Connah Kendrick

Imran Chowdhury Dipto, Bill Cassidy, Connah Kendrick et al.

This research conducts an investigation on the effect of visually similar images within a publicly available diabetic foot ulcer dataset when training deep learning classification networks. The presence of binary-identical duplicate images in datasets used to train deep learning algorithms is a well known issue that can introduce unwanted bias which can degrade network performance. However, the effect of visually similar non-identical images is an under-researched topic, and has so far not been investigated in any diabetic foot ulcer studies. We use an open-source fuzzy algorithm to identify groups of increasingly similar images in the Diabetic Foot Ulcers Challenge 2021 (DFUC2021) training dataset. Based on each similarity threshold, we create new training sets that we use to train a range of deep learning multi-class classifiers. We then evaluate the performance of the best performing model on the DFUC2021 test set. Our findings show that the model trained on the training set with the 80\% similarity threshold images removed achieved the best performance using the InceptionResNetV2 network. This model showed improvements in F1-score, precision, and recall of 0.023, 0.029, and 0.013, respectively. These results indicate that highly similar images can contribute towards the presence of performance degrading bias within the Diabetic Foot Ulcers Challenge 2021 dataset, and that the removal of images that are 80\% similar from the training set can help to boost classification performance.

Connah Kendrick, Bill Cassidy, Joseph M. Pappachan et al.

Diabetic foot ulcer is a severe condition that requires close monitoring and management. For training machine learning methods to auto-delineate the ulcer, clinical staff must provide ground truth annotations. In this paper, we propose a new diabetic foot ulcers dataset, namely DFUC2022, the largest segmentation dataset where ulcer regions were manually delineated by clinicians. We assess whether the clinical delineations are machine interpretable by deep learning networks or if image processing refined contour should be used. By providing benchmark results using a selection of popular deep learning algorithms, we draw new insights into the limitations of DFU wound delineation and report on the associated issues. This paper provides some observations on baseline models to facilitate DFUC2022 Challenge in conjunction with MICCAI 2022. The leaderboard will be ranked by Dice score, where the best FCN-based method is 0.5708 and DeepLabv3+ achieved the best score of 0.6277. This paper demonstrates that image processing using refined contour as ground truth can provide better agreement with machine predicted results. DFUC2022 will be released on the 27th April 2022.

Connah Kendrick, Bill Cassidy, Neil D. Reeves et al.

The Diabetic Foot Ulcer Challenge 2022 focused on the task of diabetic foot ulcer segmentation, based on the work completed in previous DFU challenges. The challenge provided 4000 images of full-view foot ulcer images together with corresponding delineation of ulcer regions. This paper provides an overview of the challenge, a summary of the methods proposed by the challenge participants, the results obtained from each technique, and a comparison of the challenge results. The best-performing network was a modified HarDNet-MSEG, with a Dice score of 0.7287.

Samuel William Pewton, Bill Cassidy, Connah Kendrick et al.

One of the more significant obstacles in classification of skin cancer is the presence of artifacts. This paper investigates the effect of dark corner artifacts, which result from the use of dermoscopes, on the performance of a deep learning binary classification task. Previous research attempted to remove and inpaint dark corner artifacts, with the intention of creating an ideal condition for models. However, such research has been shown to be inconclusive due to lack of available datasets labelled with dark corner artifacts and detailed analysis and discussion. To address these issues, we label 10,250 skin lesion images from publicly available datasets and introduce a balanced dataset with an equal number of melanoma and non-melanoma cases. The training set comprises 6126 images without artifacts, and the testing set comprises 4124 images with dark corner artifacts. We conduct three experiments to provide new understanding on the effects of dark corner artifacts, including inpainted and synthetically generated examples, on a deep learning method. Our results suggest that introducing synthetic dark corner artifacts which have been superimposed onto the training set improved model performance, particularly in terms of the true negative rate. This indicates that deep learning learnt to ignore dark corner artifacts, rather than treating it as melanoma, when dark corner artifacts were introduced into the training set. Further, we propose a new approach to quantifying heatmaps indicating network focus using a root mean square measure of the brightness intensity in the different regions of the heatmaps. This paper provides a new guideline for skin lesions analysis with an emphasis on reproducibility.

