Landscape of Big Medical Data: A Pragmatic Survey on Prioritized Tasks

Zhang, Zhifei; Gao, Wanling; Zhang, Fan; Huang, Yunyou; Dai, Shaopeng; Fan, Fanda; Zhan, Jianfeng; Du, Mengjia; Yin, Silin; Xiong, Lei; Du, Juan; Cheng, Yunzhong; Zhou, Xie-Xuan; Ren, Rui; Wang, Lei; Ye, Hainan

doi:10.1109/access.2019.2891948

Cited by 3 publications

(3 citation statements)

References 140 publications

(182 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Uno de ellos es recopilación de datos para el entrenamiento, puesto que se requiere un conjunto de datos bastante amplio, que contengan una gran variedad de condiciones para funcionar correctamente, además del gran esfuerzo para la recopilación (Arnal Barbedo, 2018). Por tanto, parte la comunidad científica ha optado por el uso de conjuntos de datos disponibles públicamente (Neupane & Seok, 2020;Yin et al 2021;Zhang et al 2019), entre otros, como en PlantVillage (Hughes & Salathe, 2015), el cual, es un conjunto de datos que consta de 39 clases diferentes de hojas sanas e infectadas en 14 cultivos (Xiong et al 2020). Los conjuntos de datos actuales presentan desafíos, debido a la compleja información del fondo de las imágenes y los datos de entrenamiento, cuando son insuficientes, pueden llevar a un reconocimiento incorrecto, por lo que es necesario métodos alternativos para entrenar estos sistemas inteligentes (Geetharamani & Arun Pandian, 2019).…”

Section: Introductionunclassified

Aplicación de redes neuronales convolucionales para la detección del tizón tardío Phytophthora infestans en papa Solanum tuberosum

Lozada-Portilla

Barón

Fernández

2021

Rev. U.D.C.A Act. & Div. Cient.

View full text Add to dashboard Cite

The presence of late blight in potato crops directly affects plant growth and tuber development; therefore, early detection of the disease is important. Currently, the application of convolutional neural networks is an opportunity oriented to the identification of patterns in precision agriculture, including the study of late blight in potato crops. This study describes a deep learning model capable of recognizing late blight in potato crops by means of leaf image classification. The PlantVillage augmented dataset was used in the application of this model for training. The proposed model has been evaluated from performance metrics such as precision, sensitivity, F1 score, and accuracy; to verify the effectiveness of the model in the identification and classification of late blight and compared in performance with architectures such as AlexNet, ZFNet, VGG16, and VGG19. The experimental results obtained with the selected data set showed that the proposed model achieves an accuracy of 90 % and an F1 score of 91 %. Therefore, it is concluded that the proposed model is a useful tool for farmers in the identification of late blight and scalable to mobile platforms due to the number of parameters that comprise it.

show abstract

Section: Introductionunclassified

Aplicación de redes neuronales convolucionales para la detección del tizón tardío Phytophthora infestans en papa Solanum tuberosum

Lozada-Portilla

Barón

Fernández

2021

Rev. U.D.C.A Act. & Div. Cient.

View full text Add to dashboard Cite

show abstract

“…The clinical tasks in a natural setting. As mentioned, a natural clinical setting is open and the diagnosis itself is flexible 35 , and a clinical diagnosis task is a very complex and uncertain owing to the following reasons.…”

mentioning

confidence: 99%

“…e) The data sources and types of a patient are usually multifarious and integrated, and the knowledge from different sources must be comprehensively considered 35 .…”

mentioning

confidence: 99%

A new direction to promote the implementation of artificial intelligence in natural clinical settings

Huang,

Zhang,

Wang

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) researchers claim that they have made great 'achievements' in clinical realms. However, clinicians point out the so-called 'achievements' have no ability to implement into natural clinical settings. The root cause for this huge gap is that many essential features of natural clinical tasks are overlooked by AI system developers without medical background. In this paper, we propose that the clinical benchmark suite is a novel and promising direction to capture the essential features of the real-world clinical tasks, hence qualifies itself for guiding the development of AI systems, promoting the implementation of AI in real-world clinical practice.AI researchers claim that they have obtained many significant 'achievements' in various realms of clinical medicine, i.e., cancer diagnosis 1, 2 . However, in practice, most of the AI products fail to obtain approval from the Food and Drug Administration (FDA). Moreover, the approved AI products, which are quite rare, are only limited to class II or I 1 , which means that even the approved AI devices are not qualified handling high-risk tasks such as clinical diagnosis 2 . Question marks hang over the AI systems for real-world clinical tasks. Why is there such a huge gap between the AI research and AI implementation in natural clinical setting? How to promote the AI implementation into natural clinical settings to bridge the gap?The common interpretation, given by the clinicians, for this huge gap is that many technical issues in clinical settings remain unsolved, leading to the inability of the AI system in natural clinical settings, and that the AI researchers overestimate the ability of AI system validated in the artificially designed experiments 4,5 . In order to uncover the essential reasons for the gap mentioned above, our team, consisting of AI researchers and clinicians, analyzed the development process of AI systems and give the following explanation. The features of clinical tasks in natural settings are ignored in the entire lifecycle (design, implementation, and evaluation) of the AI systems, thus the generated AI system itself has no ability to be implemented in natural clinical settings.

show abstract

Effective Semantic Features to Improve Retrieval of Lung Nodules in Ct Scan Images

Alizade

Foruzan

2022

Biomed. Eng. Appl. Basis Commun.

View full text Add to dashboard Cite

Successful treatment of a patient depends on the accurate determination of the disease type. The advent of big data facilitates the retrieving of medical images and helps physicians in reliable diagnoses using content-based medical image retrieval systems (CBMIR). They consist of a feature extraction module and a distance metric. The extracted textural or deep-based features identify different types of diseases. In the proposed retrieval algorithm, we use the gray level cooccurrence matrix as the common textural characteristics and integrate them with semantic attributes. The semantic features are the geometric characteristics of the tumor that a radiologist employ to distinguish between benign and malignant tumors. These high-level attributes include the Euler number, margin smoothness, and the aspect ratio of the lesion’s size. We used the Minkowski distance measure for computing the similarity of images and applied the proposed algorithm to 200 CT-scan data containing lung lesions obtained from the LIDC database. The types of lesions were benign and malignant. Employing an ablation study, we proved the effectiveness of the semantic feature. The precision of the retrieval results is 93% which is promising compared to recent studies. In the future, we plan to define other kinds of semantic attributes to distinguish stages 1–5 of lung tumors as well.

show abstract

Landscape of Big Medical Data: A Pragmatic Survey on Prioritized Tasks

Cited by 3 publications

References 140 publications

Aplicación de redes neuronales convolucionales para la detección del tizón tardío Phytophthora infestans en papa Solanum tuberosum

Aplicación de redes neuronales convolucionales para la detección del tizón tardío Phytophthora infestans en papa Solanum tuberosum

A new direction to promote the implementation of artificial intelligence in natural clinical settings

Effective Semantic Features to Improve Retrieval of Lung Nodules in Ct Scan Images

Contact Info

Product

Resources

About