RESUMO
BACKGROUND: Metastatic lateral lymph node dissection can improve survival in patients with rectal adenocarcinoma, with or without chemoradiotherapy. However, the optimal imaging diagnostic criteria for lateral lymph node metastases remain undetermined. OBJECTIVE: To develop a lateral lymph node metastasis diagnostic artificial intelligence tool using deep learning, for patients with rectal adenocarcinoma who underwent radical surgery and lateral lymph node dissection. DESIGN: Retrospective study. SETTINGS: Multicenter study. PATIENTS: A total of 209 patients with rectal adenocarcinoma, who underwent radical surgery and lateral lymph node dissection at 15 participating hospitals, were enrolled in the study and allocated to training (n = 139), test (n = 17), or validation (n = 53) cohorts. MAIN OUTCOME MEASURES: In the neoadjuvant treatment group, images taken before pretreatment were classified as baseline images and those taken after pretreatment as presurgery images. In the upfront surgery group, presurgery images were classified as both baseline and presurgery images. We constructed 2 types of artificial intelligence, using baseline and presurgery images, by inputting the patches from these images into ResNet-18, and we assessed their diagnostic accuracy. RESULTS: Overall, 124 patients underwent surgery alone, 52 received neoadjuvant chemotherapy, and 33 received chemoradiotherapy. The number of resected lateral lymph nodes in the training, test, and validation cohorts was 2418, 279, and 850, respectively. The metastatic rates were 2.8%, 0.7%, and 3.7%, respectively. In the validation cohort, the precision-recall area under the curve was 0.870 and 0.963 for the baseline and presurgery images, respectively. Although both baseline and presurgery images provided good accuracy for diagnosing lateral lymph node metastases, the accuracy of presurgery images was better than that of baseline images. LIMITATIONS: The number of cases is small. CONCLUSIONS: An artificial intelligence tool is a promising tool for diagnosing lateral lymph node metastasis with high accuracy. DESARROLLO DE UNA HERRAMIENTA DE INTELIGENCIA ARTIFICIAL PARA EL DIAGNSTICO DE METSTASIS EN GANGLIOS LINFTICOS LATERALES EN CNCER DE RECTO AVANZADO: ANTECEDENTES:Disección de nódulos linfáticos laterales metastásicos puede mejorar la supervivencia en pacientes con adenocarcinoma del recto, con o sin quimiorradioterapia. Sin embargo, aún no se han determinado los criterios óptimos de diagnóstico por imágenes de los nódulos linfáticos laterales metastásicos.OBJETIVO:Nuestro objetivo fue desarrollar una herramienta de inteligencia artificial para el diagnóstico de metástasis en nódulos linfáticos laterales mediante el aprendizaje profundo, para pacientes con adenocarcinoma del recto que se sometieron a cirugía radical y disección de nódulos linfáticos laterales.DISEÑO:Estudio retrospectivo.AJUSTES:Estudio multicéntrico.PACIENTES:Un total de 209 pacientes con adenocarcinoma del recto, que se sometieron a cirugía radical y disección de nódulos linfáticos laterales en 15 hospitales participantes, se inscribieron en el estudio y se asignaron a cohortes de entrenamiento (n = 139), prueba (n = 17) o validación (n = 53).PRINCIPALES MEDIDAS DE RESULTADO:En el grupo de tratamiento neoadyuvante, las imágenes tomadas antes del tratamiento se clasificaron como imágenes de referencia y las posteriores al tratamiento, como imágenes previas a la cirugía. En el grupo de cirugía inicial, las imágenes previas a la cirugía se clasificaron como imágenes de referencia y previas a la cirugía. Construimos dos tipos de inteligencia artificial, utilizando imágenes de referencia y previas a la cirugía, ingresando los parches de estas imágenes en ResNet-18. Evaluamos la precisión diagnóstica de los dos tipos de inteligencia artificial.RESULTADOS:En general, 124 pacientes se sometieron a cirugía solamente, 52 recibieron quimioterapia neoadyuvante y 33 recibieron quimiorradioterapia. El número de nódulos linfáticos laterales removidos en los cohortes de entrenamiento, prueba y validación fue de 2,418; 279 y 850, respectivamente. Las tasas metastásicas fueron 2.8%, 0.7%, y 3.7%, respectivamente. En el cohorte de validación, el área de recuperación de precisión bajo la curva fue de 0.870 y 0.963 para las imágenes de referencia y antes de la cirugía, respectivamente. Aunque tanto las imágenes previas a la cirugía como las iniciales proporcionaron una buena precisión para diagnosticar metástasis en los nódulos linfáticos laterales, la precisión de las imágenes previas a la cirugía fue mejor que la de las imágenes iniciales.LIMITACIONES:El número de casos es pequeño.CONCLUSIÓN:La inteligencia artificial es una herramienta prometedora para diagnosticar metástasis en los nódulos linfáticos laterales con alta precisión. (Traducción-Dr. Aurian Garcia Gonzalez ).
