Deep attention branch networks for skin lesion classification

Multi-scale feature fusion and class weight loss for skin lesion classification

Skin cancer is one of the common types of cancer. It spreads quickly and is not easy to detect in the early stages, posing a major threat to human health. In recent years, deep learning methods have attracted widespread attention for skin cancer detection in dermoscopic images. However, training a practical classifier becomes highly challenging due to inter-class similarity and intra-class variation in skin lesion images. To address these problems, we propose a multi-scale fusion structure that combines shallow and deep features for more accurate classification. Simultaneously, we implement three approaches to the problem of class imbalance: class weighting, label smoothing, and resampling. In addition, the HAM10000_RE dataset strips out hair features to demonstrate the role of hair features in the classification process. We demonstrate that the region of interest is the most critical classification feature for the HAM10000_SE dataset, which segments lesion regions. We evaluated the effectiveness of our model using the HAM10000 and ISIC2019 dataset. The results showed that this method performed well in dermoscopic classification tasks, with ACC and AUC of 94.0% and 99.3%, on the HAM10000 dataset and ACC of 89.8% for the ISIC2019 dataset. The overall performance of our model is excellent in comparison to state-of-the-art models.

Glaucoma detection model by exploiting multi-region and multi-scan-pattern OCT images with dynamical region score

Currently, deep learning-based methods have achieved success in glaucoma detection. However, most models focus on OCT images captured by a single scan pattern within a given region, holding the high risk of the omission of valuable features in the remaining regions or scan patterns. Therefore, we proposed a multi-region and multi-scan-pattern fusion model to address this issue. Our proposed model exploits comprehensive OCT images from three fundus anatomical regions (macular, middle, and optic nerve head regions) being captured by four scan patterns (radial, volume, single-line, and circular scan patterns). Moreover, to enhance the efficacy of integrating features across various scan patterns within a region and multiple regional features, we employed an attention multi-scan fusion module and an attention multi-region fusion module that auto-assign contribution to distinct scan-pattern features and region features adapting to characters of different samples, respectively. To alleviate the absence of available datasets, we have collected a specific dataset (MRMSG-OCT) comprising OCT images captured by four scan patterns from three regions. The experimental results and visualized feature maps both demonstrate that our proposed model achieves superior performance against the single scan-pattern models and single region-based models. Moreover, compared with the average fusion strategy, our proposed fusion modules yield superior performance, particularly reversing the performance degradation observed in some models relying on fixed weights, validating the efficacy of the proposed dynamic region scores adapted to different samples. Moreover, the derived region contribution scores enhance the interpretability of the model and offer an overview of the model's decision-making process, assisting ophthalmologists in prioritizing regions with heightened scores and increasing efficiency in clinical practice.

Identifying the role of vision transformer for skin cancer-A scoping review

Introduction

Detecting and accurately diagnosing early melanocytic lesions is challenging due to extensive intra- and inter-observer variabilities. Dermoscopy images are widely used to identify and study skin cancer, but the blurred boundaries between lesions and besieging tissues can lead to incorrect identification. Artificial Intelligence (AI) models, including vision transformers, have been proposed as a solution, but variations in symptoms and underlying effects hinder their performance.

Objective

This scoping review synthesizes and analyzes the literature that uses vision transformers for skin lesion detection.

Methods

The review follows the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Revise) guidelines. The review searched online repositories such as IEEE Xplore, Scopus, Google Scholar, and PubMed to retrieve relevant articles. After screening and pre-processing, 28 studies that fulfilled the inclusion criteria were included.

Results and discussions

The review found that the use of vision transformers for skin cancer detection has rapidly increased from 2020 to 2022 and has shown outstanding performance for skin cancer detection using dermoscopy images. Along with highlighting intrinsic visual ambiguities, irregular skin lesion shapes, and many other unwanted challenges, the review also discusses the key problems that obfuscate the trustworthiness of vision transformers in skin cancer diagnosis. This review provides new insights for practitioners and researchers to understand the current state of knowledge in this specialized research domain and outlines the best segmentation techniques to identify accurate lesion boundaries and perform melanoma diagnosis. These findings will ultimately assist practitioners and researchers in making more authentic decisions promptly.

