Disc Segmentation Research Articles

Differentiating Glaucomatous Optic Neuropathy From Non-glaucomatous Optic Neuropathies Using Deep Learning Algorithms

A deep learning framework to differentiate glaucomatous optic disc changes due to glaucomatous optic neuropathy (GON) from non-glaucomatous optic disc changes due to non-glaucomatous optic neuropathies (NGONs). Cross-sectional study. A deep-learning system was trained, validated, and externally tested to classify optic discs as normal, GON, or NGON, using 2183 digital color fundus photographs. A Single-Center data set of 1822 images (660 images of NGON, 676 images of GON, and 486 images of normal optic discs) was used for training and validation, whereas 361 photographs from 4 different data sets were used for external testing. Our algorithm removed the redundant information from the images using an optic disc segmentation (OD-SEG) network, after which we performed transfer learning with various pre-trained networks. Finally, we calculated sensitivity, specificity, F1-score, and precision to show the performance of the discrimination network in the validation and independent external data set. For classification, the algorithm with the best performance for the Single-Center data set was DenseNet121, with a sensitivity of 95.36%, precision of 95.35%, specificity of 92.19%, and F1 score of 95.40%. For the external validation data, the sensitivity and specificity of our network for differentiating GON from NGON were 85.53% and 89.02%, respectively. The glaucoma specialist who diagnosed those cases in masked fashion had a sensitivity of 71.05% and a specificity of 82.21%. The proposed algorithm for the differentiation of GON from NGON yields results that have a higher sensitivity than those of a glaucoma specialist, and its application for unseen data thus is extremely promising.

A fundus image enhancer based on illumination-guided attention and optic disc perception GAN

High-quality fundus images are essential for ophthalmologists in clinical diagnosis of eye diseases. For reasons such as the acquisition process and the retinal disease, most fundus images may suffer poor illumination, blur, and low contrast. In order to obtain high-quality fundus images, a novel network model for fundus image enhancement is constructed in this paper. The model introduces a generated adversarial network (GAN) with illumination-guided attention and optic disc perception. A U-Net with illumination-guided attention is used as the generator, and a global discriminator and a local discriminator with optic disc segmentation are used in the learning process. The model can improve the exposure level of overexposed and underexposed fundus images and also stretch the contrast. Experiments are performed on multiple fundus image datasets taken by the handheld device and high-end device to verify the robustness of the proposed illumination-guided attention and optic disc perception GAN (IGAODPGAN). The retinal structure and pathological characteristics are highlighted significantly after enhancement. Our method is superior to other state-of-the-art algorithms in terms of both subjective and objective assessment, which can provide an efficient solution for fundus image enhancement, especially for the non-uniform illuminated fundus images.

Comparison of Single-level Cervical Radiculopathy Outcomes Between Posterior Endoscopic Cervical Decompression and Anterior Cervical Discectomy and Fusion: Mid-term Results.

A retrospective cohort study. To investigate the mid-term results and technical possibilities of posterior endoscopic cervical decompression (PECD) in the treatment of cervical radiculopathy. PECD has been used in the treatment of cervical radiculopathy for the past decades; there is a paucity of studies directly comparing its outcomes with anterior cervical discectomy and fusion (ACDF) for patients with single-level cervical radiculopathy. From January 2016 to December 2018, clinical and radiologic data of 42 patients were collected. Patients were followed for a mean of 40.6 months (range: 30-54 mo) after surgery. Changes in cervical lordosis and degeneration of adjacent segments were analyzed. Dysphagia was assessed using the Bazaz score, and clinical outcomes were analyzed using the Neck Disability Index and visual analog scoring system. There were no significant differences in neurological outcomes between the two groups. Significant between-group differences in postoperative dysphagia were observed ( P < 0.05). There were significant differences in postoperative segmental Cobb angles and disc height between the two groups ( P < 0.05). Degenerative changes in the adjacent segments occurred in 5 patients in the ACDF group and 1 patient in the PECD group ( P < 0.05); no revision surgery was needed. Clinical outcomes of PECD for patients with unilateral radiculopathy were satisfactory. On the premise of a strict selection of indications, we consider this technique to be a safe supplement and alternative to ACDF for patients with unilateral cervical radiculopathy. Longer follow-up periods are required to confirm these observations.

