Explore the vast range of titles available.

AimTo develop an artificial intelligence (AI) algorithm that diagnoses cataracts/corneal diseases from multiple conditions using smartphone images.MethodsThis 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.ResultsThe 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.ConclusionsThe AI system achieved promising performance in the diagnosis of cataracts and corneal diseases.

We developed a 2.2 µm backside-illuminated (BSI) global shutter (GS) pixel featuring true charge-domain-correlated double sampling (CDS). To enhance the inverse parasitic light sensitivity (1/PLS), we implemented a thick-film epitaxial process incorporating a dual-depth deep trench isolation (DTI) structure. The thickness of the epitaxial substrate was 8.5 µm. This structure was designed using optical simulation. By using a thick epitaxial substrate, it is possible to reduce the amount of light that reaches the memory node. The dual-depth DTI design, with a shallower trench on the readout side, enables efficient signal transfer from the photodiode (PD) to the memory node. To achieve this structure, we developed a process for thick epitaxial substrate, and the dual-depth DTI can be fabricated with a single mask. This pixel represents the smallest charge-domain GS pixel developed to date. Despite its compact size, it achieves a high quantum efficiency (QE) of 83% (monochrome sample: wavelength = 560 nm) and a 1/PLS exceeding 10,000 (white halogen lamp with IR-cut filter). The pixel retains 80% of its peak QE at ±15° incident angles and maintains stable 1/PLS performance even under low F-number (F#) conditions.

CorneAI, a deep learning model designed for diagnosing cataracts and corneal diseases, was assessed for its impact on ophthalmologists’ diagnostic accuracy. In the study, 40 ophthalmologists (20 specialists and 20 residents) classified 100 images, including iPhone 13 Pro photos (50 images) and diffuser slit-lamp photos (50 images), into nine categories (normal condition, infectious keratitis, immunological keratitis, corneal scar, corneal deposit, bullous keratopathy, ocular surface tumor, cataract/intraocular lens opacity, and primary angle-closure glaucoma). The iPhone and slit-lamp images represented the same cases. After initially answering without CorneAI, the same ophthalmologists responded to the same cases with CorneAI 2–4 weeks later. With CorneAI’s support, the overall accuracy of ophthalmologists increased significantly from 79.2 to 88.8% ( P  < 0.001). Specialists’ accuracy rose from 82.8 to 90.0%, and residents’ from 75.6 to 86.2% ( P  < 0.001). Smartphone image accuracy improved from 78.7 to 85.5% and slit-lamp image accuracy from 81.2 to 90.6% (both, P  < 0.001). In this study, CorneAI’s own accuracy was 86%, but its support enhanced ophthalmologists’ accuracy beyond the CorneAI’s baseline. This study demonstrated that CorneAI, despite being trained on diffuser slit-lamp images, effectively improved diagnostic accuracy, even with smartphone images.

We developed an AI system capable of automatically classifying anterior eye images as either normal or indicative of corneal diseases. This study aims to investigate the influence of AI’s misleading guidance on ophthalmologists’ responses. This cross-sectional study included 30 cases each of infectious and immunological keratitis. Responses regarding the presence of infection were collected from 7 corneal specialists and 16 non-corneal-specialist ophthalmologists, first based on the images alone and then after presenting the AI’s classification results. The AI’s diagnoses were deliberately altered to present a correct classification in 70% of the cases and incorrect in 30%. The overall accuracy of the ophthalmologists did not significantly change after AI assistance was introduced [75.2 ± 8.1%, 75.9 ± 7.2%, respectively ( P  = 0.59)]. In cases where the AI presented incorrect diagnoses, the accuracy of corneal specialists before and after AI assistance was showing no significant change [60.3 ± 35.2% and 53.2 ± 30.9%, respectively ( P  = 0.11)]. In contrast, the accuracy for non-corneal specialists dropped significantly from 54.5 ± 27.8% to 31.6 ± 29.3% ( P  < 0.001), especially in cases where the AI presented incorrect options. Less experienced ophthalmologists were misled due to incorrect AI guidance, but corneal specialists were not. Even with the introduction of AI diagnostic support systems, the importance of ophthalmologist’s experience remains crucial.

