Early and accurate cancer diagnosis through medical imaging is crucial for guiding treatment and enhancing patient survival.However,many state-of-the-art deep learning(DL)methods remain opaque and lack clinical interp...Early and accurate cancer diagnosis through medical imaging is crucial for guiding treatment and enhancing patient survival.However,many state-of-the-art deep learning(DL)methods remain opaque and lack clinical interpretability.This paper presents an explainable artificial intelligence(XAI)framework that combines a fine-tuned Visual Geometry Group 16-layer network(VGG16)convolutional neural network with layer-wise relevance propagation(LRP)to deliver high-performance classification and transparent decision support.This approach is evaluated on the publicly available Kaggle kidney cancer imaging dataset,which comprises labeled cancerous and noncancerous kidney scans.The proposed model achieved 98.75%overall accuracy,with precision,recall,and F1-score each exceeding 98%on an independent test set.Crucially,LRP-derived heatmaps consistently localize anatomically and pathologically significant regions such as tumor margins in agreement with established clinical criteria.The proposed framework enhances clinician trust by delivering pixel-level justifications alongside state-of-the-art predictive performance.It facilitates informed decision-making,thereby addressing a key barrier to the clinical adoption of DL in oncology.展开更多
The rising concentrations of xenobiotic aromatic compounds in the environment pose significant risks to human and ecosystem health.Developing a universal,environmentally benign,and scalable platform for mineralizing o...The rising concentrations of xenobiotic aromatic compounds in the environment pose significant risks to human and ecosystem health.Developing a universal,environmentally benign,and scalable platform for mineralizing organic pollutants before their release into the environment is therefore crucial.Electrocatalysis can be highly advantageous for wastewater treatment because it is immediately responsive upon applying potential,requires no additional chemicals,and typically uses heterogeneous catalysts.However,achieving efficient electrochemical mineralization of wastewater pollutants at parts-permillion(ppm)levels remains a challenge.Here,we report the use of manganese dioxide(MnO_(2)),an Earth-abundant,chemically benign,and cost-effective electrocatalyst,to achieve over 99%mineralization of triclosan(TCS)and other halogenated phenols at ppm levels.Two highly active MnO_(2) phasesdaMnO_(2)-CC and d-MnO_(2)-CCdwere fabricated on inexpensive carbon cloth(CC)support and evaluated for their ability to oxidatively degrade TCS in pH-neutral conditions,including simulated chlorinated wastewater,real wastewater,and both synthetic and real landfill leachates.Total organic carbon analysis confirmed the effective degradation of TCS.Electron paramagnetic resonance and ultravioletevisible spectroscopy identified reactive oxygen species,enabling the construction of a detailed TCS degradation pathway.Upon optimization,the TCS removal rate reached 38.38 nmol min^(-1),surpassing previously reported rates achieved with precious and toxic metal co-catalysts.These findings highlight MnO_(2)-CC as a promising,eco-friendly electrocatalyst with strong potential for upscaled remediation of organic pollutants in wastewater treatment.展开更多
基金supported through the Ongoing Research Funding Program(ORF-2025-498),King Saud University,Riyadh,Saudi Arabia.
文摘Early and accurate cancer diagnosis through medical imaging is crucial for guiding treatment and enhancing patient survival.However,many state-of-the-art deep learning(DL)methods remain opaque and lack clinical interpretability.This paper presents an explainable artificial intelligence(XAI)framework that combines a fine-tuned Visual Geometry Group 16-layer network(VGG16)convolutional neural network with layer-wise relevance propagation(LRP)to deliver high-performance classification and transparent decision support.This approach is evaluated on the publicly available Kaggle kidney cancer imaging dataset,which comprises labeled cancerous and noncancerous kidney scans.The proposed model achieved 98.75%overall accuracy,with precision,recall,and F1-score each exceeding 98%on an independent test set.Crucially,LRP-derived heatmaps consistently localize anatomically and pathologically significant regions such as tumor margins in agreement with established clinical criteria.The proposed framework enhances clinician trust by delivering pixel-level justifications alongside state-of-the-art predictive performance.It facilitates informed decision-making,thereby addressing a key barrier to the clinical adoption of DL in oncology.
基金supported by the Innovation and Technology Commission(ITC)of the government of Hong Kong SAR,which provides regular research funding to the State Key Laboratory of Marine Pollution(SKLMP)supported by the Environment and Conservation Fund(ECF)of the government of Hong Kong SAR(16/2020).
文摘The rising concentrations of xenobiotic aromatic compounds in the environment pose significant risks to human and ecosystem health.Developing a universal,environmentally benign,and scalable platform for mineralizing organic pollutants before their release into the environment is therefore crucial.Electrocatalysis can be highly advantageous for wastewater treatment because it is immediately responsive upon applying potential,requires no additional chemicals,and typically uses heterogeneous catalysts.However,achieving efficient electrochemical mineralization of wastewater pollutants at parts-permillion(ppm)levels remains a challenge.Here,we report the use of manganese dioxide(MnO_(2)),an Earth-abundant,chemically benign,and cost-effective electrocatalyst,to achieve over 99%mineralization of triclosan(TCS)and other halogenated phenols at ppm levels.Two highly active MnO_(2) phasesdaMnO_(2)-CC and d-MnO_(2)-CCdwere fabricated on inexpensive carbon cloth(CC)support and evaluated for their ability to oxidatively degrade TCS in pH-neutral conditions,including simulated chlorinated wastewater,real wastewater,and both synthetic and real landfill leachates.Total organic carbon analysis confirmed the effective degradation of TCS.Electron paramagnetic resonance and ultravioletevisible spectroscopy identified reactive oxygen species,enabling the construction of a detailed TCS degradation pathway.Upon optimization,the TCS removal rate reached 38.38 nmol min^(-1),surpassing previously reported rates achieved with precious and toxic metal co-catalysts.These findings highlight MnO_(2)-CC as a promising,eco-friendly electrocatalyst with strong potential for upscaled remediation of organic pollutants in wastewater treatment.
