Artificial intelligence-based image classification methods for diagnosis of skin cancer: Challenges and opportunities.
Ontology highlight
ABSTRACT:
SUBMITTER: Goyal M
PROVIDER: S-EPMC8290363 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:In recent decades, the incidence of melanoma has grown rapidly. Hence, early diagnosis is crucial to improving clinical outcomes. Here, we propose and compare a classical image analysis-based machine learning method with a deep learning one to automatically classify benign vs. malignant dermoscopic skin lesion images. The same dataset of 25,122 publicly available dermoscopic images was used to train both models, while a disjointed test set of 200 images was used for the evaluation phase. The training dataset was randomly divided into 10 datasets of 19,932 images to obtain an equal distribution between the two classes. By testing both models on the disjoint set, the deep learning-based method returned accuracy of 85.4 ± 3.2% and specificity of 75.5 ± 7.6%, while the machine learning one showed accuracy and specificity of 73.8 ± 1.1% and 44.5 ± 4.7%, respectively. Although both approaches performed well in the validation phase, the convolutional neural network outperformed the ensemble boosted tree classifier on the disjoint test set, showing better generalization ability. The integration of new melanoma detection algorithms with digital dermoscopic devices could enable a faster screening of the population, improve patient management, and achieve better survival rates.
| S-EPMC10669580 | biostudies-literature
Project description:Artificial intelligence algorithms to classify melanoma are dependent on their training data, which limits generalizability. The objective of this study was to compare the performance of an artificial intelligence model trained on a standard adult-predominant dermoscopic dataset before and after the addition of additional pediatric training images. The performances were compared using held-out adult and pediatric test sets of images. We trained two models: one (model A) on an adult-predominant dataset (37,662 images from the International Skin Imaging Collaboration) and the other (model A+P) on an additional 1,536 pediatric images. We compared performance between the two models on adult and pediatric held-out test images separately using the area under the receiver operating characteristic curve. We then used Gradient-weighted Class Activation Maps and background skin masking to understand the contributions of the lesion versus background skin to algorithm decision making. Adding images from a pediatric population with different epidemiological and visual patterns to current reference standard datasets improved algorithm performance on pediatric images without diminishing performance on adult images. This suggests a way that dermatologic artificial intelligence models can be made more generalizable. The presence of background skin was important to the pediatric-specific improvement seen between models. Our study highlights the importance of carefully curated and labeled data from diverse inputs to improve the generalizability of AI models for dermatology, in this case applied to dermoscopic images of adult and pediatric lesions to improve melanoma detection.
| S-EPMC10431965 | biostudies-literature
Project description:Acute appendicitis is one of the major causes for emergency surgery in childhood and adolescence. Appendectomy is still the therapy of choice, but conservative strategies are increasingly being studied for uncomplicated inflammation. Diagnosis of acute appendicitis remains challenging, especially due to the frequently unspecific clinical picture. Inflammatory blood markers and imaging methods like ultrasound are limited as they have to be interpreted by experts and still do not offer sufficient diagnostic certainty. This study presents a method for automatic diagnosis of appendicitis as well as the differentiation between complicated and uncomplicated inflammation using values/parameters which are routinely and unbiasedly obtained for each patient with suspected appendicitis. We analyzed full blood counts, c-reactive protein (CRP) and appendiceal diameters in ultrasound investigations corresponding to children and adolescents aged 0-17 years from a hospital based population in Berlin, Germany. A total of 590 patients (473 patients with appendicitis in histopathology and 117 with negative histopathological findings) were analyzed retrospectively with modern algorithms from machine learning (ML) and artificial intelligence (AI). The discovery of informative parameters (biomarker signatures) and training of the classification model were done with a maximum of 35% of the patients. The remaining minimum 65% of patients were used for validation. At clinical relevant cut-off points the accuracy of the biomarker signature for diagnosis of appendicitis was 90% (93% sensitivity, 67% specificity), while the accuracy to correctly identify complicated inflammation was 51% (95% sensitivity, 33% specificity) on validation data. Such a test would be capable to prevent two out of three patients without appendicitis from useless surgery as well as one out of three patients with uncomplicated appendicitis. The presented method has the potential to change today's therapeutic approach for appendicitis and demonstrates the capability of algorithms from AI and ML to significantly improve diagnostics even based on routine diagnostic parameters.