TFormer: A throughout fusion transformer for multi-modal skin lesion diagnosis

Multi-modal skin lesion diagnosis (MSLD) has achieved remarkable success by modern computer-aided diagnosis (CAD) technology based on deep convolutions. However, the information aggregation across modalities in MSLD remains challenging due to severity unaligned spatial resolution (e.g., dermoscopic image and clinical image) and heterogeneous data (e.g., dermoscopic image and patients' meta-data). Limited by the intrinsic local attention, most recent MSLD pipelines using pure convolutions struggle to capture representative features in shallow layers, thus the fusion across different modalities is usually done at the end of the pipelines, even at the last layer, leading to an insufficient information aggregation. To tackle the issue, we introduce a pure transformer-based method, which we refer to as "Throughout Fusion Transformer (TFormer)", for sufficient information integration in MSLD. Different from the existing approaches with convolutions, the proposed network leverages transformer as feature extraction backbone, bringing more representative shallow features. We then carefully design a stack of dual-branch hierarchical multi-modal transformer (HMT) blocks to fuse information across different image modalities in a stage-by-stage way. With the aggregated information of image modalities, a multi-modal transformer post-fusion (MTP) block is designed to integrate features across image and non-image data. Such a strategy that information of the image modalities is firstly fused then the heterogeneous ones enables us to better divide and conquer the two major challenges while ensuring inter-modality dynamics are effectively modeled. Experiments conducted on the public Derm7pt dataset validate the superiority of the proposed method. Our TFormer achieves an average accuracy of 77.99% and diagnostic accuracy of 80.03% , which outperforms other state-of-the-art methods. Ablation experiments also suggest the effectiveness of our designs. The codes can be publicly available from https://github.com/zylbuaa/TFormer.git.

A survey, review, and future trends of skin lesion segmentation and classification

The Computer-aided Diagnosis or Detection (CAD) approach for skin lesion analysis is an emerging field of research that has the potential to alleviate the burden and cost of skin cancer screening. Researchers have recently indicated increasing interest in developing such CAD systems, with the intention of providing a user-friendly tool to dermatologists to reduce the challenges encountered or associated with manual inspection. This article aims to provide a comprehensive literature survey and review of a total of 594 publications (356 for skin lesion segmentation and 238 for skin lesion classification) published between 2011 and 2022. These articles are analyzed and summarized in a number of different ways to contribute vital information regarding the methods for the development of CAD systems. These ways include: relevant and essential definitions and theories, input data (dataset utilization, preprocessing, augmentations, and fixing imbalance problems), method configuration (techniques, architectures, module frameworks, and losses), training tactics (hyperparameter settings), and evaluation criteria. We intend to investigate a variety of performance-enhancing approaches, including ensemble and post-processing. We also discuss these dimensions to reveal their current trends based on utilization frequencies. In addition, we highlight the primary difficulties associated with evaluating skin lesion segmentation and classification systems using minimal datasets, as well as the potential solutions to these difficulties. Findings, recommendations, and trends are disclosed to inform future research on developing an automated and robust CAD system for skin lesion analysis.

CI-Net: Clinical-Inspired Network for Automated Skin Lesion Recognition

The lesion recognition of dermoscopy images is significant for automated skin cancer diagnosis. Most of the existing methods ignore the medical perspective, which is crucial since this task requires a large amount of medical knowledge. A few methods are designed according to medical knowledge, but they ignore to be fully in line with doctors' entire learning and diagnosis process, since certain strategies and steps of those are conducted in practice for doctors. Thus, we put forward Clinical-Inspired Network (CI-Net) to involve the learning strategy and diagnosis process of doctors, as for a better analysis. The diagnostic process contains three main steps: the zoom step, the observe step and the compare step. To simulate these, we introduce three corresponding modules: a lesion area attention module, a feature extraction module and a lesion feature attention module. To simulate the distinguish strategy, which is commonly used by doctors, we introduce a distinguish module. We evaluate our proposed CI-Net on six challenging datasets, including ISIC 2016, ISIC 2017, ISIC 2018, ISIC 2019, ISIC 2020 and PH2 datasets, and the results indicate that CI-Net outperforms existing work. The code is publicly available at https://github.com/lzh19961031/Dermoscopy_classification.

