Skin cancer is one of the most common forms of cancer globally, with melanoma being the most fatal form. Early and precise detection is crucial for improving treatment outcomes, as timely disease management dramatically increases survival rates. This study presents a reliable multimodal deep learning framework that integrates dermoscopic images, 3D Total Body Photography scans, and patient clinical data to enhance diagnostic accuracy in skin cancer classification. The dataset comprised a combination of publicly available sources, including the recently released ISIC 2024 dataset. An XGBoost algorithm is utilized to get the predictions from the clinical data. For image-based analysis, this study proposes a Modality-Specific Patch Embedding Data efficient image Transformer (MSPE-DeiT) that uses a modality-specific patch embedding layer to train on the dermoscopic and 3D-TBP images. MSPE-DeiT is capable of capturing both local and global contextual information from high-resolution lesion images. Furthermore, this work uses an Artificial Neural Network (ANN) architecture for clinical data classification. Bayesian optimization is applied to fine-tune the ANN’s hyperparameters, effectively mitigating vanishing gradient issues and improving model convergence. A Soft-Voting Ensemble classifier is used to integrate the results of all three models for better generalization on the unseen data. Experimental results demonstrate improvements in diagnostic accuracy on a multimodal held-out test set of around 80k images from the ISIC 2024 dataset, achieving an accuracy of 91.76%, an Area Under the Receiver Operating Characteristic Curve of 0.953, a specificity of 91.77%, and a sensitivity of 84.81%. The proposed approach is computationally inexpensive with an inference latency of 6.2 ms and a memory footprint of 83.59 MB, making it fit for deployment in clinical scenarios.
Uttam Mittal, S. Varpe, A. Sharma et al.· IEEE Access· 0 citations
PURPOSE
Bacterial wilt caused by Ralstonia solanacearum is a major constraint to bell pepper (Capsicum annuum L. var. grossum Sendt.) production worldwide, with no stable resistance available in commercially cultivated varieties. This study explored induced mutagenesis as a strategy to develop durable bacterial wilt resistance in the widely grown but highly susceptible cultivar 'California Wonder.'
MATERIALS AND METHODS
Genetic variability was induced using gamma irradiation and ethyl methane sulfonate (EMS). Mutant populations were advanced from M1 to M8 generations over 12 years (2012-2023). A total of 1,804 M2 progenies were screened under wilt-sick field conditions to identify putative resistant lines. Resistance was validated through an integrated approach including in vivo field screening, ex vivo seedling assays in Hoagland's nutrient solution, and serological confirmation using DAS-ELISA. Stable mutants were further evaluated across multiple generations and five cropping years for resistance stability, horticultural performance, and fruit quality traits. Molecular validation was performed using the SSR marker CAMS451 to confirm the association between resistance-linked alleles and phenotypic expression.
RESULTS
Screening of M2 progenies identified 22 putative resistant lines, of which 16 consistently expressed stable resistance across generations and environments. Six mutants DPCBWR-12 (1.5% EMS), DPCBWR-4 (1.75% EMS), DPCBWR-15 (1.75% EMS), DPCBWR-5 (1.75% EMS), DPCBWR-8 (16.0 kR gamma rays), and DPCBWR-3 (2.0% EMS) significantly outperformed the parent cultivar for yield-related traits and nutritional quality parameters. SSR marker analysis using CAMS451 confirmed the genetic association of resistance-linked alleles with observed phenotypic resistance.
CONCLUSIONS
This study provides the first evidence of successful induction of bacterial wilt resistance in bell pepper through gamma irradiation and EMS mutagenesis. The identified elite mutant lines possess durable resistance, improved yield, and enhanced fruit quality, making them promising candidates for multi-location testing, varietal release, and use as valuable genetic resources in sustainable bell pepper breeding programs.
Sonia Sood, T. Sood, Ruchi Sood et al.· International Journal of Rad...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
