to 2012. Only those with orbital blowout fractures were included in the study.

PREDICTOR VARIABLE

The primary predictor variable was imaging modality, with CT- and MRI-based 3D models used for plate bending and placement.

MAIN OUTCOME VARIABLE

The primary outcome variable was the orbital volume of the enclosed 3D models.

COVARIATES

Additional data collected was age, sex, and side of fractured orbit. The effect of operator variability on plate contouring and orbital volume was quantified.

ANALYSES

The Wilcoxon signed rank test was used to assess differences between orbital volumes with a significance level P < .05.

RESULTS

Of 11 eligible participants, six patients (four male and two female; mean age 31 ± 8.6 years) were enrolled. Two sets of six CT-based virtually restored orbits were smaller than the intact contralateral CT models by an average of 1.02 cm3 (95% CI -0.07 to 2.11 cm3; P = .028) and 0.99 cm3 (95% CI 0.07 to 1.91 cm3; P = .028), respectively. The average volume difference between the MRI-based virtually restored orbit and the intact contralateral MRI model was 0.97 cm3 (95% CI -1.08 to 1.94 cm3; P = .75). Imaging modality did affect orbital volume difference for 1 set of CT and MRI models (0.63 cm3; 95% CI -0.11 to 1.29 cm3; P = .046) but not the other (0.69 cm3; 95% CI -0.11 to 1.23 cm3; P = .075). Single operator variability in plate bending did not result in significant (P = .75) volume differences.

CONCLUSIONS

MRI can be used to reconstruct orbital volume with a clinically acceptable level of accuracy.

Neural network application for assessing thyroid-associated orbitopathy activity using orbital computed tomography

This study aimed to propose a neural network (NN)-based method to evaluate thyroid-associated orbitopathy (TAO) patient activity using orbital computed tomography (CT). Orbital CT scans were obtained from 144 active and 288 inactive TAO patients. These CT scans were preprocessed by selecting eleven slices from axial, coronal, and sagittal planes and segmenting the region of interest. We devised an NN employing information extracted from 13 pipelines to assess these slices and clinical patient age and sex data for TAO activity evaluation. The proposed NN's performance in evaluating active and inactive TAO patients achieved a 0.871 area under the receiver operating curve (AUROC), 0.786 sensitivity, and 0.779 specificity values. In contrast, the comparison models CSPDenseNet and ConvNeXt were significantly inferior to the proposed model, with 0.819 (p = 0.029) and 0.774 (p = 0.04) AUROC values, respectively. Ablation studies based on the Sequential Forward Selection algorithm identified vital information for optimal performance and evidenced that NNs performed best with three to five active pipelines. This study establishes a promising TAO activity diagnosing tool with further validation.

Automated Segmentation of Levator Ani Muscle from 3D Endovaginal Ultrasound Images

Levator ani muscle (LAM) avulsion is a common complication of vaginal childbirth and is linked to several pelvic floor disorders. Diagnosing and treating these conditions require imaging of the pelvic floor and examination of the obtained images, which is a time-consuming process subjected to operator variability. In our study, we proposed using deep learning (DL) to automate the segmentation of the LAM from 3D endovaginal ultrasound images (EVUS) to improve diagnostic accuracy and efficiency. Over one thousand images extracted from the 3D EVUS data of healthy subjects and patients with pelvic floor disorders were utilized for the automated LAM segmentation. A U-Net model was implemented, with Intersection over Union (IoU) and Dice metrics being used for model performance evaluation. The model achieved a mean Dice score of 0.86, demonstrating a better performance than existing works. The mean IoU was 0.76, indicative of a high degree of overlap between the automated and manual segmentation of the LAM. Three other models including Attention UNet, FD-UNet and Dense-UNet were also applied on the same images which showed comparable results. Our study demonstrated the feasibility and accuracy of using DL segmentation with U-Net architecture to automate LAM segmentation to reduce the time and resources required for manual segmentation of 3D EVUS images. The proposed method could become an important component in AI-based diagnostic tools, particularly in low socioeconomic regions where access to healthcare resources is limited. By improving the management of pelvic floor disorders, our approach may contribute to better patient outcomes in these underserved areas.