Assuntos
Adenocarcinoma , Neoplasias Retais , Humanos , Metástase Linfática , Estudos Retrospectivos , Inteligência Artificial , Linfonodos/diagnóstico por imagem , Linfonodos/patologia , Estadiamento de Neoplasias , Neoplasias Retais/diagnóstico , Neoplasias Retais/terapia , Adenocarcinoma/diagnóstico , Adenocarcinoma/cirurgiaRESUMO
INTRODUCTION: It is critical to develop accurate and universally available biomarkers for dementia diseases to appropriately deal with the dementia problems under world-wide rapid increasing of patients with dementia. In this sense, electroencephalography (EEG) has been utilized as a promising examination to screen and assist in diagnosing dementia, with advantages of sensitiveness to neural functions, inexpensiveness, and high availability. Moreover, the algorithm-based deep learning can expand EEG applicability, yielding accurate and automatic classification easily applied even in general hospitals without any research specialist. METHODS: We utilized a novel deep neural network, with which high accuracy of discrimination was archived in neurological disorders in the previous study. Based on this network, we analyzed EEG data of healthy volunteers (HVs, N = 55), patients with Alzheimer's disease (AD, N = 101), dementia with Lewy bodies (DLB, N = 75), and idiopathic normal pressure hydrocephalus (iNPH, N = 60) to evaluate the discriminative accuracy of these diseases. RESULTS: High discriminative accuracies were archived between HV and patients with dementia, yielding 81.7% (vs. AD), 93.9% (vs. DLB), 93.1% (vs. iNPH), and 87.7% (vs. AD, DLB, and iNPH). CONCLUSION: This study revealed that the EEG data of patients with dementia were successfully discriminated from HVs based on a novel deep learning algorithm, which could be useful for automatic screening and assisting diagnosis of dementia diseases.
Assuntos
Doença de Alzheimer , Aprendizado Profundo , Doença por Corpos de Lewy , Humanos , Doença por Corpos de Lewy/complicações , Doença por Corpos de Lewy/diagnóstico , Doença de Alzheimer/diagnóstico , EletroencefalografiaRESUMO
To overcome the increasing burden on pathologists in diagnosing gastric biopsies, we developed an artificial intelligence-based system for the pathological diagnosis of gastric biopsies (AI-G), which is expected to work well in daily clinical practice in multiple institutes. The multistage semantic segmentation for pathology (MSP) method utilizes the distribution of feature values extracted from patches of whole-slide images (WSI) like pathologists' "low-power view" information of microscopy. The training dataset included WSIs of 4511 gastric biopsy tissues from 984 patients. In tissue-level validation, MSP AI-G showed better accuracy (91.0%) than that of conventional patch-based AI-G (PB AI-G) (89.8%). Importantly, MSP AI-G unanimously achieved higher accuracy rates (0.946 ± 0.023) than PB AI-G (0.861 ± 0.078) in tissue-level analysis, when applied to the cohorts of 10 different institutes (3450 samples of 1772 patients in all institutes, 198-555 samples of 143-206 patients in each institute). MSP AI-G had high diagnostic accuracy and robustness in multi-institutions. When pathologists selectively review specimens in which pathologist's diagnosis and AI prediction are discordant, the requirement of a secondary review process is significantly less compared with reviewing all specimens by another pathologist.
