ABSTRACT
Purpose: To compare the diagnostic performance of virtual monoenergetic imaging (VMI), computed tomography (CT), and magnetic resonance imaging (MRI) in patients with endometrial cancer (EC). Material and methods: This retrospective study analysed 45 EC patients (mean age: 62 years, range: 44-84 years) undergoing contrast-enhanced CT with dual-energy CT (DECT) and MRI between September 2021 and October 2022. Dual-energy CT generated conventional CT (C-CT) and 40 keV VMI. Quantitative analysis compared contrast-to-noise ratio (CNR) of tumour to myometrium between C-CT and VMI. Qualitative assessment by 5 radiologists compared C-CT, VMI, and MRI for myometrial invasion (MI), cervical invasion, and lymph node metastasis. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were calculated and compared for each diagnostic parameter. Results: Virtual monoenergetic imaging showed significantly higher CNR than C-CT (p < 0.001) and a higher sensitivity for MI than C-CT (p = 0.027) and MRI (p = 0.011) but lower specificity than MRI (p = 0.018). C-CT had a higher sensitivity and AUC for cervical invasion than MRI (p = 0.018 and 0.004, respectively). Conclusions: The study found no significant superiority of MRI over CT across all diagnostic parameters. VMI demonstrated heightened sensitivity for MI, and C-CT showed greater sensitivity and AUC for cervical invasion than MRI. This suggests that combining VMI with C-CT holds promise as a comprehensive preoperative staging tool for EC when MRI cannot be performed.
ABSTRACT
Case 1 : A 75-year-old man was emergently admitted to our hospital with a complaint of continuous bleeding from the ileal conduit. The conduit was constructed by a total pelvic resection for sigmoid colon cancer that invaded the urinary bladder 24 years ago. Swollen cutaneous mucosa was seen around the ileal conduit, but no obvious bleeding spot was observed. The contrast-enhanced computed tomographic (CT) scan and 3D visualization revealed varices extending to the abdominal wall. Percutaneous transhepatic embolization successfully stopped the bleeding, but it was needed again after two years. Case 2 : A 72-yearold man with a history of open cystectomy and ileal conduit for bladder cancer came to our hospital two years after the surgery, complaining of continuous bleeding from the conduit. The skin around the stoma site was discolored purple, but no obvious bleeding site or bloody urine was observed. The CT scan similar to Case 1 revealed varices in the ileal conduit, and percutaneous transhepatic embolization successfully stopped the bleeding, but it was needed again after five months. After that, three months passed without recurrence.
Subject(s)
Urinary Diversion , Varicose Veins , Humans , Male , Aged , Varicose Veins/surgery , Varicose Veins/diagnostic imaging , Embolization, Therapeutic , Tomography, X-Ray Computed , Urinary Bladder Neoplasms/surgery , Urinary Bladder Neoplasms/complications , Hemorrhage/etiology , Hemorrhage/surgery , Hemorrhage/diagnostic imagingABSTRACT
BACKGROUND: Pediatric minimally invasive surgery requires advanced technical skills. Off-the-job training (OJT), especially when using disease-specific models, is an effective method of acquiring surgical skills. To achieve effective OJT, it is necessary to provide objective and appropriate skill assessment feedback to trainees. We aimed to construct a system that automatically evaluates surgical skills based on forceps movement using deep learning (DL). METHODS: Using our original esophageal atresia OJT model, participants were tasked with performing esophageal anastomosis. All tasks were recorded for image analysis. Based on manual objective skill assessments, each participant's surgical skills were categorized into two groups: good and poor. The motion of the forceps in both groups was used as training data. Employing this training data, we constructed an automated system that recognized the movement of forceps and determined the quality of the surgical technique. RESULTS: Thirteen participants were assigned to the good skill group and 32 to the poor skill group. These cases were validated using an automated skill assessment system. This system showed a precision of 75%, a specificity of 94%, and an area under the receiver operating characteristic curve of 0.81. CONCLUSIONS: We constructed a system that automatically evaluated the quality of surgical techniques based on the movement of forceps using DL. Artificial intelligence diagnostics further revealed the procedures important for suture manipulation. LEVELS OF EVIDENCE: Level IV.
