The deep classifiers used for chest X-ray diagnosis can be sensitive to the visual frame around the evidence, producing correct labels for the wrong reasons by relying on the background, borders, text marks, or acquisition artifacts. This framing sensitivity reduces their trustworthiness, and they can fail under a distribution shift. Inspired by biological vision, especially figure–ground segregation and selective attention, we propose a bio-inspired adversarial attention alignment training process that encourages evidence-centered decisions without changing the classifier structure. A classifier is first trained with image-level labels. Class activation mapping (CAM) is then used to produce a differentiable heatmap that indicates where the model attends. We treat this heatmap as a generated localization map and train a discriminator to distinguish the generated heatmaps from ground truth masks. The classifier is updated using a joint objective that preserves the classification performance while pushing its CAM heatmap toward a mask-like structure, reducing the reliance on background cues. We also introduce evaluation measures for the test phase, including augmentation inconsistency (prediction flip rate under angle-based augmentations) and framing sensitivity (CAM energy outside the mask). The experiments show improved lung-focused attention and robustness, while requiring masks only during training and no additional inputs at inference.

Background/Objectives: Colorectal cancer (CRC) is one of the leading causes of cancer-related mortality worldwide, and accurate histopathological tissue segmentation is critical for timely and reliable diagnosis. Healthcare systems represent complex adaptive environments where diagnostic tools must function reliably across heterogeneous clinical settings, varying staining protocols, and resource-constrained infrastructures. However, existing deep learning segmentation models often require substantial computational resources, limiting their deployment in such settings. This study proposes a novel, resource-efficient colorectal histopathology segmentation network (RCHS-Net) designed for robust clinical deployment across diverse and resource-constrained healthcare environments. Methods: RCHS-Net employs a compact multi-scale encoder with channel recalibration blocks, a gland context module (GCM) with three parallel atrous convolutions and lightweight self-attention for multi-scale contextual feature extraction, and a feature pyramid decoder (FPD) for fine-grained spatial reconstruction. To address the demands of real-world healthcare systems, feature-wise linear modulation (FiLM) conditioning enables class-aware segmentation across multiple tissue categories, while MixStyle augmentation improves stain domain generalization across heterogeneous laboratory and scanner conditions. Results: The model was evaluated on two publicly available benchmark datasets: the EBHI-Seg dataset and the GlaS dataset. On EBHI-Seg, RCHS-Net achieved a mean Dice coefficient of 95.20% and a mean IoU of 91.10% across six colorectal tissue classes, with only 243,226 trainable parameters. On the GlaS benchmark, RCHS-Net attained a Dice score of 93.39% and an IoU of 88.32%, outperforming state-of-the-art methods. Conclusions: RCHS-Net demonstrates that high-accuracy histopathology segmentation can be achieved with a compact architecture, offering a scalable and practical solution for AI-assisted cancer diagnosis across the complex, heterogeneous conditions of real-world healthcare systems, supporting scalable and equitable cancer diagnostics globally.

The accuracy of camera-based plant disease classification is crucial for smart farming applications, particularly in automated management systems using agricultural robots. To address the performance degradation caused by motion blur, we propose a knowledge distillation (KD)-based image deblurring network (KDID-Net). Our framework targets classification performance by integrating generative adversarial network (GAN)-based deblurring with fast Fourier transform (FFT)-based complex-domain KD. Specifically, the teacher model in KDID-Net employs a classification-guided (CG) block that generates logits analogous to those produced by a classifier, which are then used to compute a classification-guided enhancement loss (CGEL), thereby reinforcing features relevant to disease classification. Furthermore, the teacher network’s feature maps are subjected to FFT, and frequency-domain knowledge is distilled into a lightweight student network, enabling the recovery of fine lesion details. Consequently, the lightweight network achieves high classification accuracy while remaining suitable for agricultural robots with limited computational resources. Moreover, the disease classification results produced by the proposed method are automatically linked to the input of the open-source large language model Meta artificial intelligence (LLaMA), enabling a system that recommends optimal pesticide information for each disease class. We conducted experiments with two public datasets: the PlantVillage and FieldPlant datasets. Under the same blur conditions, KDID-Net achieved classification accuracies of 0.9432 and 0.7571, respectively, outperforming state-of-the-art (SOTA) image restoration methods and KD methods in terms of classification accuracy. These results demonstrate the effectiveness of the proposed method for plant disease classification under both simple and complex background conditions. Furthermore, the proposed model achieved superior performance compared with SOTA methods in terms of graphic processing unit (GPU) memory requirements, floating point operations (FLOPs), and inference times on computationally constrained embedded systems, demonstrating its suitability for agricultural robot applications.

Although deep learning methods have shown high performance in chest X-ray classification, high accuracy alone does not guarantee reliable reasoning. A model may still exhibit pathological behavior, such as unstable evidence usage under harmless input changes, inconsistent reasoning across augmented views, excessive dependence on surrounding frame information, and appearance bias dominance, where prediction relies too heavily on intensity while neglecting texture and shape. In this paper, we propose a bio-inspired pathology-aware, factor-aware framework for explainable and reliable chest X-ray classification, inspired by biological vision principles such as figure–ground separation, selective attention, and balanced use of complementary visual cues. During training, the method regularizes appearance bias dominance through evidence-guided counterfactual perturbations that mimic cue-suppression analysis in biological perception, thereby revealing and penalizing excessive factor dependence. During testing, it evaluates model behavior using four criteria: reasoning stability, augmentation inconsistency, appearance bias dominance, and framing sensitivity. This combination enables the framework to go beyond conventional inference-time explanation by both correcting pathological behavior during training and exposing it during evaluation. From a biomimetic perspective, the framework encourages the model to separate relevant foreground anatomy from surrounding background and to avoid over-reliance on a single dominant cue. The proposed approach improves interpretability and reliability without modifying the backbone architecture or increasing model size or inference-time cost. The proposed training process improved the F1-score of DenseNet-121 from 0.899 to 0.931, while also producing more stable and balanced reasoning.

Computational cost during model deployment can be reduced through knowledge distillation (KD) which transfers knowledge from a teacher model to a lightweight student model while maintaining performance. However, KD methods based on a single teacher often provide limited knowledge diversity and may transfer less informative features. Furthermore, the application of KD for plant disease classification in low-light noisy environments has received little attention. To address these limitations, we propose a KD framework using heterogeneous teachers with adaptive feature alignment (KDHT-AFA) that integrates an adaptive feature distillation switch (AFDS) to selectively align intermediate representations. For effective knowledge transfer, we propose a lightweight custom student model with 5.16 million parameters. The model incorporates a regional statistical hybrid attention (RSHA) to enhance important features semantically while increasing sensitivity to local structure and contrast. Additionally, we introduce a new self-collected real low-light plant disease dataset (ReLL-PDD v1) acquired under realistic agricultural conditions. For performance evaluation, we considered two open-source datasets, PlantVillage and the Potato Leaf Disease dataset, along with the ReLL-PDD v1 dataset. Our model achieved a mean accuracy of 86.88% with a harmonic mean of precision and recall (F1-score) of 86.25% on ReLL-PDD v1 dataset. On the PlantVillage and Potato Leaf Disease datasets, it obtained mean accuracies of 92.64% and 88.97% with F1-scores of 91.48% and 88.92%, respectively. Furthermore, the smart pesticide prescription module (SPPM) uses a large language model Meta artificial intelligence (LLaMA) to recommend pesticides for diseases detected by KDHT-AFA. Hence, the proposed KDHT-AFA supports real-time deployment and plant disease monitoring in low-light noisy environments.