Bill Cassidy, Christian McBride, Connah Kendrick et al.

The growing rate of chronic wound occurrence, especially in patients with diabetes, has become a concerning trend in recent years. Chronic wounds are difficult and costly to treat, and have become a serious burden on health care systems worldwide. Chronic wounds can have devastating consequences for the patient, with infection often leading to reduced quality of life and increased mortality risk. Innovative deep learning methods for the detection and monitoring of such wounds have the potential to reduce the impact to both patient and clinician. We present a novel multimodal segmentation method which allows for the introduction of patient metadata into the training workflow whereby the patient data are expressed as Gaussian random fields. Our results indicate that the proposed method improved performance when utilising multiple models, each trained on different metadata categories. Using the Diabetic Foot Ulcer Challenge 2022 test set, when compared to the baseline results (intersection over union = 0.4670, Dice similarity coefficient = 0.5908) we demonstrate improvements of +0.0220 and +0.0229 for intersection over union and Dice similarity coefficient respectively. This paper presents the first study to focus on integrating patient data into a chronic wound segmentation workflow. Our results show significant performance gains when training individual models using specific metadata categories, followed by average merging of prediction masks using distance transforms. All source code for this study is available at: https://github.com/mmu-dermatology-research/multimodal-grf

David Gillespie, Connah Kendrick, Ian Boon et al.

Prostate radiotherapy is a well established curative oncology modality, which in future will use Magnetic Resonance Imaging (MRI)-based radiotherapy for daily adaptive radiotherapy target definition. However the time needed to delineate the prostate from MRI data accurately is a time consuming process. Deep learning has been identified as a potential new technology for the delivery of precision radiotherapy in prostate cancer, where accurate prostate segmentation helps in cancer detection and therapy. However, the trained models can be limited in their application to clinical setting due to different acquisition protocols, limited publicly available datasets, where the size of the datasets are relatively small. Therefore, to explore the field of prostate segmentation and to discover a generalisable solution, we review the state-of-the-art deep learning algorithms in MR prostate segmentation; provide insights to the field by discussing their limitations and strengths; and propose an optimised 2D U-Net for MR prostate segmentation. We evaluate the performance on four publicly available datasets using Dice Similarity Coefficient (DSC) as performance metric. Our experiments include within dataset evaluation and cross-dataset evaluation. The best result is achieved by composite evaluation (DSC of 0.9427 on Decathlon test set) and the poorest result is achieved by cross-dataset evaluation (DSC of 0.5892, Prostate X training set, Promise 12 testing set). We outline the challenges and provide recommendations for future work. Our research provides a new perspective to MR prostate segmentation and more importantly, we provide standardised experiment settings for researchers to evaluate their algorithms. Our code is available at https://github.com/AIEMMU/MRI\_Prostate.

Jireh Jam, Connah Kendrick, Vincent Drouard et al.

Image inpainting is a key technique in image processing task to predict the missing regions and generate realistic images. Given the advancement of existing generative inpainting models with feature extraction, propagation and reconstruction capabilities, there is lack of high-quality feature extraction and transfer mechanisms in deeper layers to tackle persistent aberrations on the generated inpainted regions. Our method, V-LinkNet, develops high-level feature transference to deep level textural context of inpainted regions our work, proposes a novel technique of combining encoders learning through a recursive residual transition layer (RSTL). The RSTL layer easily adapts dual encoders by increasing the unique semantic information through direct communication. By collaborating the dual encoders structure with contextualised feature representation loss function, our system gains the ability to inpaint with high-level features. To reduce biases from random mask-image pairing, we introduce a standard protocol with paired mask-image on the testing set of CelebA-HQ, Paris Street View and Places2 datasets. Our results show V-LinkNet performed better on CelebA-HQ and Paris Street View using this standard protocol. We will share the standard protocol and our codes with the research community upon acceptance of this paper.

Moi Hoon Yap, Connah Kendrick, Neil D. Reeves et al.

This paper provides conceptual foundation and procedures used in the development of diabetic foot ulcer datasets over the past decade, with a timeline to demonstrate progress. We conduct a survey on data capturing methods for foot photographs, an overview of research in developing private and public datasets, the related computer vision tasks (detection, segmentation and classification), the diabetic foot ulcer challenges and the future direction of the development of the datasets. We report the distribution of dataset users by country and year. Our aim is to share the technical challenges that we encountered together with good practices in dataset development, and provide motivation for other researchers to participate in data sharing in this domain.