ABSTRACT
PURPOSE: Parkinson disease (PD) is a common progressive neurodegenerative disorder in our ageing society. Early-stage PD biomarkers are desired for timely clinical intervention and understanding of pathophysiology. Since one of the characteristics of PD is the progressive loss of dopaminergic neurons in the substantia nigra pars compacta, we propose a feature extraction method for analysing the differences in the substantia nigra between PD and non-PD patients. METHOD: We propose a feature-extraction method for volumetric images based on a rank-1 tensor decomposition. Furthermore, we apply a feature selection method that excludes common features between PD and non-PD. We collect neuromelanin images of 263 patients: 124 PD and 139 non-PD patients and divide them into training and testing datasets for experiments. We then experimentally evaluate the classification accuracy of the substantia nigra between PD and non-PD patients using the proposed feature extraction method and linear discriminant analysis. RESULTS: The proposed method achieves a sensitivity of 0.72 and a specificity of 0.64 for our testing dataset of 66 non-PD and 42 PD patients. Furthermore, we visualise the important patterns in the substantia nigra by a linear combination of rank-1 tensors with selected features. The visualised patterns include the ventrolateral tier, where the severe loss of neurons can be observed in PD. CONCLUSIONS: We develop a new feature-extraction method for the analysis of the substantia nigra towards PD diagnosis. In the experiments, even though the classification accuracy with the proposed feature extraction method and linear discriminant analysis is lower than that of expert physicians, the results suggest the potential of tensorial feature extraction.
ABSTRACT
PURPOSE: This paper considers a new problem setting for multi-organ segmentation based on the following observations. In reality, (1) collecting a large-scale dataset from various institutes is usually impeded due to privacy issues; (2) many images are not labeled since the slice-by-slice annotation is costly; and (3) datasets may exhibit inconsistent, partial annotations across different institutes. Learning a federated model from these distributed, partially labeled, and unlabeled samples is an unexplored problem. METHODS: To simulate this multi-organ segmentation problem, several distributed clients and a central server are maintained. The central server coordinates with clients to learn a global model using distributed private datasets, which comprise a small part of partially labeled images and a large part of unlabeled images. To address this problem, a practical framework that unifies partially supervised learning (PSL), semi-supervised learning (SSL), and federated learning (FL) paradigms with PSL, SSL, and FL modules is proposed. The PSL module manages to learn from partially labeled samples. The SSL module extracts valuable information from unlabeled data. Besides, the FL module aggregates local information from distributed clients to generate a global statistical model. With the collaboration of three modules, the presented scheme could take advantage of these distributed imperfect datasets to train a generalizable model. RESULTS: The proposed method was extensively evaluated with multiple abdominal CT datasets, achieving an average result of 84.83% in Dice and 41.62 mm in 95HD for multi-organ (liver, spleen, and stomach) segmentation. Moreover, its efficacy in transfer learning further demonstrated its good generalization ability for downstream segmentation tasks. CONCLUSION: This study considers a novel problem of multi-organ segmentation, which aims to develop a generalizable model using distributed, partially labeled, and unlabeled CT images. A practical framework is presented, which, through extensive validation, has proved to be an effective solution, demonstrating strong potential in addressing this challenging problem.