Deep-Learning-Based Segmentation of Extraocular Muscles from Magnetic Resonance Images

In this study, we investigated the performance of four deep learning frameworks of U-Net, U-NeXt, DeepLabV3+, and ConResNet in multi-class pixel-based segmentation of the extraocular muscles (EOMs) from coronal MRI. Performances of the four models were evaluated and compared with the standard F-measure-based metrics of intersection over union (IoU) and Dice, where the U-Net achieved the highest overall IoU and Dice scores of 0.77 and 0.85, respectively. Centroid distance offset between identified and ground truth EOM centroids was measured where U-Net and DeepLabV3+ achieved low offsets (p > 0.05) of 0.33 mm and 0.35 mm, respectively. Our results also demonstrated that segmentation accuracy varies in spatially different image planes. This study systematically compared factors that impact the variability of segmentation and morphometric accuracy of the deep learning models when applied to segmenting EOMs from MRI.

Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives

Artificial intelligence (AI) is an emerging technology in healthcare and holds the potential to disrupt many arms in medical care. In particular, disciplines using medical imaging modalities, including e.g. radiology but ophthalmology as well, are already confronted with a wide variety of AI implications. In ophthalmologic research, AI has demonstrated promising results limited to specific diseases and imaging tools, respectively. Yet, implementation of AI in clinical routine is not widely spread due to availability, heterogeneity in imaging techniques and AI methods. In order to describe the status quo, this narrational review provides a brief introduction to AI ("what the ophthalmologist needs to know"), followed by an overview of different AI-based applications in ophthalmology and a discussion on future challenges.Abbreviations: Age-related macular degeneration, AMD; Artificial intelligence, AI; Anterior segment OCT, AS-OCT; Coronary artery calcium score, CACS; Convolutional neural network, CNN; Deep convolutional neural network, DCNN; Diabetic retinopathy, DR; Machine learning, ML; Optical coherence tomography, OCT; Retinopathy of prematurity, ROP; Support vector machine, SVM; Thyroid-associated ophthalmopathy, TAO.

Micro-CT and deep learning: Modern techniques and applications in insect morphology and neuroscience

Advances in modern imaging and computer technologies have led to a steady rise in the use of micro-computed tomography (µCT) in many biological areas. In zoological research, this fast and non-destructive method for producing high-resolution, two- and three-dimensional images is increasingly being used for the functional analysis of the external and internal anatomy of animals. µCT is hereby no longer limited to the analysis of specific biological tissues in a medical or preclinical context but can be combined with a variety of contrast agents to study form and function of all kinds of tissues and species, from mammals and reptiles to fish and microscopic invertebrates. Concurrently, advances in the field of artificial intelligence, especially in deep learning, have revolutionised computer vision and facilitated the automatic, fast and ever more accurate analysis of two- and three-dimensional image datasets. Here, I want to give a brief overview of both micro-computed tomography and deep learning and present their recent applications, especially within the field of insect science. Furthermore, the combination of both approaches to investigate neural tissues and the resulting potential for the analysis of insect sensory systems, from receptor structures via neuronal pathways to the brain, are discussed.

Deep Learning-Based Medical Images Segmentation of Musculoskeletal Anatomical Structures: A Survey of Bottlenecks and Strategies

By leveraging the recent development of artificial intelligence algorithms, several medical sectors have benefited from using automatic segmentation tools from bioimaging to segment anatomical structures. Segmentation of the musculoskeletal system is key for studying alterations in anatomical tissue and supporting medical interventions. The clinical use of such tools requires an understanding of the proper method for interpreting data and evaluating their performance. The current systematic review aims to present the common bottlenecks for musculoskeletal structures analysis (e.g., small sample size, data inhomogeneity) and the related strategies utilized by different authors. A search was performed using the PUBMED database with the following keywords: deep learning, musculoskeletal system, segmentation. A total of 140 articles published up until February 2022 were obtained and analyzed according to the PRISMA framework in terms of anatomical structures, bioimaging techniques, pre/post-processing operations, training/validation/testing subset creation, network architecture, loss functions, performance indicators and so on. Several common trends emerged from this survey; however, the different methods need to be compared and discussed based on each specific case study (anatomical region, medical imaging acquisition setting, study population, etc.). These findings can be used to guide clinicians (as end users) to better understand the potential benefits and limitations of these tools.

Effective encoder-decoder neural network for segmentation of orbital tissue in computed tomography images of Graves' orbitopathy patients

PURPOSE

To propose a neural network (NN) that can effectively segment orbital tissue in computed tomography (CT) images of Graves' orbitopathy (GO) patients.