Assuntos
Inteligência Artificial , Estômago , Biópsia , HumanosRESUMO
BACKGROUND : Previous computer-aided detection systems for diagnosing lesions in images from wireless capsule endoscopy (WCE) have been limited to a single type of small-bowel lesion. We developed a new artificial intelligence (AI) system able to diagnose multiple types of lesions, including erosions and ulcers, vascular lesions, and tumors. METHODS : We trained the deep neural network system RetinaNet on a data set of 167 patients, which consisted of images of 398 erosions and ulcers, 538 vascular lesions, 4590 tumors, and 34 437 normal tissues. We calculated the mean area under the receiver operating characteristic curve (AUC) for each lesion type using five-fold stratified cross-validation. RESULTS : The mean age of the patients was 63.6 years; 92 were men. The mean AUCs of the AI system were 0.996 (95â%CI 0.992â-â0.999) for erosions and ulcers, 0.950 (95â%CI 0.923â-â0.978) for vascular lesions, and 0.950 (95â%CI 0.913â-â0.988) for tumors. CONCLUSION : We developed and validated a new computer-aided diagnosis system for multiclass diagnosis of small-bowel lesions in WCE images.
Assuntos
Endoscopia por Cápsula , Inteligência Artificial , Diagnóstico por Computador , Humanos , Intestino Delgado/diagnóstico por imagem , Masculino , Pessoa de Meia-Idade , Redes Neurais de ComputaçãoRESUMO
PURPOSE: Fertility preservation is an important issue for young cancer patients. Random-start controlled ovarian stimulation and double ovarian stimulation have been proposed for efficient oocyte retrieval within the limited time before cancer therapy. We aimed to clarify the efficacy of these new protocols within the Japanese population. METHODS: We performed a retrospective observational study at a multicenter from February 2012 to August 2017. The study entailed 50 cycles with 34 patients who underwent fertility preservation due to breast cancer. Follicular phase or luteal phase ovarian stimulation with aromatase inhibitor was performed. A second ovarian stimulation was started with or without waiting until the next menstruation. We measured the number of retrieved oocytes and cryopreserved oocytes/embryos, the ratio of mature oocytes, and the fertilization rate. RESULTS: The numbers of retrieved oocytes and frozen oocytes/embryos were not significantly different between follicular phase and luteal phase ovarian stimulation. The number of retrieved oocytes was not reduced at the second ovum pick up compared to the first ovum pick up in the double ovarian stimulation. CONCLUSIONS: Random-start controlled ovarian stimulation and double ovarian stimulation with aromatase inhibitor for breast cancer patients were effective protocols for retrieving a greater number of oocytes within the limited time.
RESUMO
AIMS: The objective of this study was to investigate the effect of the head-first or tail-first injection of sperm into the cytoplasm by Piezo-ICSI (PICSI) on oocyte survival, fertilization, embryo development and implantation ability in humans. METHODS: We retrospectively investigated 632 mature oocytes retrieved from 152 infertile patients who attended our PICSI-ET program at the Niji Clinic between October 2010 and January 2014. Of these, 342 mature oocytes retrieved from 75 patients were injected with sperm head first, and 290 mature oocytes retrieved from 77 patients were injected with sperm tail first into the cytoplasm. The rates of oocyte survival, fertilization, good-quality day-3 embryos, pregnancy, implantation and live birth were evaluated in both groups. RESULTS: There were no differences among the two groups with respect to survival, fertilization, good-quality day-3 embryos, pregnancy, implantation and live birth rates. CONCLUSION: Sperm direction (i.e., head first or tail first) does not influence the outcome of PICSI in human oocytes, including oocyte survival, fertilization, embryo development and implantation ability. These findings contribute to an understanding of factors that influence the success of human intracytoplasmic sperm injection (ICSI) techniques.
