An official publication of the International Association for Pattern Recognition

Pattern Recognition Letters aims at rapid publication of concise articles of a broad interest in pattern recognition.
Subject areas include all the current fields of interest represented by the Technical Committees of the International Association of Pattern Recognition, and other developing themes involving learning and recognition. Examples include:

• Statistical, structural, syntactic pattern recognition;
• Neural networks, machine learning, data mining;
• Discrete geometry, algebraic, graph-based techniques for pattern recognition;
• Signal analysis, image coding and processing, shape and texture analysis;
• Computer vision, robotics, remote sensing;
• Document processing, text and graphics recognition, digital libraries;
• Speech recognition, music analysis, multimedia systems;
• Natural language analysis, information retrieval;
• Biometrics, biomedical pattern analysis and information systems;
• Special hardware architectures, software packages for pattern recognition.

We invite contributions as research reports or commentaries.

Research reports should be concise summaries of methodological inventions and findings, with strong potential of wide applications.
Alternatively, they can describe significant and novel applications of an established technique that are of high reference value to the same application area and other similar areas.

Commentaries can be lecture notes, subject reviews, reports on a conference, or debates on critical issues that are of wide interests.

To serve the interests of a diverse readership, the introduction should provide a concise summary of the background of the work in an accepted terminology in pattern recognition, state the unique contributions, and discuss broader impacts of the work outside the immediate subject area. All contributions are reviewed on the basis of scientific merits and breadth of potential interests.

Special Issue on Deep Learning Models for Computer Vision in Medical Diagnosis
Submission Date: 2024-11-20

Convolutional Neural Networks (CNNs) serve as the cornerstone of contemporary deep learning methods for computer vision, fundamentally transforming the analysis of visual data. This revolution stems from the incorporation of convolutional layers, pooling layers, and fully connected layers, working collaboratively to progressively develop a nuanced understanding of input images. In the realm of medical applications, computer vision algorithms play a pivotal role in diagnosing imaging disorders, leveraging deep learning architectures to learn from both non-image and picture data through conventional deep networks and convolutional networks, respectively. The integration of deep learning in medical imaging and analysis empowers physicians and surgeons to gain clearer insights into a patient's body, facilitating the identification of potential issues or anomalies. This application spans various medical imaging modalities, including endoscopy, MRI, ultrasound, X-ray radiography, and more. Object detection algorithms, a key component of medical picture analysis, are frequently employed to identify initial abnormality symptoms in patients. Noteworthy examples include the identification of lung nodules on chest CT or X-ray images and the detection of breast lesions on mammography and ultrasound pictures.

In radiology, deep learning algorithms are applied to identify anomalies or diseases from X-ray images, categorizing them into different illness types or severity levels. This work often leverages various machine learning algorithms that have been optimized either theoretically or empirically. Within the domain of medical imaging, deep learning algorithms exhibit unparalleled precision, effectively segmenting organs or structures, classifying images, identifying anomalies, and even forecasting the course of diseases. Deep learning has emerged as a critical technique for ultrasonic image recognition, significantly enhancing diagnostic accuracy and providing valuable guidance to medical professionals assessing a patient's condition. Moreover, deep learning contributes significantly to drug discovery by aiding in the development and discovery of medicines. Patient medical histories are meticulously scrutinized, and treatment plans are formulated based on the findings. These applications extend across various industries, including medical devices and automated driving. Initial research has primarily focused on identifying conditions such as glaucoma, age-related macular degeneration, and referable diabetic retinopathy. In the automated image analysis of fundus photos and optical coherence tomography pictures, deep learning has demonstrated promising outcomes. Computer vision, empowered by deep learning, excels in diagnosing medical images with superior precision, speed, and accuracy, making fewer mistakes by identifying intricate patterns in the images. Computer vision algorithms extract imperceptible information from medical photographs, contributing to tasks involving prediction or decision-making. Currently, convolutional neural network models, limited Boltzmann machine models, and sparse models are the most frequently utilized deep learning models in computer vision. Although these models share similarities in image recognition and classification, nuances exist in feature extraction. In light of these advancements, we invite submissions and articles for a thematic article collection dedicated to Deep Learning Models for Computer Vision in Medical Diagnosis.

Potential topics include but are not limited to the following:

Explainable AI Techniques in Deep Learning Models for Interpretable Medical Image Diagnosis
Transfer Learning Approaches for Enhancing Generalization in Medical Computer Vision Models
Imbalanced Datasets on the Performance of Deep Learning Models in Medical Imaging
Multi-Modal Data for Comprehensive Medical Diagnosis Using Deep Learning Architectures
Robustness and Security of Deep Learning Models in Medical Image Classification Tasks
Novel Hybrid Architectures by Integrating Classical Image Processing Techniques with Deep Learning Models
Adversarial Attacks on the Reliability of Deep Learning Models for Medical Image Analysis
Generalization Capabilities of Pre-trained Models for Cross-Domain Medical Image Diagnosis
Scalability and Efficiency of Deep Learning Models for Real-time Medical Diagnosis Applications
Domain Adaptation Techniques to Enhance Robustness of Computer Vision-Based Medical Models: A future Perspective
Future of Clinical Metadata for Holistic Patient Diagnosis using Deep Learning Approaches in Medical Imaging

Guest editors:
Dr. Roseline Oluwaseun Ogundokun, PhDLandmark University Omu Aran, Kwara State, Nigeriaogundokun.roseline@lmu.edu.ng; dr.roselineogundokun@gmail.com
Dr. Akinbowale Nathaniel Babatunde, PhDKwara State University, Malete, Kwara State, Nigeriaakinbowale.babatunde@kwasu.edu.ng
Dr. Micheal Olaolu Arowolo, PhDBond Life Sciences Centre University of Missouri, Columbia, USAmoacvf@missouri.edu

Manuscript submission information:

The PRL's submission system (Editorial Manager®) will be open for submissions to our Special Issue from November 1st, 2024. When submitting your manuscript please select the article type VSI: DLMCVMD. Both the Guide for Authors and the submission portal could be found on the Journal Homepage: Guide for authors - Pattern Recognition Letters - ISSN 0167-8655 | ScienceDirect.com by Elsevier.

Important dates 
Submission Portal Open: November 1st, 2024
Submission Deadline: November 20th, 2024
Acceptance Deadline: March 25th, 2025