Automatic vision-based inspection systems have played a key role in product quality assessment for decades through the segmentation, detection, and classification of defects. Historically, machine learning frameworks, based on hand-crafted feature extraction, selection, and validation, counted on a combined approach of parameterized image processing algorithms and explicated human knowledge. The outstanding performance of deep learning (DL) for vision systems, in automatically discovering a feature representation suitable for the corresponding task, has exponentially increased the number of scientific articles and commercial products aiming at industrial quality assessment. In such a context, this article reviews more than 220 relevant articles from the related literature published until February 2023, covering the recent consolidation and advances in the field of fully-automatic DL-based surface defects inspection systems, deployed in various industrial applications. The analyzed papers have been classified according to a bi-dimensional taxonomy, that considers both the specific defect recognition task and the employed learning paradigm. The dependency on large and high-quality labeled datasets and the different neural architectures employed to achieve an overall perception of both well-visible and subtle defects, through the supervision of fine or/and coarse data annotations have been assessed. The results of our analysis highlight a growing research interest in defect representation power enrichment, especially by transferring pre-trained layers to an optimized network and by explaining the network decisions to suggest trustworthy retention or rejection of the products being evaluated.

The non-destructive testing methods offer great benefit in detecting and classifying the weld defects. Among these, infrared (IR) thermography stands out in the inspection, characterization, and analysis of the defects from the camera image sequences, particularly with the recent advent of deep learning. However, in IR, the defect classification becomes a cumbersome task because of the exposure to the inconsistent and unbalanced heat source, which requires additional supervision. In light of this, authors present a fully automated system capable of detecting defective welds according to the electrical resistance properties in the inline mode. The welding process is captured by an IR camera that generates a video sequence. A set of features extracted by such video feeds supervised machine learning and deep learning algorithms in order to build an industrial diagnostic framework for weld defect detection. The experimental study validates the aptitude of a customized convolutional neural network architecture to classify the malfunctioning weld joints with mean accuracy of 99% and median f1 score of 73% across five-fold cross validation on our locally acquired real world dataset. The outcome encourages the integration of thermographic-based quality control frameworks in all applications where fast and accurate recognition and safety assurance are crucial industrial requirements across the production line.

Combining targeted therapeutics can significantly help address the dynamic changes in cancer biology abnormalities and thus improve the duration of response and outcome. However, the efficacy of such approaches is highly dependent on the combination, interactions, and timing between the administered drugs. Current clinical trials can test only a low number of schedules with fixed designs. Pharmacometric tools can assist in exploring and selecting the most effective drug dosages and schedules by modeling traits of patients with different clinical and biological characteristics. This study proposes a pharmacokinetic-pharmacodynamic model describing the networked system of tumor development and angiogenesis under the control of antiangiogenic and cytotoxic, i.e., Ramucirumab and Paclitaxel second-line combination therapy. A two-step scalable algorithm is proposed to calibrate model parameters and match virtual to real population therapy outcomes, followed by fine-tuning directly on the Progression-free Survival (PFS)-2 Kaplan-Meier curve. Two cohorts of advanced gastric cancer patients were considered: a calibration cohort from South Korea, and an external verification cohort from IRCCS "S. De Bellis", an Italian research hospital. These real-world patients had heterogeneous clinical starting conditions. We perform prospective evaluations of new combination regimens that adhere to pharmacological constraints that are paramount for clinical translation, in which the administration time of the cytotoxic agent is triggered by the normalization window opening, monitored by a tumor microenvironment digital biomarker. The calibration procedure led to the discovery of a new mathematical biomarker describing the influence of intrinsic tumor growth and angiogenesis on treatment outcomes. The predictive value was assessed through the log-rank test between two PFS-2 groups, which exhibited different (p-value <0.0001) therapy response trends. Our results showcase a new regimen that, by using 33% less cytotoxic drug, achieves indistinguishable PFS-2. Additionally, we present another regimen that extends PFS-2 from 49.2% to 60.9% after 121 days of therapy (p-value <0.0001), by using the same dosing as the standard protocol. This study proposes an in-silico quantitative platform for virtual expansion of real-world patient cohorts. Furthermore, the estimation of the efficacy of adaptive dose schedules of a combined therapy can complement and inform clinical trial design.

Computational pathology enables the automatic tissue analysis of Whole Slide Images (WSIs), offering unmatched possibilities to capture quantitative tumor microenvironment (TME) characteristics that are essential for patients' prognosis and therapy response. The existing clinical and digital biomarkers do not encompass the morphometric features and spatial interactions between vascular networks and immunological compartment in the TME. To address this challenge, this work presents a high- throughput quantitative framework for automatic segmentation and assessment of aberrant phenotypes of blood vessels and immune cell clusters in hematoxylin & eosin-stained WSIs, to construct the Vascular-Immune Pathomic (VIPath) biomarker. For our study, we utilized three public datasets of Colon Adenocarcinoma (COAD) and Stomach Adenocarcinoma (STAD) from The Cancer Genome Atlas (TCGA) and Clinical Proteomic Tumor Analysis Consortium (CPTAC) projects: TCGA-COAD, TCGA-STAD, and CPTAC-COAD. Additionally, we collected two in-house gastric cancer cohorts of 80 and 51 patients : DBGC-M0 and DBGC-M1. The VIPath biomarker was incorporated in a Cox proportional hazards model trained on the TCGA-COAD. Then, it was validated for predicting Overall Survival (OS) in TCGA-STAD, DBGC-M0, and DBGC-M1, Disease Free Survival in CPTAC-COAD and second-line therapy Progression-free Survival (PFS-2) in DBGC-M1. VIPath encompasses features from both vascular and immunological compartments interacting in the TME. Results proved that VIPath was capable to significantly stratify risk groups for OS TCGA-STAD (p=0.018), OS DBGC-M0 (p=0.029), OS DBGC-M1 (p=0.014), and PFS-2 DBGC-M1 (p$< $0.005). Furthermore, when inserted in a Cox model, it led to an improvement of C-index and R² over all other considered prognostic factors, i.e., p-TNM, ECOG, MSI, HER2.