Dataset Information

An end-to-end convolutional neural network for automated failure localisation and characterisation of 3D interconnects.

ABSTRACT: The advancement in the field of 3D integration circuit technology leads to new challenges for quality assessment of interconnects such as through silicon vias (TSVs) in terms of automated and time-efficient analysis. In this paper, we develop a fully automated high-efficient End-to-End Convolutional Neural Network (CNN) model, utilizing two sequentially linked CNN architectures, suitable to classify and locate thousands of TSVs as well as provide statistical information. In particular, we generate interference patterns of the TSVs by conducting a unique concept of Scanning Acoustic Microscopy (SAM) imaging. Scanning Electron Microscopy (SEM) is used to validate and also disclose the characteristic pattern in the SAM C-scan images. By comparing the model with semi-automated machine learning approaches its outstanding performance is illustrated, indicating a localisation and classification accuracy of 100% and greater than 96%, respectively. The approach is not limited to SAM-image data and presents an important step towards zero defect strategies.

SUBMITTER: Paulachan P

PROVIDER: S-EPMC10256798 | biostudies-literature | 2023 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An end-to-end convolutional neural network for automated failure localisation and characterisation of 3D interconnects.

Paulachan Priya P Siegert Jörg J Wiesler Ingo I Brunner Roland R

Scientific reports 20230609 1

The advancement in the field of 3D integration circuit technology leads to new challenges for quality assessment of interconnects such as through silicon vias (TSVs) in terms of automated and time-efficient analysis. In this paper, we develop a fully automated high-efficient End-to-End Convolutional Neural Network (CNN) model, utilizing two sequentially linked CNN architectures, suitable to classify and locate thousands of TSVs as well as provide statistical information. In particular, we genera ...[more]

PMID: 37296180

Similar Datasets

Project description:BackgroundAutomatic segmentation and localization of lesions in mammogram (MG) images are challenging even with employing advanced methods such as deep learning (DL) methods. We developed a new model based on the architecture of the semantic segmentation U-Net model to precisely segment mass lesions in MG images. The proposed end-to-end convolutional neural network (CNN) based model extracts contextual information by combining low-level and high-level features. We trained the proposed model using huge publicly available databases, (CBIS-DDSM, BCDR-01, and INbreast), and a private database from the University of Connecticut Health Center (UCHC).ResultsWe compared the performance of the proposed model with those of the state-of-the-art DL models including the fully convolutional network (FCN), SegNet, Dilated-Net, original U-Net, and Faster R-CNN models and the conventional region growing (RG) method. The proposed Vanilla U-Net model outperforms the Faster R-CNN model significantly in terms of the runtime and the Intersection over Union metric (IOU). Training with digitized film-based and fully digitized MG images, the proposed Vanilla U-Net model achieves a mean test accuracy of 92.6%. The proposed model achieves a mean Dice coefficient index (DI) of 0.951 and a mean IOU of 0.909 that show how close the output segments are to the corresponding lesions in the ground truth maps. Data augmentation has been very effective in our experiments resulting in an increase in the mean DI and the mean IOU from 0.922 to 0.951 and 0.856 to 0.909, respectively.ConclusionsThe proposed Vanilla U-Net based model can be used for precise segmentation of masses in MG images. This is because the segmentation process incorporates more multi-scale spatial context, and captures more local and global context to predict a precise pixel-wise segmentation map of an input full MG image. These detected maps can help radiologists in differentiating benign and malignant lesions depend on the lesion shapes. We show that using transfer learning, introducing augmentation, and modifying the architecture of the original model results in better performance in terms of the mean accuracy, the mean DI, and the mean IOU in detecting mass lesion compared to the other DL and the conventional models.

Dataset Information

An end-to-end convolutional neural network for automated failure localisation and characterisation of 3D interconnects.

Publications

An end-to-end convolutional neural network for automated failure localisation and characterisation of 3D interconnects.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets