1 |
Genetic Neural Architecture Search for automatic assessment of human sperm images
|
|
|
|
In: ISSN: 0957-4174 ; Expert Systems with Applications ; https://hal.archives-ouvertes.fr/hal-03585035 ; Expert Systems with Applications, Elsevier, 2022 (2022)
|
|
Abstract:
International audience ; Male infertility is a disease that affects approximately 7% of men. Sperm morphology analysis (SMA) is one of the main diagnosis methods for this problem. However, manual SMA is an inexact, subjective, nonreproducible, and hard to teach process. Therefore, in this paper, we introduce a novel automatic SMA technique that is based on the neural architecture search algorithm, named Genetic Neural Architecture Search (GeNAS). For this purpose, we used a collection of images termed MHSMA dataset, which contains 1, 540 sperm images that have been collected from 235 patients with infertility problems. In detail, GeNAS consists of a special genetic algorithm that acts as a meta-controller which explores the constrained search space of plain convolutional neural network architectures. Every individual of this genetic algorithm is a convolutional neural network trained to predict morphological deformities in different segments of human sperm (head, vacuole, and acrosome). The fitness of each individual is calculated by a novel proposed method, named GeNAS Weighting Factor (GeNAS-WF). This technique is specially designed to evaluate the fitness of neural networks which, during their learning process, validation accuracy highly fluctuates. To speed up the algorithm, a hashing method is practiced to save each trained neural architecture fitness, so we could reuse them during fitness evaluation. In terms of running time and computational power, our proposed architecture search method is far more efficient than most of the other existing neural architecture search algorithms. Moreover, whereas most of the existing neural architecture search algorithms are designed to work well with well-prepared benchmark datasets, the overall paradigm of GeNAS is specially designed to address the challenges of real-world datasets, particularly shortage of data and class imbalance. In our experiments, the best neural architecture found by GeNAS has reached an accuracy of 91.66%, 77.33%, and 77.66% in the vacuole, head, and acrosome abnormality detection, respectively. In comparison to other proposed algorithms for MHSMA dataset, GeNAS achieved state-of-the-art results.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]; Deep Learning; Genetic Algorithm; Human Sperm Morphometry; Infertility; Neural Architecture Search
|
|
URL: https://hal.archives-ouvertes.fr/hal-03585035
|
|
BASE
|
|
Hide details
|
|
2 |
Unsupervised quantification of entity consistency between photos and text in real-world news ...
|
|
Müller-Budack, Eric. - : Hannover : Institutionelles Repositorium der Leibniz Universität Hannover, 2022
|
|
BASE
|
|
Show details
|
|
4 |
Jibes & Delights: A Dataset of Targeted Insults and Compliments to Tackle Online Abuse ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Generación de textos en ruso mediante técnicas de Aprendizaje Automático para la industria del lenguaje
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Automatic risk detection system by audiovisual signal processing ; Système de détection automatique de risques par traitement de signaux audiovisuels
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03602318 ; Signal and Image processing. Université Polytechnique Hauts-de-France; Institut national des sciences appliquées Hauts-de-France, 2021. English. ⟨NNT : 2021UPHF0040⟩ (2021)
|
|
BASE
|
|
Show details
|
|
8 |
Automatic Speech Recognition : from hybrid to end-to-end approach ; Reconnaissance automatique de la parole à large vocabulaire : des approches hybrides aux approches End-to-End
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03616588 ; Intelligence artificielle [cs.AI]. Université Paul Sabatier - Toulouse III, 2021. Français. ⟨NNT : 2021TOU30116⟩ (2021)
|
|
BASE
|
|
Show details
|
|
9 |
Large vocabulary automatic speech recognition: from hybrid to end-to-end approaches ; Reconnaissance automatique de la parole à large vocabulaire : des approches hybrides aux approches End-to-End
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03269807 ; Son [cs.SD]. Université toulouse 3 Paul Sabatier, 2021. Français (2021)
|
|
BASE
|
|
Show details
|
|
10 |
Deep Autoencoders for ATLAS Data Compression - George Dialektakis - Google Summer of Code 2021 Project ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Deep Autoencoders for ATLAS Data Compression - George Dialektakis - Google Summer of Code 2021 Project ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Affordance learning for visual-semantic perception
|
|
|
|
In: Theses: Doctorates and Masters (2021)
|
|
BASE
|
|
Show details
|
|
15 |
ISL-CSLTR: Indian Sign Language Dataset for Continuous Sign Language Translation and Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
ISL-CSLTR: Indian Sign Language Dataset for Continuous Sign Language Translation and Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Phrase-Level Action Reinforcement Learning for Neural Dialog Response Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Correcting Chinese Spelling Errors with Phonetic Pre-training ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|