| S-EPMC6760759 | biostudies-literature
Project description:Clustered regularly interspaced short palindromic repeat (CRISPR)-based genome editing (GED) technologies have unlocked exciting possibilities for understanding genes and improving medical treatments. On the other hand, Artificial intelligence (AI) helps genome editing achieve more precision, efficiency, and affordability in tackling various diseases, like Sickle cell anemia or Thalassemia. AI models have been in use for designing guide RNAs (gRNAs) for CRISPR-Cas systems. Tools like DeepCRISPR, CRISTA, and DeepHF have the capability to predict optimal guide RNAs (gRNAs) for a specified target sequence. These predictions take into account multiple factors, including genomic context, Cas protein type, desired mutation type, on-target/off-target scores, potential off-target sites, and the potential impacts of genome editing on gene function and cell phenotype. These models aid in optimizing different genome editing technologies, such as base, prime, and epigenome editing, which are advanced techniques to introduce precise and programmable changes to DNA sequences without relying on the homology-directed repair pathway or donor DNA templates. Furthermore, AI, in collaboration with genome editing and precision medicine, enables personalized treatments based on genetic profiles. AI analyzes patients' genomic data to identify mutations, variations, and biomarkers associated with different diseases like Cancer, Diabetes, Alzheimer's, etc. However, several challenges persist, including high costs, off-target editing, suitable delivery methods for CRISPR cargoes, improving editing efficiency, and ensuring safety in clinical applications. This review explores AI's contribution to improving CRISPR-based genome editing technologies and addresses existing challenges. It also discusses potential areas for future research in AI-driven CRISPR-based genome editing technologies. The integration of AI and genome editing opens up new possibilities for genetics, biomedicine, and healthcare, with significant implications for human health.
| S-EPMC10800897 | biostudies-literature
Project description:As artificial intelligence (AI) systems begin to make their way into clinical radiology practice, it is crucial to assure that they function correctly and that they gain the trust of experts. Toward this goal, approaches to make AI "interpretable" have gained attention to enhance the understanding of a machine learning algorithm, despite its complexity. This article aims to provide insights into the current state of the art of interpretability methods for radiology AI. This review discusses radiologists' opinions on the topic and suggests trends and challenges that need to be addressed to effectively streamline interpretability methods in clinical practice. Supplemental material is available for this article. © RSNA, 2020 See also the commentary by Gastounioti and Kontos in this issue.
| S-EPMC7259808 | biostudies-literature
Project description:BackgroundThis paper reviews recent literature employing Artificial Intelligence/Machine Learning (AI/ML) methods for diagnostic evaluation of head and neck cancers (HNC) using automated image analysis.MethodsElectronic database searches using MEDLINE via OVID, EMBASE and Google Scholar were conducted to retrieve articles using AI/ML for diagnostic evaluation of HNC (2009-2020). No restrictions were placed on the AI/ML method or imaging modality used.ResultsIn total, 32 articles were identified. HNC sites included oral cavity (n = 16), nasopharynx (n = 3), oropharynx (n = 3), larynx (n = 2), salivary glands (n = 2), sinonasal (n = 1) and in five studies multiple sites were studied. Imaging modalities included histological (n = 9), radiological (n = 8), hyperspectral (n = 6), endoscopic/clinical (n = 5), infrared thermal (n = 1) and optical (n = 1). Clinicopathologic/genomic data were used in two studies. Traditional ML methods were employed in 22 studies (69%), deep learning (DL) in eight studies (25%) and a combination of these methods in two studies (6%).ConclusionsThere is an increasing volume of studies exploring the role of AI/ML to aid HNC detection using a range of imaging modalities. These methods can achieve high degrees of accuracy that can exceed the abilities of human judgement in making data predictions. Large-scale multi-centric prospective studies are required to aid deployment into clinical practice.
| S-EPMC8184820 | biostudies-literature
Project description:Corona Virus Disease-2019 (COVID-19), caused by Severe Acute Respiratory Syndrome-Corona Virus-2 (SARS-CoV-2), is a highly contagious disease that has affected the lives of millions around the world. Chest X-Ray (CXR) and Computed Tomography (CT) imaging modalities are widely used to obtain a fast and accurate diagnosis of COVID-19. However, manual identification of the infection through radio images is extremely challenging because it is time-consuming and highly prone to human errors. Artificial Intelligence (AI)-techniques have shown potential and are being exploited further in the development of automated and accurate solutions for COVID-19 detection. Among AI methodologies, Deep Learning (DL) algorithms, particularly Convolutional Neural Networks (CNN), have gained significant popularity for the classification of COVID-19. This paper summarizes and reviews a number of significant research publications on the DL-based classification of COVID-19 through CXR and CT images. We also present an outline of the current state-of-the-art advances and a critical discussion of open challenges. We conclude our study by enumerating some future directions of research in COVID-19 imaging classification.
