Computational diagnostic methods on 2D photographs: A review of the literature

Hennocq, Quentin; Khonsari, Roman Hossein; Benoît, Vincent; Rio, Marlène; Garcelon, Nicolas

doi:10.1016/j.jormas.2021.04.003

Cited by 13 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the last years, numerous classic machine learning based methods have been developed for many different applications in medicine, for instance disease classi cation and diagnosis [36], medical imagining [37], smart health records [38], personalized treatment [39], epidemic control [40], or arti cial intelligence surgery [41], to name a few. Among all these methods and applications, the use of deep learning algorithms for diagnosis and disease identi cation have become of key importance in healthcare and medical services.…”

Section: Methodsmentioning

confidence: 99%

Accurate neural network classification model for schizophrenia disease based on electroencephalogram data

Luján

Sotos²,

Santos³

et al. 2022

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Electroencephalogram is a useful interface system that translates the human electrical brain activity into voltage signals. By these means, the recorded brain waves can be employed to characterize, classify, or diagnose mental disorders. A novel neural network model to classify patients with schizophrenia based on electroencephalograms is presented. The proposed model decomposes the multichannel electroencephalogram records into a group of multivariate novel radial basis functions using a fuzzy means algorithm. The decomposition permits to extract different electroencephalogram channel information and distinguish between two sort of classes i.e., schizophrenic patients and healthy controls. Results show improved accuracy compared to classical algorithms reported in the literature i.e., Support Vector Machine, Bayesian Linear Discriminant Analysis, Gaussian Naive Bayes, K-Nearest Neighbour or Adaboost. As a result, the method presented in this paper achieves the highest balanced accuracy, recall, precision and F1 score values, close to 93 % in all cases. The model presented in this paper may be integrated in real time tools involved during the diagnostic of schizophrenia.

show abstract

Section: Methodsmentioning

confidence: 99%

Accurate neural network classification model for schizophrenia disease based on electroencephalogram data

Luján

Sotos²,

Santos³

et al. 2022

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

show abstract

“…Kuru et al (2014) demonstrated the benefits of using machine learning algorithms and digital image processing techniques to build an intelligent diagnostic DSS in medical genetics. Hennocq et al (2021) presented a literature review of all the methods for analyzing 2D pictures for diagnostic purposes. Interactive data visualization dashboards are being used for visualizing and analyzing trends in large volumes of data (Huber et al 2018, West et al 2015, Morgan et al 2006, Nevo et al 2015.…”

Section: Literature Reviewmentioning

confidence: 99%

Untitled

2022

AJTE

View full text Add to dashboard Cite

ATINER is an independent and non-profit Association with a Mission to become a forum where Academics and Researchers from all over the world can meet in Athens, exchange ideas on their research and discuss future developments in their disciplines, as well as engage with professionals from other fields. Athens was chosen because of its long history of academic gatherings, which go back thousands of years to Plato's Academy and Aristotle's Lyceum. Both these historic places are within walking distance from ATINER's downtown offices. Since antiquity, Athens was an open city. In the words of Pericles, Athens"…is open to the world, we never expel a foreigner from learning or seeing". ("Pericles' Funeral Oration", in Thucydides, The History of the Peloponnesian War). It is ATINER's mission to revive the glory of Ancient Athens by inviting the World Academic Community to the city, to learn from each other in an environment of freedom and respect for other people's opinions and beliefs. After all, the free expression of one's opinion formed the basis for the development of democracy, and Athens was its cradle. As it turned out, the Golden Age of Athens was in fact, the Golden Age of the Western Civilization. Education and (Re)searching for the 'truth' are the pillars of any free (democratic) society. This is the reason why Education and Research are the two core words in ATINER's name.

show abstract

“…This algorithm is based on deep learning techniques to make a diagnosis using a photograph as input. The performance of deep learning is robust due to a large amount of training data (Latorre‐Pellicer et al, 2020), but a shortcoming raised is that some classification steps are not controlled, leading to the so‐called black box effect (Hennocq et al, 2021). The alternative is to decompose the classification phenomenon and add certain amount of patient metadata, essential for diagnosis, such as age, ethnicity, or gender (Lumaka et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

“…A widely used tool in this context is landmark-based geometric morphometrics, as this was used in 81% of the studies, according to a literature review by our team (Hennocq et al, 2021) The growth of the human face is an allometric, that is, nonlinear phenomenon (Gayon, 2000). A child is not simply a small adult; there is a change in facial ratios at different ages and a tool for automatic annotation of children's faces would probably need to be trained with children (Larson et al, 2018;Nyemb et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An automatic facial landmarking for children with rare diseases

Hennocq

Bongibault

Bizière

et al. 2023

American J of Med Genetics Pt A

Self Cite

View full text Add to dashboard Cite

Two to three thousand syndromes modify facial features: their screening requires the eye of an expert in dysmorphology. A widely used tool in shape characterization is geometric morphometrics based on landmarks, which are precise and reproducible anatomical points. Landmark positioning is user dependent and time consuming. Many automatic landmarking tools are currently available but do not work for children, because they have mainly been trained using photographic databases of healthy adults. Here, we developed a method for building an automatic landmarking pipeline for frontal and lateral facial photographs as well as photographs of external ears. We evaluated the algorithm on patients diagnosed with Treacher Collins (TC) syndrome as it is the most frequent mandibulofacial dysostosis in humans and is clinically recognizable although highly variable in severity. We extracted photographs from the photographic database of the maxillofacial surgery and plastic surgery department of Hôpital Necker–Enfants Malades in Paris, France with the diagnosis of TC syndrome. The control group was built from children admitted for craniofacial trauma or skin lesions. After testing two methods of object detection by bounding boxes, a Haar Cascade‐based tool and a Faster Region‐based Convolutional Neural Network (Faster R‐CNN)‐based tool, we evaluated three different automatic annotation algorithms: the patch‐based active appearance model (AAM), the holistic AAM, and the constrained local model (CLM). The final error corresponding to the distance between the points placed by automatic annotation and those placed by manual annotation was reported. We included, respectively, 1664, 2044, and 1375 manually annotated frontal, profile, and ear photographs. Object recognition was optimized with the Faster R‐CNN‐based detector. The best annotation model was the patch‐based AAM (p < 0.001 for frontal faces, p = 0.082 for profile faces and p < 0.001 for ears). This automatic annotation model resulted in the same classification performance as manually annotated data. Pretraining on public photographs did not improve the performance of the model. We defined a pipeline to create automatic annotation models adapted to faces with congenital anomalies, an essential prerequisite for research in dysmorphology.

show abstract

Computational diagnostic methods on 2D photographs: A review of the literature

Cited by 13 publications

References 41 publications

Accurate neural network classification model for schizophrenia disease based on electroencephalogram data

Accurate neural network classification model for schizophrenia disease based on electroencephalogram data

Untitled

An automatic facial landmarking for children with rare diseases

Contact Info

Product

Resources

About