Optical Cup and Disc Segmentation using Deep Learning Technique for Glaucoma Detection

The optic nerve damaging condition called Glaucoma. This disease is increment at an alarming rate. By the end of the 2044 there is possibility that across 111.8 million populations will be influenced by glaucoma. It is a neurodegenerative disease. If intravascular pressure is increases, optic nerve of the eye gets damage. This damage may cause permanent or total blindness in person. The Glaucoma is examined by an experienced ophthalmologist on the retinal part of the eye. This process required excessive equipment, experienced medical practitioners and also it take more time to work out manually. After considering this problem there is an extreme requirement of developing an automatic system which will effectively and automatically work properly in lack of any professional doctor and it should also take less time. Lots of different parameters are available to detect glaucoma but thebest parameter is to find out optical cup-to-disc-ratio. To increase or to enhance the precision and accuracy of the result, cup to disc value is needed to find CDR value. In order to detect glaucoma, automatic separation of the OC and DC is very essential to avoid any error. We use deeplabv3 architecture to perform segmentation of optic disc and cup and classification is done using ensemble machine learning. This proposes research achieve intersection over union (IOU) scores, 0.9423 for optic disc and 0.9310 for optic cup. We perform testing on globally accessible data-sets i.e. DRISHTI, ORIGA, and RIMONE with accuracy of 93%, 91% and 92% respectively

Dual Consistency Enabled Weakly and Semi-Supervised Optic Disc and Cup Segmentation with Dual Adaptive Graph Convolutional Networks.

Glaucoma is a progressive eye disease that results in permanent vision loss, and the vertical cup to disc ratio (vCDR) in colour fundus images is essential in glaucoma screening and assessment. Previous fully supervised convolution neural networks segment the optic disc (OD) and optic cup (OC) from color fundus images and then calculate the vCDR offline. However, they rely on a large set of labeled masks for training, which is expensive and time-consuming to acquire. To address this, we propose a weakly and semi-supervised graph-based network that investigates geometric associations and domain knowledge between segmentation probability maps (PM), modified signed distance function representations (mSDF), and boundary region of interest characteristics (B-ROI) in three aspects. Firstly, we propose a novel Dual Adaptive Graph Convolutional Network (DAGCN) to reason the long-range features of the PM and the mSDF w.r.t. the regional uniformity. Secondly, we propose a dual consistency regularization-based semi-supervised learning paradigm. The regional consistency between the PM and the mSDF, and the marginal consistency between the derived B-ROI from each of them boost the proposed model's performance due to the inherent geometric associations. Thirdly, we exploit the task-specific domain knowledge via the oval shapes of OD & OC, where a differentiable vCDR estimating layer is proposed. Furthermore, without additional annotations, the supervision on vCDR serves as weakly-supervisions for segmentation tasks. Experiments on six large-scale datasets demonstrate our model's superior performance on OD & OC segmentation and vCDR estimation. The implementation code has been made available 1.

A Novel Approach for Diabetic Retinopathy Screening Using Asymmetric Deep Learning Features

Automatic screening of diabetic retinopathy (DR) is a well-identified area of research in the domain of computer vision. It is challenging due to structural complexity and a marginal contrast difference between the retinal vessels and the background of the fundus image. As bright lesions are prominent in the green channel, we applied contrast-limited adaptive histogram equalization (CLAHE) on the green channel for image enhancement. This work proposes a novel diabetic retinopathy screening technique using an asymmetric deep learning feature. The asymmetric deep learning features are extracted using U-Net for segmentation of the optic disc and blood vessels. Then a convolutional neural network (CNN) with a support vector machine (SVM) is used for the DR lesions classification. The lesions are classified into four classes, i.e., normal, microaneurysms, hemorrhages, and exudates. The proposed method is tested with two publicly available retinal image datasets, i.e., APTOS and MESSIDOR. The accuracy achieved for non-diabetic retinopathy detection is 98.6% and 91.9% for the APTOS and MESSIDOR datasets, respectively. The accuracies of exudate detection for these two datasets are 96.9% and 98.3%, respectively. The accuracy of the DR screening system is improved due to the precise retinal image segmentation.