Interpretable and Reliable Oral Cancer Classifier with Attention Mechanism and Expert Knowledge Embedding via Attention Map

Convolutional neural networks have demonstrated excellent performance in oral cancer detection and classification. However, the end-to-end learning strategy makes CNNs hard to interpret, and it can be challenging to fully understand the decision-making procedure. Additionally, reliability is also a significant challenge for CNN based approaches. In this study, we proposed a neural network called the attention branch network (ABN), which combines the visual explanation and attention mechanisms to improve the recognition performance and interpret the decision-making simultaneously. We also embedded expert knowledge into the network by having human experts manually edit the attention maps for the attention mechanism. Our experiments have shown that ABN performs better than the original baseline network. By introducing the Squeeze-and-Excitation (SE) blocks to the network, the cross-validation accuracy increased further. Furthermore, we observed that some previously misclassified cases were correctly recognized after updating by manually editing the attention maps. The cross-validation accuracy increased from 0.846 to 0.875 with the ABN (Resnet18 as baseline), 0.877 with SE-ABN, and 0.903 after embedding expert knowledge. The proposed method provides an accurate, interpretable, and reliable oral cancer computer-aided diagnosis system through visual explanation, attention mechanisms, and expert knowledge embedding.

Cross-attention multi-branch CNN using DCE-MRI to classify breast cancer molecular subtypes

Purpose

The aim of this study is to improve the accuracy of classifying luminal or non-luminal subtypes of breast cancer by using computer algorithms based on DCE-MRI, and to validate the diagnostic efficacy of the model by considering the patient's age of menarche and nodule size.

Methods

DCE-MRI images of patients with non-specific invasive breast cancer admitted to the Second Affiliated Hospital of Dalian Medical University were collected. There were 160 cases in total, with 84 cases of luminal type (luminal A and luminal B and 76 cases of non-luminal type (HER 2 overexpressing and triple negative). Patients were grouped according to thresholds of nodule sizes of 20 mm and age at menarche of 14 years. A cross-attention multi-branch net CAMBNET) was proposed based on the dataset to predict the molecular subtypes of breast cancer. Diagnostic performance was assessed by accuracy, sensitivity, specificity, F1 and area under the ROC curve (AUC). And the model is visualized with Grad-CAM.

Results

Several classical deep learning models were included for diagnostic performance comparison. Using 5-fold cross-validation on the test dataset, all the results of CAMBNET are significantly higher than the compared deep learning models. The average prediction recall, accuracy, precision, and AUC for luminal and non-luminal types of the dataset were 89.11%, 88.44%, 88.52%, and 96.10%, respectively. For patients with tumor size <20 mm, the CAMBNET had AUC of 83.45% and ACC of 90.29% for detecting triple-negative breast cancer. When classifying luminal from non-luminal subtypes for patients with age at menarche years, our CAMBNET model achieved an ACC of 92.37%, precision of 92.42%, recall of 93.33%, F1of 92.33%, and AUC of 99.95%.

Conclusions

The CAMBNET can be applied in molecular subtype classification of breasts. For patients with menarche at 14 years old, our model can yield more accurate results when classifying luminal and non-luminal subtypes. For patients with tumor sizes ≤20 mm, our model can yield more accurate result in detecting triple-negative breast cancer to improve patient prognosis and survival.

Toward Multicenter Skin Lesion Classification Using Deep Neural Network With Adaptively Weighted Balance Loss

Recently, deep neural network-based methods have shown promising advantages in accurately recognizing skin lesions from dermoscopic images. However, most existing works focus more on improving the network framework for better feature representation but ignore the data imbalance issue, limiting their flexibility and accuracy across multiple scenarios in multi-center clinics. Generally, different clinical centers have different data distributions, which presents challenging requirements for the network's flexibility and accuracy. In this paper, we divert the attention from framework improvement to the data imbalance issue and propose a new solution for multi-center skin lesion classification by introducing a novel adaptively weighted balance (AWB) loss to the conventional classification network. Benefiting from AWB, the proposed solution has the following advantages: 1) it is easy to satisfy different practical requirements by only changing the backbone; 2) it is user-friendly with no tuning on hyperparameters; and 3) it adaptively enables small intraclass compactness and pays more attention to the minority class. Extensive experiments demonstrate that, compared with solutions equipped with state-of-the-art loss functions, the proposed solution is more flexible and more competent for tackling the multi-center imbalanced skin lesion classification task with considerable performance on two benchmark datasets. In addition, the proposed solution is proved to be effective in handling the imbalanced gastrointestinal disease classification task and the imbalanced DR grading task. Code is available at https://github.com/Weipeishan2021.

Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning?

Attention mechanism, which is a means of determining which part of the forced data is emphasized, has attracted attention in various fields of deep learning in recent years. The purpose of this study was to evaluate the performance of the attention branch network (ABN) for implant classification using convolutional neural networks (CNNs). The data consisted of 10191 dental implant images from 13 implant brands that cropped the site, including dental implants as pretreatment, from digital panoramic radiographs of patients who underwent surgery at Kagawa Prefectural Central Hospital between 2005 and 2021. ResNet 18, 50, and 152 were evaluated as CNN models that were compared with and without the ABN. We used accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristics curve as performance metrics. We also performed statistical and effect size evaluations of the 30-time performance metrics of the simple CNNs and the ABN model. ResNet18 with ABN significantly improved the dental implant classification performance for all the performance metrics. Effect sizes were equivalent to “Huge” for all performance metrics. In contrast, the classification performance of ResNet50 and 152 deteriorated by adding the attention mechanism. ResNet18 showed considerably high compatibility with the ABN model in dental implant classification (AUC = 0.9993) despite the small number of parameters. The limitation of this study is that only ResNet was verified as a CNN; further studies are required for other CNN models.

KIEGLFN: A unified acne grading framework on face images

BACKGROUND AND OBJECTIVE

Grading the severity level is an extremely important procedure for correct diagnoses and personalized treatment schemes for acne. However, the acne grading criteria are not unified in the medical field. This work aims to develop an acne diagnosis system that can be generalized to various criteria.

METHODS

A unified acne grading framework that can be generalized to apply referring to different grading criteria is developed. It imitates the global estimation of the dermatologist diagnosis in two steps. First, an adaptive image preprocessing method effectively filters meaningless information and enhances key information. Next, an innovative network structure fuses global deep features with local features to simulate the dermatologists' comparison of local skin and global observation. In addition, a transfer fine-tuning strategy is proposed to transfer prior knowledge on one criterion to another criterion, which effectively improves the framework performance in case of insufficient data.

RESULTS

The Preprocessing method effectively filters meaningless areas and improves the performance of downstream models.The framework reaches accuracies of 84.52% and 59.35% on two datasets separately.

CONCLUSIONS

The application of the framework on acne grading exceeds the state-of-the-art method by 1.71%, reaches the diagnostic level of a professional dermatologist and the transfer fine-tuning strategy improves the accuracy of 6.5% on the small data.

Classification of skin cancer using convolutional neural networks analysis of Raman spectra

BACKGROUND AND OBJECTIVE

Skin cancer is the most common malignancy in whites accounting for about one third of all cancers diagnosed per year. Portable Raman spectroscopy setups for skin cancer "optical biopsy" are utilized to detect tumors based on their spectral features caused by the comparative presence of different chemical components. However, low signal-to-noise ratio in such systems may prevent accurate tumors classification. Thus, there is a challenge to develop methods for efficient skin tumors classification.

METHODS

We compare the performance of convolutional neural networks and the projection on latent structures with discriminant analysis for discriminating skin cancer using the analysis of Raman spectra with a high autofluorescence background stimulated by a 785 nm laser. We have registered the spectra of 617 cases of skin neoplasms (615 patients, 70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) in vivo with a portable Raman setup and created classification models both for convolutional neural networks and projection on latent structures approaches. To check the classification models stability, a 10-fold cross-validation was performed for all created models. To avoid models overfitting, the data was divided into a training set (80% of spectral dataset) and a test set (20% of spectral dataset).

RESULTS

The results for different classification tasks demonstrate that the convolutional neural networks significantly (p<0.01) outperforms the projection on latent structures. For the convolutional neural networks implementation we obtained ROC AUCs of 0.96 (0.94 - 0.97; 95% CI), 0.90 (0.85-0.94; 95% CI), and 0.92 (0.87 - 0.97; 95% CI) for classifying a) malignant vs benign tumors, b) melanomas vs pigmented tumors and c) melanomas vs seborrheic keratosis respectively.

CONCLUSIONS

The performance of the convolutional neural networks classification of skin tumors based on Raman spectra analysis is higher or comparable to the accuracy provided by trained dermatologists. The increased accuracy with the convolutional neural networks implementation is due to a more precise accounting of low intensity Raman bands in the intense autofluorescence background. The achieved high performance of skin tumors classifications with convolutional neural networks analysis opens a possibility for wide implementation of Raman setups in clinical setting.