ABSTRACT
PURPOSES: We performed a conversation analysis of the speech conducted among the surgical team during three-dimensional (3D)-printed liver model navigation for thrice or more repeated hepatectomy (TMRH). METHODS: Seventeen patients underwent 3D-printed liver navigation surgery for TMRH. After transcription of the utterances recorded during surgery, the transcribed utterances were coded by the utterer, utterance object, utterance content, sensor, and surgical process during conversation. We then analyzed the utterances and clarified the association between the surgical process and conversation through the intraoperative reference of the 3D-printed liver. RESULTS: In total, 130 conversations including 1648 segments were recorded. Utterance coding showed that the operator/assistant, 3D-printed liver/real liver, fact check (F)/plan check (Pc), visual check/tactile check, and confirmation of planned resection or preservation target (T)/confirmation of planned or ongoing resection line (L) accounted for 791/857, 885/763, 1148/500, 1208/440, and 1304/344 segments, respectively. The utterance's proportions of assistants, F, F of T on 3D-printed liver, F of T on real liver, and Pc of L on 3D-printed liver were significantly higher during non-expert surgeries than during expert surgeries. Confirming the surgical process with both 3D-printed liver and real liver and performing planning using a 3D-printed liver facilitates the safe implementation of TMRH, regardless of the surgeon's experience. CONCLUSIONS: The present study, using a unique conversation analysis, provided the first evidence for the clinical value of 3D-printed liver for TMRH for anatomical guidance of non-expert surgeons.
ABSTRACT
The task of segmentation is integral to computer-aided surgery systems. Given the privacy concerns associated with medical data, collecting a large amount of annotated data for training is challenging. Unsupervised learning techniques, such as contrastive learning, have shown powerful capabilities in learning image-level representations from unlabelled data. This study leverages classification labels to enhance the accuracy of the segmentation model trained on limited annotated data. The method uses a multi-scale projection head to extract image features at various scales. The partitioning method for positive sample pairs is then improved to perform contrastive learning on the extracted features at each scale to effectively represent the differences between positive and negative samples in contrastive learning. Furthermore, the model is trained simultaneously with both segmentation labels and classification labels. This enables the model to extract features more effectively from each segmentation target class and further accelerates the convergence speed. The method was validated using the publicly available CholecSeg8k dataset for comprehensive abdominal cavity surgical segmentation. Compared to select existing methods, the proposed approach significantly enhances segmentation performance, even with a small labelled subset (1-10%) of the dataset, showcasing a superior intersection over union (IoU) score.
ABSTRACT
This paper focuses on a new and challenging problem related to instrument segmentation. This paper aims to learn a generalizable model from distributed datasets with various imperfect annotations. Collecting a large-scale dataset for centralized learning is usually impeded due to data silos and privacy issues. Besides, local clients, such as hospitals or medical institutes, may hold datasets with diverse and imperfect annotations. These datasets can include scarce annotations (many samples are unlabelled), noisy labels prone to errors, and scribble annotations with less precision. Federated learning (FL) has emerged as an attractive paradigm for developing global models with these locally distributed datasets. However, its potential in instrument segmentation has yet to be fully investigated. Moreover, the problem of learning from various imperfect annotations in an FL setup is rarely studied, even though it presents a more practical and beneficial scenario. This work rethinks instrument segmentation in such a setting and propose a practical FL framework for this issue. Notably, this approach surpassed centralized learning under various imperfect annotation settings. This method established a foundational benchmark, and future work can build upon it by considering each client owning various annotations and aligning closer with real-world complexities.
ABSTRACT
This study focuses on enhancing the inference speed of laparoscopic tool detection on embedded devices. Laparoscopy, a minimally invasive surgery technique, markedly reduces patient recovery times and postoperative complications. Real-time laparoscopic tool detection helps assisting laparoscopy by providing information for surgical navigation, and its implementation on embedded devices is gaining interest due to the portability, network independence and scalability of the devices. However, embedded devices often face computation resource limitations, potentially hindering inference speed. To mitigate this concern, the work introduces a two-fold modification to the YOLOv7 model: the feature channels and integrate RepBlock is halved, yielding the YOLOv7-RepFPN model. This configuration leads to a significant reduction in computational complexity. Additionally, the focal EIoU (efficient intersection of union) loss function is employed for bounding box regression. Experimental results on an embedded device demonstrate that for frame-by-frame laparoscopic tool detection, the proposed YOLOv7-RepFPN achieved an mAP of 88.2% (with IoU set to 0.5) on a custom dataset based on EndoVis17, and an inference speed of 62.9 FPS. Contrasting with the original YOLOv7, which garnered an 89.3% mAP and 41.8 FPS under identical conditions, the methodology enhances the speed by 21.1 FPS while maintaining detection accuracy. This emphasizes the effectiveness of the work.