Assuntos
Implantação do Embrião , Fertilização , Nascido Vivo , Oócitos , Avaliação de Processos e Resultados em Cuidados de Saúde , Injeções de Esperma Intracitoplásmicas/métodos , Adulto , Feminino , Humanos , Pessoa de Meia-Idade , Estudos RetrospectivosRESUMO
Medical Visual Question Answering (VQA) is an important task in medical multi-modal Large Language Models (LLMs), aiming to answer clinically relevant questions regarding input medical images. This technique has the potential to improve the efficiency of medical professionals while relieving the burden on the public health system, particularly in resource-poor countries. However, existing medical VQA datasets are small and only contain simple questions (equivalent to classification tasks), which lack semantic reasoning and clinical knowledge. Our previous work proposed a clinical knowledge-driven image difference VQA benchmark using a rule-based approach (Hu et al., 2023). However, given the same breadth of information coverage, the rule-based approach shows an 85% error rate on extracted labels. We trained an LLM method to extract labels with 62% increased accuracy. We also comprehensively evaluated our labels with 2 clinical experts on 100 samples to help us fine-tune the LLM. Based on the trained LLM model, we proposed a large-scale medical VQA dataset, Medical-CXR-VQA, using LLMs focused on chest X-ray images. The questions involved detailed information, such as abnormalities, locations, levels, and types. Based on this dataset, we proposed a novel VQA method by constructing three different relationship graphs: spatial relationships, semantic relationships, and implicit relationship graphs on the image regions, questions, and semantic labels. We leveraged graph attention to learn the logical reasoning paths for different questions. These learned graph VQA reasoning paths can be further used for LLM prompt engineering and chain-of-thought, which are crucial for further fine-tuning and training multi-modal large language models. Moreover, we demonstrate that our approach has the qualities of evidence and faithfulness, which are crucial in the clinical field. The code and the dataset is available at https://github.com/Holipori/Medical-CXR-VQA.
RESUMO
Chest radiography, commonly known as CXR, is frequently utilized in clinical settings to detect cardiopulmonary conditions. However, even seasoned radiologists might offer different evaluations regarding the seriousness and uncertainty associated with observed abnormalities. Previous research has attempted to utilize clinical notes to extract abnormal labels for training deep-learning models in CXR image diagnosis. However, these methods often neglected the varying degrees of severity and uncertainty linked to different labels. In our study, we initially assembled a comprehensive new dataset of CXR images based on clinical textual data, which incorporated radiologists' assessments of uncertainty and severity. Using this dataset, we introduced a multi-relationship graph learning framework that leverages spatial and semantic relationships while addressing expert uncertainty through a dedicated loss function. Our research showcases a notable enhancement in CXR image diagnosis and the interpretability of the diagnostic model, surpassing existing state-of-the-art methodologies. The dataset address of disease severity and uncertainty we extracted is: https://physionet.org/content/cad-chest/1.0/.
RESUMO
Explainability is key to enhancing the trustworthiness of artificial intelligence in medicine. However, there exists a significant gap between physicians' expectations for model explainability and the actual behavior of these models. This gap arises from the absence of a consensus on a physician-centered evaluation framework, which is needed to quantitatively assess the practical benefits that effective explainability should offer practitioners. Here, we hypothesize that superior attention maps, as a mechanism of model explanation, should align with the information that physicians focus on, potentially reducing prediction uncertainty and increasing model reliability. We employed a multimodal transformer to predict lymph node metastasis of rectal cancer using clinical data and magnetic resonance imaging. We explored how well attention maps, visualized through a state-of-the-art technique, can achieve agreement with physician understanding. Subsequently, we compared two distinct approaches for estimating uncertainty: a standalone estimation using only the variance of prediction probability, and a human-in-the-loop estimation that considers both the variance of prediction probability and the quantified agreement. Our findings revealed no significant advantage of the human-in-the-loop approach over the standalone one. In conclusion, this case study did not confirm the anticipated benefit of the explanation in enhancing model reliability. Superficial explanations could do more harm than good by misleading physicians into relying on uncertain predictions, suggesting that the current state of attention mechanisms should not be overestimated in the context of model explainability.
