Computational Medical Image Analysis: A Preface

There has been immense progress in medical image analysis over the past decade. Methodologies have transitioned from analytical to implementation-based to machine-learning-based techniques. This Special Issue was introduced to showcase the latest innovations in medical image analysis. The focus was on computational applications of medical images. The scope was not limited by the imaging modalities or applications presented. I envisaged a combination of modalities such as planar imaging (e.g., X-ray, planar nuclear imaging), anatomical imaging (e.g., computed tomography [CT], magnetic resonance [MR] imaging), nuclear medicine (e.g., positron emission tomography [PET]), bimodal or multimodal imaging (e.g., PET-CT), as well as pathology. While some applications were listed as examples in the invitation, there were no restrictions on the presented applications as long as they were clinically relevant.

This Special Issue received enthusiastic responses from the academic community. With 12 successful submissions and the interest these generated, we were motivated to work on a second edition, which is already open for submissions. Among the articles, 10 are research articles while two are review articles. Further, of the 12 articles, 10 (including both the review articles) dealt with machine-learning- and deep-learning-based methods, highlighting the transition towards these methods in the past decade. I was also glad to see the geographic diversity of the published articles. The first authors of the 12 papers were based in 11 different countries and four continents.

This Special Issue contains some very important and innovative applications. A summary of the papers along with the tackled applications is provided in

Table 1. Summary of the 12 papers published in the Special Issue ‘Computational Medical Image Analysis.

First Author/Reference	Type	Description
Santos et al [1]	Research	A computer-aided diagnosis method for eye melanoma detection using Lorenz’s attractor
Haider et al. [2]	Research	A compressed sensing-based based method for sparse reconstruction of MR images
Joshi et al. [3]	Research	A method for detecting breast cancer in histopathology images using convolutional neural networks (CNNs)
Rashed et al. [4]	Research	Evaluate various machine-learning and deep-learning techniques for classifying chest X-ray and dermoscopy images into normal and abnormal
Aguirre-Arango et al. [5]	Research	Technique for feet segmentation in thermal images that can be used for pain relief during pregnancy
Chauhan et al. [6]	Research	Evaluate several classifiers on electroencephalography (EEG) data to classify Attention Deficit Hyperactive Disorder (ADHD) patients and healthy controls
Supriyanto et al. [7]	Research	Use a geometric augmentation and generative adversarial networks (GANs) to classify clinical (white-light) images of skin lesions into cancerous and non-cancerous
Kolli et al. [8]	Research	Predict the time to wound healing based on digital images of the wound
Lipinski [9]	Research	Development of simulated dynamic susceptibility contrast MR images of the brain that can be used to evaluate quality assessment methods for disease diagnosis
Alnsaif [10]	Research	Development of a classifier to differentiate between COVID-19 and non-COVID-19 chest CT scans using features extracted from pre-trained deep-learning models
Petrikova et al. [11]	Review	Provide an overview of deep-learning-based histopathology classification tasks covering a variety of applications and organs
Martins et al. [12]	Review	Investigate recent progress in machine-learning methods for the diagnosis of oral diseases using oral X-ray images

.

I would like to thank the MDPI team for their smooth processing of the submitted articles. The editorial team and Academic Editors ensured each article received adequate consideration. The Editorial Board was called upon a few times to provide the final decision when reviewer opinions diverged. Finally, a big thank you to all reviewers who provided scientific expertise for this Special Issue despite their busy schedules. I look forward to working with all of them for the second edition and invite all authors and readers to consider this Special Issue for the submission of their research outputs.