METHODS

We analyzed orbital CT scans from 701 GO patients diagnosed between 2010 and 2019 and devised an effective NN specializing in semantic orbital tissue segmentation in GO patients' CT images. After four conventional (Attention U-Net, DeepLab V3+, SegNet, and HarDNet-MSEG) and the proposed NN train the various manual orbital tissue segmentations, we calculated the Dice coefficient and Intersection over Union for comparison.

RESULTS

CT images of the eyeball, four rectus muscles, the optic nerve, and the lacrimal gland tissues from all 701 patients were analyzed in this study. In the axial image with the largest eyeball area, the proposed NN achieved the best performance, with Dice coefficients of 98.2% for the eyeball, 94.1% for the optic nerve, 93.0% for the medial rectus muscle, and 91.1% for the lateral rectus muscle. The proposed NN also gave the best performance for the coronal image. Our qualitative analysis demonstrated that the proposed NN outputs provided more sophisticated orbital tissue segmentations for GO patients than the conventional NNs.

CONCLUSION

We concluded that our proposed NN exhibited an improved CT image segmentation for GO patients over conventional NNs designed for semantic segmentation tasks.

Orbital and eyelid diseases: The next breakthrough in artificial intelligence?

Orbital and eyelid disorders affect normal visual functions and facial appearance, and precise oculoplastic and reconstructive surgeries are crucial. Artificial intelligence (AI) network models exhibit a remarkable ability to analyze large sets of medical images to locate lesions. Currently, AI-based technology can automatically diagnose and grade orbital and eyelid diseases, such as thyroid-associated ophthalmopathy (TAO), as well as measure eyelid morphological parameters based on external ocular photographs to assist surgical strategies. The various types of imaging data for orbital and eyelid diseases provide a large amount of training data for network models, which might be the next breakthrough in AI-related research. This paper retrospectively summarizes different imaging data aspects addressed in AI-related research on orbital and eyelid diseases, and discusses the advantages and limitations of this research field.

A Sequential Machine Learning-cum-Attention Mechanism for Effective Segmentation of Brain Tumor

Magnetic resonance imaging is the most generally utilized imaging methodology that permits radiologists to look inside the cerebrum using radio waves and magnets for tumor identification. However, it is tedious and complex to identify the tumorous and nontumorous regions due to the complexity in the tumorous region. Therefore, reliable and automatic segmentation and prediction are necessary for the segmentation of brain tumors. This paper proposes a reliable and efficient neural network variant, i.e., an attention-based convolutional neural network for brain tumor segmentation. Specifically, an encoder part of the UNET is a pre-trained VGG19 network followed by the adjacent decoder parts with an attention gate for segmentation noise induction and a denoising mechanism for avoiding overfitting. The dataset we are using for segmentation is BRATS’20, which comprises four different MRI modalities and one target mask file. The abovementioned algorithm resulted in a dice similarity coefficient of 0.83, 0.86, and 0.90 for enhancing, core, and whole tumors, respectively.

Deep Learning Analyses of Brain MRI to Identify Sustained Attention Deficit in Treated Obstructive Sleep Apnea: A Pilot Study

Purpose

Persistent sustained attention deficit (SAD) after continuous positive airway pressure (CPAP) treatment is a source of quality of life and occupational impairment in obstructive sleep apnea (OSA). However, persistent SAD is difficult to predict in patients initiated on CPAP treatment. We performed secondary analyses of brain magnetic resonance (MR) images in treated OSA participants, using deep learning, to predict SAD.

Methods

26 middle-aged men with CPAP use of more than 6 hours daily and MR imaging were included. SAD was defined by psychomotor vigilance task lapses of more than 2. 17 participants had SAD and 9 were without SAD. A Convolutional Neural Network (CNN) model was used for classifying the MR images into +SAD and -SAD categories.

Results

The CNN model achieved an accuracy of 97.02±0.80% in classifying MR images into +SAD and -SAD categories. Assuming a threshold of 90% probability for the MR image being correctly classified, the model provided a participant-level accuracy of 99.11±0.55% and a stable image level accuracy of 97.45±0.63%.

Conclusion

Deep learning methods, such as the proposed CNN model, can accurately predict persistent SAD based on MR images. Further replication of these findings will allow early initiation of adjunctive pharmacologic treatment in high-risk patients, along with CPAP, to improve quality of life and occupational fitness. Future augmentation of this approach with explainable artificial intelligence methods may elucidate the neuroanatomical areas underlying persistent SAD to provide mechanistic insights and novel therapeutic targets.