Assuntos
Julgamento , Metástase Linfática , Neoplasias Retais , Humanos , Neoplasias Retais/patologia , Neoplasias Retais/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , Linfonodos/patologia , Linfonodos/diagnóstico por imagem , Inteligência Artificial , Médicos , Incerteza , Reprodutibilidade dos Testes , ConfiançaRESUMO
The volume of medical images stored in hospitals is rapidly increasing; however, the utilization of these accumulated medical images remains limited. Existing content-based medical image retrieval (CBMIR) systems typically require example images, leading to practical limitations, such as the lack of customizable, fine-grained image retrieval, the inability to search without example images, and difficulty in retrieving rare cases. In this paper, we introduce a sketch-based medical image retrieval (SBMIR) system that enables users to find images of interest without the need for example images. The key concept is feature decomposition of medical images, which allows the entire feature of a medical image to be decomposed into and reconstructed from normal and abnormal features. Building on this concept, our SBMIR system provides an easy-to-use two-step graphical user interface: users first select a template image to specify a normal feature and then draw a semantic sketch of the disease on the template image to represent an abnormal feature. The system integrates both types of input to construct a query vector and retrieves reference images. For evaluation, ten healthcare professionals participated in a user test using two datasets. Consequently, our SBMIR system enabled users to overcome previous challenges, including image retrieval based on fine-grained image characteristics, image retrieval without example images, and image retrieval for rare cases. Our SBMIR system provides on-demand, customizable medical image retrieval, thereby expanding the utility of medical image databases.
Assuntos
Algoritmos , Semântica , Humanos , Armazenamento e Recuperação da Informação , Bases de Dados FactuaisRESUMO
Dementia and mild cognitive impairment (MCI) represent significant health challenges in an aging population. As the search for noninvasive, precise and accessible diagnostic methods continues, the efficacy of electroencephalography (EEG) combined with deep convolutional neural networks (DCNNs) in varied clinical settings remains unverified, particularly for pathologies underlying MCI such as Alzheimer's disease (AD), dementia with Lewy bodies (DLB) and idiopathic normal-pressure hydrocephalus (iNPH). Addressing this gap, our study evaluates the generalizability of a DCNN trained on EEG data from a single hospital (Hospital #1). For data from Hospital #1, the DCNN achieved a balanced accuracy (bACC) of 0.927 in classifying individuals as healthy (n = 69) or as having AD, DLB, or iNPH (n = 188). The model demonstrated robustness across institutions, maintaining bACCs of 0.805 for data from Hospital #2 (n = 73) and 0.920 at Hospital #3 (n = 139). Additionally, the model could differentiate AD, DLB, and iNPH cases with bACCs of 0.572 for data from Hospital #1 (n = 188), 0.619 for Hospital #2 (n = 70), and 0.508 for Hospital #3 (n = 139). Notably, it also identified MCI pathologies with a bACC of 0.715 for Hospital #1 (n = 83), despite being trained on overt dementia cases instead of MCI cases. These outcomes confirm the DCNN's adaptability and scalability, representing a significant stride toward its clinical application. Additionally, our findings suggest a potential for identifying shared EEG signatures between MCI and dementia, contributing to the field's understanding of their common pathophysiological mechanisms.
Assuntos
Doença de Alzheimer , Disfunção Cognitiva , Aprendizado Profundo , Doença por Corpos de Lewy , Humanos , Idoso , Doença por Corpos de Lewy/diagnóstico , Doença de Alzheimer/diagnóstico , Disfunção Cognitiva/diagnóstico , EletroencefalografiaRESUMO
Spherical images taken in all directions (360 degrees by 180 degrees) can represent an entire space including the subject, providing free direction viewing and an immersive experience to viewers. It is convenient and expands the usage scenarios to generate a spherical image from a few normal-field-of-view (NFOV) images, which are partial observations. The primary challenge is generating a plausible image and controlling the high degree of freedom involved in generating a wide area that includes all directions. We focus on scene symmetry, which is a basic property of the global structure of spherical images, such as the rotational and plane symmetries. We propose a method for generating a spherical image from a few NFOV images and controlling the generated regions using scene symmetry. We incorporate the intensity of the symmetry as a latent variable into conditional variational autoencoders to estimate the possible range of symmetry and decode a spherical image whose features are represented through a combination of symmetric transformations of the NFOV image features. Our experiments show that the proposed method can generate various plausible spherical images controlled from asymmetrically to symmetrically, and can reduce the reconstruction errors of the generated images based on the estimated symmetry.
RESUMO
The use of computer-aided detection models to diagnose lesions in images from wireless capsule endoscopy (WCE) is a topical endoscopic diagnostic solution. We revised our artificial intelligence (AI) model, RetinaNet, to better diagnose multiple types of lesions, including erosions and ulcers, vascular lesions, and tumors. RetinaNet was trained using the data of 1234 patients, consisting of images of 6476 erosions and ulcers, 1916 vascular lesions, 7127 tumors, and 14,014,149 normal tissues. The mean area under the receiver operating characteristic curve (AUC), sensitivity, and specificity for each lesion were evaluated using five-fold stratified cross-validation. Each cross-validation set consisted of between 6,647,148 and 7,267,813 images from 217 patients. The mean AUC values were 0.997 for erosions and ulcers, 0.998 for vascular lesions, and 0.998 for tumors. The mean sensitivities were 0.919, 0.878, and 0.876, respectively. The mean specificities were 0.936, 0.969, and 0.937, and the mean accuracies were 0.930, 0.962, and 0.924, respectively. We developed a new version of an AI-based diagnostic model for the multiclass identification of small bowel lesions in WCE images to help endoscopists appropriately diagnose small intestine diseases in daily clinical practice.
RESUMO
Many unsupervised domain adaptation (UDA) methods have been developed and have achieved promising results in various pattern recognition tasks. However, most existing methods assume that raw source data are available in the target domain when transferring knowledge from the source to the target domain. Due to the emerging regulations on data privacy, the availability of source data cannot be guaranteed when applying UDA methods in a new domain. The lack of source data makes UDA more challenging, and most existing methods are no longer applicable. To handle this issue, this paper analyzes the cross-domain representations in source-data-free unsupervised domain adaptation (SF-UDA). A new theorem is derived to bound the target-domain prediction error using the trained source model instead of the source data. On the basis of the proposed theorem, information bottleneck theory is introduced to minimize the generalization upper bound of the target-domain prediction error, thereby achieving domain adaptation. The minimization is implemented in a variational inference framework using a newly developed latent alignment variational autoencoder (LA-VAE). The experimental results show good performance of the proposed method in several cross-dataset classification tasks without using source data. Ablation studies and feature visualization also validate the effectiveness of our method in SF-UDA.
RESUMO
In medical imaging, the characteristics purely derived from a disease should reflect the extent to which abnormal findings deviate from the normal features. Indeed, physicians often need corresponding images without abnormal findings of interest or, conversely, images that contain similar abnormal findings regardless of normal anatomical context. This is called comparative diagnostic reading of medical images, which is essential for a correct diagnosis. To support comparative diagnostic reading, content-based image retrieval (CBIR) that can selectively utilize normal and abnormal features in medical images as two separable semantic components will be useful. In this study, we propose a neural network architecture to decompose the semantic components of medical images into two latent codes: normal anatomy code and abnormal anatomy code. The normal anatomy code represents counterfactual normal anatomies that should have existed if the sample is healthy, whereas the abnormal anatomy code attributes to abnormal changes that reflect deviation from the normal baseline. By calculating the similarity based on either normal or abnormal anatomy codes or the combination of the two codes, our algorithm can retrieve images according to the selected semantic component from a dataset consisting of brain magnetic resonance images of gliomas. Moreover, it can utilize a synthetic query vector combining normal and abnormal anatomy codes from two different query images. To evaluate whether the retrieved images are acquired according to the targeted semantic component, the overlap of the ground-truth labels is calculated as metrics of the semantic consistency. Our algorithm provides a flexible CBIR framework by handling the decomposed features with qualitatively and quantitatively remarkable results.