Reduced volume of diabetic pancreatic islets in rodents detected by synchrotron X-ray phase-contrast microtomography and deep learning network

The pancreatic islet is a highly structured micro-organ that produces insulin in response to rising blood glucose. Here we develop a label-free and automatic imaging approach to visualize the islets in situ in diabetic rodents by the synchrotron radiation X-ray phase-contrast microtomography (SRμCT) at the ID17 station of the European Synchrotron Radiation Facility. The large-size images (3.2mm×15.97mm) were acquired in the pancreas in STZ-treated mice and diabetic GK rats. Each pancreas was dissected by 3000 reconstructed images. The image datasets were further analysed by a self-developed deep learning method, AA-Net. All islets in the pancreas were segmented and visualized by the three-dimension (3D) reconstruction. After quantifying the volumes of the islets, we found that the number of larger islets (=>1500 μm3) was reduced by 2-fold (wt 1004±94 vs GK 419±122, P<0.001) in chronically developed diabetic GK rat, while in STZ-treated diabetic mouse the large islets were decreased by half (189±33 vs 90±29, P<0.001) compared to the untreated mice. Our study provides a label-free tool for detecting and quantifying pancreatic islets in situ. It implies the possibility of monitoring the state of pancreatic islets in vivo diabetes without labelling.

Comparison of Lumbar Fusion Surgical Outcomes Between Patients with Lumbar Spinal Stenosis ≥80 Versus 65-79 Years Old.

BACKGROUND The efficacy of lumbar fusion surgery in patients age 80 years and older with lumbar spinal stenosis (LSS) is still controversial. This retrospective study aimed to evaluate the surgical outcomes of LSS patients ³80 vs 65-79 years. MATERIAL AND METHODS The study included 66 patients diagnosed with LSS from 2014 to 2020; 33 patients were ³80 years and 33 patients were 65-79 years. The 2 groups were matched for sex and surgical segment. All patients underwent posterior lumbar decompression, fixation, and fusion surgery. The Numerical Rating Scale (NRS) of leg and back pain, Oswestry Disability Index (ODI), Short-Form Health Survey (SF-36), and radiographic data were collected before surgery and at 3, 6, and 12 months postoperatively. RESULTS NRS (back) in the ≥80 years group was significantly higher than in the 65-79 years group at 3 months [2 (0-3) vs 1 (0-3), P=0.001]. Improvement of SF-36 (3 months: 15.7±4.9 vs 27.6±5.4, P<0.001; 6 months: 27.3±6.8 vs 31.5±5.6, P=0.011) and Physical Component Score (PCS) (3 months: 6.5±2.5 vs 17.0±3.6, P<0.001; 6 months: 15.9±3.4 vs 20.1±3.1, P<0.001) at 3 and 6 months in the ≥80 years group were significantly smaller than in 65-79 years group. There was a difference of Pfirrmann index of adjacent segment disc between the 2 groups at 12 months [≥80 vs 65-79 years group: 5.5 (4-8) vs 5 (3-8), P=0.003]. CONCLUSIONS Lumbar fusion surgery in patients ≥80 years with LSS can provide comparable improvements in clinical and radiographic outcomes compared with younger patients. Postoperative physiological function recovery was slower in patients ≥80 years.

Simultaneous segmentation of multiple structures in fundal images using multi-tasking deep neural networks