| S-EPMC8890789 | biostudies-literature
Project description:BackgroundEarly detection of melanoma can be lifesaving but this remains a challenge. Recent diagnostic studies have revealed the superiority of artificial intelligence (AI) in classifying dermoscopic images of melanoma and nevi, concluding that these algorithms should assist a dermatologist's diagnoses.ObjectiveThe aim of this study was to investigate whether AI support improves the accuracy and overall diagnostic performance of dermatologists in the dichotomous image-based discrimination between melanoma and nevus.MethodsTwelve board-certified dermatologists were presented disjoint sets of 100 unique dermoscopic images of melanomas and nevi (total of 1200 unique images), and they had to classify the images based on personal experience alone (part I) and with the support of a trained convolutional neural network (CNN, part II). Additionally, dermatologists were asked to rate their confidence in their final decision for each image.ResultsWhile the mean specificity of the dermatologists based on personal experience alone remained almost unchanged (70.6% vs 72.4%; P=.54) with AI support, the mean sensitivity and mean accuracy increased significantly (59.4% vs 74.6%; P=.003 and 65.0% vs 73.6%; P=.002, respectively) with AI support. Out of the 10% (10/94; 95% CI 8.4%-11.8%) of cases where dermatologists were correct and AI was incorrect, dermatologists on average changed to the incorrect answer for 39% (4/10; 95% CI 23.2%-55.6%) of cases. When dermatologists were incorrect and AI was correct (25/94, 27%; 95% CI 24.0%-30.1%), dermatologists changed their answers to the correct answer for 46% (11/25; 95% CI 33.1%-58.4%) of cases. Additionally, the dermatologists' average confidence in their decisions increased when the CNN confirmed their decision and decreased when the CNN disagreed, even when the dermatologists were correct. Reported values are based on the mean of all participants. Whenever absolute values are shown, the denominator and numerator are approximations as every dermatologist ended up rating a varying number of images due to a quality control step.ConclusionsThe findings of our study show that AI support can improve the overall accuracy of the dermatologists in the dichotomous image-based discrimination between melanoma and nevus. This supports the argument for AI-based tools to aid clinicians in skin lesion classification and provides a rationale for studies of such classifiers in real-life settings, wherein clinicians can integrate additional information such as patient age and medical history into their decisions.
| S-EPMC7519424 | biostudies-literature
Project description:Background and aimMelasma (ML), naevus fusco-caeruleus zygomaticus (NZ), freckles (FC), cafe-au-lait spots (CS), nevus of ota (NO), and lentigo simplex (LS), are common skin diseases causing hyperpigmentation. Deep learning algorithms learn the inherent laws and representation levels of sample data and can analyze the internal details of the image and classify it objectively to be used for image diagnosis. However, deep learning algorithms that can assist clinicians in diagnosing skin hyperpigmentation conditions are lacking.MethodsThe optimal deep-learning image recognition algorithm was explored for the auxiliary diagnosis of hyperpigmented skin disease. Pretrained models, such as VGG-19, GoogLeNet, InceptionV3, ResNet50V2, ResNet101V2, ResNet152V2, InceptionResNetV2, DesseNet201, MobileNet, and NASNetMobile were used to classify images of six common hyperpigmented skin diseases. The best deep learning algorithm for developing an online clinical diagnosis system was selected by using accuracy and area under curve (AUC) as evaluation indicators.ResultsIn this research, the parameters of the above-mentioned ten deep learning algorithms were 18333510, 5979702, 21815078, 23577094, 42638854, 58343942, 54345958, 18333510, 3235014, and 4276058, respectively, and their training time was 380, 162, 199, 188, 315, 511, 471, 697, 101, and 144 min respectively. The respective accuracies of the training set were 85.94%, 99.72%, 99.61%, 99.52%, 99.52%, 98.84%, 99.61%, 99.13%, 99.52%, and 99.61%. The accuracy rates of the test set data were 73.28%, 57.40%, 70.04%, 71.48%, 68.23%, 71.11%, 71.84%, 73.28%, 70.39%, and 43.68%, respectively. Finally, the areas of AUC curves were 0.93, 0.86, 0.93, 0.91, 0.91, 0.92, 0.93, 0.92, 0.93, and 0.82, respectively.ConclusionsThe experimental parameters, training time, accuracy, and AUC of the above models suggest that MobileNet provides a good clinical application prospect in the auxiliary diagnosis of hyperpigmented skin.
| S-EPMC10559947 | biostudies-literature
Project description:The evidence-based medicine (EBM) movement is stepping up its efforts to assess medical artificial intelligence (AI) and data science studies. Since 2017, there has been a marked increase in the number of published systematic reviews that assess medical AI studies. Increasingly, data from observational studies are used in systematic reviews of medical AI studies. Assessment of risk of bias is especially important in medical AI studies to detect possible "AI bias".
| S-EPMC9238033 | biostudies-literature