ABSTRACT
Background: Fundus fluorescein angiography (FFA) is an imaging method used to assess retinal vascular structures by injecting exogenous dye. FFA images provide complementary information to that provided by the widely used color fundus (CF) images. However, the injected dye can cause some adverse side effects, and the method is not suitable for all patients. Methods: To meet the demand for high-quality FFA images in the diagnosis of retinopathy without side effects to patients, this study proposed an unsupervised image synthesis framework based on dual contrastive learning that can synthesize FFA images from unpaired CF images by inferring the effective mappings and avoid the shortcoming of generating blurred pathological features caused by cycle-consistency in conventional approaches. By adding class activation mapping (CAM) to the adaptive layer-instance normalization (AdaLIN) function, the generated images are made more realistic. Additionally, the use of CAM improves the discriminative ability of the model. Further, the Coordinate Attention Block was used for better feature extraction, and it was compared with other attention mechanisms to demonstrate its effectiveness. The synthesized images were quantified by the Fréchet inception distance (FID), kernel inception distance (KID), and learned perceptual image patch similarity (LPIPS). Results: The extensive experimental results showed the proposed approach achieved the best results with the lowest overall average FID of 50.490, the lowest overall average KID of 0.01529, and the lowest overall average LPIPS of 0.245 among all the approaches. Conclusions: When compared with several popular image synthesis approaches, our approach not only produced higher-quality FFA images with clearer vascular structures and pathological features, but also achieved the best FID, KID, and LPIPS scores in the quantitative evaluation.
ABSTRACT
Since even subtle mucosal changes may be depicted using virtual endoscopy created by the three-dimensional reconstruction of MDCT images, we developed a novel diagnostic imaging system that integrates and displays virtual enteroscopy, curved planar reconstruction, and a virtual unfolded view, the width of which changes with increases/decreases in the inner luminal diameter. The system is also equipped with artificial intelligence that superimposes and displays depressed areas, generates an automatic small bowel centerline that connects fragmented small bowel regions, and performs electronic cleansing. We retrospectively evaluated the diagnostic performance of this system for small bowel lesions in Crohn's disease, which were divided into two groups: endoscopically-observable and endoscopically-unobservable. Lesion detection rates for stenoses, longitudinal ulcers with a cobblestone appearance, and scars were excellent in both groups. This system, when used in combination with endoscopy, shows slight mucosal changes in areas in which an endoscope cannot reach due to strictures, thereby extending the range of observation of the small bowel. This system is a useful diagnostic modality that has the capacity to assess mucosal healing and provide extraluminal information.
ABSTRACT
PURPOSE: Pancreatic duct dilation is associated with an increased risk of pancreatic cancer, the most lethal malignancy with the lowest 5-year relative survival rate. Automatic segmentation of the dilated pancreatic duct from contrast-enhanced CT scans would facilitate early diagnosis. However, pancreatic duct segmentation poses challenges due to its small anatomical structure and poor contrast in abdominal CT. In this work, we investigate an anatomical attention strategy to address this issue. METHODS: Our proposed anatomical attention strategy consists of two steps: pancreas localization and pancreatic duct segmentation. The coarse pancreatic mask segmentation is used to guide the fully convolutional networks (FCNs) to concentrate on the pancreas' anatomy and disregard unnecessary features. We further apply a multi-scale aggregation scheme to leverage the information from different scales. Moreover, we integrate the tubular structure enhancement as an additional input channel of FCN. RESULTS: We performed extensive experiments on 30 cases of contrast-enhanced abdominal CT volumes. To evaluate the pancreatic duct segmentation performance, we employed four measurements, including the Dice similarity coefficient (DSC), sensitivity, normalized surface distance, and 95 percentile Hausdorff distance. The average DSC achieves 55.7%, surpassing other pancreatic duct segmentation methods on single-phase CT scans only. CONCLUSIONS: We proposed an anatomical attention-based strategy for the dilated pancreatic duct segmentation. Our proposed strategy significantly outperforms earlier approaches. The attention mechanism helps to focus on the pancreas region, while the enhancement of the tubular structure enables FCNs to capture the vessel-like structure. The proposed technique might be applied to other tube-like structure segmentation tasks within targeted anatomies.