Introduction: Fundal imaging is the most commonly used non-invasive technique for early detection of many retinal diseases such as diabetic retinopathy (DR). An initial step in automatic processing of fundal images for detecting diseases is to identify and segment the normal landmarks: the optic disc, blood vessels, and macula. In addition to these structures, other parameters such as exudates that help in pathological evaluations are also visible in fundal images. Segmenting features like blood vessels pose multiple challenges because of their fine-grained structure that must be captured at original resolution and the fact that they are spread across the entire retina with varying patterns and densities. Exudates appear as white patches of irregular shapes that occur at multiple locations, and they can be confused with the optic disc, if features like brightness or color are used for segmentation.Methods: Segmentation algorithms solely based on image processing involve multiple parameters and thresholds that need to be tuned. Another approach is to use machine learning models with inputs of hand-crafted features to segment the image. The challenge in this approach is to identify the correct features and then devise algorithms to extract these features. End-to-end deep neural networks take raw images with minimal preprocessing, such as resizing and normalization, as inputs, learn a set of images in the intermediate layers, and then perform the segmentation in the last layer. These networks tend to have longer training and prediction times because of the complex architecture which can involve millions of parameters. This also necessitates huge numbers of training images (2000‒10,000). For structures like blood vessels and exudates that are spread across the entire image, one approach used to increase the training data is to generate multiple patches from a single training image, thus increasing the total number of training samples. Patch-based time cannot be applied to structures like the optic disc and fovea that appear only once per image. Also the prediction time is larger because segmenting a full image involves segmenting multiple patches in the image.Results and Discussion: Most of the existing research has been focused on segmenting these structures independently to achieve high performance metrics. In this work, we propose a multi-tasking, deep learning architecture for segmenting the optic disc, blood vessels, macula, and exudates simultaneously. Both training and prediction are performed using the whole image. The objective was to improve the prediction results on blood vessels and exudates, which are relatively more challenging, while utilizing segmentation of the optic disc and the macula as auxiliary tasks. Our experimental results on images from publicly available datasets show that simultaneous segmentation of all these structures results in a significant improvement in performance. The proposed approach makes predictions of all four structures in the whole image in a single forward pass. We used modified U-Net architecture with only convolutional and de-convolutional layers and comparatively.

Lumbar intervertebral disc segmentation for computer modeling and simulation

Background and objectiveThe present work had as its main objective the development of a method for localizing and automatically segmenting lumbar intervertebral discs (IVD) in 3D from magnetic resonance imaging (MRI), with the goal of supporting the generation of finite element (FE) models from actual lumbar spine anatomy, by providing accurate and personalized information on the shape of the patient's IVD. The extension of the method to allow performing separate segmentations of the IVD's two main structures – annulus fibrosus (AF) and nucleus pulposus (NP) – as well as automatically detecting degenerated IVD where this distinction is no longer possible was also an objective of the work. MethodsThe method presented here evolves from 2D segmentations in the sagittal profile using Gabor filters towards 3D segmentations. It works by detecting the spine curves and intensity regions corresponding to IVD. As so, the 2D method from Zhu et al. (2013) was partially implemented, modified and adapted to 3D use, and then tested with eight spines from two separated online datasets. The 3D adaptation was achieved by using vertebral body segmentation masks to approximate the shape of the vertebrae and to adjust the spine curves accordingly. ResultsThe method showed average values of 85%, 83% and 96% for the Dice coefficient, sensitivity and specificity, respectively. The method correctly identified 65 of 68 (96%) IVD as either healthy or degenerated. The method's Dice coefficient is within the range of existing 3D IVD segmentation methods in the literature (81–92%). The method took on average 6–7 s to perform a full 3D segmentation, which is well within the range of the existing methods (2 s – 19 min). ConclusionsThe developed method can be used to generate accurate 3D models of the IVD based on MRI, with AF/NP distinction and detection of marked degeneration by comparing each IVD with the remaining spine levels. Further work shall improve the method towards distinguishing between specific levels of degeneration for clinically oriented FE modeling.

Assisting Glaucoma Screening Process Using Feature Excitation and Information Aggregation Techniques in Retinal Fundus Images