Bill Cassidy, Connah Kendrick, Neil D. Reeves et al.

Diabetic foot ulcer classification systems use the presence of wound infection (bacteria present within the wound) and ischaemia (restricted blood supply) as vital clinical indicators for treatment and prediction of wound healing. Studies investigating the use of automated computerised methods of classifying infection and ischaemia within diabetic foot wounds are limited due to a paucity of publicly available datasets and severe data imbalance in those few that exist. The Diabetic Foot Ulcer Challenge 2021 provided participants with a more substantial dataset comprising a total of 15,683 diabetic foot ulcer patches, with 5,955 used for training, 5,734 used for testing and an additional 3,994 unlabelled patches to promote the development of semi-supervised and weakly-supervised deep learning techniques. This paper provides an evaluation of the methods used in the Diabetic Foot Ulcer Challenge 2021, and summarises the results obtained from each network. The best performing network was an ensemble of the results of the top 3 models, with a macro-average F1-score of 0.6307.

Chuin Hong Yap, Moi Hoon Yap, Adrian K. Davison et al.

Facial expression spotting is the preliminary step for micro- and macro-expression analysis. The task of reliably spotting such expressions in video sequences is currently unsolved. The current best systems depend upon optical flow methods to extract regional motion features, before categorisation of that motion into a specific class of facial movement. Optical flow is susceptible to drift error, which introduces a serious problem for motions with long-term dependencies, such as high frame-rate macro-expression. We propose a purely deep learning solution which, rather than tracking frame differential motion, compares via a convolutional model, each frame with two temporally local reference frames. Reference frames are sampled according to calculated micro- and macro-expression duration. As baseline for MEGC2021 using leave-one-subject-out evaluation method, we show that our solution achieves F1-score of 0.105 in a high frame-rate (200 fps) SAMM long videos dataset (SAMM-LV) and is competitive in a low frame-rate (30 fps) (CAS(ME)2) dataset. On unseen MEGC2022 challenge dataset, the baseline results are 0.1176 on SAMM Challenge dataset, 0.1739 on CAS(ME)3 and overall performance of 0.1531 on both dataset.

Jireh Jam, Connah Kendrick, Vincent Drouard et al.

Facial image inpainting, with high-fidelity preservation for image realism, is a very challenging task. This is due to the subtle texture in key facial features (component) that are not easily transferable. Many image inpainting techniques have been proposed with outstanding capabilities and high quantitative performances recorded. However, with facial inpainting, the features are more conspicuous and the visual quality of the blended inpainted regions are more important qualitatively. Based on these facts, we design a foreground-guided facial inpainting framework that can extract and generate facial features using convolutional neural network layers. It introduces the use of foreground segmentation masks to preserve the fidelity. Specifically, we propose a new loss function with semantic capability reasoning of facial expressions, natural and unnatural features (make-up). We conduct our experiments using the CelebA-HQ dataset, segmentation masks from CelebAMask-HQ (for foreground guidance) and Quick Draw Mask (for missing regions). Our proposed method achieved comparable quantitative results when compare to the state of the art but qualitatively, it demonstrated high-fidelity preservation of facial components.

Jireh Jam, Connah Kendrick, Vincent Drouard et al.

Facial image inpainting is a problem that is widely studied, and in recent years the introduction of Generative Adversarial Networks, has led to improvements in the field. Unfortunately some issues persists, in particular when blending the missing pixels with the visible ones. We address the problem by proposing a Wasserstein GAN combined with a new reverse mask operator, namely Reverse Masking Network (R-MNet), a perceptual adversarial network for image inpainting. The reverse mask operator transfers the reverse masked image to the end of the encoder-decoder network leaving only valid pixels to be inpainted. Additionally, we propose a new loss function computed in feature space to target only valid pixels combined with adversarial training. These then capture data distributions and generate images similar to those in the training data with achieved realism (realistic and coherent) on the output images. We evaluate our method on publicly available dataset, and compare with state-of-the-art methods. We show that our method is able to generalize to high-resolution inpainting task, and further show more realistic outputs that are plausible to the human visual system when compared with the state-of-the-art methods.