Assuntos
Glioma , Armazenamento e Recuperação da Informação , Algoritmos , Glioma/diagnóstico por imagem , Humanos , Imageamento por Ressonância Magnética , Redes Neurais de ComputaçãoRESUMO
One major challenge in medical imaging analysis is the lack of label and annotation which usually requires medical knowledge and training. This issue is particularly serious in the brain image analysis such as the analysis of retinal vasculature, which directly reflects the vascular condition of Central Nervous System (CNS). In this paper, we present a novel semi-supervised learning algorithm to boost the performance of random forest under limited labeled data by exploiting the local structure of unlabeled data. We identify the key bottleneck of random forest to be the information gain calculation and replace it with a graph-embedded entropy which is more reliable for insufficient labeled data scenario. By properly modifying the training process of standard random forest, our algorithm significantly improves the performance while preserving the virtue of random forest such as low computational burden and robustness over over-fitting. Our method has shown a superior performance on both medical imaging analysis and machine learning benchmarks.
RESUMO
A husband and his wife, both 34 years old, consulted our clinic because of primary infertility. Sperm analysis revealed that the sperm concentration, motility, and progressive motility were (42.8±22.8)×106/mL, 23.3%±12.2%, and 12.9%±6.1%, respectively. Based on Krugar strict morphology criteria, 100% of the sperm were teratozoospermic, with 7.9% DNA fragmentation index. Observation of the sperm under a transmission electron microscope revealed that most parts of the fibrous sheath (FS) surrounding the tails of the sperm were missing from midway through the principal piece to the end piece, although the sperm's heads, necks and midpieces were morphologically normal. To collect oocytes, the gonadotropin-releasing hormone antagonist protocol was carried out, and 7 oocytes were retrieved. Intracytoplasmic sperm injection (ICSI) was performed for all the teratozoospermic sperm. Of the 7 oocytes, 3 were fertilized, and one 8-cell embryo and 2 expanded blastocysts were vitrified. Although repeated transfers of expanded blastocysts resulted in no implantation, one 8-cell embryo transfer in a hormone replacement therapy cycle led to pregnancy. The pregnancy using an 8-cell vitrified embryo resulted in the delivery of a healthy female baby at 38 weeks of gestation. No congenital malformations were found until 28 days after birth. Our results demonstrated that healthy birth could be achieved following the transfer of an embryo derived from ICSI using teratozoospermic sperm exhibiting the dysplasia of the fibrous sheath (DFS). Furthermore, while the previous reports on DFS have not investigated male infertility, we evaluated sperms from various aspects such as Kruger sperm function test, chromatin dispersion test, electron microscopy findings, time-lapse images of the obtained embryos, and concluded that ICSI could be desirable as a treatment policy for DFS.
RESUMO
The application of deep learning to neuroimaging big data will help develop computer-aided diagnosis of neurological diseases. Pattern recognition using deep learning can extract features of neuroimaging signals unique to various neurological diseases, leading to better diagnoses. In this study, we developed MNet, a novel deep neural network to classify multiple neurological diseases using resting-state magnetoencephalography (MEG) signals. We used the MEG signals of 67 healthy subjects, 26 patients with spinal cord injury, and 140 patients with epilepsy to train and test the network using 10-fold cross-validation. The trained MNet succeeded in classifying the healthy subjects and those with the two neurological diseases with an accuracy of 70.7 ± 10.6%, which significantly exceeded the accuracy of 63.4 ± 12.7% calculated from relative powers of six frequency bands (δ: 1-4 Hz; θ: 4-8 Hz; low-α: 8-10 Hz; high-α: 10-13 Hz; ß: 13-30 Hz; low-γ: 30-50 Hz) for each channel using a support vector machine as a classifier (p = 4.2 × 10-2). The specificity of classification for each disease ranged from 86-94%. Our results suggest that this technique would be useful for developing a classifier that will improve neurological diagnoses and allow high specificity in identifying diseases.