The rapidly increasing trend of retinal diseases needs serious attention, worldwide. Glaucoma is a critical ophthalmic disease that can cause permanent vision impairment. Typically, ophthalmologists diagnose glaucoma using manual assessments which is an error-prone, subjective, and time-consuming approach. Therefore, the development of automated methods is crucial to strengthen and assist the existing diagnostic methods. In fundus imaging, optic cup (OC) and optic disc (OD) segmentation are widely accepted by researchers for glaucoma screening assistance. Many research studies proposed artificial intelligence (AI) based decision support systems for glaucoma diagnosis. However, existing AI-based methods show serious limitations in terms of accuracy and efficiency. Variations in backgrounds, pixel intensity values, and object size make the segmentation challenging. Particularly, OC size is usually very small with unclear boundaries which makes its segmentation even more difficult. To effectively address these problems, a novel feature excitation-based dense segmentation network (FEDS-Net) is developed to provide accurate OD and OC segmentation. FEDS-Net employs feature excitation and information aggregation (IA) mechanisms for enhancing the OC and OD segmentation performance. FEDS-Net also uses rapid feature downsampling and efficient convolutional depth for diverse and efficient learning of the network, respectively. The proposed framework is comprehensively evaluated on three open databases: REFUGE, Drishti-GS, and Rim-One-r3. FEDS-Net achieved outperforming segmentation performance compared with state-of-the-art methods. A small number of required trainable parameters (2.73 million) also confirms the superior computational efficiency of our proposed method.

Use of Segment Anything Model (SAM) and MedSAM in the optic disc Segmentation of colour retinal fundus images: Experimental Finding

Detection of Optic Disc segmentation in retinal fundus images is important step in identification of various abnormal conditions like diabetic retinopathy, Glaucoma etc. and is an important part of eye that is routinely examined. We have used Segment Anything model (SAM) by Meta AI and based fine-tuned model MedSAM for segmentation of optic disc in retinal fundus images. We have used Indian Diabetic Retinopathy dataset (IDRiD) segmentation part. It consists of 81 original colour fundus images in jpg files split into train and test set. Ground-truth images for the lesions (Microaneurysms, Haemorrhages, Hard Exudates and Soft Exudates divided into train and test set - TIF Files) and Optic Disc (divided into train and test set - TIF Files). This dataset is feed into the deep learning neural network model; Segment Anything Model (SAM) and MedSAM for the image segmentation task. The Dice Similarity Coefficient (DSC) is used in the experiment for observing the model performance. We have used 80% for training and 20% for testing of Indian Diabetic Retinopathy Dataset (IDRiD) in both models. After 100 epochs with 32 batch size it is observed that average Dice Similarity Coefficient (DSC) of SAM and MedSAM models in the optic disc segmentation task are, 85.97 % and 90.15 %. Also, in finding it is observed that SAM and MedSAM both have very low DSC where the fundus images are having very high brightness.

Retracted: Segmentation of Optic Disc and Cup Using Modified Recurrent Neural Network.

[This retracts the article DOI: 10.1155/2022/6799184.].

Use of Segment Anything Model (SAM) and MedSAM in the optic disc Segmentation of colour retinal fundus images: Experimental Finding

Detection of Optic Disc segmentation in retinal fundus images is important step in identification of various abnormal conditions like diabetic retinopathy, Glaucoma etc. and is an important part of eye that is routinely examined. We have used Segment Anything model (SAM) by Meta AI and based fine-tuned model MedSAM for segmentation of optic disc in retinal fundus images. We have used Indian Diabetic Retinopathy dataset (IDRiD) segmentation part. It consists of 81 original colour fundus images in jpg files split into train and test set. Ground-truth images for the lesions (Microaneurysms, Haemorrhages, Hard Exudates and Soft Exudates divided into train and test set - TIF Files) and Optic Disc (divided into train and test set - TIF Files). This dataset is feed into the deep learning neural network model; Segment Anything Model (SAM) and MedSAM for the image segmentation task. The Dice Similarity Coefficient (DSC) is used in the experiment for observing the model performance. We have used 80% for training and 20% for testing of Indian Diabetic Retinopathy Dataset (IDRiD) in both models. After 100 epochs with 32 batch size it is observed that average Dice Similarity Coefficient (DSC) of SAM and MedSAM models in the optic disc segmentation task are, 85.97 % and 90.15 %. Also, in finding it is observed that SAM and MedSAM both have very low DSC where the fundus images are having very high brightness.

