Deep learning has demonstrated remarkable accuracy analyzing images for cancer detection tasks in recent years. The accuracy that has been achieved rivals radiologists and is suitable for implementation as a clinical tool. However, a significant problem is that these models are black-box algorithms therefore they are intrinsically unexplainable. This creates a barrier for clinical implementation due to lack of trust and transparency that is a characteristic of black box algorithms. Additionally, recent regulations prevent the implementation of unexplainable models in clinical settings which further demonstrates a need for explainability. To mitigate these concerns, there have been recent studies that attempt to overcome these issues by modifying deep learning architectures or providing after-the-fact explanations. A review of the deep learning explanation literature focused on cancer detection using MR images is presented here. The gap between what clinicians deem explainable and what current methods provide is discussed and future suggestions to close this gap are provided.

Deep learning offers significant advancements in the accuracy of prostate identification and classification, underscoring its potential for clinical integration. However, the opacity of deep learning models presents interpretability challenges, critical for their acceptance and utility in medical diagnosis and detection. While explanation methods have been proposed to demystify these models, enhancing their clinical viability, the efficacy and acceptance of these methods in medical tasks are not well documented. This pilot study investigates the effectiveness of deep learning explanation methods in clinical settings and identifies the attributes that radiologists consider crucial for explainability, aiming to direct future enhancements. This study reveals that while explanation methods can improve clinical task performance by up to 20%, their perceived usefulness varies, with some methods being rated poorly. Radiologists prefer explanation methods that are robust against noise, precise, and consistent. These preferences underscore the need for refining explanation methods to align with clinical expectations, emphasizing clarity, accuracy, and reliability. The findings highlight the importance of developing explanation methods that not only improve performance but also are tailored to meet the stringent requirements of clinical practice, thereby facilitating deeper trust and a broader acceptance of deep learning in medical diagnostics.

Explainability techniques have been recently postulated as being effective for localizing medical regions of interest. However, there has been recent criticisms regarding the validity of these approaches in terms of robustness and accuracy. This study explores if combining two saliency methods, namely Saliency Maps and Grad-CAM, improves the robustness and accuracy of localization. The experiments are three-part. First, the accuracy of localization is measured and repeatability experiments are performed to determine if the results are repeatable across model architectures. Second, cascading randomization experiments are conducted to determine the robustness to changes in model parameters. Third, we measure the overlap between Saliency Maps and Grad-CAM and show there is a relationship between the overlap and accuracy of prediction.

Global supply chains face increasing disruptions from cyber threats, geopolitical instability, extreme weather events, and a range of economic, social, and environmental sustainability challenges. As these disruptions intensify, enhancing Supply Chain Resilience (SCR) has become a strategic priority. This study investigates how Distributed Ledger Technology (DLT) can contribute to SCR by mitigating vulnerabilities and strengthening key capabilities within global supply chains. A qualitative research approach is employed, utilizing expert evaluations to examine DLT’s impact on supply chain vulnerabilities and capabilities. Five workshops were conducted with 25 industry professionals from logistics, IT, procurement, and risk management. Experts examined how DLT could address disruptions stemming from supplier instability, poor traceability, and regulatory and environmental pressures, while highlighting its potential to drive ethical sourcing and environmentally responsible practices. The structured discussions were guided by theoretical frameworks and expert evaluations were synthesized into two analytical matrices illustrating DLT’s influence on SCR. The findings reveal that the contribution of DLT to SCR and sustainability is highly context-dependent, with its effectiveness hinging on how it is embedded within governance structures and aligned with the interplay of complementary technologies. Building on these insights, the study presents the DLT-LFL (Distributed Ledger Technology–Learning Feedback Loop) framework, which integrates sensing, decision-making, adaptation, and predictive learning from distributed operational data, allowing supply chains to better anticipate disruptions, adjust processes dynamically, and continuously strengthen resilience and sustainable practices. The study also develops a practical checklist to assess how effective DLT applications and their integration with predictive and AI-driven analytics reduce vulnerabilities, strengthen capabilities, mitigate risks, and support adaptive decision-making.