Connah Kendrick, David Gillespie, Moi Hoon Yap

We propose a new type of General Adversarial Network (GAN) to resolve a common issue with Deep Learning. We develop a novel architecture that can be applied to existing latent vector based GAN structures that allows them to generate on-the-fly images of any size. Existing GAN for image generation requires uniform images of matching dimensions. However, publicly available datasets, such as ImageNet contain thousands of different sizes. Resizing image causes deformations and changing the image data, whereas as our network does not require this preprocessing step. We make significant changes to the standard data loading techniques to enable any size image to be loaded for training. We also modify the network in two ways, by adding multiple inputs and a novel dynamic resizing layer. Finally we make adjustments to the discriminator to work on multiple resolutions. These changes can allow multiple resolution datasets to be trained on without any resizing, if memory allows. We validate our results on the ISIC 2019 skin lesion dataset. We demonstrate our method can successfully generate realistic images at different sizes without issue, preserving and understanding spatial relationships, while maintaining feature relationships. We will release the source codes upon paper acceptance.

Jireh Jam, Connah Kendrick, Vincent Drouard et al.

The state-of-the-art facial image inpainting methods achieved promising results but face realism preservation remains a challenge. This is due to limitations such as; failures in preserving edges and blurry artefacts. To overcome these limitations, we propose a Symmetric Skip Connection Wasserstein Generative Adversarial Network (S-WGAN) for high-resolution facial image inpainting. The architecture is an encoder-decoder with convolutional blocks, linked by skip connections. The encoder is a feature extractor that captures data abstractions of an input image to learn an end-to-end mapping from an input (binary masked image) to the ground-truth. The decoder uses learned abstractions to reconstruct the image. With skip connections, S-WGAN transfers image details to the decoder. Additionally, we propose a Wasserstein-Perceptual loss function to preserve colour and maintain realism on a reconstructed image. We evaluate our method and the state-of-the-art methods on CelebA-HQ dataset. Our results show S-WGAN produces sharper and more realistic images when visually compared with other methods. The quantitative measures show our proposed S-WGAN achieves the best Structure Similarity Index Measure (SSIM) of 0.94.

Chuin Hong Yap, Connah Kendrick, Moi Hoon Yap

With the growth of popularity of facial micro-expressions in recent years, the demand for long videos with micro- and macro-expressions remains high. Extended from SAMM, a micro-expressions dataset released in 2016, this paper presents SAMM Long Videos dataset for spontaneous micro- and macro-expressions recognition and spotting. SAMM Long Videos dataset consists of 147 long videos with 343 macro-expressions and 159 micro-expressions. The dataset is FACS-coded with detailed Action Units (AUs). We compare our dataset with Chinese Academy of Sciences Macro-Expressions and Micro-Expressions (CAS(ME)2) dataset, which is the only available fully annotated dataset with micro- and macro-expressions. Furthermore, we preprocess the long videos using OpenFace, which includes face alignment and detection of facial AUs. We conduct facial expression spotting using this dataset and compare it with the baseline of MEGC III. Our spotting method outperformed the baseline result with F1-score of 0.3299.

Omaima FathElrahman Osman, Remah Mutasim Ibrahim Elbashir, Imad Eldain Abbass et al.

Facial wrinkle is one of the most prominent biological changes that accompanying the natural aging process. However, there are some external factors contributing to premature wrinkles development, such as sun exposure and smoking. Clinical studies have shown that heavy smoking causes premature wrinkles development. However, there is no computerised system that can automatically assess the facial wrinkles on the whole face. This study investigates the effect of smoking on facial wrinkling using a social habit face dataset and an automated computerised computer vision algorithm. The wrinkles pattern represented in the intensity of 0-255 was first extracted using a modified Hybrid Hessian Filter. The face was divided into ten predefined regions, where the wrinkles in each region was extracted. Then the statistical analysis was performed to analyse which region is effected mainly by smoking. The result showed that the density of wrinkles for smokers in two regions around the mouth was significantly higher than the non-smokers, at p-value of 0.05. Other regions are inconclusive due to lack of large scale dataset. Finally, the wrinkle was visually compared between smoker and non-smoker faces by generating a generic 3D face model.