Journal Articles
Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915
Browse
3 results
Search Results
Item Transformer-based multiple instance learning network with 2D positional encoding for histopathology image classification(Springer Nature Switzerland AG, 2025-05) Yang B; Ding L; Li J; Li Y; Qu G; Wang J; Wang Q; Liu BDigital medical imaging, particularly pathology images, is essential for cancer diagnosis but faces challenges in direct model training due to its super-resolution nature. Although weakly supervised learning has reduced the need for manual annotations, many multiple instance learning (MIL) methods struggle to effectively capture crucial spatial relationships in histopathological images. Existing methods incorporating positional information often overlook nuanced spatial correlations or use positional encoding strategies that do not fully capture the unique spatial dynamics of pathology images. To address this issue, we propose a new framework named TMIL (Transformer-based Multiple Instance Learning Network with 2D positional encoding), which leverages multiple instance learning for weakly supervised classification of histopathological images. TMIL incorporates a 2D positional encoding module, based on the Transformer, to model positional information and explore correlations between instances. Furthermore, TMIL divides histopathological images into pseudo-bags and trains patch-level feature vectors with deep metric learning to enhance classification performance. Finally, the proposed approach is evaluated on a public colorectal adenoma dataset. The experimental results show that TMIL outperforms existing MIL methods, achieving an AUC of 97.28% and an ACC of 95.19%. These findings suggest that TMIL’s integration of deep metric learning and positional encoding offers a promising approach for improving the efficiency and accuracy of pathology image analysis in cancer diagnosis.Item Potential rapid intraoperative cancer diagnosis using dynamic full-field optical coherence tomography and deep learning: A prospective cohort study in breast cancer patients(Elsevier B V on behalf of the Science China Press, 2024-06-15) Zhang S; Yang B; Yang H; Zhao J; Zhang Y; Gao Y; Monteiro O; Zhang K; Liu B; Wang SAn intraoperative diagnosis is critical for precise cancer surgery. However, traditional intraoperative assessments based on hematoxylin and eosin (H&E) histology, such as frozen section, are time-, resource-, and labor-intensive, and involve specimen-consuming concerns. Here, we report a near-real-time automated cancer diagnosis workflow for breast cancer that combines dynamic full-field optical coherence tomography (D-FFOCT), a label-free optical imaging method, and deep learning for bedside tumor diagnosis during surgery. To classify the benign and malignant breast tissues, we conducted a prospective cohort trial. In the modeling group (n = 182), D-FFOCT images were captured from April 26 to June 20, 2018, encompassing 48 benign lesions, 114 invasive ductal carcinoma (IDC), 10 invasive lobular carcinoma, 4 ductal carcinoma in situ (DCIS), and 6 rare tumors. Deep learning model was built up and fine-tuned in 10,357 D-FFOCT patches. Subsequently, from June 22 to August 17, 2018, independent tests (n = 42) were conducted on 10 benign lesions, 29 IDC, 1 DCIS, and 2 rare tumors. The model yielded excellent performance, with an accuracy of 97.62%, sensitivity of 96.88% and specificity of 100%; only one IDC was misclassified. Meanwhile, the acquisition of the D-FFOCT images was non-destructive and did not require any tissue preparation or staining procedures. In the simulated intraoperative margin evaluation procedure, the time required for our novel workflow (approximately 3 min) was significantly shorter than that required for traditional procedures (approximately 30 min). These findings indicate that the combination of D-FFOCT and deep learning algorithms can streamline intraoperative cancer diagnosis independently of traditional pathology laboratory procedures.Item Remote exploration and monitoring of geothermal sources: A novel method for foliar element mapping using hyperspectral (VNIR-SWIR) remote sensing(Elsevier Ltd, 2023-06) Rodriguez-Gomez C; Kereszturi G; Jeyakumar P; Pullanagari R; Reeves R; Rae A; Procter JNHyperspectral remote sensing is an emerging technique to develop new cost- and time-effective geophysical mapping methods. To overcome challenges introduced by plant cover in geothermal systems globally, we hypothesise that foliage can be used as a proxy to map underlying surface geothermal activity and heat-flux due to their capability on elemental uptake from geothermal fluids and host rock/soil. This study shows for the first time that foliar elemental mapping can be used to image geothermal systems using both high-resolution airborne and satellite hyperspectral images. This study has specifically targeted kanuka shrub (kunzea ericoides var. microflora) as a proxy media to develop air- and spaceborne hyperspectral solutions to monitor inaccessible, biologically and culturally sensitive geothermal areas. Using high resolution airborne AisaFENIX and PRISMA hyperspectral data, foliar element maps for Ag, As, Ba and Sb have been developed using Kernel Partial Least Squares Regression and Random Forest classification models to track their foliar distribution and develop a conceptual model for metal and thermal induced changes in plants. Our study shows evidence that the created foliar element maps are in concordance with independent LiDAR-retrieved canopy structure and height as well as temperature effects of the underlying geothermal field. This study has proven air- and spaceborne hyperspectral sensors can indeed capture critical information within the VNIR and SWIR regions (e.g. ∼452, ∼500, ∼670, ∼820, ∼970, ∼1180, ∼1400 and ∼2000 nm) that can be used to identify metal and thermal-induced spectral changes in plants reliably (overall accuracy of 0.41–0.66) with remotely sensed imagery. Our non-invasive method using hyperspectral remote sensing can complement existing practices for exploration and management of renewable geothermal resources through timely monitoring from air- and spaceborne platforms.