Training immunophenotyping deep learning models with the same-section ground truth cell label derivation method improves virtual staining accuracy.

Introduction: Deep learning (DL) models predicting biomarker expression in images of hematoxylin and eosin (H&E)-stained tissues can improve access to multi-marker immunophenotyping, crucial for therapeutic monitoring, biomarker discovery, and personalized treatment development. Conventionally, these models are trained on ground truth cell labels derived from IHC-stained tissue sections adjacent to H&E-stained ones, which might be less accurate than labels from the same section. Although many such DL models have been developed, the impact of ground truth cell label derivation methods on their performance has not been studied. Methodology: In this study, we assess the impact of cell label derivation on H&E model performance, with CD3+ T-cells in lung cancer tissues as a proof-of-concept. We compare two Pix2Pix generative adversarial network (P2P-GAN)-based virtual staining models: one trained with cell labels obtained from the same tissue section as the H&E-stained section (the 'same-section' model) and one trained on cell labels from an adjacent tissue section (the 'serial-section' model). Results: We show that the same-section model exhibited significantly improved prediction performance compared to the 'serial-section' model. Furthermore, the same-section model outperformed the serial-section model in stratifying lung cancer patients within a public lung cancer cohort based on survival outcomes, demonstrating its potential clinical utility. Discussion: Collectively, our findings suggest that employing ground truth cell labels obtained through the same-section approach boosts immunophenotyping DL solutions.

Multi-center evaluation of artificial intelligent imaging and clinical models for predicting neoadjuvant chemotherapy response in breast cancer.

BACKGROUND: Neoadjuvant chemotherapy (NAC) plays an important role in the management of locally advanced breast cancer. It allows for downstaging of tumors, potentially allowing for breast conservation. NAC also allows for in-vivo testing of the tumors' response to chemotherapy and provides important prognostic information. There are currently no clearly defined clinical models that incorporate imaging with clinical data to predict response to NAC. Thus, the aim of this work is to develop a predictive AI model based on routine CT imaging and clinical parameters to predict response to NAC. METHODS: The CT scans of 324 patients with NAC from multiple centers in Singapore were used in this study. Four different radiomics models were built for predicting pathological complete response (pCR): first two were based on textural features extracted from peri-tumoral and tumoral regions, the third model based on novel space-resolved radiomics which extract feature maps using voxel-based radiomics and the fourth model based on deep learning (DL). Clinical parameters were included to build a final prognostic model. RESULTS: The best performing models were based on space-resolved and DL approaches. Space-resolved radiomics improves the clinical AUCs of pCR prediction from 0.743 (0.650 to 0.831) to 0.775 (0.685 to 0.860) and our DL model improved it from 0.743 (0.650 to 0.831) to 0.772 (0.685 to 0.853). The tumoral radiomics model performs the worst with no improvement of the AUC from the clinical model. The peri-tumoral combined model gives moderate performance with an AUC of 0.765 (0.671 to 0.855). CONCLUSIONS: Radiomics features extracted from diagnostic CT augment the predictive ability of pCR when combined with clinical features. The novel space-resolved radiomics and DL radiomics approaches outperformed conventional radiomics techniques.

Anthocyanin ameliorates hypoxia and ischemia induced inflammation and apoptosis by increasing autophagic flux in SH-SY5Y cells.

Inhibition of the oxidative stress induced by hypoxia and ischemia would be beneficial for reducing neuroinflammation and promoting nerve cell survival. We had previously reported a kind of anthocyanin (pentunidin-3-O-rutinoside (p-coumaroyl)-5-O-glucoside) to reduce the damage to neurovascular unit in middle cerebral artery occlusion (MCAO) rats. However, the neuroprotective mechanism of anthocyanin remains to be elucidated. Neuronal autophagy, after ischemic hypoxia, seems to be part of the pro-survival signal. In the current study, we used oxygen and glucose deprivation (OGD) to stimulate SH-SY5Y cells, and observed whether anthocyanin could reduce the inflammatory response and apoptosis, and explored the role of autophagy in this process. Anthocyanin significantly increased the autophagic flux, inhibited oxidative stress, and reduced inflammatory response and neuronal apoptosis in OGD exposed SH-SY5Y cells. The autophagy agonist rapamycin enhanced the anti-inflammatory effect of anthocyanin, while the autophagy inhibitor 3-methyladenine (3-MA) forbade its protective effect. Our finding, therefore, suggested the reduction of hypoxia and ischemia induced oxidative stress, along with inflammation and apoptosis, by anthocyanin, to occur via increase of autophagic flux in SH-SY5Y cells.

Flow visualization for interactive simulation of drugs injection during chemoembolization.

Chemoembolization is an important therapeutic procedure. A catheter was navigated to the artery that feeds the tumor, and chemotherapy drugs and embolus are injected directly into the tumor. There is a risk that embolus may lodge incorrectly and deprive normal tissue of its blood supply. This paper focuses on visualization of the flow particles in simulation of chemotherapy drugs injection for training of hand-eye coordination skills. We assume that the flow follows a defined path in the hepatic vascular system from the catheter tip. The vascular model is constructed using sweeping and blending operations. Quadrilaterals which are aligned to face the viewer are drawn for the trail of each particle. The quadrilateral in the trail is determined using bilinear interpolation. On simulated fluoroscopic image, the flow is rendered as overlaying and semitransparent quadrilaterals representing the particles' trails. This visualization model achieves a good visual approximation of the flow of particles inside the vessels under fluoroscopic imaging.