Purpose Deep-learning-based supervised CT segmentation relies on fully and densely labeled data, the labeling process of which is time-consuming. In this study, our proposed method aims to improve segmentation performance on CT volumes with limited annotated data by considering category-wise difficulties and distribution. Methods We propose a novel confidence-difficulty weight (CDifW) allocation method that considers confidence levels, balancing the training across different categories, influencing the loss function and volume-mixing process for pseudo-label generation. Additionally, we introduce a novel Double-Mix Pseudo-label Framework (DMPF), which strategically selects categories for image blending based on the distribution of voxel-counts per category and the weight of segmentation difficulty. DMPF is designed to enhance the segmentation performance of categories that are challenging to segment. Result Our approach was tested on two commonly used datasets: a Congenital Heart Disease (CHD) dataset and a Beyond-the-Cranial-Vault (BTCV) Abdomen dataset. Compared to the SOTA methods, our approach achieved an improvement of 5.1% and 7.0% in Dice score for the segmentation of difficult-to-segment categories on 5% of the labeled data in CHD and 40% of the labeled data in BTCV, respectively. Conclusion Our method improves segmentation performance in difficult categories within CT volumes by category-wise weights and weight-based mixture augmentation. Our method was validated across multiple datasets and is significant for advancing semi-supervised segmentation tasks in health care. The code is available at https://github.com/MoriLabNU/Double-Mix .

Purpose To determine whether convolutional neural networks (CNN) can classify the severity of central vision loss using fundus autofluorescence (FAF) images and color fundus images of retinitis pigmentosa (RP), and to evaluate the utility of those images for severity classification. Study design Retrospective observational study. Methods Medical charts of patients with RP who visited Nagoya University Hospital were reviewed. Eyes with atypical RP or previous surgery were excluded. The mild group was comprised of patients with a mean deviation value of > − 10 decibels, and the severe group of < − 20 decibels, in the Humphrey field analyzer 10-2 program. CNN models were created by transfer learning of VGG16 pretrained with ImageNet to classify patients as either mild or severe, using FAF images or color fundus images. Results Overall, 165 patients were included in this study; 80 patients were classified into the severe and 85 into the mild group. The test data comprised 40 patients in each group, and the images of the remaining patients were used as training data, with data augmentation by rotation and flipping. The highest accuracies of the CNN models when using color fundus and FAF images were 63.75% and 87.50%, respectively. Conclusion Using FAF images may enable the accurate assessment of central vision function in RP. FAF images may include more parameters than color fundus images that can evaluate central visual function.

This study presents a novel framework for classifying and visualizing pneumonia induced by COVID-19 from CT images. Although many image classification methods using deep learning have been proposed, in the case of medical image fields, standard classification methods are unable to be used in some cases because the medical images that belong to the same category vary depending on the progression of the symptoms and the size of the inflamed area. In addition, it is essential that the models used be transparent and explainable, allowing health care providers to trust the models and avoid mistakes. In this study, we propose a classification method using contrastive learning and an attention mechanism. Contrastive learning is able to close the distance for images of the same category and generate a better feature space for classification. An attention mechanism is able to emphasize an important area in the image and visualize the location related to classification. Through experiments conducted on two-types of classification using a three-fold cross validation, we confirmed that the classification accuracy was significantly improved; in addition, a detailed visual explanation was achieved comparison with conventional methods.

PurposeArtery contrasted computed tomography (CT) enables accurate observations of the arteries and surrounding structures, thus being widely used for the diagnosis of diseases such as aneurysm. To avoid the complications caused by contrast agent, this paper proposes an aorta-aware deep learning method to synthesize artery contrasted CT volume form non-contrast CT volume.MethodsBy introducing auxiliary multi-resolution segmentation tasks in the generator, we force the proposed network to focus on the regions of aorta and the other vascular structures. Then, the segmentation results produced by the auxiliary tasks were used to extract aorta. The detection of abnormal CT images containing aneurysm was implemented by estimating the maximum axial radius of aorta.ResultsIn comparison with the baseline models, the proposed network with auxiliary tasks achieved better performances with higher peak signal-noise ratio value. In aorta regions which are supposed to be the main region of interest in many clinic scenarios, the average improvement can be up to 0.33dB. Using the synthesized artery contrasted CT, the F score of aneurysm detection achieved 0.58 at slice level and 0.85 at case level. ConclusionThis study tries to address the problem of non-contrast to artery contrasted CT modality translation by employing a deep learning model with aorta awareness. The auxiliary tasks help the proposed model focus on aorta regions and synthesize results with clearer boundaries. Additionally, the synthesized artery contrasted CT shows potential in identifying slices with abdominal aortic aneurysm, and may provide an option for patients with contrast agent allergy.

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.

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.