Subject(s)
Abdomen , Image Processing, Computer-Assisted , Humans , Image Processing, Computer-Assisted/methods , Pancreas , Tomography, X-Ray Computed , Pancreatic Ducts/diagnostic imagingABSTRACT
In the mouse olfactory system, odor information is converted to a topographic map of activated glomeruli in the olfactory bulb (OB). Although the arrangement of glomeruli is genetically determined, the glomerular structure is plastic and can be modified by environmental stimuli. If the pups are exposed to a particular odorant, responding glomeruli become larger recruiting the dendrites of connecting projection neurons and interneurons. This imprinting not only increases the sensitivity to the exposed odor, but also imposes the positive quality on imprinted memory. External odor information represented as an odor map in the OB is transmitted to the olfactory cortex (OC) and amygdala for decision making to elicit emotional and behavioral outputs using two distinct neural pathways, innate and learned. Innate olfactory circuits start to work right after birth, whereas learned circuits become functional later on. In this paper, the recent progress will be summarized in the study of olfactory circuit formation and odor perception in mice. We will also propose new hypotheses on the timing and gating of olfactory circuit activity in relation to the respiration cycle.
Subject(s)
Sensation , Smell , Animals , Mice , Odorants , Amygdala , PerceptionABSTRACT
This review aims to provide an overview of neoplastic lesions associated with genetic diseases affecting the female reproductive organs. It seeks to enhance our understanding of the radiological aspects in diagnosing genetic diseases including hereditary breast and ovarian cancer syndromes, Lynch syndrome, Peutz-Jeghers syndrome, nevoid basal cell carcinoma syndrome, and Swyer syndrome, and explores the patterns and mechanisms of inheritance that require elucidation. Additionally, we discuss the imaging characteristics of lesions occurring in other regions due to the same genetic diseases.
Subject(s)
Genetic Diseases, Inborn , Humans , Female , Genetic Diseases, Inborn/diagnostic imaging , Genital Diseases, Female/diagnostic imaging , Diagnostic Imaging/methods , Genitalia, Female/diagnostic imagingABSTRACT
This review focuses on inflammatory diseases of female and male genital organs and discusses their epidemiology, pathogenesis, clinical presentation, and imaging findings. The female section covers pelvic inflammatory disease (PID) primarily caused by sexually transmitted infections (STIs) that affect the uterus, fallopian tubes, and ovaries. Unusual causes such as actinomycosis and tuberculosis have also been explored. The male section delves into infections affecting the vas deferens, epididymis, testes, prostate, and seminal vesicles. Uncommon causes such as tuberculosis, and Zinner syndrome have also been discussed. In addition, this review highlights other conditions that mimic male genital tract infections such as vasculitis, IgG4-related diseases, and sarcoidosis. Accurate diagnosis and appropriate management of these inflammatory diseases are essential for preventing serious complications and infertility. Imaging modalities such as ultrasound, magnetic resonance imaging, and computed tomography play a crucial role in diagnosis. Understanding the diverse etiologies and imaging findings is vital for the effective management of inflammatory diseases of the genital organs.
Subject(s)
Pelvic Inflammatory Disease , Tuberculosis , Male , Humans , Female , Pelvic Inflammatory Disease/complications , Pelvic Inflammatory Disease/diagnosis , Genitalia/diagnostic imaging , Uterus , Prostate , Tuberculosis/complicationsABSTRACT
BACKGROUND: We report a new real-time navigation system for laparoscopic hepatectomy (LH), which resembles a car navigation system. MATERIAL AND METHODS: Virtual three-dimensional liver and body images were reconstructed using the "New-VES" system, which worked as roadmap during surgery. Several points of the patient's body were registered in virtual images using a magnetic position sensor (MPS). A magnetic transmitter, corresponding to an artificial satellite, was placed about 40 cm above the patient's body. Another MPS, corresponding to a GPS antenna, was fixed on the handling part of the laparoscope. Fiducial registration error (FRE, an error between real and virtual lengths) was utilized to evaluate the accuracy of this system. RESULTS: Twenty-one patients underwent LH with this system. Mean FRE of the initial five patients was 17.7 mm. Mean FRE of eight patients in whom MDCT was taken using radiological markers for registration of body parts as first improvement, was reduced to 10.2 mm (p = .014). As second improvement, a new MPS as an intraoperative body position sensor was fixed on the right-sided chest wall for automatic correction of postural gap. The preoperative and postoperative mean FREs of 8 patients with both improvements were 11.1 mm and 10.1 mm (p = .250). CONCLUSIONS: Our system may provide a promising option that virtually guides LH.