Use of Segment Anything Model (SAM) and MedSAM in the optic disc Segmentation of colour retinal fundus images: Experimental Finding

Detection of Optic Disc segmentation in retinal fundus images is important step in identification of various abnormal conditions like diabetic retinopathy, Glaucoma etc. and is an important part of eye that is routinely examined. We have used Segment Anything model (SAM) by Meta AI and based fine-tuned model MedSAM for segmentation of optic disc in retinal fundus images. We have used Indian Diabetic Retinopathy dataset (IDRiD) segmentation part. It consists of 81 original colour fundus images in jpg files split into train and test set. Ground-truth images for the lesions (Microaneurysms, Haemorrhages, Hard Exudates and Soft Exudates divided into train and test set - TIF Files) and Optic Disc (divided into train and test set - TIF Files). This dataset is feed into the deep learning neural network model; Segment Anything Model (SAM) and MedSAM for the image segmentation task. The Dice Similarity Coefficient (DSC) is used in the experiment for observing the model performance. We have used 80% for training and 20% for testing of Indian Diabetic Retinopathy Dataset (IDRiD) in both models. After 100 epochs with 32 batch size it is observed that average Dice Similarity Coefficient (DSC) of SAM and MedSAM models in the optic disc segmentation task are, 85.97 % and 90.15 %. Also, in finding it is observed that SAM and MedSAM both have very low DSC where the fundus images are having very high brightness.

"Insert flipping technique:" An effective way of restoring segmental lordosis and disc height with tall bullet cages.

The study design was a retrospective study. The objectives of the present study are dual; to describe a simple and effective way of restoring intervertebral disc (IVD) height by the "Insert Flip Technique" of cage insertion and to demonstrate effective restoration of IVD height and segmental lordosis (SL) and their influence on the functional outcome postoperatively. IVD height and SL were recorded pre- and postoperatively. Each motion segment was instrumented with pedicle screws to allow segmental stabilization. Patients were called for follow-up at 6 weeks, 3 months, and 1 year postoperatively and were assessed clinically for back pain and leg pain (VAS and Oswestry Disability Index scores recorded).The bullet cages are designed such that they are lordotic in the superior-inferior plane and neutral in the mediolateral plane. Usually, the cage is inserted with superior and inferior surfaces of the cage impacting against superior and inferior end plates of the adjacent vertebral body. However, with the proposed technique, the cages were inserted such that the narrower mediolateral surfaces of the cage engaged with superior and inferior vertebral end plates. The cage was then flipped within the disc space such that the superior-inferior surfaces of the bullet cage impacted against the superior and inferior end plates of the vertebral body to create desired lordosis. There was a significant improvement seen in the postoperative Cobb's angle and disc height after placement of a tall bullet cage compared to the preoperative Cobb's angle and disc height. This modification of technique helped in gaining lordosis with taller bullet cages in minimally invasive surgery transforaminal lumbar interbody fusion with no/minimal complication and also reduced the need for bone resection during insertion of the cage.

The Root Causes of Lumbar Canal Stenosis: An Insight with a Narrative Review

In the older population, lumbar spinal stenosis is a frequent degenerative condition that can cause clinical symptoms such as neurogenic claudication or sciatica, either with or without low back pain. Anatomically, there are three different forms of lumbar spinal stenosis: central, foraminal, and lateral recess. The relationship between Ligamentum Flavum (LF) hypertrophy and mechanical stress, as seen in segmental instability or disc space expansion, and their correlation with lumbar facet joint arthropathy is still not clear. This review places particular emphasis on the causes like LF hypertrophy, lumbar segmental instability, lumbar segmental motion, disc degeneration, lumbar spine facet joint orientation, facet joint tropism and facet joint Osteoarthritis (OA) in Lumbar Canal Stenosis (LCS) studied in various different studies discovered in various other search databases. The present research will also help surgeons and radiologists to interpret neuroradiological data appropriately for surgery as well as non surgical treatment and get a better knowledge of the architecture of these structures and how they appear on neuroimaging investigations for further proper and apt management of LCS. Additionally, it would assist in creating a diagnostic algorithm for better functional results.

Domain and Content Adaptive Convolution Based Multi-Source Domain Generalization for Medical Image Segmentation.