Subject(s)
Hepatectomy , Laparoscopy , Humans , Hepatectomy/methods , Hepatectomy/instrumentation , Laparoscopy/methods , Laparoscopy/instrumentation , Female , Male , Middle Aged , Aged , Imaging, Three-Dimensional , Liver Neoplasms/surgery , Surgical Navigation Systems , Adult , Magnetics/instrumentation , Surgery, Computer-Assisted/methodsABSTRACT
AIM: To develop an artificial intelligence (AI) algorithm that diagnoses cataracts/corneal diseases from multiple conditions using smartphone images. METHODS: This study included 6442 images that were captured using a slit-lamp microscope (6106 images) and smartphone (336 images). An AI algorithm was developed based on slit-lamp images to differentiate 36 major diseases (cataracts and corneal diseases) into 9 categories. To validate the AI model, smartphone images were used for the testing dataset. We evaluated AI performance that included sensitivity, specificity and receiver operating characteristic (ROC) curve for the diagnosis and triage of the diseases. RESULTS: The AI algorithm achieved an area under the ROC curve of 0.998 (95% CI, 0.992 to 0.999) for normal eyes, 0.986 (95% CI, 0.978 to 0.997) for infectious keratitis, 0.960 (95% CI, 0.925 to 0.994) for immunological keratitis, 0.987 (95% CI, 0.978 to 0.996) for cornea scars, 0.997 (95% CI, 0.992 to 1.000) for ocular surface tumours, 0.993 (95% CI, 0.984 to 1.000) for corneal deposits, 1.000 (95% CI, 1.000 to 1.000) for acute angle-closure glaucoma, 0.992 (95% CI, 0.985 to 0.999) for cataracts and 0.993 (95% CI, 0.985 to 1.000) for bullous keratopathy. The triage of referral suggestion using the smartphone images exhibited high performance, in which the sensitivity and specificity were 1.00 (95% CI, 0.478 to 1.00) and 1.00 (95% CI, 0.976 to 1.000) for 'urgent', 0.867 (95% CI, 0.683 to 0.962) and 1.00 (95% CI, 0.971 to 1.000) for 'semi-urgent', 0.853 (95% CI, 0.689 to 0.950) and 0.983 (95% CI, 0.942 to 0.998) for 'routine' and 1.00 (95% CI, 0.958 to 1.00) and 0.896 (95% CI, 0.797 to 0.957) for 'observation', respectively. CONCLUSIONS: The AI system achieved promising performance in the diagnosis of cataracts and corneal diseases.
ABSTRACT
OBJECTIVES: In this study we aimed to develop an artificial intelligence-based model for predicting postendoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP). METHODS: We retrospectively reviewed ERCP patients at Nagoya University Hospital (NUH) and Toyota Memorial Hospital (TMH). We constructed two prediction models, a random forest (RF), one of the machine-learning algorithms, and a logistic regression (LR) model. First, we selected features of each model from 40 possible features. Then the models were trained and validated using three fold cross-validation in the NUH cohort and tested in the TMH cohort. The area under the receiver operating characteristic curve (AUROC) was used to assess model performance. Finally, using the output parameters of the RF model, we classified the patients into low-, medium-, and high-risk groups. RESULTS: A total of 615 patients at NUH and 544 patients at TMH were enrolled. Ten features were selected for the RF model, including albumin, creatinine, biliary tract cancer, pancreatic cancer, bile duct stone, total procedure time, pancreatic duct injection, pancreatic guidewire-assisted technique without a pancreatic stent, intraductal ultrasonography, and bile duct biopsy. In the three fold cross-validation, the RF model showed better predictive ability than the LR model (AUROC 0.821 vs. 0.660). In the test, the RF model also showed better performance (AUROC 0.770 vs. 0.663, P = 0.002). Based on the RF model, we classified the patients according to the incidence of PEP (2.9%, 10.0%, and 23.9%). CONCLUSION: We developed an RF model. Machine-learning algorithms could be powerful tools to develop accurate prediction models.
Subject(s)
Cholangiopancreatography, Endoscopic Retrograde , Pancreatitis , Humans , Cholangiopancreatography, Endoscopic Retrograde/adverse effects , Cholangiopancreatography, Endoscopic Retrograde/methods , Artificial Intelligence , Retrospective Studies , Pancreatitis/diagnosis , Pancreatitis/epidemiology , Pancreatitis/etiology , Pancreatic Ducts , Risk FactorsABSTRACT
PURPOSE: We propose a large-factor super-resolution (SR) method for performing SR on registered medical image datasets. Conventional SR approaches use low-resolution (LR) and high-resolution (HR) image pairs to train a deep convolutional neural network (DCN). However, LR-HR images in medical imaging are commonly acquired from different imaging devices, and acquiring LR-HR image pairs needs registration. Registered LR-HR images have registration errors inevitably. Using LR-HR images with registration error for training an SR DCN causes collapsed SR results. To address these challenges, we introduce a novel SR approach designed specifically for registered LR-HR medical images. METHODS: We propose style-subnets-assisted generative latent bank for large-factor super-resolution (SGSR) trained with registered medical image datasets. Pre-trained generative models named generative latent bank (GLB), which stores rich image priors, can be applied in SR to generate realistic and faithful images. We improve GLB by newly introducing style-subnets-assisted GLB (S-GLB). We also propose a novel inter-uncertainty loss to boost our method's performance. Introducing more spatial information by inputting adjacent slices further improved the results. RESULTS: SGSR outperforms state-of-the-art (SOTA) supervised SR methods qualitatively and quantitatively on multiple datasets. SGSR achieved higher reconstruction accuracy than recently supervised baselines by increasing peak signal-to-noise ratio from 32.628 to 34.206 dB. CONCLUSION: SGSR performs large-factor SR while given a registered LR-HR medical image dataset with registration error for training. SGSR's results have both realistic textures and accurate anatomical structures due to favorable quantitative and qualitative results. Experiments on multiple datasets demonstrated SGSR's superiority over other SOTA methods. SR medical images generated by SGSR are expected to improve the accuracy of pre-surgery diagnosis and reduce patient burden.
Subject(s)
Image Processing, Computer-Assisted , Neural Networks, Computer , Humans , Signal-To-Noise Ratio , Image Processing, Computer-Assisted/methodsABSTRACT
Ossification of the ligaments progresses slowly in the initial stages, and most patients are unaware of the disease until obvious myelopathy symptoms appear. Consequently, treatment and clinical outcomes are not satisfactory. This study is aimed at developing an automated system for the detection of the thoracic ossification of the posterior longitudinal ligament (OPLL) using deep learning and plain radiography. We retrospectively reviewed the data of 146 patients with thoracic OPLL and 150 control cases without thoracic OPLL. Plain lateral thoracic radiographs were used for object detection, training, and validation. Thereafter, an object detection system was developed, and its accuracy was calculated. The performance of the proposed system was compared with that of two spine surgeons. The accuracy of the proposed object detection model based on plain lateral thoracic radiographs was 83.4%, whereas the accuracies of spine surgeons 1 and 2 were 80.4% and 77.4%, respectively. Our findings indicate that our automated system, which uses a deep learning-based method based on plain radiographs, can accurately detect thoracic OPLL. This system has the potential to improve the diagnostic accuracy of thoracic OPLL.