The domain gap caused mainly by variable medical image quality renders a major obstacle on the path between training a segmentation model in the lab and applying the trained model to unseen clinical data. To address this issue, domain generalization methods have been proposed, which however usually use static convolutions and are less flexible. In this paper, we propose a multi-source domain generalization model based on the domain and content adaptive convolution (DCAC) for the segmentation of medical images across different modalities. Specifically, we design the domain adaptive convolution (DAC) module and content adaptive convolution (CAC) module and incorporate both into an encoder-decoder backbone. In the DAC module, a dynamic convolutional head is conditioned on the predicted domain code of the input to make our model adapt to the unseen target domain. In the CAC module, a dynamic convolutional head is conditioned on the global image features to make our model adapt to the test image. We evaluated the DCAC model against the baseline and four state-of-the-art domain generalization methods on the prostate segmentation, COVID-19 lesion segmentation, and optic cup/optic disc segmentation tasks. Our results not only indicate that the proposed DCAC model outperforms all competing methods on each segmentation task but also demonstrate the effectiveness of the DAC and CAC modules. Code is available at https://git.io/DCAC.

Polarformer: Optic Disc and Cup Segmentation Using a Hybrid CNN-Transformer and Polar Transformation

The segmentation of optic disc (OD) and optic cup (OC) are used in the automatic diagnosis of glaucoma. However, the spatially ambiguous boundary and semantically uncertain region-of-interest area in pictures may lead to the degradation of the performance of precise segmentation of the OC and OD. Unlike most existing methods, including the variants of CNNs (Convolutional Neural Networks) and U-Net, which limit the contributions of rich global features, we instead propose a hybrid CNN-transformer and polar transformation network, dubbed as Polarformer, which aims to extract discriminative and semantic features for robust OD and OC segmentation. Our Polarformer typically exploits contextualized features among all input units and models the correlation of structural relationships under the paradigm of the transformer backbone. More specifically, our learnable polar transformer module optimizes the polar transformations by sampling images in the Cartesian space and then mapping them back to the polar coordinate system for masked-image reconstruction. Extensive experimental results present that our Polarformer achieves superior performance in comparison to most state-of-the-art methods on three publicly available datasets.

Is spinal sagittal alignment of diffuse idiopathic skeletal hyperostosis relevant to thoracolumbar pain? A controlled study

ObjectivesThe extension of diffuse idiopathic skeletal hyperostosis (DISH) from the low thoracic spine to the lumbar spine result in adjustment of spinal sagittal alignment in surgical patients. The aim of this study was to investigate changes in sagittal alignment and back pain in the thoracolumbar spine in nonsurgical DISH and control participants selected from a radiological database.MethodsParticipants in the DISH and the control group were selected by searching for “DISH or degenerative changes in the thoracic spine” in the radiology database of Taizhou Hospital between 2018 and 2021 using Resnick and Niwayama’s criteria. The subjects with spinal tumors, previous spinal surgery, vertebral fractures, inflammatory diseases, poor-quality radiographs, or loss of follow-up were excluded. Demographic and clinical characteristics were recorded retrospectively via the hospital information system and telephone follow-up. Segmental disc angles (SDAs), lumbar lordosis (LL), and bridge scores were analyzed using images of three-dimensional CT.ResultsThe final participants consisted of 51 individuals with DISH (DISH group) and 102 individuals without DISH (control group). Depending on the presence of thoracolumbar pain, the DISH group was divided into the DISH group with thoracolumbar pain (DISH+Pain) and the DISH group without thoracolumbar pain (DISH-Pain). The LL and SDAs of T11-T12 and T12-L1 were significantly greater in the DISH group than in the control group. In addition, the SDA of L1-L2 was significantly smaller in the DISH+Pain group than in the DISH-Pain group, whereas there was no significant difference in lumbar lordosis between the DISH+Pain group and the DISH-Pain group. The bridge scores in DISH+Pain group was larger in T10-T11 (p = 0.01) and L1-L2 (p < 0.01) spine segments than those in DISH-Pain group.ConclusionThe extension of DISH from thoracic to lumbar spine may increase lumbar lordosis and SDAs in the thoracolumbar spine. The DISH patients with more bony bridging and small L1-L2 SDA may be more likely have thoracolumbar pain. Adjustment of sagittal alignment of the spine in the development of DISH may be of clinical importance.